006300   SINGH P K, DUTTA A (National Institute of Technology (NIT), Durgapur- 713 209, Email: pks.16ms1101@phd.nitdgp.ac.in) : Socio-metrics of digital payments in demographic dividend: Descriptive analysis of dichotomous preferences. Appl Innov Res 2019, 1(3&4), 171-7.

Innovation in financial services has attracted a lot of attention and becomes the focal point in some jurisdiction further taking a very effective approach for facilitation of the technology enabled innovation. Digital disruptions have affected the all aspect of social mechanism and economic function, with higher density of mobile consumers and internet penetrations as compared to banking and other financial services facilitation. Technical firms have been providing new integrated faster, effective and inclusive innovative solutions; and it accelerates the inclusive digital payment systems. The variant methods of digital payments adopted by urban and semi urban consumers for their usual financial transactions is growing exponentially; however, post demonetization by Government of India, there was urgent need for alternative payment mechanism not only for urban consumers but also support the utilization by rural consumers in demographic dividend. The concept for the study has been to explore strategic advantages of digital payments and diagnosis for the current ecosystem in the support for better adoption of digital payments by the retail consumers in given mixed demography. In the present study, we have approached the Dhanbad district and collected data from different demography for our pilot survey. We have analyzed structured questionnaire based data to understand the various challenged with digital payments in demographic dividend for study area getting dichotomous preferences.

5 illus, 1 table, 24 ref

005042   SINGH A, CHATTERJEE N (IBM Research, Bangalore- 560 045) : Unsupervised graph-based discourse planning and generation. IETE Tech Rev 2019, 36(5), 526-34.

Generating short textual descriptions from structured data is an important problem in the field of Natural Language Generation. Recently, significant progress has been made by neural models in generating short descriptive texts from structured data. But a drawback with such techniques is that they require a large amount of data for training the model. We present an unsupervised approach to this problem. We use a method that relies on finding a Hamiltonian path through a graph of information triples which are connected via edges representing discourse relations. In addition to this, we present a rule-based approach to domain-independent surface realization. We conduct experiments on a dataset of infoboxes extracted from Wikipedia. By comparing against human-generated discourses, we report high quality of discourses generated by our system, which are close enough to textual descriptions authored by human beings.

5 illus, 2 tables, 26 ref

005030   BAHRI O B, LAZREG N, BESBES K (Monastir Univ, Monastir, Tunisia) : Smartphone-based telemedicine supported by pico-satellite constellation. IETE J Res 2019, 65(5), 726-35.

Many people in developing countries are required to travel for several hours to see a doctor. The concept of so called telemedicine accompanied with developments in the field of wireless communications may improve the health care. Here presented telemedicine system is for a distance consultation. It is based on a pocket smartphone using its camera to develop a video broadcasting mission for a real-time consultation. However, developing countries in the Middle East and North Africa suffer network coverage in most areas. To overcome this issue, the system includes a software defined radio in order to integrate the small satellite technology in the telemedicine routine. The proposed pico-satellite constellation can provide an interesting solution for near real-time transmission, which will significantly improve the health care in remote areas.

8 illus, 7 tables, 24 ref

005041   RAM G, KAR R, MANDAL D, GHOSHAL S P (VIT Univ, Vellore, Tamil Nadu) : Optimal design of linear antenna arrays of dipole elements using flower pollination algorithm. IETE J Res 2019, 65(5), 694-701.

This paper describes the synthesis of the radiation characteristics of linear antenna arrays of dipole elements using a nature inspired algorithm called flower pollination algorithm (FPA), which is applied as an optimization algorithm. In FPA, element’s current excitation and the inter-element spacing are used as the optimizing variables to obtain better radiation characteristics of the antenna arrays. The advent is illuminated by 12-, 16-, and 20-elements linear arrays of dipole elements. The simulation results show the influence of this approach on the maximum side lobe level reduction with fixed first null beam width. The obtained results are validated in a practical simulation environment, called computer simulation technology-microwave studio software.

10 illus, 5 tables, 23 ref

005032   BOORGULA V, RAM S S T (Trinity Coll of Engineering and Technology, Karimnagar, Telangana) : Incipient fault diagnosis in stator winding of synchronous generator: A CMFFLC technique. IETE J Res 2019, 65(5), 667-78.

In the paper, a combined strategy of moth–flame optimization (MFO) algorithm and fuzzy logic controller (FLC) for incipient fault diagnosis of the synchronous generator is proposed. The motivation behind the proposed topology is to analyse the beginning issues exhibited by an asynchronous generator under different situations like healthy and unhealthy conditions. Initially, a synchronous generator is assessed in the ordinary condition and from that point onwards, fault is made in the synchronous generator and the framework practices are checked and signals are measured which can be viewed as mis-shaped waveforms. For the collection of data-set from the input current signal, MFO is presented which extracts the signal and structures the possible datasets. In light of the fulfilled data-set, the FLC performs and diagnoses the kind of fault that has happened in the stator winding of the synchronous generator. In order to evaluate the effectiveness of the proposed method, the incipient faults are analysed. The proposed technique is implemented in MATLAB/Simulink platform and this is approved utilizing execution measures, for example, accuracy, precision, recall, and specificity. Likewise, the proposed method is analysed with factual measures, for example, the root mean square error, mean absolute percentage error, mean bias error, and consumption time; and the execution is evaluated by utilizing the examination at various strategies like artificial neural network, fuzzy, and adaptive neuro fuzzy inference system techniques.

14 illus, 4 tables, 33 ref

005038   LOPEZ-ARREDONDO J, TLELO-CUAUTLE E, FRAGA L G D L (Electronics Dep, Instituto Nacional de Astrofisica, Puebla, Mexico) : High-Q and wide-bandwidth capacitor multiplier optimized by NSGA-II. IETE J Res 2019, 65(5), 661-6.

Power management applications require the use of large value on-chip capacitors that can be implemented by active circuits scaling the value of a physical capacitor. However, a good capacitor scaler must provide the best frequency response and high quality factor (Q), accompanied by the minimum power consumption and silicon area. In this manner, a new C-multiplier topology is introduced herein, designed by using 180 nm CMOS integrated circuit technology, and optimized by applying the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). Spice is linked to NSGA-II to evaluate electrical characteristics, while Q and the quiescent current (IQ) were selected as the optimization objectives. The feasible solutions are given in a Pareto front, from which we selected the one providing the best frequency response with a multiplication factor (MF) = 1001 and Q = 278, and consuming 93 mA of static current. Finally, we show that the optimized C-multiplier achieves class AB performance and fits the passive model of a real capacitor very accurately in a wide range of frequencies.

10 illus, 1 table, 12 ref

005043   TAN E T, HALIM Z A (Sains Malaysia Univ, Nibong Tebal, Malaysia) : Health care monitoring system and analytics based on internet of things framework. IETE J Res 2019, 65(5), 653-60.

The Internet of things (IoT) has been a controversial domain of inquiry in engineering applications since the term was first introduced in 2000. The emergence of IoT also promotes the advancement of health care monitoring from face-to-face consultation to telemedicine or eHealth system. This paper presents the prototyping of an embedded health care monitoring system based on the IoT paradigm. The proposed system architecture consists of three sensors for the measurement of three basic vital signs, body temperature, pulse rate, and blood pressure. The integrated sensors are interfaced with the Intel Edison platform, and the output readings are transferred to IBM Bluemix for cloud storage and display. Taking advantage of IoT, the condition of the physical body can be monitored remotely and diagnosed with anomalies by doctors. The paper also presents the health care analytical framework related to diabetes and kidney disease. The prediction results from the analytics show the potential of the classification model to be integrated into the proposed system to identify the potential risk of certain diseases at early stages of early treatment. In the preliminary investigation, the accuracy of the developed model to differentiate between a healthy person and patients with diabetes and kidney disease is 90.54 % and 87.88 %, respectively. Concerning the functionality of the proposed system architecture, the sensors’ measurement accuracy is above 90 % compared to conventional medical equipment.

4 illus, 5 tables, 14 ref

005037   KUMAR V, KUMAR D (Computer Science and Engineering Dep, Thapar Univ, Patiala, Punjab) : Gene expression data clustering using variance-based harmony search algorithm. IETE J Res 2019, 65(5), 641-52.

The advancement in microarray technology has led to a flare-up of gene expression data, thus giving rise to need of efficient technique to analyze these massive data-sets. Among the existing techniques, clustering is a well-known technique used for analysis of microarray data. In this paper, a novel metaheuristic clustering approach for analysis of gene expression is proposed. A variance-based harmony search algorithm is used as an underlying metaheuristic algorithm. The performance of the proposed approach has been tested on 6 real-life data-sets and compared with 12 well-known clustering techniques. The experimental results reveal that the proposed technique outperforms the other existing techniques. The statistical and biological significance tests have also been carried out to demonstrate the superiority of the proposed technique.

5 illus, 5 tables, 34 ref

005031   BAKHTIARI A, SADEGHZADEH R A, MOGHADASI M N (Islamic Azad Univ, Tehran, Iran) : Gain enhanced miniaturized microstrip patch antenna using metamaterial superstrates. IETE J Res 2019, 65(5), 635-40.

In this paper, a high-gain miniaturized microstrip patch antenna was designed using engineered magnetic materials as both substrate and superstrate. The proposed antenna was numerically analyzed, fabricated, and measured. To obtain high permeability and permittivity, an engineered magnetic material with Electric-LC Resonators in the superstrate layer and 2nd kind Hilbert fractals in the substrate were used. Equivalent material parameters technique was also used for efficient simulation of metamaterials in the substrate and the superstrate. The simulation and measurement results show a gain improvement of 8.1 dB, and a miniaturization factor of 4.8 for the miniaturized antenna at 534 MHz. Additionally, using superstrate causes to reduce antenna size to 170 x 170 x 37 mm³ and patch size less than λ/100 resonance frequency.

8 illus, 2 tables, 13 ref

005036   KRISHNA D R, PANDHARIPANDE V M (ECE Dep, Osmania Univ, Hyderabad- 500 007) : Design and development of cavity-backed reconfigurable square spiral antenna. IETE J Res 2019, 65(5), 627-34.

The paper presents design, simulation and experimental results for the reconfigurable square spiral antenna. This antenna is reconfigurable for two bands: band-I is 0.4–3 GHz which covers GSM, CDMA, Wi-Fi, multipoint communication system and band-II is 4.4–5.9 GHz which covers Wi-Max, 802.11Y, WLAN and 802.11a/h/j/n/ac standards. The antenna can be tuned to other aerospace and electronic warfare applications. This antenna structure offers a good radiation efficiency as the cavity is filled with low dielectric constant material and has high gain and directivity. PIN diodes have been used to achieve the reconfigurability.

19 illus, 16 ref

005035   KHAN M, AHMED W, GOLANDAZ T M (Computer Science and Engineering Dep, Visvesvaraya Technological Univ, Bangalore- 560 045) : Accelerating dense matrix computations with effective workload partitioning on heterogeneous architectures. IETE J Res 2019, 65(5), 613-26.

The emergence of High Performance Computing (HPC) has enabled the researchers to perform large scientific computations efficiently and quickly. But as the heterogeneity of the processing units of the HPC systems increased, the utilization of all the resources became an issue. Fully harnessing the power of these systems requires efficient division of work across all the processing units. This solves the issue of under-utilization of resources and improves performance of the application. In this research work, we present a dynamic approach to workload partitioning that obtains the optimal workload partition and schedules them to processing units for parallel processing. Our workload partitioning technique is able to respond automatically to performance variation to provide good performance, it requires very negligible training and is implemented as a library. Performance results show that our dynamic approach is better than static and linear approach. By running the Dense Matrix-Matrix Multiplication kernel library by our proposed method on both CPU and Graphics Processing Unit (GPU) in parallel, we obtain average speedups from 2.69× to 3.14× over CPU and 1.12× to 1.38× over GPU. We used our method on multi-GPUs for which we obtain average speedups of 5.31× over CPU and 1.91× over single GPU.

14 illus, 3 tables, 35 ref

005040   RAJENDRAN V, KUMAR G B (Vellore Institute of Technology, Chennai, Tamil Nadu) : A robust syllable centric pronunciation model for Tamil text to speech synthesizer. IETE J Res 2019, 65(5), 601-12.

The Human–Computer Interaction era contrived the researchers to work on speech and languages to develop interactive interfaces. A speech synthesizer is one such interface facilitating people to amalgamate with the digital era. The present work is focused on developing a Letter-To-Sound mapping for a Tamil speech synthesizer, which is an intriguing task due to the script to sound mapping irregularities in Tamil. Tamil is a syllable-timed language, hence a new syllable centric rule-based approach is formulated in the present work with a more extended set of rules than the existing rule-bases in the literature. This proposed rule-based system outperforms the existing rulebased systems with a low Character Error Rate and High Mean Similarity Score.

12 illus, 37 ref

005028   AKGUN D, CANKAYA I, KACAR S (Computer Engineering Dep, Sakarya Univ, Sakarya, Turkey) : A method for the computational frequency sweep analysis of nonlinear ODEs using GPU acceleration. IETE J Res 2019, 65(5), 589-600.

Computational sweep analysis of nonlinear ODEs (ordinary differential equations) is of importance in engineering system analysis and design. Sweep analyses usually demand intense computational power according to the number of points and the number of system parameters. This paper presents an efficient parallel algorithm for the sweep analysis of nonlinear ODEs based on graphical processing unit acceleration. The developed method preserves the jump phenomenon characteristics intrinsic to nonlinear ODEs and reduces the effects of irregular computational load. Experiments were realized using Duffing equation by sweeping frequency, amplitude, and equation coefficients. Directly, data parallel implementation and proposed implementations are compared to show the efficiency of the proposed method. Experimental results show that the new method provides significant reductions in the computational durations when compared to sequential implementation.

10 illus, 4 tables, 30 ref

005033   CHATURVEDI D, RAGHAVAN S (Electronics and Communication Engineering Dep, National Institute of Technology, Tiruchirappalli, Tamil Nadu) : A half-mode SIW cavity-backed semi-hexagonal slot antenna for WBAN application. IETE J Res 2019, 65(5), 582-8.

A half-mode substrate integrated waveguide (HMSIW) antenna covering industrial, scientific, and medical radio band at 5.8 GHz is designed, fabricated, and tested. An HMSIW technique is used to reduce the size to almost 50% while maintaining the same performance of the antenna. Afterwards, a semi-hexagonal slot is etched on the patch, which excites and tunes the dominant-mode of the cavity in the band of interest. Inspite of a substantial miniaturization, the proposed antenna provides a gain of 6.1 dBi with front to back ratio of more than 10 dB along with a fair radiation efficiency of 83% in free space. In order to examine the performance of the antenna in the presence of a body, the antenna is tested on pork tissues. The measured on-body peak gain and simulated radiation efficiency are obtained as 5.25 dBi and 69%, respectively. The antenna shows robust performance in the presence of pork tissues and the specific absorption rate value is under the Federal Communications Commission (FCC) guidelines, which makes it a suitable choice for wireless body area network applications.

8 illus, 3 tables, 22 ref

005039   PARKOS III J J, KLINE J L, TREXLER J C (Biological Sciences Dep, Florida International Univ, Florida- 33181, Email: Parkos@illinois.edu) : Signal from the noise: Model-based interpretation of variable correspondence between active and passive samplers. Ecosphere 2019, 10(9), e02858.

Combining information from active and passive sampling of mobile animals is challenging because active-sampling data are affected by limited detection of rare or sparse taxa, while passive-sampling data reflect both density and movement. We propose that a model-based analysis allows information to be combined between these methods to interpret variation in the relationship between active estimates of density and passive measurements of catch per unit effort to yield novel information on activity rates (distance/time). We illustrate where discrepancies arise between active and passive methods and demonstrate the model-based approach with seasonal surveys of fish assemblages in the Florida Ever-glades, where data are derived from concurrent sampling with throw traps, an enclosure-type sampler producing point estimates of density, and drift fences with unbaited minnow traps that measure catch perunit effort (CPUE). We compared incidence patterns generated by active and passive sampling, used hier archical Bayesian modeling to quantify the detection ability of each method, characterized interspecific and seasonal variation in the relationship between density and passively measured CPUE, and used apredator encounter-rate model to convert variable CPUE–density relationships into ecological information on activity rates. Activity rate information was used to compare interspecific responses to seasonal hydrology and to quantify spatial variation in non-native  fish activity. Drift fences had higher detection probabilities for rare and sparse species than throw traps, causing discrepancies in the estimated spatial distribution of non-native species from passively measured CPUE and actively measured density. Detection probabilityof the passive sampler, but not the active sampler, varied seasonally with changes in water depth. The relationship between CPUE and density was sensitive to fluctuating depth, with most species not having aproportional relationship between CPUE and density until seasonal declines in depth. Activity rate estimates revealed interspecific differences in response to declining depths and identified locations and species with high rates of activity. We propose that variation in catchability from methods that passively measure CPUE can be sources of ecological information on activity. We also suggest that model-based combining of data types could be a productive approach for analyzing correspondence of incidence and abundance patterns in other applications.

6 illus, 5 tables, 60 ref

005034   GADDAM K R, VADAPALLY V, SINGH S, HAIBATPURE S, MAHESHWARI K, MEHTA V P, KOLLURU M M (Ganga Kaveri Seeds Private Limited, Medchal- 501 401, Email: ksm.mohan@gmail.com) : Image capturing of major plant pathogens using smart mobile phone camera. Curr Trends Biotechnol Pharm 2019, 13(3), 336-45.

Many developing countries, resource poor organizations and universities does not possess sophisticated microscope due to non affordable price or lack of trained personnel to handle the equipment. Therefore, a simple photographing of microorganism has been developed using smartphone camera. The study was conducted to photograph the plant pathogens using in built smartphone cameras. The method has been tested against 18 microorganisms of which, 15 are fungal, three bacteria, pollen grains of paddy and maize for their fertility. The images quality captured with smart phone camera were, being analogous to expensive camera designed for the microscope.Further, live video of yeast cells was also recorded using smart phone camera. We believe that this technology can be an inexpensive, easy and quick to learn for light microscopy in plant pathology for resource poor agriculture R&D institutions, research scholars and academic students for their thesis purpose.

15 illus, 31 ref

005044   THACHIL K K, JAYS J, VIJAYBHANU P (M.S. Ramaiah Univ of Applied Sciences, Bangalore- 560 054, Email: knolinkthachil@gmail.com) : Molecular docking studies and ADME prediction of novel hybrid molecules of benzoxazinyl pyrazole arylidenes. Int J Pharm Ther 2019, 10(3), 74-8.

Most of the nitrogen and oxygen containing heterocycles possess wide range of biological activities. Combination of heterocylic molecules proved to be a successful approach for augmenting biological activities. Novel hybrid Molecules of Benzoxazinyl Pyrazole Arylidenes were designed and synthesized by appropriate synthetic routes.Novel hybrid molecules were screened for their in silico antibacterial activity. This approach paved the way to explore the specificity of newly synthesized hydrid molecules. The novel hybrid molecules were docked with dihydrofolate reductase of S.aureus (PDB ID: 3SRW); dihydrofolate reductase of E.coli (PDB ID: 1RX7); The docked poses were ranked based on their docking scores and ligand –receptor binding free energy with the enzyme. The above studies revealed that docking of hybrid molecules (4- hydroxy.3-methoxybenzylidene substituted benzoxazinyl pyrazole) showed promising inhibitory activity. Thus molecular docking helped in exploring the selectivity of newly synthesized hybrid molecules in the active site of enzyme. ADME properties of hybrid molecules were predicted using QuikProp and all the molecules showed drug like properties.

5 illus, 4 tables, 5 ref

005045   VIJAY BHANU P, JAYS J, THACHIL K K (M.S. Ramaiah Univ of Applied Sciences, Bangalore– 560 054, Email: vijaybhanu.p@gmail.com) : Molecular docking studies of novel coumarino pyrazolinone derivatives as potent antibacterial agents. Int J Pharm Ther 2019, 10(3), 70-3.

The emerging resistance of some antimicrobial species to synthetic antimicrobial agents makes it necessary to continue the search for new antimicrobial agents. As vast number of reports are available pertaining to the antimicrobial activities of coumarins and pyrazolines, novel coumarino pyrazolin-5-one derivatives were designed. Molecular docking studies was carried out to identify the specificity of these derivatives using ‘Glide’ on two antibacterial targets; Dihydrofolate reductase (DHFR) of Staphylococcus aureus (PDB ID: 3SRW); Dihydrofolate reductase of Escherichia Coli (PDB ID: 1RX7). From the results obtained, it was found that compounds CP1c and CP1e were more potent against DHFR.

3 illus, 2 tables, 6 ref

005029   ARA I (Pabna Univ of Science and Technology, Pabna, Bangladesh) : Parameters estimation of Fitzhugh-Nagumo model. Biomed Res 2019, 30(5), 713-5.

One of the simplest single cell models is what is now called the FitzHugh–Nagumo (FHN) model. The model was originally developed as simplification of the Hodgkin–Huxley model by FitzHugh. It exists many variations of the original FHN model. The aim of this paper is to find the parameter thresholds used in FHN model for regular excitation. The thresholds of different parameters are presented. We observe that regular activation occurred when the excitation current is above a threshold level. Sensitivity of different FitzHugh-Nagumo parameters on cardiac excitation is observed. This study represents the first stage toward the development of an accurate computer model of heart activation.

5 illus, 7 ref

003797   TUNTAS R (Bussiness Administration Dep, Van Yuzunco Yil Univ, Van, Turkey, Email: rtuntas@hotmail.com) : A neural network based controller design for temperature control in heat exchanger. Indian J Chem Technol 2019, 26(4), 342-6.

The temperature of outlet fluid of the heat exchanger system is controlled with Artificial Neural Network Based Model Reference (ANNBMR) control method. The ANNBMR controller designed arranges the temperature of the outlet fluid to reach a desired reference value in the shortest possible time, despite the flow and temperature variation of input fluid. The simulation of ANNBMR controller designed with the use of the plant model of the heat exchanger system is carried out in MATLAB Simulink and simulation results are obtained. The simulations results of the proposed ANNBMR controller is compared with the simulations results of the PID conventional controller. The proposed controller shows better performance and reduces both settling time and maximum overshoot and by shortening the error signal between the input and output in a shorter period of time. The obtained simulation results prove that the proposed control method is quite successful.

7 illus, 3 tables, 14 ref

003786   PATEL P (EC Dep, SVCST, Bhopal, Email: singhpriyanka714@gmail.com) : Review on improving received signal strength based location estimation in WSN. Curr Trends Technol Sci 2019, 8(4), 920-4.

A wireless network is any type of electronic network that uses wireless information connections to plug network nodes. Wireless networks square measure laptop networks UN agency don't seem to be connected by cables in spite of the type. the utilization of a wireless network allows enterprises to stop the pricey suggests that of introducing cables into buildings or as an affiliation between totally different instrumentality locations. The cornerstone of wireless systems is radio waves, AN implementation that happens at the physical higher level of network structure.

1 illus, 13 ref

003799   YADAV K S, SINGH D K (Digital Communication Dep, Swami Vivekanand Coll of Science & Tech, Bhopal, Email: Kamalashankar40@gmail.com) : A review of Wi-max network. Curr Trends Technol Sci 2019, 8(4), 915-9.

Wi-max stands for worldwide ability of microwave access. Together with the development of mobile communication and broadband technology, WiMax has become a hot spot for world medium operators and makers. WiMax guarantees to deliver the web throughout the world, and connect the long distance of broadband wireless property services. WiMAX can provide broadband wireless access at information rates of multiple Mbit/s to the end-user and at intervals a spread of many kilometers. a similar radio technology also will provide high-speed information services to all or any mobile terminals (laptops, PDAs, etc.) with AN optimized exchange between output and coverage. Ultimately, it'll modify the "Portable Internet" usage replicating on the move a similar user expertise as reception or at the workplace. Given its large advantages, WiMAX can develop as a robust radio access answer with several integration synergies in mobile or fixed specification. WiMAX also will modify end-users to profit from AN "Always Best Connected" expertise once accessing their applications via the simplest available network, at home, on the pause, or on the move. Projected technique improving SNR and min BER. 

3 illus, 14 ref

003784   PAL A R, SAHA D (Computer Science and Engineering Dep, Engineering and Management Coll, West Bengal- 721 171, Email: chhaandasik@gmail.com) : Word Sense disambiguation in Bengali language using unsupervised methodology with modifications. Sadhana 2019, 44(7), 168.

In this work, Word Sense Disambiguation (WSD) in Bengali language is implemented using unsupervised methodology. In the first phase of this experiment, sentence clustering is performed using Maximum Entropy method and the clusters are labelled with their innate senses by manual intervention, as these sense-tagged clusters could be used as sense inventories for further experiment. In the next phase, when a test data comes to be disambiguated, the Cosine Similarity Measure is used to find the closeness of that test data with the initially sense-tagged clusters. The minimum distance of that test data from a particular sense-tagged cluster assigns the same sense to the test data as that of the cluster it is assigned with. This strategy is considered as the baseline strategy, which produces 35 % accurate result in WSD task. Next, two extensions are adopted over this baseline strategy: (a) Principal Component Analysis (PCA) over the feature vector, which produces 52 % accuracy in WSD task and (b) Context Expansion of the sentences using Bengali WordNet coupled with PCA, which produces 61 % accuracy in WSD task. The data sets that are used in this work are obtained from the Bengali corpus, developed under the Technology Development for the Indian Languages (TDIL) project of the Government of India, and the lexical knowledge base (i.e., the Bengali WordNet) used in the work is developed at the Indian Statistical Institute, Kolkata, under the Indradhanush Project of the DeitY, Government of India. The challenges and the pitfalls of this work are also described in detail in the pre-conclusion section.

6 illus, 5 tables, 35 ref

003787   PRAKASH B, VISWANATHAN V (Vellore Institute of Technology, Chennai- 600 127, Email: prakash.bala@vit.ac.in) : Distributed cat modeling based agile framework for software development. Sadhana 2019, 44(7), 166.

Software development is a challenging process that requires in-depth understanding and an effective model such that the developed software inherits good quality and reliability, and attains customer satisfaction towards achieving the goals successfully. The effectiveness of the software is enabled by modifying the operating modules of the software through a model, like agility. In this paper, the catastrophic and distributed computing models are integrated into the software development process. The proposed model is termed as a distributed cat model that is developed with the aim to handle the risk factors engaged in various developing stages of the agile model. The risk factors that affect the communication, planning, release, design, coding and testing modules of the agile modules are deeply learned and executed such that the risk factors are tackled by various modules present in the proposed distributed cat model. The effectiveness of the proposed model is analysed based on the performance metrics such as Index of Integration (IoI) and Usability Goals Achievement Metric (UGAM), for which five products, including the hotel management system, Customer Relationship Management system (CRM), rainfall prediction system, temperature monitoring system and meta-search system, are employed. The analysis is performed using the parameters like mean difference, variance, standard deviation and correlation coefficient. The result proves that the proposed model offers a great positive deviation contributing to high degree of performance in software development.

6 illus, 5 tables, 25 ref

003791   SHAH B, DALWADI G, BHASKER R, SHAH H, KOTHARI N (Reliance Jio Infocomm Ltd, Navi Mumbai- 400 701, Email: brijesh_i_shah@yahoo.com) : Estimation of azimuth of a macro cell through user data for LTE access network. Sadhana 2019, 44(7), 164.

The number of antennas on a site increases due to a simultaneous deployment of multi-band and multi-mode radios to combat extremely growing data demand in the network. The correct values of physical parameters of antennas, including azimuth, height and tilt, are essential to optimize the radio frequency (RF)network automatically. It is seen that poor results in RF network optimization are mainly due to incorrect azimuth. The proposed algorithm can estimate the azimuth of an antenna in the field using passive monitoring data from the user equipment. It has been developed to identify the correct value of azimuth without doing thefield audit, which can significantly reduce the time for optimization and operational expenditure (OPEX) as well. The field trial reveals that the estimated azimuth value closely matches within ±12 ° range in comparison to theactual value in the field. Moreover, field results show that the same algorithm is equally applicable for urban and rural morphologies as well. It can also be automated to sanctify the physical site database with proper azimuthvalues at large level without introducing any kind of human error.

10 illus, 2 tables, 20 ref

003764   BALAKRISHNAN N, SHANTHARAJAH S P (Master of Computer Applications Dep, Sona Coll of Technology, Tamil Nadu- 636 005, Email: nbkkar29@gmail.com) : Histogram-Equalized hypercube adaptive linear regression for image quality assessment. Sadhana 2019, 44(7), 162.

Image Quality Assessment (IQA) becomes intensely salient in several applications, namely, acquisition of images, watermarking, image compression, image transmission, enhancement of images and so on, due to the extensive use of digital images. In the past decades, considerable advancements have been developed in IQA using Region of Interest (ROI). However, ROI localization is a labour-intensive process that takes multiple passes of sliding-window in search of proper ROI. The efficiency of examination, reduction in the time taken for ROI localization by multiple passes and the quality of the image can be improved by the proposed method, Histogram-Equalized Hypercube Adaptive Linear Regression (HE-HALR) scheme. HE-HALR scheme first performs the pre-processing step for input images. In this step, the features used to describe the quality of images are analysed using Histogram-Equalization-based Contrast Masking (HE-CM) model. The HE-CM model performs ROI localization with the parallelization programming that identifies the contrast masking and luminance value in a parallel manner. With the resultant feature vectors, dimensional reduction is performed using machine learning technique, namely, hypercubical neighbourhood. Finally, IQA is performed with the dimensionality-reduced features using Adaptive Linear Regression.

12 illus, 1 table, 25 ref

003766   BIRAJADAR P, HARIA M, KULKARNI P, GUPTA S, JOSHI P, SINGH B, GADRE V (Indian Institute of Technology Bombay, Mumbai- 400 076, Email: birajadar20@gmail.com) : Towards smartphone-based touchless fingerprint recognition. Sadhana 2019, 44(7), 161.

The widely used conventional touch-based fingerprint identification system has drawbacks like the elastic deformation due to nonuniform pressure, fingerprints collection time and hygiene. To overcome these drawbacks, recently the touchless fingerprint technology is gaining popularity and various touchless fingerprint acquisition solutions have been proposed. Nowadays due to the wide use of the smartphone in various biometric applications, smartphone-based touchless fingerprint systems using an embedded camera have been proposed in the literature. These touchless fingerprint images are very different from conventional ink-based and live-scan fingerprints. Due to varying contrast, illumination and magnification, the existing touch-based fingerprint matchers do not perform well while extracting reliable minutiae features. A touchless fingerprint recognition system using a smartphone is proposed in this paper, which incorporates a novel monogenic-wavelet-based algorithm for enhancement of touchless fingerprints using phase congruency features. For the comparative performance analysis of our system, we created a new touchless fingerprint database using the developed android app and this is publicly made available along with its corresponding live-scan images for further research. The experimental results in both verification and identification mode on this database are obtained using three widely used touch-based fingerprint matchers. The results show a significant improvement in Rank-1 accuracy and equal error rate (EER) achieved using the proposed system and the results are comparable to that of the touch-based system.

20 illus, 2 tables, 41 ref

003779   KITTUR A S, PAIS A R (National Institute of Technology Karnataka, Surathkal- 575 025, Email: apurva.kittur@gmail.com) : A new batch verification scheme for ECDSA signatures. Sadhana 2019, 44(7), 157.

In this paper, we propose an efficient batch verification algorithm for ECDSA*(Elliptic Curve Digital Signature Algorithm)* signatures. Our scheme is efficient for both single and multiple signers. ECDSA* signature is a modified version of ECDSA, which accelerates the verification of ECDSA signature by more than 40 %. However, the highlighting feature of our proposed scheme is its efficiency for varied batch sizes. The scheme is resistant to forgery attacks by either signer or intruder. The performance of our scheme remains consistent for higher batch sizes too (≥8). Our paper also discusses the possible attacks on ECDSA signaturesand also how our scheme is resistant to such attacks.

16 tables, 19 ref

003794   SUBALALITHA C N (Computer Science and Engineering Dep, SRM Institute of Science and Technology, Kattankulathur- 603 203, Email: subalalitha@gmail.com) : Information extraction framework for Kurunthogai. Sadhana 2019, 44(7), 156.

Kurunthogai is a classical Tamil poetic masterpiece and it is the second book of Ettuthokai which is one of the Sangam literary works. The poems of Kurunthogai expresses the love life between men and women who lived during the Sangam age. Kurunthogai is a massive work written by many authors. The poems are written based on the five different landscapes namely, Kurinchi, Mullai, Marutham, Neythal, and Pa¯lai. So, the poems contain much valuable historical information related to these landscapes. This paper proposes a templatebased Information Extraction (IE) framework for Kurunthogai which automatically extracts the names of flora, fauna, foods, vessels, and water bodies described in it. Furthermore, it extracts Noun Unigrams, Verb Unigrams, Adjective-Noun Bigrams, and Adverb-Verb Bigrams. Tamil Morphological Analyzer tool has been used to extract the N-grams. The state-of-art IE techniques have attempted to extract information from expository texts, whereas, the proposed IE framework extracts information from a literature-based text. The existing techniques extract information from monolingual texts, whereas, the proposed IE framework extracts information from bilingual texts. The proposed IE framework has achieved a precision of 88.8%. The proposed framework can be applied for any literature type of texts and be used in various applications of Natural Language Processing.

2 illus, 2 tables, 18 ref

003795   SUBHAA R, JAWAHAR N, PONNAMBALAM S G (SSM Institute of Engineering and Technology, Dindigul- 624 002, Email: rsubhaa@yahoo.com) : An improved design for cellular manufacturing system associating scheduling decisions. Sadhana 2019, 44(7), 155.

This paper presents a model for the design of Cellular Manufacturing System (CMS) to evolve simultaneously structural design decisions of Cell Formation (CF) and operational issue decisions of optimal schedule. This integrated decision approach is important for designing a better performing cell. The model allows machine duplication and incorporates cross-flow for scheduling flexibility. The cross-flow is the term introduced to mean the inter-cell movement of parts from parent cell to identical machines in other cells though machines are available in the parent cell. This cross-flow facilitates routing flexibility and paves way for reduced schedule length thereby optimizing resources leading to minimized operational cost. A non-linear integer mathematical programming model is formulated with the objective function of minimizing operating cost which is the sum of Machine Utility Cost (MUC) and inter-cell costs. The MUC is a new cost parameter based on machine utility and it integrates CF, scheduling, and machine duplication decisions. The proposed model belongs to the class of NP-hard problems. A hybrid heuristic (HH) that has ‘‘Simulated Annealing Algorithm (SAA) embedded with Genetic Algorithm (GA)’’ is proposed. A comparison with the mathematical solution reveals that the proposed HH is capable of providing solutions closer to optimal in a computationally efficient manner. The model is validated by studying the effect of integrated decisions, machine duplications, and association of scheduling and cross-flow. The model validation reveals that the proposed CMS model evolves CF, scheduling, and machine duplication decisions with minimum operating cost. Thus, it can be inferred that the proposed model gives optimal integrated decisions for designing an effectively and efficiently performing cells and thus evolves improved CMS design decisions.

8 illus, 17 tables, 51 ref

003782   NAUSHAD S M, DEVI A R R, HUSSAIN T, ALROKAYAN S A, RAMAIAH M J, KUTALA V K (Sandor Specialty Diagnostics, Hyderabad- 500 034, Email: naushadsm@gmail.com) : In silico analysis of the structural and functional implications of SLC19A1 R27H polymorphism. J Genet 2019, 98, 85.

In view of the documented association of solute carrier family 19 member 1 (SLC19A1) G80A (R27H) polymorphism with the risk for different types of cancers and systemic lupus erythematosus (SLE), we have reanalysed the case–control study on breast cancer to ascertain the conditions in which this polymorphic variant exerts the risk of breast cancer. Association statistics have revealed that this polymorphism exerts the risk for breast cancer under the conditions of low folate intake, and in the absence of well-documented protective polymorphism in cytosolic serine hydroxymethyltransferase. To substantiate this observation, we have developed a homology model of SLC19A1 using glycerol-3-phosphate transporter (d1pw4a) as a template where 73% of the residues were modelled at 90% confidence while 162 residues were modelled ab initio. The wild and mutant proteins shared same topology in S3, S5, S6, S7, S11 and S12 transmembrane domains. The topology varied at S1 (28–43 residue vs 28–44 residue), S2 (66–87 residue vs 69–87 residue), S4 (117–140 residue vs 117–139 residue), S8 (305–325 residue vs 305–324 residue), S9 (336–356 residue vs 336–355 residue), and S10 (361–386 residue vs 361–385 residue) transmembrane domains between wild versus mutant proteins. S2 domain is shortened by three amino acid residues in the mutant while in other domains the difference corresponds to one amino acid residue. The 3DLigandSite analysis revealed that the metallic-ligand-binding sites at 273Trp, 277Asn, 379Leu, 439Phe and 442Leu are although unaffected, there is a loss of active sites corresponding to nonmetallic ligand binding. Tetrahydrofolate and methotrexate have lesser affinity towards the mutant protein than the wild protein. To conclude, the R27H polymorphism affects the secondary and tertiary structures of SLC19A1 with the significant loss in ligand-binding sites.

6 illus, 4 tables, 21 ref

003790   SANYAL P, BARUI S, DEB P, SHARMA H C (Pathology Dep, Military Hospital Jalandhar Cantt, Punjab- 144 005, Email: sbruit@gmail.com) : Performance of a convolutional neural network in screening liquid based cervical cytology smears. J Cytol 2019, 36(3), 146-51.

Cervical cancer is the second most common cancer in women. The liquid based cervical cytology (LBCC) is a useful tool of choice for screening cervical cancer. To train a convolutional neural network (CNN) to identify abnormal foci from LBCC smears.  We have chosen retrospective study design from archived smears of patients undergoing screening from cervical cancer by LBCC smears. 2816 images, each of 256 × 256 pixels, were prepared from microphotographs of these LBCC smears, which included 816 “abnormal” foci (low grade or high grade squamous intraepithelial lesion) and 2000 ‘normal’ foci (benign epithelial cells and reactive changes). The images were split into three sets, Training, Testing, and Evaluation. A convolutional neural network (CNN) was developed with the python programming language. The CNN was trained with the Training dataset; performance was assayed concurrently with the Testing dataset. Two CNN models were developed, after 20 and 10 epochs of training, respectively. The models were then run on the Evaluation dataset.  A contingency table was prepared from the original image labels and the labels predicted by the CNN. Combined assessment of both models yielded a sensitivity of 95.63 % in detecting abnormal foci, with 79.85 % specificity. The negative predictive value was high (99.19 %), suggesting potential utility in screening. False positives due to overlapping cells, neutrophils, and debris was the principal difficulty met during evaluation. The CNN shows promise as a screening tool; however, for its use in confirmatory diagnosis, further training with a more diverse dataset will be required.

7 illus, 6 tables, 34 ref

003775   ISMAEL O F, HUSSAIN Z M (Kufa Univ, Najaf, Iraq, Email: zahir.hussain@uokufa.edu.iq) : SVD-Structural similarity in the wavelet-gabor domain: Improved confidence for face recognition under noise, blur and haze. J Comput Sci 2019, 15(8), 1209-24.

In this work we propose and investigate the performance of a new similarity measure based on Singular Value Decomposition (SVD) and structural similarity in the wavelet and Gabor domains. The reasoning behind this combination is to utilize SVD in getting independent components, wavelet decomposition to get the complex frequency features and Gabor filtering to get textural features. A comparison has been made versus correlative and structural similarity measures like SSIM (Structural Similarity Index Measure), Complex-Wavelet SSIM (CWSSIM) and FSIM (FeatureBased Similarity). In these tests, a reference image is tested for similarity against several face images in a database under adverse conditions like noise, blur and haze. A new haze formation approach has also been proposed. Similarity level and similarity confidence are taken as the performance measures. Two confidence measures, different in strength of confidence, have been proposed and tested versus a recently-proposed confidence measure that relies on the difference between the maximal similarity (best match in the database) minus the second maximum similarity (second-best match in the database). Simulation using AT&T database has shown that the proposed SVDStructural Similarity in Wavelet-Gabor Domain (SVWG) outperforms existing measures by far. SVWG can give more robust decisions (near-optimal confidence); also, can work under more adverse conditions (lower SNR, more blur or haze) where other similarity measures fail.

9 illus, 35 ref

003765   BENGANI S, VADIVEL S, JOTHI J A A (Computer Science Dep, Birla Institute of Technology and Science Pilani, Dubai, UAE, Email: vadivel@dubai.bits-pilani.ac.in) : Efficient music auto-tagging with convolutional neural networks. J Comput Sci 2019, 15(8), 1203-8.

Technology is revolutionizing the way in which music is distributed and consumed. As a result, millions of songs are instantly available to millions of people, on the Internet. This has created the need for novel music search and discovery services. Music is often searched using descriptive keywords, or tags, based on the content of the song. Hence, one very important task in achieving a great music search engine is automatic tagging of music. Currently, deep learning techniques using convolutional neural networks produce state- ofthe-art results for this task. Several deep learning algorithms are able to achieve good results but at the cost of efficiency. As neural networks get deeper, the cost of computation grows exponentially. In this paper, we present a deep learning-based ensemble method that achieves near state-of-the-art performance on the music auto-tagging task. Our method is significantly more efficient in terms of computation time and disk space. This opens up the option of using our proposed model directly on a mobile device.

2 illus, 6 tables, 14 ref

003772   ELMENSHAWY D, HELMY W, EL-TAZI N (Information Systems Dep, Cairo Univ, Cairo, Egypt, Email: d.ezzat@fci-cu.edu.eg) : A clustering based approach for contextual anomaly detection in Internet of Things. J Comput Sci 2019, 15(8), 1195-1202.

Internet of Things (IoT) is a network which connects different communication devices with the internet to attain quick, robust and realtime information transfer and communication, achieving intelligent management. IoT is still in its infancy so it faces numerous challenges varying from data management to security concerns. Sensors generate enormous quantities of data that need to be handled efficiently to have successful deployment of IoT applications. Concerning data management, a great challenge that faces the IoT environment is the detection of contextual anomalies. Contextual anomaly detection is a sophisticated task because the context has to be taken into consideration in the anomaly detection process rather than checking only the deviation of the data value as in point anomaly detection. As a result, in this paper, a novel clustering based algorithm is proposed to detect contextual anomalies in Internet of Things. Attributes were separated into two different categories, namely contextual attributes and behavioral attributes. K-Means clustering technique was applied on the contextual and behavioral attributes separately, then the intersection between the contextual and behavioral clusters was used to detect the contextual anomalies. Moreover, the algorithm was applied on a real room occupation dataset of size around 20,000 records and the experiments showed promising results.

2 illus, 2 tables, 23 ref

003796   TIKITO I, ARASS M E, SOUISSI N (Mohammed V Univ, Rabat, Morocco, Email: tikito.iman@gmail.com) : Meta-analysis of data collect methods. J Comput Sci 2019, 15(8), 1184-94.

Several organizations from different sectors depend increasingly on knowledge extracted from huge volumes of data generated by different sources, such as IoT, sensors and databases. At the core of data lifecycle, data reliability, analytics, security, scalability and use are important concerns. Coping with these issues in handling data requires understanding the challenges associated with it. Analysis process and storage devices have been widely studied. However, very few studies have explored the collect data phase. In this study we aim to analyse more the collect phase of data lifecycle to provide an optimized and smart approach. This paper aim to provide the right method to follow in data collect phase within different domain according to client needs and requirements. It provides not only a detailed view of the main steps, but also based on a prior literature review on different existing methods. This allowed us subsequently to establish a correspondence with the SLR method on which we based our method. We use an explicit example to illustrate the steps of our method.

6 illus, 2 tables, 60 ref

003767   BRIHADISWARAN G, HAPUTHANTHRI D, GUNATHILAKA S, MEEDENIYA D, JAYARATHNA S (Moratuwa Univ, Colombo, Sri Lanka, Email: dulanim@cse.mrt.ac.lk) : EEG-based processing and classification methodologies for autism spectrum disorder: A review. J Comput Sci 2019, 15(8), 1161-83.

Autism Spectrum Disorder is a lifelong neurodevelopmental condition which affects social interaction, communication and behaviour of an individual. The symptoms are diverse with different levels of severity. Recent studies have revealed that early intervention is highly effective for improving the condition. However, current ASD diagnostic criteria are subjective which makes early diagnosis challenging, due to the unavailability of well-defined medical tests to diagnose ASD. Over the years, several objective measures utilizing abnormalities found in EEG signals and statistical analysis have been proposed. Machine learning based approaches provide more flexibility and have produced better results in ASD classification. This paper presents a survey of major EEG-based ASD classification approaches from 2010 to 2018, which adopt machine learning. The methodology is divided into four phases: EEG data collection, pre-processing, feature extraction and classification. This study explores different techniques and tools used for pre-processing, feature extraction and feature selection techniques, classification models and measures for evaluating the model. We analyze the strengths and weaknesses of the techniques and tools. Further, this study summarizes the ASD classification approaches and discusses the existing challenges, limitations and future directions.

15 illus, 5 tables, 50 ref

003768   CHANG C, EDWIN, UTAMA D N (Computer Science Dep, Bina Nusantara Univ, Indonesia- 11480, Email: calvin.chang@binus.ac.id) : An extended version of the fuzzy-Euclidean intelligent fitness model (FEIFM) implementation for selecting personal vehicle. J Comput Sci 2019, 15(8), 1123-32.

Indeed, intelligent model is a sub-domain in computer science that its purposes utilized in numerous pieces of reality. Particularly in case of automotive industry, to select the most appropriate personal vehicle is challenging for the customers. The challenge was taken as a main problem of this study. In this research, the reasonableness is characterized by the customer parameters which portray the customer's identity. By utilizing the mix technique for fuzzy-logic and Euclidean distance calculation, the customer’s identities are fitted into the personal-vehicle parameters. At long last, the constructed model for choosing personal vehicle plays several customer’s parameters; e.g., age, gender, education, income and job. The model designed thru utilizing the object-oriented methodology. The result of simulation of 66 purchasers and 44 conceivable vehicles are able to propose the most reasonable vehicle for every purchaser. As an extended version, the model successfully delivers the completed scheme due to added parameters and method. It is a truthful contribution provided by this research.

8 illus, 2 tables, 23 ref

003798   VASANTHAPRIYAN S, RANDIMA V (Computing and Information Systems Dep, Sabaragamuwa Univ of Sri Lanka, Belihuloya- 70140, Email: priyan@appsc.sab.ac.lk) : Design IoT based smart electricity power saving university: Analysis from a lecture hall. J Comput Sci 2019, 15(8), 1097-1107.

Managing and controlling the electricity consumption in a productive manner is a red hot topic in today’s world. Many countries have considered this problem and they have suggested automate systems to overcome this problem. Since, Sri Lankan has not used such kind of automated system to control the electricity power consumption, our system will be a suitable solution for that. Today, IoT is a technological paradigm that is used to build such kind of automates systems. In our proposed system also, IoT and sensor technologies are used. It is a system that responds to human presence and provides related actions according to the human occurrences area environmental condition. It is control the electric devices such as lights, fans and AC in the lecture hall according to temperature and light intensity values that detect by the sensors. We used Kinect sensor to detect human presence. DHT22 and LDR sensors were used respectively to sensor the temperature, humidity and light intensity of human occupant area. Arduino- mega board was used to control the DHT22 and LDR sensors. In the research process we found the comfortable temperature and light intensity values that suitable for lecture hall and used those values to implement the prototype. Also, it provides real-time information such as current environmental condition of specific place and relevant messages including actions that need to take by using website. The main objectives of this research are reduce the wastage of electric power and provide suitable IoT based solution for reduced the electric power consumption.

9 illus, 4 tables, 19 ref

003778   KHAIRUDDIN A R, ALI N A, ALWEE R, HARON H, ZAIN A M (Teknologi Malaysia Univ, Bahru, Malaysia, Email: alifjam1991@gmail.com) : Parameter optimization of gradient tree boosting using dragonfly algorithm in crime forecasting and analysis. J Comput Sci 2019, 15(8), 1085-96.

Crime forecasting and analysis are very important in predicting future crime patterns and beneficial to the authorities in planning effective crime prevention measures. One of the challenges found in crime analysis is the crime data itself as its form, representation and distribution are varied and unpredictable. To handle such data, most researchers have been focusing on applying various Artificial Intelligence (AI) techniques as an analytical tool. Among them, Gradient Tree Boosting (GTB) is a newly emerged AI technique for forecasting especially in crime analysis. GTB possesses a unique feature among other AI techniques which is its robustness towards any data representation and distribution. Subsequently, this study would like to adopt GTB in modelling crime rates based on 8 defined crime types. Similar to other AI techniques, GTB’s overall performance is heavily influenced by its input parameter configuration. To assess such a challenge, this study would like to propose a hybrid DA-GTB crime forecasting model that is equipped with a metaheuristic optimization algorithm called Dragonfly Algorithm (DA) in optimizing GTB’s three main parameters namely number of trees, size of individual trees and learning rate. From the experimental result obtained, the application of DA for parameter optimization yielded a positive impact in enhancing GTB forecasting performance as it produced the smallest error compared to nonoptimized GTB. This indicates that the proposed model is able to perform well using time series data with a limited and small sample size.

3 illus, 4 tables, 24 ref

003793   SONOBE T (National Institute of Informatics, Tokyo- 101-8430, Email: tomohiro_sonobe@nii.ac.jp) : Variable selection with pagerank for SAT solvers. J Comput Sci 2019, 15(8), 1074-84.

How to choose decision variables often determines the performance of SAT solvers. In state-of-the-art SAT solvers, Variable State Independent Decaying Sum (VSIDS) has been used as a standard technique in the decision process. In this study, we analyze the VSIDS from the point of view of PageRank and propose a technique for improving the VSIDS. While the VSIDS focuses on local search spaces, the PageRank values are based on the relative importance from a global point of view. From this fact, we utilize the PageRank values for controlling the VSIDS and improve the performances of representative SAT solvers, MiniSAT and Glucose.

7 illus, 2 tables, 31 ref

003763   AMRAOUI S, ELMAALLAM M, BENSAID H (Mohammed V Univ, Rabat, Morocco, Email: soumaya.amraoui@gmail.com) : An algorithm to determine the maturity improvement plan for information system risk management: Application on a case study. J Comput Sci 2019, 15(8), 1050-64.

A good and relevant Risk Management process is a key issue when Information System effective governance is concerned. Therefore, several paradigms have been devised to help achieving such goal. Among these paradigms, maturity models are quite popular. The main aim of a maturity model is to help users improve their activities capability. However, one of the major challenges encountered when using these models is the definition of the improvement plan after the evaluation. This challenge is all the stronger and costly when it comes to an activity whose elements or phases have an important interdependence such as IS risk management. In this article, we propose an algorithm called “Path Prerequisites” to help users define a graduate improvement plan, easily and efficiently, from a given maturity level to a target one, while handling criteria dependencies constraints. The algorithm is based on an acyclic graph representation of the control objectives and the dependencies among them and it corresponds to a guided (backwards) traversal of the graph. We assess the algorithm by applying it to a study case.

9 illus, 14 tables, 32 ref

003776   JAOUEDI N, BOUJNAH N, BOUHLEL M S (SETIT, Sfax, Tunisia, Email: neziha_jaouedi@yahoo.fr) : Deep learning approach for human action recognition using gated recurrent unit neural networks and motion analysis. J Comput Sci 2019, 15(7), 1040-9.

Human action recognition is a computer vision task. The evaluation of action recognition algorithms relies on the proper extraction and learning of the data. The success of the deep learning and especially learning layer by layer led to many imposing results in several contexts that include neural network. Here the Recurrent Neural Networks (RNN) with hidden unit has demonstrated advanced performance on tasks as varied as image captioning and handwriting recognition. Specifically Gated Recurrent Unit (GRU) is able to learn and take advantage of sequential and temporal data required for video recognition. Moreover video sequence can be better described on both visual and moving features. In this paper, we present our approach for human action recognition based on fusion and combination of sequential visual features and moving path. We evaluate our technique on the challenging UCF Sports Action, UCF101 and KTH dataset for human action recognition and obtain competitive results.

5 illus, 4 tables, 37 ref

003781   MUMIN M A A, SEDDIQUI M H, IQBAL M Z, ISLAM M J (Computer Science and Engineering Dep, Shahjalal Univ of Science and Technology, Sylhet, Bangladesh, Email: mumin-cse@sust.edu) : Shu-torjoma: An English↔Bangla statistical machine translation system. J Comput Sci 2019, 15(7), 1022-39.

An efficient and publicly open machine translation system is in dire need to get the maximum benefits of Information and Communication Technology through removing the language barrier in this era of globalization. In this study, we present a Phrase-Based Statistical Machine Translation (PBMT) system between English and Bangla languages in both directions. To the best of our knowledge, the system is trained on the largest dataset of more than three million tokens each side in English↔Bangla translation task. In the system, we perform data preprocessing and use optimized parameters to produce efficient system output. We analyze our system output from several viewpoints: overall results, comparisons with the available systems, sentence type and length effect, and behaviour of two challenging linguistic properties– prepositional phrase and noun inflection. Our analysis provides useful insights that translating into morphologically richer language is harder than translating from them and this is mainly due to the difficulties of translating noun inflections. Comparisons with the available systems show that our system outperforms the other systems significantly and gain 10.84 BLEU, 2.18 NIST and 19.02 TER points over the next best system. The analysis of the sentence type and length effect shows that simple sentences are easier to translate and the sentences longer than 15 words are harder to translate for English↔Bangla translation task. To foster the English↔Bangla machine translation research, we have developed development and test datasets, which are representative in sentence length and balanced in genre to be used as a benchmark and are made publicly available.

9 illus, 6 tables, 54 ref

003759   AHMED A-F, MOHAMED R, MOSTAFA B (Computer Science Dep, IBB Univ, IBB Yemen, Email: flahi763@gmail.com) : Arabic poetry authorship attribution using machine learning techniques. J Comput Sci 2019, 15(7), 1012-21.

In this study, authorship attribution in Arabic poetry will be conducted to determine the authorship of a specified text after documents with recognized authorships have been allocated. This work also measures the impact performance of Naïve Bayes, Support Vector Machine and Linear discriminant analysis for Arabic poetry authorship attribution using text mining classification. Several features such as lexical features, character features, structural features, poetry features, syntactic features, semantic features and specific word features are utilized as the input data for text mining, using classification algorithms Linear discriminant analysis, Support Vector Machine and Naïve Bayes by Arabic Poetry Authorship Attribution Model (APAAM). The dataset of Arabic poetry is divided into two sets: known poetic in training dataset texts and anonymous poetic texts in a test dataset part. In the experiment, a set of 114 random poets from entirely different eras are used. The highest performance accuracy value is 99, 12 %; the performance rate at the attribute level is 98.246 %; the level of techniques is 92.836 %.

5 illus, 4 tables, 27 ref

003761   ALIWY A H, TAHER H A (Computer Science Dep, Computer Science and Mathematics Coll, Najaf, Iraq, Email: ahmedh.almajidy@uokufa.edu.iq) : Word sense disambiguation: Survey study. J Comput Sci 2019, 15(7), 1004-11.

The process of identifying the correct sense of a given word in a particular sentence is called Word Sense Disambiguation (WSD). It is complex problem because it involves drawing knowledge from various sources. Significant amount of effort has been put into resolving this problem in machine learning since its inception but the toil is still ongoing. Many techniques were used in WSD and implemented on different corpora for almost all languages. In this paper, WSD algorithms were classified to three categories as Knowledge-based, supervised and unsupervised techniques. Each category will be studied in details with explanation of almost all the algorithms in each category. Hence work examples for each method were taken with the used language, the used corpora and other factors. The benefits and drawback of each method were recorded. Some of these techniques have limitations in some situations, therefore this work will helps the researchers in the field of natural language processing to select the suitable algorithms to solve their particular problem in WSD. The novelty of the work can be seen in the comparison of the used works and the used algorithms. From this work, it was concluded that (i) some methods give high accuracy for language but low for other, (ii) the size of the used data set affects the performance of the used algorithm, (iii) some of these approaches can be run fastly but with limitation of the accuracy and (iv) most of these approaches are implemented for many languages successfully.

2 tables, 32 ref

003769   CHOCHIANG K, CHOOTHONG A, INTARASOMBAT P, MASOSOT V, PRASITSUPPAROTE A (Prince of Songkla Univ, Phuket Campus, Thailand, Email: kitsiri.c@phuket.psu.ac.th) : Psychological acceptability weighted priority scheduling: A case study of animal hospital. J Comput Sci 2019, 15(7), 995-1003.

A solution to the patient scheduling problem for a case study animal hospital called Mix+Factor scheduling is proposed in this work. Mix scheduling is based on the weighted sum of patient arrival order, the job type and the priority. The priority is based on the veterinarian opinion on the treatment type. Factor is an additional function based on the psychological acceptability of the patient owners in allowing some later jobs to be moved ahead in the waiting queue. The experimental results are conducted on three synthesis workloads to create a light-load, normal-load and high-load conditions. The synthesis workloads are created according to the mixture of jobs at the case study animal hospital. The results show that the Mix+Factor algorithm provides similar or better average waiting time performance in comparison with the currently used algorithms, namely First-Come-First-Served. In addition, Mix+Factor can also provide a better scheduling in order to reduce the waiting time for specific patients such as violence animals or patients with appointments. A study on potential benefit of opening an extra treatment room shows that an extra treatment room can significantly reduce the waiting time and better serve the specific patients than that of the currently used algorithm.

11 tables, 9 ref

003774   ISKANDARANI M Z (Al-Ahliyya Amman Univ, Amman, Jordan, Email: m.iskandarani@ammanu.edu.jo) : Abnormalities in ultrasonic (C-Scan) images of composite structures: Impact damaged versus hole damaged. J Comput Sci 2019, 15(7), 972-82.

This paper is about applying image processing to detect different types and levels of damage in composite structures using in C-scan images produced by ultrasonic testing. This method plays an important role as it can detect any discontinuities or flaws in the specimen. To analyze such critical image in an, automated inspection environment an image processing method that correlates Threshold values to Gradient Field values is used to extract important information from the c-scan images in order to detect abnormalities that may exist. The paper presents an improved approach to composite damage characterization using Threshold Level Variation as an input variable to Gradient Fields. Furthermore, the detailed results showed an important dependency between what can be detected and the used threshold level. At each level certain abnormalities appeared. Setting threshold value is proved to be a function of image type and quality, purpose and application.

22 illus, 2 tables, 20 ref

003780   MITTAL U, SRIVASTAVA S, CHAWLA P (Computer Science and Engineering Dep, Lovely Professional Univ, Punjab- 144 001, Email: priyanka.22046@lpu.co.in) : Object detection and classification from thermal images using region based convolutional neural network. J Comput Sci 2019, 15(7), 961-71.

In recent years, object detection and classification has gained so much popularity in different application areas like face detection, selfdriving cars, pedestrian detection, security surveillance systems etc. The traditional detection methods like background subtraction, Gaussian Mixture Model (GMM), Support Vector Machine (SVM) have certain drawbacks like overlapping of objects, distortion due to smoke, fog, lightening conditions etc. In this paper, thermal images are used as thermal cameras capture the image by using the heat generated by the objects. Thermal camera images are not influenced by smoke and bad weather conditions which makes them a built-up apparatus in inquiry and safeguards or fire-fighting applications. These days, deep learning techniques are extensively used for detection and classification. In this paper, a comparative analysis has been done by applying Faster region based convolutional neural network on thermal images and visual spectrum images. The experimental results show that thermal camera images are better as compared to visible spectrum images.

7 illus, 4 tables, 39 ref

003760   ALI M H, ISMAIL E S, HAMZAH F M (Kebangsaan Malaysia Univ, Selangor, Malaysia, Email: esbi@ukm.edu.my) : A practical and secure hash function-based password authentication scheme. J Comput Sci 2019, 15(7), 954-60.

In this study, we propose a practical and secure hash functionbased password authentication scheme using smart cards. Our proposed scheme offers some advantages and interesting features. Firstly, the scheme does not require a verification table and is secure against the replay attacks, an attack that most of the existing schemes suffer. Secondly, any user of the scheme be allowed to change his or her account’s password efficiently. Thirdly, the time complexity for each algorithm in the proposed scheme are relatively low and minimal compared to some existing well-known password authentication schemes.

3 illus, 1 table, 29 ref