Subhash Tatale

Subhash Tatale

Auto-generated profile, based on publicly available information

Subhash Tatale

Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, India

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 March 2020 in International Journal of Scientific Research in Science, Engineering and Technology
Verified
Journal Article
Open access
NSNitin Sakhare
Nitin Sakhare
STSubhash B. Tatale
Subhash B. Tatale
SSS.R. Sakhare
S.R. Sakhare
HDHemant Dusaane
Hemant Dusaane
MPMamta Puri
Mamta Puri
PGPadmavati Ghule
Padmavati Ghule
Due to rise in number of vehicles the traffic management has become a major problem. Manual traffic system is not efficient. This paper presents adaptive traffic management system using Internet of Things (IoT) and Image processing. The proposed system has capability to analyze real time data using image processing. Using cameras, different lanes are monitored constantly. The data obtained from different lanes are examined. Detection and counting of number of vehicles in each lane is done by using image processing. The count from each lane is sent to the central processing unit. According to the count of vehicles algorithm calculates waiting time for each lane, then the signal lights will be decided. This system reduces the average waiting time and increases the efficiency of traffic clearance. The system also reduces the pollution due CO2 emission and useful in emergency situations, thus being adaptive traffic management using Internet of Things (IoT).

30 April 2022 in Revue d'intelligence artificielle
Verified
Journal Article
Closed access
STSubhash Tatale
Subhash Tatale
VPVudatha Chandra Prakash
Vudatha Chandra Prakash
Combinatorial testing is an effective method for generating test cases. Pairwise testing is a combinatorial approach that evaluates the interactions between the input test parameters while reducing test case size by selecting a broader search area. Most combinatorial testing research focuses on developing novel approaches for generating an optimal number of test cases that cover pairwise combinations of input test parameters. Using existing test case generation techniques, optimal or near-optimal combinatorial test cases are generated in polynomial time. The authors presented the Q-value-based Particle Swarm Optimization (Q-PSO) technique for efficiently and effectively generating an optimal number of test cases. The primary goals of the proposed technique are to generate test cases using a Q-value based PSO, which is easier to build and has fewer parameters to define than other meta-heuristic search methodologies and to put the proposed technique into practice and report on an empirical study that examines and verifies the significant impact factors in the proposed approach. Q-value is used to evaluate the particles (referred to as test cases) in the Q-PSO. The reward is totalled in the Q-value, which serves as the fitness function for PSO evolution. The Q-value of each particle determines its performance and indicates how quickly the particle can lead the system's state to the set of objective states. The authors used the Q-PSO technique to validate the efficiency and efficacy of the proposed approach. The Q-PSO technique's results are compared to existing metaheuristics and computation-based techniques. In most inputs based on the development environment, meta-heuristic search techniques take significantly longer than other greedy techniques. For some inputs, the proposed Q-PSO technique outperforms existing meta-heuristics techniques. Q-PSO results are also compared to IPOG, ITCH, Jenny, TConfig, TVG, and other well-known computational-based techniques. The goal of the comparison is to examine how the size of the test cases generated has grown over time.

4 January 2022 in International Journal of System Assurance Engineering and Management
Verified
Journal Article
Closed access
PDF file
STSubhash Tatale
Subhash Tatale
VPV. Chandra Prakash
V. Chandra Prakash

28 February 2022 in Ingénierie des Systèmes d'information
Verified
Journal Article
Closed access
STSubhash Tatale
Subhash Tatale
VPVudatha Chandra Prakash
Vudatha Chandra Prakash
Generation of test cases is one of the essential activities of the software testing process. The process of executing a programme to identify defects to improve the system's quality is known as software testing. Manually writing test cases takes time, effort, and money. On the other hand, generating test cases automatically is the solution to this problem. For this automation process, a model-based test case generation technique would be acceptable. A model is usually required to generate test cases in the model-based testing technique. Nowadays, researchers have relied on the activity diagram to generate test cases. Test cases for combinatorial logic systems are required. Combinatorial testing is essential for producing a small number of test cases and identifying errors occurred by interactions between system input parameters. Information about constraints, parameters and its values are required for generation of test cases. It is difficult to extract information regarding constraints, parameters, its values, and interactions between parameters from an Activity Diagram. A novel approach is proposed to extract this information from an Activity Diagram. The authors created a tool that automatically generates combinatorial test cases using UML Activity Diagrams. The proposed tool has two main parts. First, the combinatorial test design model is developed for extraction of input parameters. Second part is generation of optimized number of combinatorial test cases using Particle Swarm Optimization algorithm. Finally, the authors experimented on a real-world case study namely viz. Railway Reservation using the proposed tool, and it is shown that the proposed tool generated optimum number of combinatorial test cases.

16 March 2017
Verified
Conference Paper
Closed access
NBNivedita S. Bhirud
Nivedita S. Bhirud
STSubhash Tatale
Subhash Tatale
To generate large-scale resource management, grid based computing play a crucial role. It represents various geographically dispersed computational resources, i.e. workstations, PCs, cluster, storage devices, and database as fused integrated system, which can play dual roles of synchronized resource donator and consumer in such distributed computation environment. Now a day, in ubiquitous environment the use of embedded devices and mobile has grown intensively, produces abundant data which need to be processed. But, as these ubiquitous devices have limited power in terms of bandwidth, CPU, battery, storage; these applications services require more powerful computational resources. To fulfill these requirements, Grid can act as promising computational services provider to ubiquitous computing application. In this paper, we represent a competitive model, describing the interaction between Grid computational resources as competing service provider whereas ubiquitous applications as consumer. We represent Contract Net Protocol model for such competitive environment for quality of service (QoS) offered by Grid Service Provider (GSP). We have also studied model for the same competitive environment based on equilibrium behavior under definite QoS provision and the stochastic demand. Our proposed model and performance results give out appropriate strategies for real-time grid environment.

1 June 2019
Verified
Conference Paper
Closed access
STSubhash Tatale
Subhash Tatale
PKPooja Kharade
Pooja Kharade
ASAltaf Shaikh
Altaf Shaikh
AKAnuj Kamble
Anuj Kamble
SKShashank Kuyate
Shashank Kuyate
In order to convert a physical problem into a computational one, there should be libraries to support the execution of the program. Insilico is a library used to simulate network of neurons. The simulator numerically integrates a system of coupled non-linear ordinary differential equation (ODE). This study is to provide a stepwise optimization mechanism for the sequential code of this library into a highly parallelized one which can exploit the available processor capabilities and which in turn will effectively reduce the time and increase the efficiency of the application. The one under study is an API to simulate neurons of the olfactory system whose code is highly data dependent with a number of integral calculations. We propose a way of optimizing the application by parallelizing it through OpenMP and efficiently using the massive thread and data parallelism available on the same.