2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)最新文献

{"title":"Optimized Test Case Generation for Basis Path Testing using Improved Fitness Function with PSO","authors":"Updesh Jaiswal, Amarjeet Prajapati","doi":"10.1145/3474124.3474197","DOIUrl":"https://doi.org/10.1145/3474124.3474197","url":null,"abstract":"The generation of an optimal number of test cases for the Basis path testing is a crucial and challenging optimization problem in the field of software testing. In the literature, a variety of Basis path testing approaches have been proposed. Recently, the search-based optimization approaches for the Basis path testing have been found more effective compared to the traditional analytical based approaches of Basis path testing. Even the existing search-based Basis path testing approaches can generate effective test cases covering most of the paths, still, there are many paths are remained uncovered. In this work, we propose a Particle Swarm Optimization (PSO) based test case selection approach for the Basis path testing. In this contribution, we introduce an improved fitness function namely Improved Fitness Function (IFF) that can guide the PSO based optimization process towards selection of best test case. For this, we use a High Probability of Coverage (HPC) path to define the IFF. To demonstrate our proposed approach, we conducted a detailed case study over the Largest among Three Numbers (LTN) program. The results of our case study show that the proposed approach can produce more better results in terms of all linearly independent paths coverage of Control Flow Graph (CFG).","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124662647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Locally Linear Embedding based Indoor Localization in Internet of Things","authors":"Akshat Jain, Neeraj Jain","doi":"10.1145/3474124.3474183","DOIUrl":"https://doi.org/10.1145/3474124.3474183","url":null,"abstract":"With the upcoming of smart cities, numerous indoor localization applications plays a significant role. In outdoor, a Global Positioning System (GPS) is majorly used as it’s easy to deploy and provides high accuracy. However, in indoor localization accuracy becomes a challenge due to poor signal strength. This invokes the necessity for a mechanism to get precise node location. In this paper, a multilateration and Locally Linear Embedding (LLE) based localization approach is proposed. In the proposed mechanism, distance-RSSI characterization is done at the initial stage to obtain distances between each pair of sensor nodes. The multilateration method is used to obtain the course grain location of sensor nodes. Finally, LLE is applied to refine locations. Simulation results show that the proposed mechanism is robust and accurately localizes sensor nodes as compared to existing algorithms in an indoor environment.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128580569","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Malignancy Grade Identification and Classification of Brain MR Images with New 2D Co-occurrence Matrix and Wavelet Transformation","authors":"Ankit Vidyarthi, Jyoti Nagpal","doi":"10.1145/3474124.3474130","DOIUrl":"https://doi.org/10.1145/3474124.3474130","url":null,"abstract":"Malignancy is one of such terms in medical science that always requires quick attention. The proper identification and classification of such malignant cells were always considered as the challenging task. Moreover, with the use of computer assisted automation systems, identification of grading becomes easier but it requires a strong running algorithm for maintaining trust on results. This paper proposed a new algorithm in machine learning environment that fetches hidden patterns from the input MR images and found some relevant information about malignant cells. The proposed algorithm is the 2D co-occurrence matrix that uses pixel information for creating sample space. In addition of this 2D wavelet transformation was used to reduce the input image dimensions and fetching spectral information. The collective use of the DWT with proposed algorithm fetches better feature information about malignancy in brain MR images. The experimental result shows that the proposed approach gives better classification accuracy and performs well as compared with existing methods.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131009221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Close-Price Prediction using Online Kernel Adaptive Filtering","authors":"S. Mishra, Tanveer Ahmed, V. Mishra","doi":"10.1145/3474124.3474155","DOIUrl":"https://doi.org/10.1145/3474124.3474155","url":null,"abstract":"Stock price prediction is a challenging and a tedious task. Although various methods have been developed for issue, an investigation on accurate and low latency methods is not given much attention. In addition, traditional regression and classification methods require batch-oriented and independent training. Thus, they are not suitable for stock price prediction as the data we are working with is non-stationary with so many confluencing factors. In this paper, we propose an online learning-based kernel adaptive filtering approach for stock price prediction. Specifically, we work with ten different kernel filtering algorithms and propose a method to predict the next closing price. The idea is tested on fifty stocks of the NSE index with nine different time-windows such as one-minute, five-minutes, ten-minutes, fifteen-minutes, twenty-minutes, thirty-minutes, one hour, and one day. To this, it should be noted here that this article is the first wherein a stock is analyzed by looking at these different time windows. Moreover, the empirical results suggest that Kernel adaptive filtering is an efficient tool for high-frequency trading as well. The work presented here shows the predictive capability and superiority of the kernel adaptive filtering class of algorithms over classical regression and classification methods.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"2023 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114167454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TryItOut : Machine Learning Based Virtual Fashion Assistant","authors":"Ankit Ankit, Bharti Bharti, C. Prakash","doi":"10.1145/3474124.3474206","DOIUrl":"https://doi.org/10.1145/3474124.3474206","url":null,"abstract":"Image-based virtual try-on systems for fitting new in-shop clothes into a person image have attracted increasing research attention yet is still challenging. They are a future shopping method which can transform the way users shop. They not only change the target clothes into the most fitting shape seamlessly but also preserve the clothes identity such as texture, embroidery, prints etc. in the generated image. In this study, Generative adversarial networks (GAN) Model has been explored for generation of the clothing image and try-on image using CVPR Dataset. A novel approach to generate different poses using the state-of-the art Look into Person (LIP) Parser Model and superimposing the target cloth image. The segmentation of different clothing types was also done in order to identify the texture and clothing type of the person’s clothes and performs well for the images containing obstructions too. The proposed model overcome the limitations of low quality and clear background input images.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122674808","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FABEMD based Innovative Watermarking Method","authors":"Eswaraiah Rayachoti, Sudhir Tirumalasetty","doi":"10.1145/3474124.3474147","DOIUrl":"https://doi.org/10.1145/3474124.3474147","url":null,"abstract":"Telemedicine is overcoming obsession and is now a thriving research area. Commuting therapeutic images between distant locations is a common occurrence in telemedicine, as therapeutic images are often used by remote specialists to make inferences about diagnosis. The majority of therapeutic photographs are sent through the internet. When commuting over the internet, therapeutic photos can be attacked by various types of noise. The use of noise-affected therapeutic images may result in a misdiagnosis. As a result, the remote authority must vouch for the validity of the significant component (ROI) in the therapeutic picture and retrieve the ROI if it has been harmed by noise. This paper introduces a ground breaking watermarking method that uses Fast and Adaptive Bi-dimensional Empirical Mode Decomposition (FABEMD) to recover the ROI in a therapeutic picture when it is attacked by noise. Experiments with this novel technique have shown that the ROI in therapeutic images can be returned to its original state.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114447637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative Study of Topic Modeling and Word Embedding Approaches for Web Service Clustering","authors":"N. Agarwal, Geeta Sikka, L. Awasthi","doi":"10.1145/3474124.3474169","DOIUrl":"https://doi.org/10.1145/3474124.3474169","url":null,"abstract":"Vector space representation of web services plays a prominent role in enhancing the performance of different web service-based processes like clustering, recommendation, ranking, discovery, etc. Generally, Term Frequency - Inverse Document Frequency (TF-IDF) and topic modeling methods are widely used for service representation. In recent years, word embedding techniques have attracted researchers a lot because they can map services or documents based on semantic similarity. This paper provides a comparative analysis of two topic modeling techniques, i.e., Latent Dirichlet Allocation (LDA) and Gibbs Sampling algorithm for Dirichlet Multinomial Mixture (GSDMM) & two word embedding techniques, i.e., word2vec and fastText. These topic modeling and word embedding techniques are applied to a dataset of web service documents for vector space representation. K-Means clustering is used to analyze the performance, and results are evaluated based on standard evaluation criteria. Results demonstrate that word2vec model outperforms other techniques and provides a satisfactory improvement on clustering.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127685050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Functional Brain Image Clustering and Edge Analysis of Acute Stroke Speech Arrest MRI","authors":"Sudhanshu Saurabh, P. Gupta","doi":"10.1145/3474124.3474207","DOIUrl":"https://doi.org/10.1145/3474124.3474207","url":null,"abstract":"In the area of neural imaging the statistical and Mathematical analysis plays an important role in supervising the fMRI images of human brain. In this work, we have performed a cluster analysis of fMRI images of human brain with a connectivity architecture that takes the sequence of brain images. In particular, the edge extent is a major challenging piece of work in brain edge detection planning and it’s quantitative estimation. Edge detection is a fundamentally focus on to distinguish the tissues :WM, GM and CSF the signal intensities are abruptly changes along edge. Here, we have discussed the effectiveness of the procedure to location intensity of brain image and edge detection tasks. Cluster analysis for fMRI images with brain connectivity architecture that takes the sequence of brain image data. (i) Simulation of how clustering can be used for neuroimaging atlas to parcellate the brain. (ii) Investigated the quantitative evaluation of ROI. (iii) Analyzed the intensity in arbitrary frame from video data of speech arrest MRI. Due to overlapped voxel at the edges of brain region are not defined by specific intensities therefore we focus on intensities of MR images of the and performed the clustering using Python. Finally, we have compared the intensities of the MR images histogram.In the distribution of all the voxel intensities the realted intensities of and WM, GM,and CSF voxel respectively in the histogram are used the gradient based method to distinguish the distribution respectively with spatial prior = 0.1. We demonstrate the gradient information contains contrast and intensity of the brain image.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126667283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Traffic Signal Management using DRL for a Real-time Road Network in ITS","authors":"A. Paul, Krishn Bera, Devtanu Misra, Sattwik Barua, Saurabh Singh, Nishu Nishant Kumar, S. Mitra","doi":"10.1145/3474124.3474187","DOIUrl":"https://doi.org/10.1145/3474124.3474187","url":null,"abstract":"The acceleration of urbanisation and the development of the pace of industrialisation help to grow the population of metropolitan areas, thus increasing the density of traffic flow. The sole way of managing traffic congestion is to mitigate it through optimising traffic signals at the intersections of a vast road network. The synchronization amongst the traffic signals at intersections is strongly needed in order to alleviate congestion and to allow vehicles to travel smoothly along intersections. Reinforcement Learning (RL) techniques in Intelligent transportation system (ITS) are not feasible for the management of traffic signals of large road networks due to enormous information of the state-action pairs. To overcome this problem, the emerging technology of Deep Learning allows RL to form Deep Reinforcement Learning (DRL) to measure up previously unwavering decision-making issues, for handling high-dimensional states and action spaces. DRL agents perform tasks through perception, monitoring the environment through action and learning as well as analysing the results of actions. In the present work, a single DRL agent is trained using the Policy Gradient algorithm in four different categories of Deep Neural Networks (DNN) to control the traffic signals dynamically. In case of a static road network, the functional implementation and efficacy of the Policy Gradient algorithm cannot be analysed accurately due to the less intricate details of static network. Hence, two different dynamic real time road networks have been considered here. Moreover, the real-time spatio-temporal information congregated from the dynamic real time map is provided as an input, so that the traffic signal duration can be adjusted adaptively in order to manage the traffic flow appropriately. The overall success of the agent’s efficiency in different DNN models is compared here using simulation experiment. The viability of the simulation experiment is investigated using three separate simulation metrics against the baseline, which is fixed signal duration frameworks and indeed the suggested method outperforms the baseline. Moreover, The GRU model excels all other models in both the dynamic networks.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"26 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113978245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An AI based Solution for Predicting the Text Pattern from Sign Language","authors":"Bhargav, DN Abhishek, Deekshitha, Skanda Talanki, Sumalatha Aradhya, Thejaswini","doi":"10.1145/3474124.3474210","DOIUrl":"https://doi.org/10.1145/3474124.3474210","url":null,"abstract":"A large social group get benefit from sign language detection through technology, but it is an overlooked concept. Communicating with others in society is a primary aim of learning sign language. Communication between members of this social group is rare due to limited access to technology. Hearing-impaired people are left behind. As normal people cannot make signs, they need to use texting methods to communicate with hearing-impaired people, which is less than ideal. Increasingly, deaf people must be able to communicate naturally no matter the practitioner's knowledge of sign language. An analysis of sign language is based on the patterns of movement generated by the hand or finger, commonly referred to as sign language. The aim of this paper is to recognize sign language gestures using convolutional neural networks. The proposed solution would generate the text pattern from the sign gesture. An RGB camera was used to capture static sign language gestures. Preprocessed images were used to create the cleaned input images. The dataset of sign language gestures was trained and tested on multiple convolutional neural network layers. The trained model recognizes the hand gestures and generates the speech from the text. In addition to outlining the challenges posed by such a problem, it also outlines future opportunities.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123041654","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}