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

{"title":"A Full Mirror Computation Model for Edge-Cloud Computing","authors":"Yuanda Wang, Ye Xia, Youlin Zhang, D. Melissourgos, Olufemi O. Odegbile, Shigang Chen","doi":"10.1145/3474124.3474142","DOIUrl":"https://doi.org/10.1145/3474124.3474142","url":null,"abstract":"Edge computing has been gaining momentum lately as a means to complement cloud computing for shorter response time, better user experience, and improved data security. Traditional approaches of edge-cloud computing take two major forms: One is to offload the computation from an edge device to the cloud so as to take advantage of the virtually unlimited resources in the cloud and reduce the computation time. The other is to move selected computation to the edge devices where data are produced, actions are performed and users are located. However, in practice, it is often difficult to split the computation tasks of an application and decide which tasks should be performed in the cloud and which at the edge. The reason is that, for the same computation, it may sometimes be beneficial to execute it in the cloud while other times at the edge, depending on run-time conditions such as the data size, the type of computation, and the communication delay, which all varies from time to time. This paper proposes a new edge-cloud computing model, called the full mirror model, which provides a generic method to circumvent the problem of dynamic decisions on the execution location. With a two-thread implementation mechanism, the new model is able to achieve an execution completion time approximately equal to the smaller one between cloud execution and edge execution, regardless of what run-time conditions are. We test the new model by modifying an existing program for network traffic analysis so that it runs at both the edge and the cloud in a coordinated fashion. The experimental results demonstrate that the proposed model outperforms edge-alone computing and cloud-alone computing in reducing the execution time.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"292 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":"124202686","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":"Recent Trends in Artificial Intelligence for Emotion Detection using Facial Image Analysis","authors":"P. Jain, S. Quadri, Muskan Lalit","doi":"10.1145/3474124.3474205","DOIUrl":"https://doi.org/10.1145/3474124.3474205","url":null,"abstract":"Humans have certain social and emotional capabilities that help them to interact with other human beings, one such capability is to recognize the other human's emotions. This capability enhances human interactions to a great extent. As we move towards the age of increasing Human-Machine Interaction systems, we must strive to program our machines to achieve the so-called social and emotional capabilities algorithmically. A primary research frontier in emotion detection is recognizing it using facial images. Being able to recognize the emotions of a human being helps the machine adjust and tune itself to the human's needs and comfort. Emotion detection can be performed using various modalities such as video, audio, images, text, biometric information, etc. This study, explores the emerging trends in emotion recognition through facial images. Automated recognition of emotions of people has the potential to predict psychiatric illness or other latent mental health issues.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"28 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":"124549975","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":"Shallow learning for MTL in end-to-end RNN for basic sequence tagging","authors":"Rajat Subhra Bhowmick, Trina Ghosh, Astha Singh, Sayak Chakraborty, J. Sil","doi":"10.1145/3474124.3474160","DOIUrl":"https://doi.org/10.1145/3474124.3474160","url":null,"abstract":"Multitask learning (MTL) has been successfully applied for sequence tagging tasks in many machine learning approaches. The idea of MTL is employed to obtain better performance by sharing information among the tasks compared to a single task. However, most of the MTL in end-to-end sequence tagging models perform by sharing the entire set of parameters resulting in overwriting of parameters and need retraining of all the parameters. In the paper, a novel pipeline architecture has been proposed that effectively combines two RNN based sub-networks for sequence tagging tasks with minimal training overhead and truly acts as an end-to-end system. The proposed architecture performs Named entity recognition (NER) tagging as the primary sequence tagging task along with phrase tagging that works as the assistance sequence tagging task. To utilize the learning from the assisted network, we modify the base network by adding fully connected (FC) layers for NER. Our MTL approach tries to retain the learning parameters from individual tasks and, retraining is done only to the FC(shallow) layers of the modified base network. To validate the proposed MTL settings, we train on CoNLL 2003 corpus and compare the result with previously well established end-to-end based NER tagging models.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"9 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":"123116722","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":"Prostate Cancer Prognosis Using Multi-Layer Perceptron and Class Balancing Techniques","authors":"Surbhi Gupta, Manoj Kumar","doi":"10.1145/3474124.3474125","DOIUrl":"https://doi.org/10.1145/3474124.3474125","url":null,"abstract":"Prostate malignancy is one of the most common malignancies. Early prediction of a cancer diagnosis can upsurge the endurance rate of cancer patients. The advancement of cancer research is boosted with the advent of artificial intelligence. Researchers have developed programmes to aid in cancer detection and prognosis due to the availability of open-source healthcare statistics. Machine Learning (ML) algorithms play a vital role in the field of cancer prognosis. The current study highlights the applications of neural networks to predict prostate cancer. We have accessed prostate cancer records from a publically accessible data repository (Kaggle). Current research work stresses the applications of neural learning approach for cancer prognosis and attaining more accurate prediction outcomes. The study also stresses on the impact of different balancing techniques on imbalanced data. The proposed method enhanced the accurateness from 72% on the imbalanced data to 97% on the oversampled dataset. This study aims to determine whether an artificial neural network (multilayer perceptron, MLP) can accurately predict the diagnosis of prostate cancer. In addition, the experimental results confirm the necessity of data balancing techniques in classification.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"110 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":"115251909","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":"A Study of Network-on-Chip Performance","authors":"A. V. Bhaskar","doi":"10.1145/3474124.3474129","DOIUrl":"https://doi.org/10.1145/3474124.3474129","url":null,"abstract":"Network-on-Chip (NoC) technology was introduced by incorporating the concepts of computer networks for on-chip communication. The packet based communication has advantages over conventional bus based communication architectures. In this work we explore the performance of NoC by varying the parameters of NoC like topology, injection rate, routing algorithm, traffic pattern ...etc. We compare the throughput and latency for different configurations of NoC. From the performance analysis a mesh network with 4x4 size, number of virtual channels 4, traffic pattern as tornado and routing algorithm as dimension order routing has the low latency and high throughput.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"1 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":"130808330","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":"Applying Cognitive and Neural Network Approach over Control Flow Graph for Software Defect Prediction","authors":"K. Rajnish, Vandana Bhattacharjee, Vishnu Chandrabanshi","doi":"10.1145/3474124.3474127","DOIUrl":"https://doi.org/10.1145/3474124.3474127","url":null,"abstract":"∗Like all other engineering products, prediction of defects in software, plays an important role in the dynamic research areas of software engineering. A defect is an error, bug, flaw, fault, breakdown or mistakes in software that causes it to create an inaccurate or unpredicted outcome. Most of the faults are from source code or design, some of them are from the improper code generating from compilers. The software engineering community is striving for valid measurements to enhance the quality of software. As software ages, the task of maintaining and comprehending them becomes complex and expensive. It has been estimated that 60% of the software maintenance effort is due to the comprehension of the source code. The cognitive informatics plays an important role to quantify the degree of difficulty or the efforts employed by developers to comprehend the source code. In 2003, the cognitive weight has been assigned to each possible basic control structure of software by conducting several empirical studies. These cognitive weights are utilized by several researchers to evaluate the cognitive complexity for software system. In this paper an attempt has been made to classify the Control Flow Graphs (CFGs) node according to their node features and each unique feature value is assigned an integer encoding value which we find the appropriate parameters (or features) of the source code file through cognitive complexity measures and incorporate of cognitive complexity measures outcome as nodes in CFGs and generates same based on the node-connectivity’s for a graph. Vector matrix of graph is then created and apply Graph Convolutional Network (GCN) to get the feature representation of graph. Finally, we developed deep neural network Keras Model (KM) to predict software defects. The framework used is Python Programming Language with Keras and TensorFlow. An analysis is done based on the data collected from PG students of our institute. The approaches are evaluated based on Accuracy, Receiver Operating Characteristics (ROC), known as the Area Under Curve (AUC), F-Measure, and Precision. The experimental results indicated that KM model classifiers outperformed well in all evaluation criteria against state of art methods (Naïve Bayes classifier (NB), Support Vector Machine (SVM) classifier and Random forest (RF) classifier. ∗Place the footnote text for the author (if applicable) here. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from permissions@acm.org. IC3 ’21, Au","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"18 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":"130881476","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":"Improving Classification Performance of Deep Learning Models Using Bio-Inspired Computing","authors":"Vaishali Baviskar, M. Verma, Pradeep Chatterjee","doi":"10.1145/3474124.3474174","DOIUrl":"https://doi.org/10.1145/3474124.3474174","url":null,"abstract":"Deep learning models have paved the way towards generating high-efficiency classification systems for multiple applications. These applications include lung disease classification, electrocardiogram classification, electroencephalogram classification; forest cover classification, etc. All these applications rely on efficient feature selection capabilities of deep learning models. Models like convolutional neural network (CNN), recurrent neural networks (RNNs), long-short-term-memory (LSTM) etc. are used for this purpose. These models tend to evaluate all possible feature combinations via iterative window-based feature processing. Thereby trying to cover indefinite number of feature combinations in order to classify a definite number of features into a definite number of classes. All these models have a stopping-criteria, which depends upon the error rate difference of previous current iteration. If the error rate is less than a particular threshold, and number of iterations are above a certain predefined value, then training of these networks is stopped. This property of deep learning models limits their real-time performance, because training stops even if the accuracy is lower than expected. The reason for this low accuracy is high dimensionality of search space, due to which selection of the most optimum features is skipped. In order to reduce the probability of such conditions, this text proposes a bio-inspired Genetic Algorithm model for accuracy-based feature selection. The selected features are given to different deep learning models like LSTM RNN, and their internal performance is evaluated. Here, heart failure disease dataset from kaggle is used, and it is observed that due to pre-feature selection process, overall accuracy of these models is improved by 10, while precision, recall fMeasure scores are improved by 15 for heart disease data sets. The specificity and sensitivity performance is improved by 20 when compared with RNN and LSTM models individually.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"1 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":"126642034","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":"Investigate the Impact of Resampling Techniques on Imbalanced Datasets: A Case Study in Plant Disease Prediction","authors":"A. Bhatia, A. Chug, A. Singh, Dinesh Singh","doi":"10.1145/3474124.3474164","DOIUrl":"https://doi.org/10.1145/3474124.3474164","url":null,"abstract":"In the current circumstances, plant disease prediction is drawing the attention of various scientists and agricultural experts. The prediction of plant diseases is the foundation of the early identification of diseases in plants efficiently using machine-learning algorithms. However, this area of agriculture science faces the challenge of the imbalanced dataset. Imbalanced datasets can bias the results of machine learning models towards the major class containing the largest number of samples of datasets. This problem can be dealt with the use of resampling techniques that balance the dataset to improve the efficiency of machine learning models. Hence, in the current study, the impact of resampling techniques such as Importance Sampling, Random over Sampling, Synthetic Minority Over-sampling Technique, and Random under Sampling has been evaluated on imbalanced plant disease datasets, i.e., Tomato Powdery Mildew Disease and Soybean Large using various machine-learning classifiers, i.e., Random Forest, Naïve Bayes, Multinomial Logistic Regression and Bagged Classification and Regression Tree. The results of this evaluation show that amongst all the resampling techniques Random Over Sampling has performed the best with 99.24% accuracy for Tomato Powdery Mildew Disease dataset for Random Forest Classifier, whereas Synthetic Minority Over-sampling Technique performed the best with 98.53% accuracy for Soybean Large dataset in case of Bagged Classification and Regression Tree Classifier.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"27 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":"114041398","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":"Virtual Machine Introspection in Virtualization: A Security Perspective","authors":"D. Kapil, P. Mishra","doi":"10.1145/3474124.3474140","DOIUrl":"https://doi.org/10.1145/3474124.3474140","url":null,"abstract":"Virtualization technology has gained enough attention in several fields such as Cloud Computing, the Internet of Things (IoT), and software defined networking (SDN), etc. However, security issues in virtualization impose several questions on the adoption of this technology and raise strong security concerns. Most of the researchers have employed traditional security approaches in virtualization. However, these approaches are not effective enough for the modern environment. Instead, Introspection-based approaches such as Virtual Machine Introspection (VMI) are more useful to protect the virtualized environment. VMI approaches provide robust solutions in identifying the user and kernel-level processes-based attacks by positioning the security tool outside the VM. The successful implementation of these solutions is still challenging due to having heterogeneous design architectures of hypervisors. In this paper, a comprehensive study of VMI approaches is provided with the perspective of facilitating secure attack detection solutions in the virtualization environment. Various open research challenges are identified and discussed in detail. A brief discussion on the various VMI libraries is provided to give some practical insights to readers. We hope that our work will motivate researchers to work in this direction more actively.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"119 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":"126855600","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":"Topic Wise Influence Maximisation based on fuzzy modelling, Sentiments, Engagement, Activity and Connectivity Indexes","authors":"Neetu Sardana, Dhanshree Tejwani, Tanvi Thakur, Mansi Mehrotra","doi":"10.1145/3474124.3474192","DOIUrl":"https://doi.org/10.1145/3474124.3474192","url":null,"abstract":"People's interactions, communications, and engagement have all changed as a result of the rise of social media. These networks are vital for expanding scope and impact. People in these networks influence each other. Social influencers spread the knowledge in the network. Identification of such influencers is a challenging task. Generally, in past studies varied qualitative metrics like centrality, connectivity etc has been popularly used for identifying the influencers. In a network it has been noticed that every person interacts in the network in context to its own interest areas. He influences specific to his interest domains. Based on this belief, the aim of this paper is to detect topic-wise influencers in social media so that we can target person or influencer appropriately for influence maximisation. This paper focuses on measuring the strength of topic-level social influence using sentiments of the text used for interaction by social network user and later fuzzy modeling has been applied. Fuzzy modeling help in finding the person probability index of influence (positive or negative) in context to a different topics he is contributing in social media. In addition, three user features- engagement Index, activity index and connectivity Index has been utilized to compute the user overall influencer score. For experimentation, the tweets from the Twitter have been used to evaluate the proposed method.","PeriodicalId":144611,"journal":{"name":"2021 Thirteenth International Conference on Contemporary Computing (IC3-2021)","volume":"12 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":"132661271","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}