{"title":"Challenges and Approaches of Code-mixed Hate Speech Detection","authors":"Swayam Samparna Dash, Nikunja Bihari Kar","doi":"10.1109/MLCSS57186.2022.00060","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00060","url":null,"abstract":"The online platform and social media are very eye catchy for internet users. Platforms like YouTube, Twitter, Instagram, etc., are higher in demand due to their brilliant services. Users of these sights frequently comment on others' posts which may contain toxic speech. Some platforms also raise concerns about emerging of this activity. As the increase of hate speech is just next to impossible to control, the need to detect these contents through automated hate speech detection technologies arises. In this work, we focused on multi-lingual issues, especially Indo-European code-mixed languages. At first, we identified some issues related to code-mixed Indian languages. Then, we focused on the available solutions to this problem. We have gone through the works performed on machine learning and deep learning techniques and identified the limitations of those works. We have analyzed the present solutions and gone through the comparative studies of those. Our implementation is conducted on code-mixed twitter datasets providing several perceptions on hate speech. We have performed the experimental work on HASOC 2021 dataset. Our work contributes to the field of hate speech detection by comparing feature extraction and classifier algorithms (Machine Learning and Deep Learning). More specifically, the proposed work aimed at distinguishing Hate and Non-Hate speech from normal text.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116062657","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}
A. Kakumani, L. P. Sree, Chittimalla Sai Krishna, Greeshmitha Uppalapati, Gudimetla Santhoshi Sri Pavithra, Seshadri Harshini
{"title":"Semantic Segmentation of Cells in Microscopy Images via Pretrained Autoencoder and Attention U-Net","authors":"A. Kakumani, L. P. Sree, Chittimalla Sai Krishna, Greeshmitha Uppalapati, Gudimetla Santhoshi Sri Pavithra, Seshadri Harshini","doi":"10.1109/MLCSS57186.2022.00025","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00025","url":null,"abstract":"Cell segmentation is one of the most important steps for medical image examination. With the rapid advancement of the convolutional neural networks, deep learning-based approach has become popular for the segmentation and analyzing the cells. Despite this, accurate, general, and consistent segmentation is still required to accurately evaluate its morphological features, phenotypes, and sub-cellular dynamics. Previously U-Net architecture approaches have been proposed. However, a loss of some spatial information is observed. To enhance the performance of U-Net on various segmentation challenges, we have come up with a novel architecture called Pretrained Autoencoder with Attention U-N et. Trained autoencoder weights are assigned to the contraction pathway of U-Net and in addition to that attention block is added to the expansion pathway of the vanilla U-Net. The auto-encoder helps in pretraining the weights of the pixels and the attention block pays more attention to the relevant regions. Our approach achieved 98.27% accuracy when it came to segmenting the cells, it outperformed the state-of-the-art U-N et in terms of traditional parameters.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128704259","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":"Impact of Clustering technique in enhancing the Blockchain network performance","authors":"Amrutanshu Panigrahi, Ajit Kumar Nayak, R. Paul","doi":"10.1109/MLCSS57186.2022.00072","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00072","url":null,"abstract":"Blockchain technology facilitates transparency, de-centralization, immutability, and security for each transaction. The decentralization characteristics enable the block chain network to have different nodes as the Certificate Authority (CA) for a different transactions. Choosing a different validator for every individual transaction may increase the security perspective of the transaction, but it can lead to one major concern such as the network overhead increase. There can be several numbers of transactions for a single network and selecting a validator every time can cause a block propagation delay which also decreases the network efficiency. To avoid such kind of issue clustering of network nodes can be an emerging solution. In the current research work, the entire network participating nodes are considered for making different clusters based on the response time factor. Every cluster has the average response time as the threshold value. The node that wants to initiate a transaction needs to raise a minimum response time requirement and the cluster selection procedure will be executed based on the received response time value. In the current research work, the K-Means clustering with the Elbow method as an internal validation method is considered to decide the number of clusters. The computational time for both cases is compared to measure the effectiveness of the clustering process on the blockchain network.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129059278","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":"Machine learning approaches in medical image analysis of PCOS","authors":"Naila Jan, Anaa Makhdoomi, Palak Handa, Nidhi Goel","doi":"10.1109/MLCSS57186.2022.00017","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00017","url":null,"abstract":"Polycystic Ovary Syndrome (PCOS) is a complex hormonal disorder which is associated with diverse symptoms such as irregular menstrual cycles, obesity, acne issues, hirsutism, alopecia, and excess secretion of androgen in women. These symptoms may vary from patient to patient and therefore it is important to get it diagnosed at an early stage as it may lead to serious health conditions like heart diseases, diabetes, endometrial cancer etc. Diagnosis of PCOS is performed using physical examination, laboratory tests and ultrasound imaging. Ultrasound is used to detect follicles or immature eggs present inside an ovary. Ovaries with PCOS can be easily detected using ultrasound where trans vaginal ultrasound is considered to be the most efficient technique as it provides an internal view of the ovaries especially in patients suffering from obesity. The ultrasound report consist of details like number of follicles present, and size of ovaries, luminal thickness etc., Manual detection is costly, and lengthy and may be prone to physician's error due to shortage of health staff in developing countries like India and lead to higher false positive rates. Therefore, an automated system for PCOS segmentation and classification can help in escalating this task. This paper reviews existing state-of-the-art works where classification and segmentation have been used for automated detection of PCOS. Various machine learning, deep learning and transfer learning techniques are discussed. It was observed that this research field needs technological advancements through release of open-source datasets, and robust automatic pipelines for fruitful detection of PCOS in women.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130396586","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":"Computer Aided Study on Pharmacological Action and Molecular Mechanism of Salidroside","authors":"Han Junjun, Liu Junxia","doi":"10.1109/MLCSS57186.2022.00034","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00034","url":null,"abstract":"In order to grasp the pharmacological action and molecular mechanism of Salidroside, the computer aided technology is used to analyze it. Firstly, the research progress of pharmacological action and molecular mechanism of salidroside is discussed. Secondly, the computer aided model is established based on bat algorithm. And the pharmacological action and molecular mechanism are analyzed through case analysis, and results show that the proposed model can effectively obtain the pharmacological action and molecular mechanism of salidroside.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121373694","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}
N. Jena, Suhadra Sahoo, Chinmayee Biswal, B. K. Sahu
{"title":"Frequency stability analysis of an isolated micro grid system","authors":"N. Jena, Suhadra Sahoo, Chinmayee Biswal, B. K. Sahu","doi":"10.1109/MLCSS57186.2022.00068","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00068","url":null,"abstract":"Frequency stability in an isolated micro grid (MG) is a major issue to the load perturbation. So, automatic generation control (AGC) is inevitable to enhance the performance of the MG. In this work, a Selfish Herd Optimizer (SHO) based fractional two stage controller is employed to reap the enhanced frequency response with better stability. The proposed controller's performance is compared with a one stage classical controller endorsing integer & non-integer operators which has been reported in a recently published article. Here, stochastic model of wind and solar has been consider to realize the power fluctuation as happens in reality. Further, to observe the potency of this controller a random load based response has been evaluated.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"204 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116181254","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}
Apurva Singh, Aayushi Singh, Ritu Rani, A. Dev, Arun Sharma
{"title":"Hand Gesture Detection Using Convexity Hull and Convolutional Neural Network","authors":"Apurva Singh, Aayushi Singh, Ritu Rani, A. Dev, Arun Sharma","doi":"10.1109/MLCSS57186.2022.00027","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00027","url":null,"abstract":"Since the beginning of mankind, communication has always played a key role in everyday life and at the same time has pushed mankind to achieve targets for more convenient modes of communication. From the invention of the telephone to us having access to touch screen smartphones - we have come a long way. Unfortunately, we haven't been able to catch up at the same pace for people with speech impairment. While multiple studies on sign language recognition have been performed, there are still multiple constraints and limitations which are to be tackled. In this paper, application of convexity hull algorithm on hand gesture recognition has been proposed, where we further discuss the role of convexity defect and application of cosine rule in convexity hull. However, different skin tones and hand signs with similar gestures can cause false prediction thus to combat these limitations, CNN model has been proposed through which accuracy of 90% was achieved.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115850922","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":"Image-Based Food Calorie Estimation Using Incremental Learning","authors":"R. Desai, Amay Gada, Pranit Bari","doi":"10.1109/MLCSS57186.2022.00021","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00021","url":null,"abstract":"The burgeoning prevalence of obesity worldwide has triggered interest in the health and quality of life repercussions it carries. Weight loss shows promising results when it comes to tackling the consequences. Dietitians and nutritionists recommend logging daily intake of food items. Manual entry is tedious; hence, we propose a digital system that allows one to recognize a food item and estimate its calories by clicking a single image from the top. The proposed system identifies food items using an incrementally trained AdaBoost classifier, which takes as input a 94 dimension feature vector. The image is further processed using morphological operations, edge detection algorithms and contour detection techniques to segment the food item and compute its volume for calorie estimation. The classification algorithm gives a 90% accuracy while the estimated calories have a relative error of 18%.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132049530","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":"Study on The Psychological Stress Biofeedback Training System Based on Multiple Physiological Parameters","authors":"Jing Shen, Yue Cui","doi":"10.1109/MLCSS57186.2022.00051","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00051","url":null,"abstract":"In the development of modernization, although the innovation of information technology has brought new opportunities for the development of various fields, it has also increased the pressure of people's life and work in practice and innovation. In the long run, it will not only produce a variety of types of mental and psychological diseases, but also aggravate the difficulty of social construction and development. Nowadays, China's research on the treatment of mental illness is mainly focused on drugs. Although such research can alleviate the psychological problems of patients in a certain sense, it will also produce excessive diagnosis and treatment costs, and it is easy to make patients feel dependent for a long time. The new biofeedback technology could not only prevent patients from taking drugs for long periods of time, but also curb the side effects of medical treatments. Therefore, based on the systematic understanding of the biofeedback training system and the existing clinical application effects at home and abroad, this paper conducted an empirical analysis of the psychological stress biofeedback training system with a variety of biological parameters as the core. The final results show that it is very important to explore the application value of biofeedback technology system in depth during the study of psychological stress.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130706784","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}
Ishika Naik, Anika Jagati, Shruti Mishra, S. Satapathy
{"title":"Customer Relations and Marketing Analysis Model for Sales Enhancement","authors":"Ishika Naik, Anika Jagati, Shruti Mishra, S. Satapathy","doi":"10.1109/MLCSS57186.2022.00030","DOIUrl":"https://doi.org/10.1109/MLCSS57186.2022.00030","url":null,"abstract":"With the advancement of technology in each sector, more and more companies are becoming data-driven. Machine learning techniques have shaped businesses into becoming more profitable by automating processes and providing useful insights into their activities. The e-commerce retailers need to ensure customer satisfaction as their reputation and popularity relies solely on the customers. If customers witness the product qualities to be bad and delays in expected order deliveries, the sales of the particular retailer are bound to drop. Thus, identifying the performance of products is an important aspect of every e-commerce website. The paper concentrates on combining the various factors that might affect the ratings given by the customers and determining the product quality using machine learning techniques. The factors taken into consideration are the seller profiles associated with the e-commerce websites, the delay in order deliveries, the sentiment of the customer reviews and the product characteristics like price and volume.","PeriodicalId":322975,"journal":{"name":"2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132686044","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}