2022 IEEE International Conference on Data Science and Information System (ICDSIS)最新文献_第8页

sEMG Sensor-Based Human Lower Limb Activity Recognition Using Machine Learning Algorithms 基于表面肌电信号传感器的人类下肢活动识别与机器学习算法

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915897

Ankit Vijayvargiya, Bhoomika Dubey, Nidhi Kumari, K. Kumar, Himanshu Suthar, Rajesh Kumar

{"title":"sEMG Sensor-Based Human Lower Limb Activity Recognition Using Machine Learning Algorithms","authors":"Ankit Vijayvargiya, Bhoomika Dubey, Nidhi Kumari, K. Kumar, Himanshu Suthar, Rajesh Kumar","doi":"10.1109/ICDSIS55133.2022.9915897","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915897","url":null,"abstract":"Human lower limb activity recognition focuses on determining the activities of a person by monitoring their actions on the basis of datasets acquired via sensors such as accelerometers, gyroscopes, surface electromyography (sEMG), etc. sEMG is a computer-aided approach that incorporates useful information regarding movements of limbs and is also used for analyzing and recording the electrical activity generated by skeletal muscles. This paper demonstrates the analysis of the sEMG sensor-based dataset obtained from different muscles of 22 subjects performing activities such as walking, sitting, and standing. Out of these subjects, 11 seemed normal and the rest exhibited abnormalities. As a consequence of unprocessed data, discrete wavelet transform is applied to denoise the signal. Further, the overlapping windowing approach is used to execute the signal’s segmentation, followed by the procedure of feature extraction, which is carried out by extracting five-time domain features. Several machine learning models, such as random forest, gradient boosting, k-nearest neighbors, support vector machine using radial basis function, and the polynomial kernel were implemented. The results show that random forest, having cross-validation of 5-fold, achieved the best accuracy for normal (85.68%) and abnormal subjects (83.96%) in determining human activity.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130782963","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}

引用次数: 1

Deepfake Detection in Videos and Picture: Analysis of Deep Learning Models and Dataset 视频和图片中的深度伪造检测:深度学习模型和数据集的分析

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915885

S. Chauhan, Nitin Jain, Satish Chandra Pandey, Aakash Chabaque

{"title":"Deepfake Detection in Videos and Picture: Analysis of Deep Learning Models and Dataset","authors":"S. Chauhan, Nitin Jain, Satish Chandra Pandey, Aakash Chabaque","doi":"10.1109/ICDSIS55133.2022.9915885","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915885","url":null,"abstract":"Deepfake detection is the concept of distinguishing a computer manipulated graphic from a real recorded graphic. The technology used for this purpose is deep learning. It is a sub branch of artificial intelligence. With technology becoming more readily available, deepfakes are also increasing in use in recent years. It becomes evident that a system is needed that detects deepfakes and prevents its use in suspicious activities. Development of a deepfake detection technology becomes evident to avoid the use of deepfakes in such activities. For this purpose, many tech giants have assimilated huge datasets which consist of videos that were made using deepfakes already available. To detect a deepfake, one requires an equally capable or even better algorithm and detection technique. Generative Adversarial Nets, GANs, is one such technique that might be able to rival other deepfake techniques. This paper will discuss various methods to apply to detect deep fakes along with the process, libraries used, dataset liabilities and limitations, analysis and efficiency. Since Deep Learning technology is evolving each day with new innovations, this paper provides a comparative study about methods that have already been tested and their limitations with respective models and how to possibly make them more efficient.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"66 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130875815","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}

引用次数: 1

An Optimization Based Anonymous Messaging System for Data Security in Delay Tolerant Network 基于优化的容延迟网络数据安全匿名消息传递系统

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915944

P. Gantayat, R. Tiwari, A. Misra

{"title":"An Optimization Based Anonymous Messaging System for Data Security in Delay Tolerant Network","authors":"P. Gantayat, R. Tiwari, A. Misra","doi":"10.1109/ICDSIS55133.2022.9915944","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915944","url":null,"abstract":"Nowadays, the essential need of the Delay Tolerant Network (DTN) is anonymity and security. The protection of sensitive information is more critical in communication environments. Moreover, anonymous communication plays an important role to enhance the communication of DTN. So in this research work design, a novel Honey Bee-based Anonymous Messaging System (HBAMS) model for enhancing the security and communication in the DTN environment and the developed framework is implemented in MATLAB tool. Additionally, design a message forwarding system for enhancing the performance of delivering messages from the source to the destination. As well, a public key cryptosystem is utilized to encrypt data from the plain text into a ciphertext for enhancing security. Consequently, update the honey bee fitness in the cryptosystem to accurate key generation. To check the reliability of the designed model launch attack in the DTN environment and the attack is identified and neglected using the designed model. The gained performance of the designed model is compared with other existing techniques in terms of delivery rate, overhead, packet drop, delay, and CPU time.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131060616","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}

引用次数: 0

Smart System for Realtime Electrocardiogram Monitoring and Storage 智能实时心电图监测与存储系统

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915837

Shree Vallabha A, P. Nethra, R. Rashmitha, T. Prathyusha, S. Bharathi

{"title":"Smart System for Realtime Electrocardiogram Monitoring and Storage","authors":"Shree Vallabha A, P. Nethra, R. Rashmitha, T. Prathyusha, S. Bharathi","doi":"10.1109/ICDSIS55133.2022.9915837","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915837","url":null,"abstract":"In the past few years, the fields of Internet of things, cloud computing and mobile application development have significantly advanced and improved the remote healthcare industry. IOT technology especially has helped in bringing together the both doctors and patients massively. Through this paper, an IOT based solution for Electrocardiogram(ECG) monitoring and the result storage is proposed. The system is built with sensors, ESP32 Wi-Fi module, ESP32 Camera module, Web Sockets and cloud based web applications. Cloud services are helping us tremendously in storing data and real-time monitoring of that data for better diagnosis and treatment of the patient are provided. Patients vital data can be sent to physicians and monitored on a regular basis. According to the current research, heart disease is increasing massively in India. It states that with upcoming years, the number of heart patients in India will surpass all the countries. This fact itself shows how important it is for monitoring the heart condition. The ECG machines which are available in hospitals are quiet expensive. The aim of this project is to provide a cost efficient solution which helps people to afford ECG monitoring at ease.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128200132","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}

引用次数: 0

Web-Based Heart Disease Prognosis using Neural Network and Hybrid Approach 基于网络的心脏疾病预测应用神经网络和混合方法

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915876

Sujal B H, Nanthini J, M. Reddy

{"title":"Web-Based Heart Disease Prognosis using Neural Network and Hybrid Approach","authors":"Sujal B H, Nanthini J, M. Reddy","doi":"10.1109/ICDSIS55133.2022.9915876","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915876","url":null,"abstract":"Heart illness alludes to a condition where the veins are obstructed and the heart quits working. A considerable lot of the specialists have reasoned that this illness has turned into the main source for death cases. It is frightened that irregularities must be distinguished and perceived in its last stages. Anyway it is treatable assuming the individual distinguishes the sickness prior. The objective of this task is to foster an information science structure which tends to how to find the possibilities of presence of coronary illness by applying different characterization calculations, impact and appropriation of different boundaries that are assuming a significant part in sickness expectation alongside perceptions on cardiovascular clinical documentation. To limit the indicative blunder brought about by the intricacy of visual and emotional understanding, this work significantly means to observe the ideal order calculation on the coronary illness impacted wellbeing records and significantly affecting boundaries. This can be utilized for foreseeing coronary illness on the order reports. This exploratory work centers around the exhibition of the framework that was tried and ordered by different calculations, for example, Random Forest, Vector support, Logistic relapse, KNN, Naiive Bayes, Gradient helping calculations, Neural organization and hybrid models for building the coronary illness forecast model and assessing the presentation of the model. A web application is made to take a gander at the aftereffects of the models and their way of behaving with the assistance of a dataset. This way we get to know whether the individual has higher possibilities of getting a coronary illness or not.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124336369","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}

引用次数: 0

A Federated Texture Learning and Scheduling (FTLS) for Energy Efficient Data Aggregation Model in WSN System 基于联邦纹理学习和调度的WSN系统节能数据聚合模型

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915975

C. L. Anitha, R. Sumathi

{"title":"A Federated Texture Learning and Scheduling (FTLS) for Energy Efficient Data Aggregation Model in WSN System","authors":"C. L. Anitha, R. Sumathi","doi":"10.1109/ICDSIS55133.2022.9915975","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915975","url":null,"abstract":"In the Wireless Sensor Network (WSN) system, the sensor data aggregation and the dissemination are major key factor that needs to consider for the effective sensor data transmission over the sensor nodes. For that, the statistical parameters from the sensor data that are captures by the sensor deices in different applications. The wireless sensors are sending their parameters to the sink for further analytical process and for the sensor data aggregation. The main features of this paper is to analyse the different clustering models for the sensor data feature learning models to enhance the texture based learning model by using Federated Texture Learning and Scheduling (FTLS). This also improves the data preprocessing, aggregation and clustering, based on the feature learning and scheduling of cluster management. This leads to energy efficient clustering model and the data aggregation model in WSN network system. Typically, the sensor data prediction and the arrangement becomes the critical issue in the industrial communication systems based on the size of data arguments. Considering of this, the proposed work intends to develop an optimization model for reducing the dimensionality of sensor data with improved classification performance. Related to that the machine learning based clustering technique is to develop the data arrangement with better performance rate in terms of statistical analysis and reduced time complexity factors. The experimental result justifies the performance of proposed work by comparing the existing methods by using validation of parameters of statistical analysis such as Sensitivity, Precision, F-Score and Accuracy.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"99 42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121490273","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}

引用次数: 0

Effective Reinforcement Learning using Transfer Learning 使用迁移学习的有效强化学习

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915962

N. Sandeep Varma, K. Pradyumna Rahul, Vaishnavi Sinha

引用次数: 0

HCGAN-Net: Classification of HSIs using Super PCA based Gabor Filtering with GAN HCGAN-Net:使用基于GAN的Gabor滤波的超级PCA对hsi进行分类

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915861

M. Sireesha, P. Naganjaneyulu, K. Babulu

{"title":"HCGAN-Net: Classification of HSIs using Super PCA based Gabor Filtering with GAN","authors":"M. Sireesha, P. Naganjaneyulu, K. Babulu","doi":"10.1109/ICDSIS55133.2022.9915861","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915861","url":null,"abstract":"The hyperspectral image (HSI) classification applications become widespread in multiple applications. Therefore, the accurate classification of ground features using HSIs is an important research topic that has received a lot of interest. However, the conventional approaches failed to classify the pixels perfectly, which resulted in reduced accuracy. Thus, this work is focused on implementation of HSI classification using generative adversarial networks (HCGAN-Net). Initially, Gabor filtering is applied on HSIs for elimination of different types of noises, which also extracts the spatial features. Then, probabilistic principal component analysis (PCA) is applied to perform the dimensionality reduction operation, which also selects the best features using probability dependencies between spatial features. Then, spatial features are extracted for each spectral band and forms the hybrid spatial-spectral features. Finally, HCGAN-Net is used to performs the HSI classification operation using trained spatial-spectral features. The simulation results show that the proposed HCGAN-Net resulted in superior subjective and objective performance as compared to state of art HSI classifiers on various datasets.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"47 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126006917","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}

引用次数: 0

Study and Analysis of Energy Efficient Data Aggregation Techniques for Wireless Sensor Networks 无线传感器网络中节能数据聚合技术的研究与分析

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915854

S. Kokilavani, N. Sathish Kumar, A. S. Narmadha

{"title":"Study and Analysis of Energy Efficient Data Aggregation Techniques for Wireless Sensor Networks","authors":"S. Kokilavani, N. Sathish Kumar, A. S. Narmadha","doi":"10.1109/ICDSIS55133.2022.9915854","DOIUrl":"https://doi.org/10.1109/ICDSIS55133.2022.9915854","url":null,"abstract":"Data aggregation is an important process in WSN. It is a process of data condensation from all source nodes in the network propagating towards the destination node (or) base station. Redundant information is removed from the data streams and only the superior data is forwarded to the base station. Hence this plays a very important role in cost minimization and better energy management. Aggregations of data, redundancy removal, energy efficiency, Energy Consumption, network life time, efficient routing algorithms, storage capacity, and bandwidth constraints, delay optimizations are some of the challenging task in this network. The hypothetical analysis and the simulation assessment shows that the proposed aggregation protocols demonstrate a better performance in the privacy preserving and the communication efficiency. This paper presents a hypothetical study, simulation testing using NS-2 Simulator and performance comparison of factors with proposed data aggregation algorithms. From the analysis it is observed that the proposed algorithm demonstrates a superior network life time and better energy consumption when compared to the other classical algorithms.","PeriodicalId":178360,"journal":{"name":"2022 IEEE International Conference on Data Science and Information System (ICDSIS)","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133935023","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}

引用次数: 0

Skin Lesion Segmentation Using SCU-Net with FNLM Preprocessing 基于FNLM预处理的SCU-Net皮肤病灶分割

2022 IEEE International Conference on Data Science and Information System (ICDSIS) Pub Date : 2022-07-29 DOI: 10.1109/ICDSIS55133.2022.9915935

V. S. S. P. R. Gottumukkala, N. Kumaran, V. Sekhar

引用次数: 0