检索结果-内蒙古大学图书馆

6th International Conference on Innovative Computing and Communication, ICICC 2023

作者： Chakraverty, Yuvraj Kaintura, Aman Kumar, Bharat Khanna, Ashish Sharma, Moolchand Pareek, Piyush Kumar Department of Computer Science and Engineering Maharaja Agrasen Institute of Technology New Delhi India Department of Artificial Intelligence and Machine Learning and IPR Cell Nitte Meenakshi Institute of Technology Bengaluru India

ISBN: (纸本)9789819940707

Online comments can often be toxic, offensive, and harmful to individuals and communities. In recent years, there has been a growing need to automatically identify and mitigate these toxic comments. For this problem, NLP models are often used to identify such toxicity and harshness but each model has its own efficiency and performance limitations. In this paper, we propose the use of the bidirectional encoder representations from transformers (BERT) algorithm for toxicity classification of online comments. BERT is a state-of-the-art natural language processing model developed by Google in 2018 that has shown strong results on a variety of tasks. In this paper, we used the BERT algorithm for toxicity classification and evaluated its performance on a real world dataset and performed comparative analysis with conventional NLP models, logistic regression (TF-IDF) over which BERT showed an improvement of 6.9% in accuracy, 26.1% in f1-score, 21.5% in ROC score;logistic regression (BOW) over which BERT showed an improvement of 9.1% in accuracy, 70.6% in f1-score, 39.8% in ROC score;multinomialNB (BOW) over which BERT showed an improvement of 9.2% in accuracy, 25.9% in f1-score, 10.6% in ROC score. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A Resourceful Energy Management and Improved Security in Wireless Sensor Networks by Optimized Energy-Based Security Prototype

引用

SN computer science 2025年第3期6卷 1-13页

作者： Arya, Nancy Deore, Shailesh Shivaji Sharma, Mahendra Verma, Amit Patibandla, R. S. M. Lakshmi Krishna, K. Murali Pareek, Piyush Kumar Department of Computer Science and Engineering School of Engineering & Sciences GD Goenka University Sohna Gurugram India Department of Computer Engineering SSVPS B S DEORE College of Engineering Maharashtra Dhule India DoIT IMT College of Engineering UP Greater Noida India Department of Computer Science University Centre for Research and Development Chandigarh University Gharuan Punjab Mohali India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Department of Electronics Communication Engineering Rajalakshmi Engineering College TN Chennai India Department of AIML and IPR Cell Nitte Meenakshi Institute of Technology Bengaluru India

One must admit that while using a number of remote sensing points with limited nodes, it is crucial to optimize resource usage as intensely as possible and have a secure network with the least compromises, even though WSNs are applied in increasing numbers of industries. When deploying WSN, power utilization and ability to withstand a number of threats and attacks are important factors to be considered. This work presents a technique for a routing protocol that determines the shortest path between two nodes in a network while at the same time trying to conserve energy. Lifetime and energy consumption of the networks are two important factors when designing new protocols for WSN. An important problem of finding a load-sharing routing method with less energy consumption is difficult. TBEBR routing protocol optimizes the parameters that lead to minimal energy dissipation to enhance the lifetime of the network by identifying the path with the least energy consumption possible. Throughput, overhead, packet loss and end to end delay were used as performance parameters to assess the routing protocol. The analysis of the overall efficiency of the routing concept as well as the method of its application was described. As far as the performance of network and nodes is concerned, it is clear that TBEBR outperforms both DSR and AODV. For WSNs, the proposed routing protocol aims at minimizing the energy issue, which is a disadvantage of the technology. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： DoS attack EWMA Unit energy requirement WSN

来源：评论

学校读者我要写书评

暂无评论

Robust Fingerprint Minutiae Extraction and Matching Using Fully Connected Deep Convolutional Neural Network and Improved SIFT 2

Robust Fingerprint Minutiae Extraction and Matching Using Fu...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Husain, Saif O. Reddy, R.Archana Pareek, Piyush Kumar Jagannathan, Srinivasan Jyothi, M. College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq School of Computer Science and Engineering Sr University Warangal India Nitte Meenakshi Institute of Technology Department of Aiml & Ipr Cell Bengaluru India Madanapalle Institute of Technology & Science Department of Computer Applications Madanapalle India G.Narayanamma Institute of Technology and Science Department of Information Technology Hyderabad India

ISBN: (纸本)9798350373110

Fingerprint is a most well-known biometric based authentication system that gives a unique identity for each person. In this paper, an authentication framework to enhance the Fingerprint Minutiae Extraction and Matching (FMEM) technique is proposed. A Fully Connected Deep Convolutional Neural Network with Improved Scale-Invariant Feature Transform (FCDCNN-ISIFT) is proposed for feature extraction and feature matching. Initially, the fingerprint images are collected from Fingerprint Verification Competition 2004 (FVC2004) which are first pre-processed using Histogram Equalization (HE) and Normalization. The images are segmented and enhanced by estimating ridge orientation and ridge frequency, and performing Gabor filtering, binarization and thinning. The fingerprint feature extraction and matching test is done using FCDCNN-ISIFT. The FCDCNN is built for detecting minutiae and the ISIFT is applied to the high contrast images to enhance the quality of latent fingerprints. Finally, the loss function is measured to determine the minutiae detection loss. The experimental results show better accuracy of 99.41%, f1-score of 97.73%, and Equal Error Rate (EER) of 1.75% when compared to results of existing approaches like Contrast Limited Adaptive Histogram Equalization - Random Sample Consensus (CLAHE - RANSAC) and Deep Convolutional Neural Network (DCNN). © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimized Convolution Neural Network Based Fake News Detection Using Sentiment Analysis 3

Optimized Convolution Neural Network Based Fake News Detecti...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Pillai, Sanjaikanth E. Vadakkethil Somanathan Rajashekaran, Karthik Reddy, R. Archana Pareek, Piyush Kumar Sontakke, Dipti School Of Electrical Engineering And Computer Science University Of North Dakota Grand Forks United States New York University Department Of Computer Science New YorkNY United States School Of Computer Science And Engineering Sr University Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Aiml And Ipr Cell Bengaluru India Capgemini Inc United States

ISBN: (纸本)9798350318609

In the era of social media, the social media and smartphone popularity has enhanced exponentially. By the electronic media, fake news has rising quick with new information which are hugely untrustworthy. The search engine like google are incapable for fraudulent of news because its limitation with restricted keywords. The Optimized Convolution Neural Network (OPCNN) is proposed for classifying fake news into actual and fraudulent news based on sentiment analysis. which accommodate varying complexity levels by adjusting its architecture in Fake News Detection (FND). The Principal Component Analysis (PCA) is used to extract features from preprocessed images which reduces the data dimension comprising numerous related variables and recalls the high change in real data. The ISOT dataset is preprocessed through four various techniques. The recall, accuracy, f1 score and precision with ISOT dataset are considered to evaluate OPCNN performance. The OPCNN realizes 99.58% recall, 99.67% accuracy, 99.61% f1score and 99.64% precision for ISOT dataset when matched to previous techniques like Random Forest (RF) and Sea Turtle Foraging Optimization-based Fake News Detection and Classification (STODL-FNDC). © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Predicting Natural Hazards and Disaster Risks using Improved Particle Swarm Optimization based Support Vector Machine

Predicting Natural Hazards and Disaster Risks using Improved...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Alzubaidi, Laith H. Kumar Pareek, Piyush Reddy, R. Archana Abed, Z. Das, Abhijeet The Islamic University Engineering College of Technical Engineering Department of Computers Techniques Najaf Iraq Nitte Meenakshi Institute of Technology Department of Aiml & Ipr Cell Bengaluru India Sr University School of Computer Science and Engineering Warangal India Ahl Al Bayt University Karbala Iraq Department of Civil Engineering Bhubaneswar India

ISBN: (纸本)9798350360660

Predicting natural hazards before its occurrence is crucial to reduce the impact it causes economically to the cities/areas. Therefore, advanced Machine Learning (ML) models can be used to manage disasters by performing an early detection of hazards susceptible locations. The geographical data on natural hazards is collected pre-processed to eliminate the null values. The data is applied with the normalization technique and performed data scaling to transform all the variables to the same range. To obtain complex hierarchical features, Residual Network (ResNet) is used and the extracted features are selected using Attention Based Isolated Forest (ABIF) to solve the standard linear or quadratic optimization problem. To obtain the optimal solution in predicting the natural hazards the parameters of Support Vector Machine (SVM) are optimised using Improved Particle Swarm Optimization (IPSO). This ensures the model's generalization and predictive ability and to handle high dimension data. The results showed that the proposed IPSO-SVM achieved better prediction accuracy with 98.59%, and precision of 97.74% when compared to the conventional ML methods such as Natural Gradient Boosting Machines (NGBoost) and AdaBag- Nearest Shrunken Centroids (AB-NSC). © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Quantum Machine Learning in Healthcare: Developments and Challenges

Quantum Machine Learning in Healthcare: Developments and Cha...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Rani, Sita Kumar Pareek, Piyush Kaur, Jaskiran Chauhan, Meetali Bhambri, Pankaj Guru Nanak Dev Engineering College Department of Computer Science and Engineering Ludhiana India Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Ipr Cell Bengaluru India Guru Nanak Dev Engineering College Department of Information Technology Ludhiana India

ISBN: (纸本)9798350398465

Machine learning is playing a very significant role to process voluminous data and its classification in a variety of domains. Due to better performance and rapid development in the last decade, quantum computing is also benefiting many areas. With the amalgamation of these two technologies, a new domain for processing big data more efficiently and accurately has evolved, known as quantum machine learning. Healthcare is one of the prominent domains where a huge volume of data is produced from several processes. Efficient processing of healthcare data and records is very important to facilitate many biological and medical processes to provide better treatments to patients. The fundamental aim of this paper is to present a state-of-the-art review of quantum computing concepts, quantum machine learning framework, and the various applications of quantum machine learning in the domain of healthcare. The comparison of QML healthcare models with ML-based healthcare applications is discussed in this work. The authors also present the various challenges faced in the deployment of quantum machine learning algorithms in the domain of healthcare and possible future research directions. © 2023 IEEE.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Automated Cybersecurity Attack Detection Using Prairie Dog Optimization and Multilayer Perceptron in Healthcare System 3

Automated Cybersecurity Attack Detection Using Prairie Dog O...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Pillai, Sanjaikanth E. Vadakkethil Somanathan Poddar, Sanjay Susanta Nagendar, Y. Pareek, Piyush Kumar Zanke, Pankaj School Of Electrical Engineering And Computer Science University Of North Dakota Grand Forks United States Fortinet Ltd DallasTX United States School Of Computer Science And Engineering Sr University Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Aiml And Ipr Cell Bengaluru India Sapiens International Corporation United States

ISBN: (纸本)9798350318609

Internet of Things (IoT) technologies have become an inevitable part of our lives with many innovations and conveniences in many fields such as education, healthcare, social life and security. While healthcare network complexity and connectivity are developing in a superior manner at the same time, cyber-attack surfaces and vulnerabilities are also increasing dramatically. Harming people either physically or digitally are some of the threat to the health and life of patients through data breaches across multiple departments of health systems. In this research, the prairie dog optimization (PDO) algorithm and multilayer perceptron (MLP) is proposed cyber-attack detection model. The proposed approach was performed the several IoMT cybersecurity datasets using Intensive Care Unit (ICU Dataset), Washington University in St. Louis enhanced healthcare monitoring system (WUSTL-EHMS) datasets, Edith Cowan University- Internet of Health Things (ECU-IoHT), and TON-IoT. PDO is used for selecting the optimal features from the attained dataset, MLP parameters is performed by hyperparameter optimization as well as 10-fold cross-validation technique for performance assessment. The proposed method has the potential to counter cyber-attacks in healthcare applications, it attained higher precision at 99.54%, accuracy of 99.45%, recall 99.56% and f1-score 99.46% in ECU-IoHT dataset. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Transductive - Long Short-Term Memory Network for the Fake News Detection 3

Transductive - Long Short-Term Memory Network for the Fake N...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Pillai, Sanjaikanth E Vadakkethil Somanathan Avacharmal, Rajiv Reddy, R. Archana Pareek, Piyush Kumar Zanke, Pankaj School Of Electrical Engineering And Computer Science University Of North Dakota Grand Forks United States Center For Data Science And Artificial Intelligence New York Life Insurance Company Farmington HillsMI United States School Of Computer Science And Engineering Sr University Telangana Warangal India Nitte Meenakshi Institute Of Technology Department Of Aiml And Ipr Cell Bengaluru India Sapiens International Corporation United States

ISBN: (纸本)9798350318609

Recently, fake news and rumors are distributing majorly and rapidly in all over world. That circumstance causes the production and propagation of incorrect news articles. As well as mis data and fake news are maximized through user without correct verification. In this manuscript, proposed a Transductive - Long Short-Term Memory (T-LSTM) method for detecting fake news. The Buzzfeed and ISOT datasets are used in this manuscript for fake news detection and it is pre-processed by tokenization, removal of stop word and stemming. Then, the reduction of feature is performed by using Probability Principal Component Analysis (PPCA) and it is classified by using T-LSTM method. The proposed T-LSTM method attained accuracy 96.51 %, precision 94.64 %, recall 92.33 % and f1-score 93.57% on Buzzfeed dataset. The proposed T-LSTM method attained accuracy 98.43%, precision 97.76%, recall 97.02% and f1-score 97.35% on ISOT dataset. The proposed T-LSTM method performed well than other existing methods like LSTM -Levy Flight (LSTM-LF) and OptNet. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Fault Detection and Diagnosis in Electrical Distribution System Using Generative Adversarial Networks with Deep Belief Networks 4

Fault Detection and Diagnosis in Electrical Distribution Sys...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Veeramachaneni, Vinod Pareek, Piyush Kumar Alsalami, Zaid Ajzan Thangam, V. Thirumani Thanalakshmi, S. Colorado Technical University Department of Information Technology Colorado Springs United States Nitte Meenakshi Institute of Technology Department of Aiml & Ipr Cell Bengaluru India College of Technical Engineering The Islamic University Department of Computers Techniques Engineering Najaf Iraq New Prince Shri Bhavani College of Engineering and Technology Department of Computer Science and Engineering Chennai India Gojan School of Business and Technology Chennai India

ISBN: (纸本)9798350352931

In recent years, electrical faults aim to detect early and diagnose to mitigate equipment damage, catastrophic failures and power outages of the distribution network. Traditional approaches for fault detection and diagnosis in electric distribution system had several challenges which include renewable energy integration, more complex due to increasing loads and diverse fault types in sophisticated detection of devices. Therefore, this research proposes Generative Adversarial Networks with Deep Belief Networks (GAN-DBN) for fault detection and diagnosis in electrical distribution system which is employed on Institute of Electrical and Electronics Engineers Node Test Feeder (IEEENTF) dataset. Then, preprocessing is done by using Fast Fourier Transform (FFT) for harmonic distortion analysis, faults and load unbalances detection. After that, features are extracted by using Convolutional Neural Networks (CNN) autoencoder which represents discriminative faults. Next, the classification of hierarchical representation of data is utilized to extract high level features from raw data through GAN-DBN. Finally, GAN-DBN identifies anomaly data for generated distribution in electrical system. The proposed GAN-DBN achieved better results in accuracy (0.9999), specificity (0.9998) precision (0.9995), recall (0.9996), F1-score (0.9997) when compared with existing CNN. © 2024 IEEE.

关键词： Power distribution faults

来源：评论

学校读者我要写书评

暂无评论

Medicinal Plant Identification in Real-Time Using Deep Learning Model

引用

SN computer science 2024年第1期5卷 73页

作者： Kavitha, S. Kumar, T. Satish Naresh, E. Kalmani, Vijay H. Bamane, Kalyan Devappa Pareek, Piyush Kumar Department of MCA Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering BMS Institute of Technology and Management Bengaluru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Information Technology Rajarambapu Institute of Technology Affiliated to Shivaji University Kolhapur Sakharale Maharashtra Islampur India Department of Information Technology D. Y. Patil College of Engineering Akurdi Pune India Department of AIML and IPR Cell Nitte Meenakshi Institute of Technology Bengaluru India

Medicinal plants have a long tradition of being cultivated and harvested in India. The Indian Forest is the principal repository for many useful medicinal herbs. As a result of their critical role in maintaining people's life, medicinal plants have traditionally been the subject of intensive research and consideration. Yet, correctly identifying plants used in medicine is a laborious process that takes a lot of time and expertise. Because of this, a vision-based approach may aid scientists and regular people in the rapid and precise identification of herb plants. Therefore, this research suggests a vision-based smart method to recognize herb plants by creating a deep learning (DL) model. Although there is a wide variety of useful plants, we limit ourselves to just six from the Kaggle database: betel, curry, tulsi, mint, neem, and Indian beech. For each medicinal plant, we collected 500 images. The data undergo a process of resizing and augmentation to increase the sample size. For the fully automatic identification of medicinal leaves, the MobileNet DL model is selected. To determine the model's effectiveness, it must first be trained, then validated, and ultimately tested. The DL model is evaluated using measures including accuracy, precision, and recall. For this reason, the DL model was able to correctly identify medicinal leaves at an accuracy rate of 98.3%. After being thoroughly investigated, the DL model is uploaded to the cloud, and a mobile app is created for the real-time identification of medicinal leaves. To recognize leaf images, the built mobile app accesses the DL model on the cloud. The automated recognition of plants represents an extremely promising option for filling the taxonomic gap and gaining a lot of interest from the fields of botany and machine vision. © 2023, The Author(s).

关键词： Accuracy Augmentation Cloud Deep learning Medicine Mobile application Plant Resize

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：