检索结果-内蒙古大学图书馆

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Nair, Rekha R. Babu, Tina Singh, Tripty Duraisamy, Prakash Mehra, Vishal Dayananda Sagar University School of Engineering Department of Computer Applications Bengaluru India Dayananda Sagar University School of Engineering Department of Computer Science and Engineering Bengaluru India Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India University of South Alabama Department of Computer Science United States

ISBN: (纸本)9798350335095

Online classroom discipline is a key concern for teachers now a days. The issue also attracts significant attention from the public and the media. In addition to this using mobile phone in class is one of the reasons for not paying the attention. For avoiding this issue, developed a model called "Class Room Attention Model". The proposed model collects the data using camera, and with the help of machine learning models automatically detects whether the student in the class is paying attention or not. The suggested method uses Tensor Flow to detect the mobile phone and media pipe for extracting the body features using the YOLO model. The model detects presence of mobile in the classroom in addition to the prediction of the students attentiveness. The proposed efficient and accurate model to identify the attention of a student in a class room with the random forest classifier provided an accuracy of 97.65 % for attention of student and 93.81% for mobile detection. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Colon Cancer Prediction with Transfer Learning and K-Means Clustering 7th

Colon Cancer Prediction with Transfer Learning and K-Means...

引用

7th International Conference on Emerging applications of Information Technology, EAIT 2022

作者： Babu, Tina Nair, Rekha R. Department of Computer Science and Engineering School of Engineering Dayananda Sagar University Karnataka Bengaluru India Department of Computer Applications School of Engineering Dayananda Sagar University Karnataka Bengaluru India

ISBN: (纸本)9789811951909

The automatic diagnosis of colon cancer is important for patients and their prognosis through the analysis of histopathological images. Traditional feature extraction methods extract low-level image features, and prior knowledge is required to choose meaningful features, which may be modified significantly by humans. Hence, unsupervised and supervised deep convolutions neural networks were utilized to analyze histopathological images of colon cancer. To overcome the impact of the unbalanced histopathology images in sub-classes, the balanced sub-classes are turned right and left, up and down, and rotated counter clockwise by 90∘ and 180∘. The proposed experimental findings for supervised histopathological image classification of colon cancer demonstrate that Inception_V3 and Inception ResNet_V2 outperform current algorithms. These findings suggest that the Inception_ResNet_V2 network is superior deep learning architecture for analyzing histopathological images for diagnosis colon cancers. As a result, in order to perform unsupervised image analysis, Inception_ResNet_V2 is utilized to extract features from colon cancer histopathology images. In addition, a new autoencoder network was created to convert the features collected by Inception_ResNet_V2 to a low-dimensional space for image clustering analysis. The test results demonstrate that the proposed autoencoder network outperforms the Inception_ResNet_V2 network in terms of clustering. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Neural Networks-Based Predictive Models for Self-Healing in Cloud Computing Environments 2

Neural Networks-Based Predictive Models for Self-Healing in ...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Sujatha, D. Michael Raj, T.F. Ramesh, G. Agoramoorthy, Moorthy Ahamed Ali, S. St.Peters College of Engineering and Technology Department of Computer Science and Engineering Avadi Chennai India Sclas Smats Department of Computer Applications TamilNadu Chennai India K.L.N.College of Engineering Department of Information Technology Sivagangai Tamilnadu Pottapalayam India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Easwari Engineering College Computer Science and Engineering Ramapuram Chennai India

ISBN: (纸本)9798350306415

Due to the widespread adoption of cloud computing, protecting the security and uptime of cloud services is of crucial importance. Unforeseen malfunctions and performance bottlenecks in cloud settings can lead to considerable downtime and financial losses. Systems that can automatically detect, diagnose, and recover from errors using self-healing mechanisms are a promising new approach. This study investigates how neural network-based prediction models can be used to improve cloud-based systems' inherent capacity for self-healing. This research introduces a novel method of using neural networks to forecast cloud system failures and performance irregularities. The proposed prediction models are able to spot warning signs by assessing past data and current metrics in real time. Neural networks may accurately anticipate outcomes by recognizing complicated patterns and learning from large, varied information. Various forms of neural networks, including deep learning designs, are evaluated to determine their efficacy in diverse contexts. The study also looks into proactively reducing faults by incorporating these predictive models into self-healing systems. Responses, such as resource reallocation, workload migration, and backup procedures, are triggered automatically when problems are predicted. This preventative method drastically lessens the amount of time users spend waiting for their cloud-based systems to restart. Extensive simulations and real-world case studies yielded experimental data that prove the prediction models based on neural networks proposed for self-healing in cloud computing are effective. The models' proficiency in failure prediction enables corrective measures to be taken promptly and precisely. Implementing these predictive models in massive cloud environments is also discussed, as are their scalability, flexibility, and real-world consequences. by tapping into the potential of neural networks for predictive analysis, this study adds to the develop

关键词： Cloud Computing LSTM Neural Network Self-Healing

来源：评论

学校读者我要写书评

暂无评论

Coupling Mobile Brain Imaging and Virtual Reality Omnidirectional Treadmill to Explore Attenuated Situational Awareness during Distracted Walking

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年第3期16卷 1063-1076页

作者： Chuang, Chun-Hsiang Chiu, Tsai-Feng Hsu, Hao-Che Lin, Shih-Syun National Tsing Hua University Research Center for Education and Mind Sciences College of Education The Institute of Information Systems and Applications College of Electrical Engineering and Computer Science Hsinchu300 Taiwan National Tsing Hua University Research Center for Education and Mind Sciences Hsinchu300 Taiwan National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300193 Taiwan National Taiwan Ocean University Department of Computer Science and Engineering Keelung20224 Taiwan

Walking while engaging in distracting activities affects our perception of changes happening on the road, leading to exposure to hazardous conditions. This study aimed to evidence that pedestrians who become distracted when absorbed in their smartphones fail to maintain situational awareness. Thirty-six recruited participants performed a psychomotor vigilance task and a wayfinding task designed to simulate a multitasking scenario;meanwhile, an auditory oddball paradigm presented to participants tested their situational awareness of an external stimulus. The experiment was conducted in virtual reality (VR) environment with an omnidirectional treadmill. Participant's behavioral and electroencephalographic (EEG) responses were measured and analyzed using a newly proposed brain network measure, phase locking distance (PLD), to capture multitasking-associated couplings between brain regions. The current study supports the notion that multitasking can lead to diminished behavioral performance and changes in walking patterns. Despite the increased interregional brain connectivity, which may be an adaptive response to heightened cognitive demands, the associated reduction in event-related EEG activity suggests competition for neural resources during multitasking. Moreover, the observed EEG activities could indicate additional information processing capacity limitations and provide evidence of decreased situational awareness during multitasking, thereby increasing susceptibility to potentially hazardous situations. © 2016 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Potato Leaf Disease Detection Method is Based on the Support Vector Machines 2

Potato Leaf Disease Detection Method is Based on the Support...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Srivastava, Animesh Singh Rawat, Bhupender Sawan, Vikash Vishal Dhondiyal, Shiv Ashish Graphic Era Hill University Department of Computer Science & Engineering Dehradun India College of Smart Computing COER University Roorkee India GLA University Department of Computer Engineering & Applications Uttar Pradesh Mathura India School of Computer Application Lovely Professional University Punjab Jalandhar India Department of Computer Science & Engineering Dehradun India

ISBN: (纸本)9798331519056

Potato production is challenged by plant diseases whose adverse effects are a reduction in the yield of the crops, and which have undesirable economic implications. Recognizing these diseases is of utmost importance since control should be applied. This paper describes a method for diagnosing diseases of the potato using Support Vector Machine (SVM) classification. A SVM is an ML algorithm that is effective in classification tasks such as classifying potato leaves in terms of their diseases. The results show that the proposed method is useful and works rather well for detecting potato plant leaf diseases. In this paper, the SVM method emphasizes detecting various potato plant leaf diseases for efficient intervention before the late stage of visual assessment for microbial-introduced disease. The main aim of this research is to assist in overcoming the limitations of existing agricultural practices in speeding up the diagnosis and control of diseases affecting potato plants. So the SVM-based methods can help farmers in making timely decisions, reducing economic losses, and increasing agricultural productivity. With linear SVM, the accuracy stands at 93.1%. Nevertheless, when non-linear SVM is employed, the accuracy rises to 95.6%. © 2024 IEEE.

关键词： Agricultural economics

来源：评论

学校读者我要写书评

暂无评论

Mental Health Predictive Analysis using Multiple Machine Learning Techniques 2

Mental Health Predictive Analysis using Multiple Machine Lea...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Tressa, Neethu Asha, V. Prasad, Arpana Prathith Pramodh Kumar, D. Saju, Binju New Horiznon College of Engineering Department of Master of Computer Applications Bengaluru India Adi Shankara Institute of Engineering & Technology Department of Computer Science - Ai Engineering Kerala Kalady India

ISBN: (纸本)9798350369960

The growth in mental health issues and the demand for high-quality medical care have prompted the requirement of machine learning techniques in the psychological research area. For the better prediction of mental health complications, this work presents an up-to-date thorough evaluation of machinelearning algorithms. This article reviews the difficulties, limitations and future directions of using machine learning approaches in psychological health. By searching reliable databases, relevant studies and publications on machine learning methods were collected for predicting mental health related issues. For the completion of this work, 40 research outcomes were analyzed using screening and classification procedures. The analyzed works were categorized according to mental health conditions such as schizophrenia, bipolar disorder, depression or anxiety, PTSD, and mental health conditions affecting children. While discussing the results, the difficulties and limitations that many researchers have encountered when studying mental health related problems were also considered. The paper also encompasses specific directions for future research work that are feasible and the need for utilizing varying approaches in machine learning for psychological health disorder predictions. © 2023 IEEE.

关键词： Decision Tree Classifier Flask Deployment K Nearest Neighbor Classifier Logistic Regression Algorithm Naïve Bayes Random Forest Stacking

来源：评论

学校读者我要写书评

暂无评论

Smart Intelligence-Driven Deep Learning Framework for Reliable Detection and Accurate Classification of Skin Cancer Diseases 3

Smart Intelligence-Driven Deep Learning Framework for Reliab...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Rathish Babu, T.K.S. Chandramohan, S. Be, Hajira Niroshini Infantia, H. Srm Institute of Science and Technology Department of Computer Science Engineering Ramapuram Chennai89 India Sri Chandrasekarendra Saraswathi Viswa Maha Vidyalaya Department of Computer Science Engineering Chennai India Karpaga Vinayaga College of Engineering and Technology Department of Computer Applications Maduranthakam Taluk India St. Joseph's Institute of Technology Department of Information Technology OMR Chennai600119 India

ISBN: (纸本)9798331509675

The interest in skin cancer detection is growing remarkably because of the prevalence of this health condition worldwide. It improves the chances of survival and enhances general treatment outcomes when diagnosis has been done early. Most the traditional methods for skin lesion detection involve visual inspection performed by dermatologists;hence, it is time-consuming and, to some extent, subjective. Therefore, with the rise of deep learning-Artificial Intelligence, auto-detection of skin cancer has gained a foothold in improving diagnostic accuracy, hence treatment outcomes. The presented paper proposes a GAN-based approach for skin cancer detection by deep learning analysis of dermoscopic images, classifying them as malignant and benign. The proposed approach uses the generator and discriminator parts of GAN to obtain an effective discrimination between cancerous and non-cancerous lesions with high precision. The proposed method incorporates the native abilities of GANs for boosting diagnostic precision. GANs consist of two major components: a generator and a discriminator. These two adversaries collaborate with each other in a way to encourage the classification performance of the framework. The generator synthesizes the realistic data representations by augmenting the dataset with various variations of dermoscopic images. This helps not only to compensate for the insufficiency of annotated data but also to make the model generalize more robustly to diverse skin lesion patterns. At the same time, the discriminator learns to distinguish malignant from benign lesions with high accuracy by using the adversarial nature in GAN training. These results clearly indicate the effectiveness of the proposed GAN-based approach over state-of-the-art traditional deep learning models. GAN makes not only the detection system more robust but also reduces its dependency on large annotated datasets. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Outline of Data Encryption Standard (DES) Tools and Its Facets within the Realm of Cloud Computing

An Outline of Data Encryption Standard (DES) Tools and Its F...

引用

2023 International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2023

作者： Kukreti, Riya Kavitha, R. Joshi, Apoorva Tula's Institute Department of Computer Science and Engineering Dehradun India Department of Computer Science and Information Technology Bangalore India Noida Institute of Engineering and Technology Computer Applications Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350344387

The development of Discrete Event Simulation (DES) systems for enhancing decision-making and research in cloud computing has experienced a substantial growth. The growing diversity of cloud systems makes it extremely challenging to effectively manage cloud resources and services inside data centers. The increasing prevalence of Internet of Things (IoT) gadgets, smartphone apps, and cloud services, together with the introduction of concepts like Edge and Fog Computing, have made this system more complex. A significant amount of time and effort must be invested in these tasks. In intricate hyperscale computer environments, decision assistance is provided by the safe and dependable DES technology. This study aims to provide a comprehensive evaluation of DES systems made especially for cloud computing environments. The study carefully evaluates these instruments in a number of categories and is based on a thorough investigation of recent literature. This study goes beyond conventional stand-alone simulation systems by incorporating custom extensions and add-ons designed for certain cloud computing tasks. In addition to highlighting CloudSim's increasing significance as the main platform for simulated research, this also draws attention to the lack of tools made expressly for distributed execution. © 2023 IEEE.

关键词： Cloud computing Cloud Simulation Tools Data Centre Fog Computing

来源：评论

学校读者我要写书评

暂无评论

Multi-objective Fuzzy Reliability Redundancy Allocation for xj -out-of- mj System Using Fuzzy Rank-Based Multi-objective PSO 9th

Multi-objective Fuzzy Reliability Redundancy Allocation for ...

引用

9th International Symposium on Applied Computing for Software and Smart systems, ACSS 2022

作者： De, Satyajit Roy, Pratik Chowdhury, Anil Bikash Department of Computer Science Maheshtala College WB Maheshtala700141 India Department of Computer Engineering and Applications GLA University UP Mathura281406 India Department of Computer Applications Techno India University WB Kolkata700091 India

ISBN: (纸本)9789811967900

The main goal of this paper is to solve a fuzzy multi-objective reliability redundancy allocation problem (MORRAP) for xj -out-of- mj series-parallel system. We consider that system reliability and system cost are two conflicting objectives. Due to the incompleteness and uncertainty of input information, we formulate the objectives by considering the reliability and cost of each component as a triangular fuzzy number (TFN). Here, the fuzzy multi-objective optimization problem of system reliability and cost is analyzed simultaneously using our proposed fuzzy rank-based multi-objective particle swarm optimization (FRMOPSO) algorithm. Comparing the results of FRMOPSO with standard particle swarm optimization (PSO), we see that better optimum reliability and cost have been achieved in the FRMOPSO technique. To illustrate the effectiveness of our proposed technique, we consider the problem of the over-speed protection system of gas turbines containing two mutually conflicting reliability and cost objectives with entropy and several other constraints. We present graphically the effect of optimum system reliability and cost with respect to the percentage change of different parameters. We also compare the convergence rate of FRMOPSO with PSO. Our proposed algorithm shows better results. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Secure Communication over IoT Networks using Mutual Authentication

Secure Communication over IoT Networks using Mutual Authenti...

引用

2024 International Conference on Computational Intelligence and Computing applications, ICCICA 2024

作者： Verma, Dinesh Chander Chopra, Amit Kanika Kaushik, Vinita Kaur, Jaspreet Panipat Institute Of Engineering & Technology Department Of Computer Applications Panipat India Maharaja Agrasen University Department Of Computer Science & Engineering H.P Baddi India Thompson Rivers University KamloopsBC Canada

ISBN: (纸本)9798350306446

Internet of Things (IoT) network transmit the data in an open environment and it can be intercepted by unauthorized users. Different sensors share their data with each other without authentication and it becomes a major security concern. Data privacy and integrity are other security issues. In this paper, a secure communication using mutual authentication model will be introduced to secure the transmisssion over IoT networks. It will isolate the communication between filed sensors and gateways as well as it will also protect the data exchange between gateways and server. Its performance will be analyzed using. Long Range Low powered technology (LoRa) under the constraints of intruder density that varies from 5 to 25 nodes with the legitimate sensors density (100-600) © 2024 IEEE.

关键词： Authentication

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：