检索结果-内蒙古大学图书馆

6th Parul International Conference on engineering and Technology, PICET 2024

作者： Nishitha, Kapuluri Mohan, Bharathi G. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita University Chennai India Faculty of Engineering and Technology Botho University Gaborone Botswana

ISBN: (纸本)9798350369748

This research introduces a sophisticated framework for real-time video captioning that seamlessly integrates a cohesive ensemble of machine learning *** development of open-domain video descriptions that can manage variable-length input (sequences of words) and output (sequences of frames)while being sensitive to temporal structure is required due tothe complex dynamics present in real-world films. Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks are used to extract descriptive narratives and brief summaries from movies. LSTMs have demonstrated state-of- the-art performance in the generation of picture captions andare great at capturing sequential information. Our algorithmis trained on pairs of videos and matching texts to provide relevant captions for video events. It gains the ability to connecta string of words to a sequence of video frames. The modelnot only learns the temporal structure inside the sequence of frames, but also develops a language model for generating coherent and contextually relevant sentences. Our approach usesthe VGG16 model to extract visual features, which results in a rich representation of the video information. These visual cues, along with the LSTM-based sequence-to-sequence model, enable the production of elaborate captions that faithfully capture the temporal dynamics and visual aspects of the video clips. © 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

A Comprehensive Review of Large Language Models in Abstractive Summarization of News Articles

A Comprehensive Review of Large Language Models in Abstracti...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Bharathi Mohan, G. Akashvarma, M. Yashaswini, G. Keerthana, E. Siddharth, S. Saipooja, K. Prasanna Kumar, G. Doss, Srinath Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai India Botho University Faculty of Engineering and Technology Botswana

ISBN: (纸本)9798350361537

Recent years have seen significant advancements in Large Language Models (LLMs), particularly in their application to natural language processing tasks. One prominent application is the abstractive summarization of news articles, a process that distills extensive textual information into a succinct yet comprehensive representation. The significance of this task lies in its capacity to efficiently distill key information. This paper focuses on evaluating the performance of various LLMs - Llama-2-7b, T5, Bart, and Pegasus - specifically fine-tuned on the CNN Daily dataset of news articles. QLoRA and Prompt-Based Fine-Tuning Approaches are employed systematically to compare the efficacy of these models in generating summaries that capture the essence of news articles. Evaluation metrics, including ROUGE, BLEU, and cosine similarity, are utilized to assess summarization quality. The findings reveal distinctive results among the selected LLMs such that Llama-2 excels in ROUGE-1 and ROUGE-L with scoreS of 0.45 and 0.427, Pegasus demonstrates remarkable performance in ROUGE-2 and cosine similarity with scores 0.19 and 0.6 respectively. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Voting Classifier and Metaheuristic Optimization for Network Intrusion Detection

引用

computers, Materials & Continua 2023年第2期74卷 3183-3198页

作者： Doaa Sami Khafaga Faten Khalid Karim Abdelaziz A.Abdelhamid El-Sayed M.El-kenawy Hend K.Alkahtani Nima Khodadadi Mohammed Hadwan Abdelhameed Ibrahim Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt The Department of Civil and Environmental Engineering Florida International UniversityMiamiFLUSA Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt

Managing physical objects in the network’s periphery is made possible by the Internet of Things(IoT),revolutionizing human *** attacks and unauthorized access are possible with these IoT devices,which exchange data to enable remote *** attacks are often detected using intrusion detection methodologies,although these systems’effectiveness and accuracy are *** paper proposes a new voting classifier composed of an ensemble of machine learning models trained and optimized using metaheuristic *** employed metaheuristic optimizer is a new version of the whale optimization algorithm(WOA),which is guided by the dipper throated optimizer(DTO)to improve the exploration process of the traditionalWOA *** proposed voting classifier categorizes the network intrusions robustly and *** assess the proposed approach,a dataset created from IoT devices is employed to record the efficiency of the proposed algorithm for binary attack *** dataset records are balanced using the locality-sensitive hashing(LSH)and Synthetic Minority Oversampling Technique(SMOTE).The evaluation of the achieved results is performed in terms of statistical analysis and visual plots to prove the proposed approach’s effectiveness,stability,and *** achieved results confirmed the superiority of the proposed algorithm for the task of network intrusion detection.

关键词： Voting classifier whale optimization algorithm dipper throated optimization intrusion detection internet-of-things

来源：评论

学校读者我要写书评

暂无评论

Assessing Quality of Service Performance in SDN controllers: POX vs. OpenDaylight 6

Assessing Quality of Service Performance in SDN Controllers:...

引用

6th International Conference on Advancements in computing, ICAC 2024

作者： Lokuliyana, Shashika Wijesiri, Pipuni Jayakody, Anuradha Abeygunawardhana, Pradeep K.W. Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798331517878

This research offers a comparative analysis of Qual-ity of Service (QoS) within Software Defined Networks (SDN) by assessing the POX and OpenDaylight controllers across various network topologies. The results show that OpenDaylight has a 32.59% higher average throughput than POX, demonstrating its superior data handling capabilities. Conversely, POX exhibits a 54.53% lower average delay and an 85.05% higher average jitter compared to OpenDaylight, highlighting its effectiveness in maintaining lower latency and variability in packet transmission times. These contrasting performances provide essential insights for network engineers in selecting the optimal SDN controller based on specific network demands, significantly influencing the overall network efficiency and stability. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Adversarial Neural Network Classifiers for COVID-19 Diagnosis in Ultrasound Images

引用

computers, Materials & Continua 2022年第1期70卷 1683-1697页

作者： Mohamed Esmail Karar Marwa Ahmed Shouman Claire Chalopin Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering(FEE)Menoufia UniversityMenouf32952Egypt Department of Computer Engineering and Networks College of Computing and Information TechnologyShaqra UniversityShaqra11961Saudi Arabia Department of Computer Science and Engineering Faculty of Electronic Engineering(FEE)Menoufia UniversityMenouf32952Egypt Innovation Center for Computer Assisted Surgery(ICCAS) Universit鋞LeipzigLeipzig04103Germany

The novel Coronavirus disease 2019(COVID-19)pandemic has begun in China and is still affecting thousands of patient livesworldwide *** X-ray and Computed Tomography are the gold standardmedical imaging modalities for diagnosing potentially infected COVID-19 cases,applying Ultrasound(US)imaging technique to accomplish this crucial diagnosing task has attracted many physicians *** this article,we propose two modified deep learning classifiers to identify COVID-19 and pneumonia diseases in US images,based on generative adversarial neural networks(GANs).The proposed image classifiers are a semi-supervised GAN and a modifiedGANwith auxiliary *** one includes a modified discriminator to identify the class of the US image using semi-supervised learning technique,keeping its main function of defining the“realness”of tested *** tests have been successfully conducted on public dataset of US images acquired with a convex US *** study demonstrated the feasibility of using chest US images with two GAN classifiers as a new radiological tool for clinical check of COVID-19 *** results of our proposed GAN models showed that high accuracy values above 91.0%were obtained under different sizes of limited training data,outperforming other deep learning-based methods,such as transfer learning models in the recent ***,the clinical implementation of our computer-aided diagnosis of US-COVID-19 is the future work of this study.

关键词： COVID-19 medical imaging machine learning applications adversarial neural networks ultrasound

来源：评论

学校读者我要写书评

暂无评论

Practical Realization of Only Active Floating Lossless Inductance Simulator 10

Practical Realization of Only Active Floating Lossless Induc...

引用

10th International Conference on engineering, Applied Sciences, and Technology, ICEAST 2024

作者： Roongmuanpha, Natchanai Unhavanich, Sumalee Pukkalanun, Tattaya Tangsrirat, Worapong School Of Engineering Department Of Computer Engineering Bangkok10520 Thailand Faculty Of Digital Technology Bangkok10300 Thailand School Of Engineering Department Of Instrumentation And Control Engineering Bangkok10520 Thailand

ISBN: (纸本)9798350385946

This paper describes an electronically controllable floating lossless inductance simulator circuit implemented with only off-the-shelf available integrated circuits, namely LT1228 and operational amplifier (OA). The proposed design consists solely of two LT1228s and a single OA. By using an active element named LT1228, the equivalent inductance can be tuned electronically with depended on the externally supplied current applied to LT1228. The proposed simulator imposed just one component matching restriction that required the equality of two transconductances. It is easily attainable with a simple current mirror. The worthiness of the proposed floating inductance simulator has been proven and applied to the construction of the 2nd-order RLC highpass/bandpass filter as an application. PSPICE simulations are used to investigate the characteristics of the proposed simulator and its filter realization. © 2024 IEEE.

关键词： Operational amplifiers

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Model Depending on Optimized Support Vector Machine

引用

computers, Materials & Continua 2023年第7期76卷 499-515页

作者： Amel Ali Alhussan Fatma M.Talaat El-Sayed M.El-kenawy Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Doaa Sami Khafaga Mona Alnaggar Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Machine Learning&Information Retrieval Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams UniversityCairo11566Egypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Robotics and Intelligent Machines Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikh33516Egypt

In computer vision,emotion recognition using facial expression images is considered an important research *** learning advances in recent years have aided in attaining improved results in this *** to recent studies,multiple facial expressions may be included in facial photographs representing a particular type of *** is feasible and useful to convert face photos into collections of visual words and carry out global expression *** main contribution of this paper is to propose a facial expression recognitionmodel(FERM)depending on an optimized Support Vector Machine(SVM).To test the performance of the proposed model(FERM),AffectNet is *** uses 1250 emotion-related keywords in six different languages to search three major search engines and get over 1,000,000 facial photos *** FERM is composed of three main phases:(i)the Data preparation phase,(ii)Applying grid search for optimization,and(iii)the categorization *** discriminant analysis(LDA)is used to categorize the data into eight labels(neutral,happy,sad,surprised,fear,disgust,angry,and contempt).Due to using LDA,the performance of categorization via SVM has been obviously *** search is used to find the optimal values for hyperparameters of SVM(C and gamma).The proposed optimized SVM algorithm has achieved an accuracy of 99%and a 98%F1 score.

关键词： Facial expression recognition machine learning linear dis-criminant analysis(LDA) support vector machine(SVM) grid search

来源：评论

学校读者我要写书评

暂无评论

Polymorphic Security Enhancements for Corporate Environments Utilizing Behavior Analytics

Polymorphic Security Enhancements for Corporate Environments...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Wijesinghe, W.M.A.J. Abeysinghe, Y.P.P. Rukshana, M.A.F. Adhikari, A.M.P.S. Abeywardhana, Kavinga Yapa Siriwardhana, Deemantha Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350367560

Employers should recognize that employees are the most vulnerable aspect of business environments since these cyber hazards are growing because of user neglect, lack of fundamental security discipline, and a fast-changing threat context. The theoretical approach proposed in the study bridges the difference by carefully following and handling the staff's internet presence. Overall, the study describes a comprehensive solution to govern the security of employees' internet presence by utilizing Artificial Neural Networks (ANN) for advanced intrusion detection, Natural Language Processing (NLP) for implementation and enforcement of browser-based security policies, visual and text data recognition to identify phishing attempts, and lastly analyzing and profiling users based on their online presence via a mathematical model. As a result, this study provides a comprehensive solution for mitigating risks related to human factors in corporate environments. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Recognition Using computer Vision: A Comprehensive Approach 15

Multimodal Emotion Recognition Using Computer Vision: A Comp...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Mohan, G. Bharathi Sarrvesh, N. Hrishikeasan, N.P. Boopalamani, J. Doss, Srinath Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Faculty of Engineering and Technology Botho university Botswana

ISBN: (纸本)9798350370249

Real-time understanding and response to human emotions have become critical in today’s connected world of prevalent human-computer interaction. This study presents a novel approach to real-time emotion detection using a camera-based system that analyzes both voice and facial expressions. Our method advances the state-of-the-art by integrating deep learning techniques with parallel models for audio and visual inputs through a weighted fusion approach, a strategy not commonly employed in existing systems. Utilizing datasets such as CK+48 and the Ryerson Audio-Visual Database of Emotional Speech and Song (Ravdess), our system achieves superior performance metrics, including an accuracy of up to 92.92% and an F1 score of 92.94%. Encapsulated within a user-friendly microservice with an intuitive online interface, our solution enables seamless real-time interaction using only a webcam and microphone. Ongoing efforts focus on refining the system’s ability to recognize diverse voices and expressions, aiming to create technology that empathizes with human emotions and enhances interpersonal interactions. ©2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Agricultural Efficiency with IoT-Enabled Precision Irrigation Management Using LoRaWAN Technology 16

Enhancing Agricultural Efficiency with IoT-Enabled Precision...

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Jayasinghe, J.A.S.K. Thennakoon, T.M.H.L. Ruchira, U.G.C. Wimalasena, N.G.C.L. Jayakody, J.A.D.C.A. Pandithage, Dinithi Sri Lanka Institute of Information Technology Faculty of Computing Department of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798331505264

The Internet of Things-empowered precision irrigation management system with LoRaWAN technology is presented given the growing food requirements across the world and pressing calls for judicious use of water in agriculture. Flow Pilot, specifically designed for chili farms, optimizes water application while enhancing crop health using precise and automated irrigation. The Flow Pilot features advanced sensors such as soil moisture, temperature, humidity, and rain sensors that collect real-time environmental data transmitted over a LoRaWAN network for analysis. Flow Pilot uses the Machine learning algorithm by analyzing sensor data to make localized irrigation recommendations based on crop needs, environmental factors, and weather forecasting. LoRaWAN gateways will support this for long-ranged communications over power-consuming agricultural fields. Besides this, it can use different network architectures. There is also an automated water tank management module that regulates the supply of water and pH levels to have optimal conditions for crop growth. A visually simple dashboard interface enables farmers to inspect and operate irrigation processes remotely, hence rendering the whole process far more efficient. Finally, over the extensive period of field tests executed by the project, Flow Pilot was able to save water, improve crop yields, and help support sustainable agriculture. For example, this testing supports the potential of IoT with LoRaWAN technologies, such as the Flow Pilot implementation, for a game change in conventional irrigation practices into a modern, scalable, and reliable solution. © 2024 IEEE.

关键词： Soil moisture

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：