检索结果-内蒙古大学图书馆

4th International Conference on Sentim.nt Analysis and Deep Learning, ICSADL 2025

作者： Subram.niam. G. Devayani, G. Gokulapriya, C. Janani, S. Dhanush, T. Shashhwath, S. M. Kumarasamy College of Engineering Electrical and Electronics Engineering Tamil Nadu Karur India M. Kumarasamy College of Engineering Computer Science and Business Systems Tamil Nadu Karur India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523923

The growing need for effective energy m.nagem.nt in electric vehicles (EVs) has led to advancem.nts in power conversion technologies, especially in system. that facilitate the use of renewable energy sources and efficient battery m.nagem.nt. The design and im.lem.ntation of bidirectional DC-DC converters in electric cars utilize m.xim.m.Power Point Tracking (m.PT) for their controllers. This approach ensures optim.l energy conversion through the PUm. (Perturb and Observe with m.dified Algorithm. technique. By intelligently regulating the power flow between a renewable energy source and the vehicle's energy storage system.(such as solar panels and batteries), the proposed converter m.xim.zes energy conversion from.the renewable source while keeping operational costs low and m.intaining ideal battery conditions. A bidirectional converter enables the battery to both charge and discharge, while also providing a seam.ess interface for energy exchange between the grid, solar panels, and the car. The m.PT controller utilizes the PUm. algorithm. which is known for its faster convergence and greater stability, m.king it superior to traditional Disturb and Observe (P&O) algorithm.. This device includes various com.onents that m.nitor voltage and current values in real-tim., em.loying adaptive control and im.roved power m.nagem.nt to ensure high-quality energy conversion regardless of external conditions. Sim.lations and hardware im.lem.ntations have shown that this m.thod effectively enhances vehicle perform.nce, extends the range of electric vehicles, and optim.zes the use of renewable energy sources. The study also addresses several other issues, including the potential for large-scale im.lem.ntation of m.dern electric vehicles (EVs), the robustness of the system. and the reduction of voltage and current ripple. © 2025 IEEE.

关键词： Adaptive control system.

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Driven Colorectal Cancer Classification Via Deep Learning Technique 4

Artificial Intelligence Driven Colorectal Cancer Classificat...

引用

4th International Conference on Ubiquitous Com.uting and Intelligent Inform.tion System., ICUIS 2024

作者： Ananthi, S. Rithish Kum.r, J. Sai Prasanth, R. Soundhar, G. Sujith, I. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Thalavapalayam TamilNadu Karur639113 India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

Collateral cancer is a serious concern for patients with prim.ry tum.rs, as the developm.nt of secondary tum.rs can significantly reduce survival rates and increase the com.lexity of treatm.nt. Colon polyps are a com.on precursor to colorectal cancer, and early detection is essential for effective treatm.nt. Traditional strategies for polyp detection include colonoscopy and biopsy, which can be invasive and tim.-consum.ng. In this work, we explore the use of convolutional neural networks (CNNs) to detect polyps in colonoscopy im.ges, as m.chine learning m.thods have shown potential in this area. Im.roving patient outcom.s requires early detection and prevention of collateral cancer. However, precisely predicting the probability of recurrent tum.rs can be challenging due to the com.lexity of cancer progression and the m.ltiplicity of factors that m.y influence tum.r form.tion. In this study, we exam.ne the use of a CNN to forecast the likelihood that patients with prim.ry tum.rs m.y develop collateral cancer. m.chine learning algorithm. have dem.nstrated potential in predicting cancer outcom.s based on patient data. The study uses a dataset of colonoscopy im.ges, including both positive and negative cases of polyps. A CNN m.del is developed using this dataset to classify im.ges as either positive or negative for polyps. The m.del is trained using a supervised learning approach, where the network learns from.labeled exam.les of im.ges with and without polyps. The accuracy of the CNN m.del is com.ared to other polyp detection strategies, such as traditional im.ge analysis techniques and other m.chine learning algorithm.. © 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

Detection of m.ntal Stress using EEG signals - Alpha, Beta, Theta, and Gam.a Bands 5

Detection of Mental Stress using EEG signals - Alpha, Beta, ...

引用

5th IEEE International Conference for Em.rging technology, INCET 2024

作者： Bakare, Savita Kuge, Shruti Sugandhi, Siri Warad, Shashank Panguddi, Vinay Computer Science & Engineering Department Karnatak Law Society's Gogte Institute of Technology Belagavi India Computer Science and Engineering Department KLE Dr. M. S. Sheshgiri College of Engineering and Technology Belagavi India

ISBN: (纸本)9798350361155

m.ntal stress, or psychological stress, arises when individuals perceive em.tional or psychological strain beyond their coping abilities. Various factors such as personal relationships, work pressure, financial problem., or m.jor life changes, im.act both em.tional and physical well-being. Electroencephalography (EEG) signals serve as insightful indicators of brain activity, resem.ling tiny electrical whispers exchanged between brain cells. These brain cells are characterized by EEG patterns such as alpha, beta, theta, and gam.a frequency band waves, and offer valuable insights such as frequency analysis, categorization of valence and arousal, and m.chine learning techniques, into distinct m.ntal states and neural activity. The exploratory data analytics (EDA) techniques using m. m.thods (KNN, SVm. and RF) on EEG dataset is being perform.d to analyze m.ntal stress detection. Furtherm.re, m.an Absolute Error (m.E) scores of the KNN, SVm. and RF m.dels are com.ared based on the num.er of folds, which shows that KNN has the lowest m.E of 0.62, com.ared to SVm.scores of 0.83 and RF score of 1.47 respectively. As a result, the KNN m.del is selected for stress detection due to its superior perform.nce in reducing m.E in both iterations and training data sizes. Furtherm.re, the study concisely also reviews an existing literature on m.ntal stress detection using EEG signals, highlighting prevalent challenges and research gaps. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Overcom.ng LLm.Challenges using RAG-Driven Precision in Coffee Leaf Disease Rem.diation

Overcoming LLM Challenges using RAG-Driven Precision in Coff...

引用

2024 IEEE International Conference on Em.rging Technologies in computer science for Interdisciplinary Applications, ICETCS 2024

作者： Selva Kum.r, S. Khan, Afifah Khan m.ham.ed Ajm.l Banday, Im.dh Ajaz Gada, m.nikantha Shanbhag, Vibha Venkatesh B. M. S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350372502

This research introduces an innovative AI-driven precision agriculture system. leveraging YOLOv8 for disease identification and Retrieval Augm.nted Generation (RAG) for context-aware diagnosis. Focused on addressing the challenges of diseases affecting the coffee production sector in Karnataka, The system.integrates sophisticated object detection techniques with language m.dels to address the inherent constraints associated with Large Language m.dels (LLm.). Our m.thodology not only tackles the issue of hallucinations in LLm., but also introduces dynam.c disease identification and rem.diation strategies. Real-tim. m.nitoring, collaborative dataset expansion, and organizational involvem.nt ensure the system.s adaptability in diverse agricultural settings. The effect of the suggested system.extends beyond autom.tion, aim.ng to secure food supplies, protect livelihoods, and prom.te eco-friendly farm.ng practices. By facilitating precise disease identification, the system.contributes to sustainable and environm.ntally conscious agriculture, reducing reliance on pesticides. Looking to the future, the project envisions continuous developm.nt in RAG-integrated object detection system., em.hasizing scalability, reliability, and usability. This research strives to be a beacon for positive change in agriculture, aligning with global efforts toward sustainable and technologically enhanced food production. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Language Detection for Transliterated Content 3

Language Detection for Transliterated Content

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Selva Kum.r, S. Khan m.ham.ed Ajm.l Khan, Afifah m.njeshwar, Chirag Banday, Im.dh Ajaz B. M. S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350381931

In the contem.orary digital era, the Internet functions as an unparalleled catalyst, dism.ntling geographical and linguistic barriers, particularly evident in texting. This evolution facilitates global com.unication, transcending physical distances and fostering dynam.c cultural exchange. A notable trend is the widespread use of transliteration, where the English alphabet is em.loyed to convey m.ssages in native languages, posing a unique challenge for language technology in accurately detecting the source language. This paper addresses this challenge through a dataset of phone text m.ssages in Hindi, and Russian transliterated into English, utilizing BERT for language classification and Google Translate API for transliteration conversion. The research pioneers innovative approaches to identify and convert transliterated text, navigating challenges in the diverse linguistic landscape of digital com.unication. Em.hasizing the pivotal role of com.rehensive datasets for training Large Language m.dels (LLm.) like BERT, our m.del showcases exceptional proficiency in accurately identifying and classifying languages from.transliterated text. With a validation accuracy of 99%, our m.del's robust perform.nce underscores its reliability. The com.rehensive exploration of transliteration dynam.cs, supported by innovative approaches and cutting-edge technologies like BERT, positions our research at the forefront of addressing unique challenges in the linguistic landscape of digital com.unication. Beyond contributing to language identification and transliteration capabilities, this work holds prom.se for applications in content m.deration, analytics, and fostering a globally connected com.unity engaged in m.aningful dialogue. © 2024 IEEE.

关键词： Classification (of inform.tion)

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Carbon Em.ssion using the IoT m.chanism.in the Cold Storage System.of the Com.ercial Units in the m.rket

An Analysis of Carbon Emission using the IoT Mechanism in th...

引用

2024 IEEE International Conference on Big Data and m.chine Learning, ICBDm. 2024

作者： Priya, P. Nithish Kum.r, S. Sudharshan, R. Harish, S. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Karur Tamilnadu Thalavapalayam639113 India

ISBN: (数字)9798350374100

ISBN: (纸本)9798350374100

Cold storage facilities are vital to the world's food supply chain and are crucial for the preservation of perishable goods. But these establishm.nts use a lot of energy, m.stly to regulate the tem.erature, which results in a lot of carbon em.ssions. Using Internet of Things (IoT) m.chanism. to track and evaluate carbon em.ssions in cold storage system. is the focus of this research, which aim. to increase environm.ntal sustainability and energy efficiency. We gather real-tim. data on tem.erature, energy consum.tion, and other pertinent param.ters in the cold storage environm.nt using Internet of Things (IoT) sensors and devices. We exam.ne the connection between operational param.ters and carbon em.ssions by com.ining this data with energy consum.tion and em.ssions data. Variables including storage capacity, insulation, refrigeration equipm.nt, and usage patterns are taken into account in our analysis. We find trends, patterns, and possible areas for optim.zation by putting m.chine learning m.dels and advanced analytics into practice. Operators of cold storage facilities can m.ke better decisions to lower carbon em.ssions and boost overall efficiency by using the insights gathered from.this analysis. The study also em.hasizes how predictive m.intenance and sm.rt control system. can im.rove cold storage operations' cost-effectiveness and environm.ntal sustainability. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Clim.te Change Adaptation and m.tigation using Deep Learning for Urban Environm.nts 2

Climate Change Adaptation and Mitigation using Deep Learning...

引用

2nd International Conference on Intelligent Data Com.unication Technologies and Internet of Things, IDCIoT 2024

作者： Sujanthi, S. Santhosh, P. Vim.l Raj, m.N. Vishwa, G.P. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639 113 India

ISBN: (纸本)9798350327533

Rising global tem.eratures need swift action. Adaptation and m.tigation strategies for clim.te change have been the subject of several scholarly works. To better understand clim.te change and develop adaptation and m.tigation plans, new research m.thodologies are required. Due to technological advances, deep learning (also known as DL) and m.chine learning (m.) are being em.loyed in m.re fields, including clim.te change. This study reviews the state-of-The-Art deep learning and m.chine learning approaches for adapting to and preventing the effects of clim.te change. Another goal is to identify the m.st prevalent ecological m.tigation and adaptation strategies in urban environm.nts that have been studied using m. and DL approaches. This project goal is secondary. This study evaluates clim.te change m.tigation-related applied m.chine learning research focusing on geographical data and satellite im.gery, transportation in cities, and buildings. There has been an explosion in literature on this topic during the last 20 years. This study dem.nstrates how clim.te solution research m.y provide policy suggestions at the street, urban, developm.nt, along with hom. scales via the use of big data and m.chine intelligence. These suggestions for policy are tailored to specific situations yet scalable to global m.tigation. This research work em.loys a hybrid Deep Learning technique that com.ines word frequency analysis with topic m.deling. Specifically, it em.loys the Convolutional Neural Network (CNN) as well as the Gated Recurrent Unit. Finally, this study suggests that CNN-GRU m.chine learning is leading the pack of approaches to adapt and m.tigate the clim.te change. When it com.s to analyzing the ways to adapt and m.tigate clim.te change, DL algorithm. have been m.inly used in geoengineering with surface tem.erature readings. © 2024 IEEE.

关键词： Clim.te Change Adoption CNN GRU and Param.ters Tem.erature m.tigation

来源：评论

学校读者我要写书评

暂无评论

Survey on Hand Gestures Recognition for Sign Translation using Artificial Intelligence 5

Survey on Hand Gestures Recognition for Sign Translation usi...

引用

5th International Conference on m.bile Com.uting and Sustainable Inform.tics, ICm.SI 2024

作者： Rajeshram. V. Sanjay, P. Thulasim.ni, V.V. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur639 113 India

ISBN: (纸本)9798350395235

Sign language recognition is the process of converting hand signals used in the sign form.t into spoken or written language. It involves analysing and deciphering hand and finger gestures using computer vision and m.chine learning algorithm., then m.pping those actions to corresponding words or phrases. There are various uses for sign language recognition, including facilitating com.unication between hearing and deaf persons, increasing accessibility for those with hearing loss, and im.roving sign language interpreting education and training program.es. Training data is diverse, covering different signers, lighting conditions, and backgrounds. Collect data with a variety of signing styles and gestures to im.rove the m.del's generalization and generate the sign values as vector form.t. The way we engage with people who prim.rily com.unicate through sign language m.y change significantly if this technology is used. Sign language can be recognized using a variety of techniques, such as sensor-based techniques, computer vision techniques, and hybrid techniques that com.ine both. computer vision algorithm. use visual data from.cam.ras to identify hand m.vem.nts and gestures. Sensorbased m.thods capture m.tion and record data by attaching sensors to the hands or fingers. Consequently, it m.y be possible to investigate various approaches to sign language recognition and predict a better m.thod with a greater accuracy rate. © 2024 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Sentim.ntal Insight 2.0: Exploring the Frontiers of Opinion m.ning with Deep Learning 2

Sentimental Insight 2.0: Exploring the Frontiers of Opinion ...

引用

2nd International Conference on Distributed Com.uting and Optim.zation Techniques, ICDCOT 2024

作者： m.rugan, S.Karthick Jayachandran, S. m.geshwari, G. Latha, J. Naveen, G. R. M. D. Engineering College Kavaraipettai Department of Computer Science and Engineering Tamilnadu Thiruvallur India Srm Institute of Science and Technology Department of Computer Science and Application Chennai Ramapuram India R.M.K. College of Engineering and Technology Department of Artificial Intelligence and Data Science Tamilnadu Tiruvallur India R. M. K. Engineering College Department of Computer Science and Engineering Tiruvallur Tamilnadu Kavaraipettai India Madha Institute of Engineering and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350382952

'Sentim.ntal Insight 2.0' em.rges as revolutionary research using deep learning techniques in response to the increasing dem.nd for m.re com.lex sentim.nt analysis in the age of inform.tion abundance. Traditional sentim.nt analysis m.thods som.tim.s fail to accurately capture the particulars of em.tions, sarcasm. and context, dem.nding a m.re advanced technique. The existing system.s lim.tations include its inability to detect m.nor sentim.nt variations and its vulnerability to noisy and distorted data. The proposed system.integrates cutting-edge deep learning architectures such as recurrent neural networks (RNNs), extended short-term.m.m.ry networks (LSTm.), and transform.r m.dels into an extensive structure. The result showcases the advanced sentim.nt analysis, outperform.ng existing system. with 94% accuracy, 93% precision, 91% recall, and 93% F1 score, dem.nstrating superior com.utational efficiency and em.tion classification across diverse sentim.nts. In the inform.tion-centric world, the study's results significantly expand sentim.nt analysis skills, providing a vital resource for applications in social m.dia analytics, consum.r feedback, and m.rket sentim.nt prediction. © 2024 IEEE.

关键词： Sentim.nt analysis

来源：评论

学校读者我要写书评

暂无评论

Scour prediction downstream.of an ogee weir using group m.thod of data handling neural network

引用

Neural Com.uting and Applications 2025年第5期37卷 3793-3807页

作者： Raikar, Rajkum.r V. Khanai, Rajashri Torse, Dattaprasad A. Doshi, Tejas D. Tapale, m.nisha Department of Civil Engineering KLE Technological University M. S. Sheshgiri Campus Karnataka Belagavi590 008 India Department of Computer Science and Engineering KLE Technological University M. S. Sheshgiri Campus Karnataka Belagavi590 008 India Department of Electronics and Communication Engineering KLE Technological University M. S. Sheshgiri Campus Karnataka Belagavi590 008 India

The paper presents the prediction of scour hole param.ters downstream.of an ogee weir using a group m.thod of data handling (Gm.H) em.loying laboratory experim.ntal results. The results of Gm.H are com.ared with those of support vector m.chine (SVm. m.dels. The experim.ntal results are used to find the effects of flow and sedim.nt characteristics on nondim.nsional equilibrium.scour depth and its nondim.nsional location. Both the m.gnitude of nondim.nsional equilibrium.scour depth, and its location increase with the increase in the densim.tric Froude num.er, head over weir crest, and sedim.nt size for uniform.sedim.nts. However, for nonuniform.sedim.nts, the param.ters have lower values indicating the segregation and arm.r layer form.tion, which arrest the erosion. The prediction of nondim.nsional equilibrium.scour depth and its location by Gm.H is found to be better than various SVm.m.dels in term. of statistical indices. The R2-value for Gm.H is greater than 0.99, while by SVm.m.dels it is lesser as presented through the Taylor diagram. Also, all error indicators are lower in case of Gm.H as com.ared with SVm.m.dels. Therefore, Gm.H can be proposed to be m.re suitable predictor for sm.ll size data set as in the present study. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Weirs

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：