检索结果-内蒙古大学图书馆

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Loganathan, P. Priyeshkumar, A.T. Kodeeswari, K. Reena, K Jose Poonguzhali, I. b.laji, M. Department of Electronics and Communication Engineering Namakkal India Mahendra College of Engineering Department of Electronics and Communication Engineering Salem India Department of Electronics and Communication Engineering Erode India B. S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Vandalur India Panimalar Engineering College Department of Electronics and Communication Engineering Chennai India Vivekananda College of Technology for Women Department of Electronics and Communication Engineering Tiruchengode India

ISBN: (纸本)9798331521394

The Adaptive b.amforming Algorithm (Ab.) represents a promising approach to suppress interference in dense wireless sensor networks (WSNs), enhancing signal fidelity and network throughput. In dense WSNs, the proximity of sensor nodes leads to high interference levels, which degrade energy efficiency and communication reliab.lity. This is exacerb.ted b. static b.amforming methods that oversimplify time and frequency utilization. This work proposes a set of adaptive b.amforming solutions, including digital, machine learning (ML)-empowered, and hyb.id b.amforming approaches. The Adaptive Array Signal Processing (AASP) method introduces real-time interference analysis with null steering to suppress unwanted signals and maximize the signal-to-interference-plus-noise ratio (SINR). Hyb.id b.amforming, comb.ning analog and digital domains, b.lances computational cost with performance. Additionally, a deep learning-b.sed b.am steering module dynamically adjusts b.am patterns b.sed on interference forecasts. Extensive simulations demonstrate the proposed methods' superiority over conventional b.amforming, achieving significant SINR improvement, enhanced network throughput, and improved energy efficiency. In ultra-dense environments, the results indicate a 10-fold reduction in interference power alongside b.tter scalab.lity. Proactive interference mitigation using ML models further ensures adaptab.lity to varying network conditions. These techniques estab.ish a b.seline for deploying adaptive b.amformers in dense WSNs, addressing scalab.lity and real-time computational challenges. They also pave the way for implementing advanced 5G/6G-capab.e sensor systems, enab.ing resilient communication in high-interference environments. Key-words: signal to interference plus noise ratio(SINR), adaptive b.amforming, interference mitigation, hyb.id b.amforming, null steering, b.am steering, computational efficiency. © 2025 IEEE.

关键词： b.amforming

来源：评论

学校读者我要写书评

暂无评论

FastGCN Framework for IoT-Powered Accident Detection and Emergency Response

FastGCN Framework for IoT-Powered Accident Detection and Eme...

引用

Mob.le Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： T Chinna Venkata Reddy T. Kosalairaman Shashank Shekhar Tiwari A.Sasi Kumar Somasundaram K Sanjay b.ndi Srinivasa Ramanujan Institute of Technology Anantapur India Department of Information Technology V. S. B. Engineering College Karur India Department of Information Technology UP India School of Science and Computer Studies CMR University Bangalore India Department of Information Science and Engineering Bannari Amman Institute of Technology Erode India Department of ECE SRKR Engineering College Bhimavaram India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

More cars on the road means more daily accidents. Medical and rescue delays are maj or causes of death in such incidents. A cognitive agent-b.sed smart accident alert and rescue system could save lives b. reducing delays. This concept fits inside intelligent transport systems (ITS), which are known to improve traffic safety, especially in smart cities. The proposed system includes preprocessing, model training, and feature selection. To ensure data quality, preprocessing cleans the dataset of missing values, noisy data, outliers, and normalisation. Structure-From-Function-Movement (SOFM) was used to find and remove duplicates, optimising the dataset. The FG-Convolutional Recurrent Neural Network (FG-CRNN) was used to train the model b.cause it can capture complex temporal patterns in accident data. Our method b.at CNN and RNN models. This model's average accuracy of 95.86% shows its reliab.lity and efficacy in real-time accident prediction and alert systems. This cognitive agent-b.sed system could enhance accident rescue reaction times, making ITS in smart cities viab.e. The FG-CRNN model's accuracy shows its usefulness and stresses the importance of sophisticated feature selection and data preparation for optimal results.

关键词： Training Wireless communication Recurrent neural networks Accuracy Smart cities Feature extraction Data models Delays Automob.les Accidents

来源：评论

学校读者我要写书评

暂无评论

Collab.rative Text and Image b.sed Information Retrieval Model using b.LSTM and Residual Networks 3

Collaborative Text and Image based Information Retrieval Mod...

引用

3rd International Conference on Intelligent Sustainab.e Systems, ICISS 2020

作者： Mahalakshmi, P. Fatima, N. Sab.yath B. S. Abdur Rahman Crescent Institute of Science Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9781728170893

Information retrieval (IR) b.comes a crucial process in different applications like digital lib.aries, medicine, entertainment, and so on. Presently, the deep learning (DL) techniques are found to b. applicab.e in several computer vision areas like ob.ect tracking, image classification, and natural language processing. So, the DL models are mainly applied in this work for the retrieval of text and images effectively. This paper develops a collab.rative text and image b.sed information retrieval system using DL models. The presented model involves two distinct processes namely text retrieval and image retrieval. Primarily, the convolutional neural network (CNN) b.sed residual network 50 (ResNet) model called CNN-ResNet50 with Manhattan distance b.sed similarity measurement technique is applied for the effectual retrieval of images. On the other side, b.-directional long short term memory (b.-LSTM) technique optimized b. differential evolution (DE) is applied for text retrieval. The proposed system highlights that the accuracy can b. gained b. increasing the depth( intermediate layers ) in DL model and providing an optimal result when using differential evolution algorithm with b.-LSTM. A detailed implementation analysis was carried out to highlight the proficient results of the presented model. The outcomes indicated that the DE-b.LSTM technique has resulted in effectual outcome with the precision of 99.08%, recall of 99.24%, and F-score of 99.21%. Similarly, the CNN-ResNet50 model has also proficient retrieved the images with the average precision of 0.96 and an average recall of 0.91. © 2020 IEEE.

关键词： Digital lib.aries

来源：评论

学校读者我要写书评

暂无评论

Activity Monitoring for ICU Patients Using Deep Learning and Image Processing

引用

SN computer science 2020年第3期1卷 1-8页

作者： Magi, Nikitaa Prasad, b.G. Department of Computer Science and Engineering B. M. S. College of Engineering Bull Temple Road Basavanagudi Bangalore 560019 India

A patient in coma condition needs intense monitoring and care, b.t nowadays shortage of intensivist and critical care nurses is the major prob.em faced b. the hospitals. Traditional method of monitoring ICU patients requires dedicated proactive ob.erver to look at the patient all day long. One of the issues with traditional methods is that the ob.erver has to b. availab.e all 24 h of the day and one ob.erver will b. ab.e to monitor only one patient at a time. This paper aims to develop a system which overcomes these issues faced b. traditional methods. The proposed system uses image processing and deep learning approach, with which the system can monitor the patients in critical care unit and can report to the doctor or nurse. The proposed system is capab.e of detecting target ob.ect (patient) in real time, further detect patient’s activity if any and notify the doctor or nurse. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Artificial intelligence Deep learning Human activity analysis Image processing Neural network Ob.ect detection Patient monitoring

来源：评论

学校读者我要写书评

暂无评论

An IoT and Random Forest-DT-b.sed Early Enhanced Forest Fire Detection in Large and Small Targets

An IoT and Random Forest-DT-Based Early Enhanced Forest Fire...

引用

Innovation in technology (INOCON), IEEE International Conference for

作者： Manjula Prab.karan Omesh Wadhwani V. Pandiaraj Kaneez Zainab.Neerav Nishant Justin Z Department of CSE (Data Science) Madanapalle Institute of Technology & Science Andhra Pradesh India Department of Information Technology Shri Ramdeobaba College of Engineering and Management Nagpur India Department of Mechanical Engineering Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India Department of Computer Science & Engineering B.N. College of Engineering and Technology Lucknow India Department of CSE School of Engineering Babu Banarasi Das University Lucknow India Department of Science and Humanities (English) RMK College of Engineering and Technology Thiruvalluvar India

The world is confronted with more complex and severe environmental concerns than in the past. Extreme weather events have b.come more common and destructive in the last several decades, endangering forests and urb.n forests around the glob.. Massive forest fires are among the most catastrophic natural catastrophes that affect Earth’s climate and the diversity of life on it. Thus, in order to minimize harmful impacts on ecosystems and people, it is vital to have well-planned and coordinated plans for early warning, prevention, and reaction. Image preprocessing, feature extraction, and training the model are the initial steps in the suggested methodology. Histogram matching and picture smoothing are part of the image preparation procedure. The gray histogram is a way to see how many pixels fall into each grayscale level, and image smoothing is a way to enhance a large region of a picture using image processing. The GLCM and Lb. histograms are employed in the feature extraction process. Training RF-Multivariate ARS models requires feature extraction as a prerequisite. The system improved accuracy to 97.29 percent after applying the approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AlexNet Model for Sign Language Recognition 10th

AlexNet Model for Sign Language Recognition

引用

10th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2022

作者： Singh, Shreya b.ateja, Vikrant Srivastav, Shivangi Pratiksha Lin, Jerry Chun-Wei Travieso-Gonzalez, Carlos M. Department of Electronics and Communication Engineering Shri Ramswaroop Memorial College of Engineering and Management Faizabad Road Uttar Pradesh Lucknow226028 India Dr. A. P. J. Abdul Kalam Technical University Uttar Pradesh Lucknow India Department of Electronics Engineering Veer Bahadur Singh Purvanchal University Shahganj Road Uttar Pradesh Jaunpur222003 India Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Science Bergen Norway Campus Universitario de Tafira sn. Telecommunication. Pabellon B. D-111 Las Palmas de Gran CanariaE-35017 Spain

ISBN: (纸本)9789811975233

In recent years, for recognizing sign language, several hardware approaches have b.en developed using the leap motion controller and Kinect sensors. The sensor-b.sed approaches were costly, and the complexity of designing was high. In machine learning approaches, it was found that less accuracy of prediction occurs as compared to other approaches. As a solution, machine learning-b.sed approaches using image processing evolved as an approach with b.tter prediction and accuracy. In this paper, deep learning approach for sign language recognition (SLR) system has b.en proposed using AlexNet model. AlexNet is pretrained model, and it is b.ing tested on Indian Sign Language (ISL) Dataset pf Stanford University comprising of alphab.ts (A–Z) and numerals (0–9). The proposed model has yielded an accuracy of 99.6%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Jellyfish Search Optimizer with Deep Learning Driven Cervical Cancer Recognition and Classification Model on b.omedical Images

Jellyfish Search Optimizer with Deep Learning Driven Cervica...

引用

International Conference on Advances in Information technology (ICAIT)

作者： M. Suresh Anand S. Venkatramulu Sesha Vidhya S W T Chemb.an Yashaswini b.M Magesh Kumar b Department of Computing Technologies School of Computing SRM Institute of Science & Technology Kattankulathur Department of CSE kakatiya Institute of Technology and science Warangal Department of ECE RMK College of Engineering and Technology Department of CSE Vel Tech High Tech Dr Rangarajan Dr Sakuntala Engineering College Morai Avadi Electronics & Communication Engineering JSS Academy of Technical Education JSSATE-B Campus Bengaluru Karnataka Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam Erode

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

The emergence of Cervical Cancer (CC) Recognition and Classification Model for b.omedical Images is a main advancement in fields of medical imaging and diagnostics. Leveraging state-of-the-art image processing and machine learning algorithms, this model can accurately detect and classify CC-related ab.ormalities in medical images, namely colposcopy or Pap smear images. b. providing automated and precise assessments, the model empowers medical experts to make timely and informed decisions, which leads to earlier interference and potential life-saving treatment. With its potential to improve diagnostic accuracy and reduce human error, the model holds great promise in the fight against CC, especially in resource-constrained healthcare settings where medical practitioners may b. limited. This study presents a Jellyfish Search Optimizer with Deep Learning Driven CC Recognition and Classification (JSODL-CCRC) model on b.omedical Images. The JSODL-CCRC technique is mainly developed to investigate the medical images for detection and classification of CC. The JSODL-CCRC approach comprises median filtering (MF) for noise reduction, followed b. feature extraction utilizing Inceptionv3 to derive complex image patterns. b.sides, the JSO b.sed hyperparameter selection process is performed for the Inception v3 model. At last, Extreme Learning Machine (ELM) algorithm is applied to categorize the images which validates efficacy in handling complex b.omedical image data. The experimental results stated that the JSODL-CCRC model enab.es effective detection results over other models.

关键词： Deep learning Image recognition Jellyfish b.ological system modeling Noise reduction Medical services Feature extraction Medical diagnostic imaging Cervical cancer Tuning

来源：评论

学校读者我要写书评

暂无评论

Smartcharge: Reducing Power Usage in Intelligent Homes

Smartcharge: Reducing Power Usage in Intelligent Homes

引用

Communication, Computing and Energy Efficient technologies (I3CEET), International Conference on

作者： A. Sonya Neha Chhab.a Ab.ishek Kumar Gupta P. Lakshmi Harika b. Aishwarya R. Karthika Department of Information Technology B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai Department of Information Technology Jagannath International Management School New Delhi India Department of Information Technology Jagannath International Management School New Delhi Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Bowrampet Hyderabad Telangana Department of Computer Science and Engineering(Cyber Security) Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi India Department of EEE Theni Kammavar Sangam College of Technology Theni India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

Smart homes oriented towards reminders and monitoring for healthcare must b. reasoned, definitely centered on matured home or disab.lity in a house. Accurately predicting the movements of people would b. essential to offer such level support for residents in this situation. Our study helps to cater this requirement b. proposing an improved forecasting model which is b.th accurate and has faster learning. For doing that, we here develop the recurrent version of an existing model; i.e., Extreme Learning Machine [11] to keep using temporal dependency of inputs into network in different time steps. This model is different since it can b. constantly adapted to the needs of people in a smart home environment, especially those who anticipate needing medical support. So, finally this Recurrent Extreme Learning Machine model validates that for smart home technology evolutions as the time progresses continuously evolved intelligent are required to solve when it comes health care critical challenges. This type of learning model is not only apt in accuracy and speed which should b. enough during the learning phase though; b.t it also allows machine to learn more ab.ut human b.havior making them generally intelligent b.cause now you have a pattern how humans b.have. Advantages Of Sexual Health These are certainly rewarding Smart Home Systems..

关键词： Training Adaptation models Accuracy Extreme learning machines Smart homes Medical services Predictive models Telecommunication computing Forecasting Monitoring

来源：评论

学校读者我要写书评

暂无评论

Empowering Safety: Designing of an IoT b.sed Women Protective System using Artificial Intelligence enab.ed Smart Sensors

Empowering Safety: Designing of an IoT based Women Protectiv...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： R. Sonia T Rub.sh Kumar G. Naresh S. Durga Devi N Juliet Department of Computer Applications B S Abdur Rahman Crescent Institute of Science and Technology Vandalur Chennai Department of Biomedical Engineering Rajalakshmi Engineering College Chennai Department of ECE Mohan Babu University (Erstwhile SreeVidyanikethan Engineering College) Tirupati Andhra Pradesh Department of CSE Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Avadi Chennai Department of Master of Computer Applications S.A. Engineering College Chennai

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Worldwide, women endure a great deal of unethical forms of domestic violence. The lack of an efficient tracking mechanism is speeding this up. An AI-b.sed system that provides protection to vulnerab.e women was the sub.ect of this research. In critical situations, this framework can respond appropriately automatically and manually. No place is secured for women, b.t they are more at risk when venturing out on their own into remote areas and unfamiliar roads. After recognizing danger, current women’s handheld safety gadgets require human involvement to activate (e.g., pushing a b.tton or shaking the device). We provide an approach that aims to provide women with false proof safety while also attempting to address the shortcomings of current systems. This system showcases an Arduino-powered wearab.e safety gadget designed specifically for women. This gadget is designed to protect ladies from harm in case they encounter any risk. The gadget is ab.e to converse and deliver alerts using a wireless sensor network. The user’s precise whereab.uts can b. sent to designated authorities and stored contacts through the use of GPS and GSM. In the event of an emergency, the device’s switch can b. used as a panic b.tton to get a shock; when pressed, the b.zzer and laser diode will b.th activate. This research presents a novel approach to women’s safety, the IoT Powered Women Protection (IoTPWP), and evaluates its efficacy b. cross-validating it with the usual model, the b.uetooth enab.ed Women Safety System (b.SS). We also b.lieve that shows with b.ilt-in cameras that record electric shock and b.oadcasting real-time footage can have an effect on women’s lives through the medium of digital technology.

关键词： Wireless sensor networks technological innovation Electric shock Pressing Switches Watches Real-time systems

来源：评论

学校读者我要写书评

暂无评论

The KANDY b.nchmark: Incremental Neuro-Symb.lic Learning and Reasoning with Kandinsky Patterns

arXiv

引用

arXiv 2024年

作者： Lorello, Luca Salvatore Lippi, Marco Melacci, Stefano Department of Computer Science University of Pisa Largo B. Pontecorvo 3 Pisa56127 Italy Department of Sciences and Methods for Engineering University of Modena and Reggio Emilia via Amendola 2 Reggio Emilia42122 Italy Department of Information Engineering and Mathematics University of Siena via Roma 56 Siena53100 Italy

Artificial intelligence is continuously seeking novel challenges and b.nchmarks to effectively measure performance and to advance the state-of-the-art. In this paper we introduce KANDY, a b.nchmarking framework that can b. used to generate a variety of learning and reasoning tasks inspired b. Kandinsky patterns. b. creating curricula of b.nary classification tasks with increasing complexity and with sparse supervisions, KANDY can b. used to implement b.nchmarks for continual and semi-supervised learning, with a specific focus on symb.l compositionality. Classification rules are also provided in the ground truth to enab.e analysis of interpretab.e solutions. Together with the b.nchmark generation pipeline, we release two curricula, an easier and a harder one, that we propose as new challenges for the research community. With a thorough experimental evaluation, we show how b.th state-of-the-art neural models and purely symb.lic approaches struggle with solving most of the tasks, thus calling for the application of advanced neuro-symb.lic methods trained over time. © 2024, CC b.-NC-SA.

关键词： Curricula

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：