检索结果-内蒙古大学图书馆

3rd IEEE Mysore Sub Section International Conference, MysuruCon 2023

作者： Hegde, Ramakrishna Kripa Das, Sujan D Sriraksha, M.S. Siri, R. Siri Gowri, H. Soumyasri, S.M. Vidyavardhaka College of Engg. Computer Science Engineering Mysuru India PES University Computer Science Engineering Bengaluru India The National Institute of Engineering Master of Computer Applications Mysuru India

ISBN: (纸本)9798350340358

The field of autonomous driving cars is a rapidly growing area of research, machine learning and image recognition technology plays a pivotal role in ensuring their safe navigation on the roads. Different driving modes are offered by modern cars to accommodate various road conditions and driver preferences. However, manually selecting these modes can be cumbersome. Addressing the dynamic nature of mode switching in autonomous driving systems presents a multifaceted challenge. The system must continuously assess a multitude of variables such as traffic patterns, road conditions, weather conditions, and the wear and tear of vehicle components. Traffic conditions can change rapidly, requiring real-time analysis of traffic flow and congestion. Road conditions, including the presence of obstacles, construction zones, or slippery surfaces, demand instant adaptation for safe navigation. Weather conditions further complicate the scenario, as rain, snow, fog, or even intense sunlight can impact visibility and road grip. Addressing these challenges requires sophisticated algorithms capable of processing vast amounts of data from various sensors in real time. Machine learning models must be trained to recognize patterns in diverse conditions, enabling the system to make informed decisions swiftly and accurately. Moreover, the system must possess the ability to prioritize these factors based on their immediate impact on driving safety and efficiency. This can be a future enhancement of the paper. By leveraging machine learning algorithms, the mode selection process can be automated. The system constantly monitors driving conditions, learns from real-time camera sensor data and selects the most optimal mode to adapt to current situation. Different models such as Convolutional Neural Network (CNN), CNN with MobileNetV2 as base and decision trees are analyzed. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Integrative Remote Sensing Approaches Using Generative Adversarial Networks for Urban Heat Island Analysis and Mitigation

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 681-698页

作者： Sundar, Ganapathy Patchaiammal, Pitchaimuthu Venkateshwarulu, Balaji Vijayan Kumar, Thangavel Pradeesh Rajamannar, Kesavamoorthy Tripathi, Rajesh Kumar Department of Computer Applications Sindhi College Chennai India Department of Information Science and Engineering HKBK College of Engineering VTU Belagum Bengaluru Nagawara India VIT School of Agricultural Innovations and Advanced Learning (VAIAL) VIT Vellore India Department of Computer Science and Engineering CMR Institute of Technology Bengaluru India Department of Computer Engineering and Applications GLA University Uttar Pradesh Mathura India

The phenomenon of urban heat islands (UHI) presents a critical challenge for urban sustainability, exacerbating local temperatures, increasing energy demands, and impairing public health. Traditional methods for addressing UHI are often resource-intensive and slow. This study introduces a novel approach, utilizing a Hybrid CycleGAN-SVM (HCGS) model that leverages the synergy of Generative Adversarial Networks (GANs) and Support Vector Machines (SVMs) to efficiently analyze and mitigate UHI effects through high-resolution satellite imagery and temperature data. The model incorporates Enhanced Vision Transformers (EViTs) for superior feature extraction, adept at capturing intricate spatial and spectral urban patterns. The CycleGAN component of the model generates high-quality synthetic imagery, enhancing the dataset and addressing class imbalances, thereby bolstering the SVM classifier’s ability to precisely pinpoint heat-prone urban areas. Implemented in Google Colab, the HCGS model demonstrated exceptional performance, achieving a classification accuracy of 0.98. This indicates its potential as an effective tool for urban heat mitigation, offering actionable insights for urban planning and policy-making. By integrating advanced machine learning techniques with remote sensing data, the HCGS model paves the way for innovative climate adaptation strategies, fostering more sustainable and resilient urban environments. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Enhanced Vision Transformers EViTs GANs Generative Adversarial Networks HCGS model Hybrid CycleGAN-SVM Satellite imagery Support Vector Machines SVM UHI effect Urban heat island

来源：评论

学校读者我要写书评

暂无评论

Bubble Prediction in Stock Markets: Leveraging SVM and Technical Indicators for High Accuracy 3

Bubble Prediction in Stock Markets: Leveraging SVM and Techn...

引用

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

作者： Yuvaraj, S. Chenni Kumaran, J. Manogar, E. Doss, P.Lourdu Mahimai Gunasekaran, M. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering TamilNadu Chennai India B.S. Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Chennai India

ISBN: (纸本)9798331509675

Predicting stock market bubbles is indispensable for risk control and refinement of trading strategies. Therefore, this study presents a Machine-Learning Framework to detect price bubble formations based on Support Vector Machine (SVM) and through important technical indicators. Among these are momentum indicators, such as the Relative Strength Index (RSI), and the Moving Average Convergence Divergence (MACD) histogram, which are complemented with volatility measures from Bollinger Bands and with normalized volume indicators, all to improve predictive accuracy. Recent historical stock data were fed to the model during training and testing, yielding exceptional accuracy: 98.54% on the test set and 98.95% on the training set. The performance evaluation was carried out based on Classification Reports, Confusion Matrices, Receiver Operating Characteristic (ROC) curve, and Precision-Recall metrics, thus confirming the performance efficiency of the developed framework. With this approach, bubbles' early detection allows traders and analysts a powerful tool to make informed decisions in risk mitigation or strategic enhancement. © 2025 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Impact of nutrients in food quality and safety by machine learning classifier using internet of things

引用

International Journal of Information Technology (Singapore) 2024年第5期16卷 2803-2812页

作者： Balamurugan, S. Gurumoorthi, E. Devi, P.P. Maruthamuthu, R. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & amp Department of IT CMR College of Engineering and Technology Telangana Hyderabad India Department of Computer Applications Madanapalle Institute of Technology and Science AP Madanapalle India

The traditional Food Supply Chain (FSC) is challenged by a number of issues, including uncertainty, security, expense, complexity, and quality worries. A precise supply chain is required to address these problems. Managing the supply chain to distribute high-quality goods is a difficult task in the modern food sector. The efficient Tree Augmented Naive Bayes linked with FSC utilizing Internet of Things (IoT) is proposed in this paper to enable tracking, tracing, and managing the full food supply chain process, including supplier, exporter, and consumers. This paper's goals are to evaluate the food safety and create the best possible chronological data for the analysis of potential future assumptions. It also intends to connect the producer and the buyer by delivering high-quality food goods while using IoT technology to transport food from the producers to the customers. IoT-based food supply chain traceability is used to successfully transact data with ambiguous, unreliable, and inadequate data. In order to provide secure backdrop and food safety for FSC process utilizing IoT technology, the suggested effective Tree Augmented Naive Bayes algorithm would be able to overcome the challenges of conventional supply chain. © Bharati Vidyapeeth's institute of computer applications and Management 2024.

关键词： Bayes classifier algorithm Food safety and IoT FSC Traceability Tree augmented Naive Bayes

来源：评论

学校读者我要写书评

暂无评论

Novel Anchor Generation Based Residual Network for Object Tracking in Video-Surveillance applications

引用

SN computer science 2025年第2期6卷 1-12页

作者： Mohanapriya, D. Rajalakshmi, K. Helen Josephine, V.L. Panneerselvam, Karthick Department of Computer Science (SF) Sourasthra College Tamil Nadu Madurai India Department of Computer Applications CMR Institute of Technology Karnataka Bangalore India Business Analytics School of Business and Management Christ University Karnataka Bangalore India Department of Computer Science and Engineering KPR Institute of Engineering and Technology Tamilnadu Uthupalayam 641407 India

The activity of the object in question is alerted directly upon completion of an effective object tracking. Dependent on hardware support or not, a strong object tracking protocol is required for a precise object tracking application. According to these methods, tracking an object accurately within a predetermined processing time window required a significant amount of computer complexity. In contrast, a variety of quality-degrading elements, including occlusion, shifting lighting, shadows, and so on, have an adverse effect on tracking. All of these tracking shortcomings will be fixed by a revolutionary residual network based on loss operator and anchor creation. Detection of object has concerns that rely on the process of feature extraction to afford efficient quality. For this purpose a model called ResNet has been used that comprises thirty layers and hence named as Resnet-thirty. These networks are a type of Convolutional Neural Network (CNN) that contain residual connections among various layers. The various merits of these connections is the network has the capability to learn the features of global, local and intermediate in parallel. As such, the system is robust against changes in lighting. These variations in light were understood in terms of tracking objects within a changing background. The proposed work uses MOT datasets. This dataset comprises of MOT 15, MOT16, MOT17 and MOT20. The results have been found by using these datasets. Hence, it evidently outperforms in terms of precision, recall, MOTA, IDF, MOTP, SAIDF and F1 measure to track the objects. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： computer vision Loss operator Object tracking Residual network

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classifiers for Predicting the Risk of Cardiovascular Disease in Healthcare 4.0 3

Machine Learning Classifiers for Predicting the Risk of Card...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Kumari, Palak Kumar, Ashish Chatterjee, Kakali Master of Computer Applications Patna Women's College Patna India National Institute of Technology Patna Dept. of Computer Science and Engineering Patna India

ISBN: (纸本)9798331528201

Cardiovascular disease (CVD) generic phrase used to describe heart or blood vessel illness. Conditions that impact the body's, brain's, or heart's blood flow. Reduced blood flow can result from factors such as blood clots, leading to heart attack, angina, or stroke. Other potential meanings of CVD. These models offer key benefits like clear interpretability and the ability to analyze complex patterns, significantly enhancing the accuracy of cardiovascular disease risk predictions. The demerits of using SVM, LR, K-NN, and MLP for CVD prediction include inter-pretability issues, overfitting risks, data requirements, feature selection challenges, scalability concerns, algorithm complexity, and class imbalance. Collaboration between machine learning experts and healthcare professionals is essential for developing accurate and reliable CVD prediction models that enhance patient care. CVD is a significant health threat, often leading to fatal complications. Early detection is crucial for effective intervention. This study employs SVM (accuracy is 0.84%), LR (accuracy is 0.86%), K-NN (accuracy is 0.94%), and MLP (accuracy is 0.79%) machine learning techniques to enhance CVD detection by addressing outliers and null values, contributing to advancing automatic detection initiatives. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

An AI-Driven Intelligent Traffic Management Model for 6G Cloud Radio Access Networks

引用

IEEE Wireless Communications Letters 2023年第6期12卷 1056-1060页

作者： Swain, Smruti Rekha Saxena, Deepika Kumar, Jatinder Singh, Ashutosh Kumar Lee, Chung-Nan National Institute of Technology Department of Computer Applications Kurukshetra136119 India Goethe University Frankfurt Department of Computer Science Frankfurt60323 Germany National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804 Taiwan

This letter proposes a novel Cloud Radio Access Network (C-RAN) traffic analysis and management model that estimates probable RAN traffic congestion and mitigate its effect by adopting a suitable handling mechanism. A computation approach is introduced to classify heterogeneous RAN traffic into distinct traffic states based on bandwidth consumption and execution time of various job requests. Further, a cloud-based traffic management is employed to schedule and allocate resources among user job requests according to the associated traffic states to minimize latency and maximize bandwidth utilization. The experimental evaluation and comparison of the proposed model with state-of-the-art methods reveal that it is effective in minimizing the worse effect of traffic congestion and improves bandwidth utilization and reduces job execution latency up to 17.07% and 18%, respectively. © 2012 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Smart question answering system using vectorization approach and statistical scoring method

引用

Materials Today: Proceedings 2023年 80卷 3719-3725页

作者： Manjunath, T.N. Yogish, Deepa Mahalakshmi, S. Yogish, H.K. Information Science & Engineering B M S Institute of Technology &Management Karnataka Bangalore560064 India K S School of Engineering & Management Computer Science & Engineering Affiliated to Visvesvaraya Technological University Karnataka Belagavi India Department of Master of Computer Applications M S Ramaiah Institute of Technology Karnataka Bangalore560054 India

In this digital era, internet users are increasing day by day to extract information related to various fields such as health, economic, educational, politics and daily needs from Information Retrieval Systems (IRS) such as Google, Ask, Yahoo etc. Information Retrieval (IR) is a conventional method which depends on metadata searching method that is searching of adocuments for information within documents and information about documents. Lot of research in the IR area improves accessing the quality of information. Most of the search engines such as Google, Yahoo, Ask Jeeves depends on keyword based query processing mechanism internally which can't handle natural language questions which results in returning long list of documents for a query. The task of users is to manually explore each document to retrieve correct answer which is a time consuming process. To overcome the problems of conventional search engines, smart question answering system comes to play. The objective of Smart Automated Answering system is to impart accurate and valid answers to user question in natural language rather than set of full documents. The Smart Question answering system which accepts user question in Natural language in specific domain and provide short and precise answer using Natural language processing technique, used for pre-processing, normalized term weighting-TF-IDF with cosine similarity approach for document retrieval and enhanced BM25 ranking function to extract answer. The main focus is on decreasing the response time, designing ranking function and giving the pertinent responses to the users’ intent. The system achieved an overall Precision of 93.2%, Recall of 84.3% and F-measure of 88.5% with 80% of Accuracy. © 2021

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Detection of Acute Lymphoblastic Leukemia Using a Novel Bone Marrow Image Segmentation

引用

Tsinghua science and Technology 2025年第2期30卷 610-623页

作者： M.Anline Rejula Ben M Jebin Ravi Selvakumar S.Amutha Eberlein George Department of Computer Applications-PG Scott Christian College(Autonomous)Nagercoil 629003India Department of Computer Science Malankara Catholic CollegeMariagiri 629153India School of Computer Science and Engineering Vellore Institute of TechnologyChennai 600127India Department of Pediatrics Government Medical College and HospitalGovernment of Tamil NaduNamakkal 637001India

In our study,we present a novel method for automating the segmentation and classification of bone marrow images to distinguish between normal and Acute Lymphoblastic Leukaemia(ALL).Built upon existing segmentation techniques,our approach enhances the dual threshold segmentation process,optimizing the isolation of nucleus and cytoplasm *** is achieved by adapting threshold values based on image characteristics,resulting in superior segmentation outcomes compared to previous *** address challenges,such as noise and incomplete white blood cells,we employ mathematical morphology and median filtering *** methods effectively denoise the images and remove incomplete cells,leading to cleaner and more precise ***,we propose a unique feature extraction method using a hybrid discrete wavelet transform,capturing both spatial and frequency *** allows for the extraction of highly discriminative features from segmented images,enhancing the reliability of *** classification purposes,we utilize an improved Adaptive Neuro-Fuzzy Inference System(ANFIS)that leverages the extracted *** enhanced classification algorithm surpasses traditional methods,ensuring accurate identification of acute lymphoblastic *** innovation lies in the comprehensive integration of segmentation techniques,advanced denoising methods,novel feature extraction,and improved *** extensive evaluation on bone marrow samples from the Acute Lymphoblastic Leukemia Image DataBase(ALL-IDB)for Image Processing database using MATLAB 10.0,our method demonstrates outstanding classification *** segmentation accuracy for various cell types,including Band cells(96%),Metamyelocyte(99%),Myeloblast(96%),***(97%),***(97%),and Neutrophil cells(98%),further underscores the potential of our approach as a high-quality tool for ALL diagnosis.

关键词： Adaptive Neuro-Fuzzy Inference System(ANFIS) blood cells segmentation leukemia classification

来源：评论

学校读者我要写书评

暂无评论

Apply Deep Learning-based CNN and LSTM for Visual Image Caption Generator 3

Apply Deep Learning-based CNN and LSTM for Visual Image Capt...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Indumathi, N. Divyalakshmi, R.J. Stalin, J. Ramachandran, V. Rajaram, P. Srm Institute of Science and Technology Computer Science and Applications Chennai India Sethu Institute of Technology Computer Science and Business Systems Virudhunagar India Computer Science and Engineering Gitam School of Computing Bengaluru India

ISBN: (纸本)9798350399264

Implemented Image captioning is becoming a need. Deep neural network models enable integrated applications to generate and caption images. Image captioning describes an image. It requires identifying an image's main objects, properties, and relationships. It produces correct sentences. The creation of image caption generators, which examine the content of an image and offer pertinent descriptions, makes use of deep learning and computer vision techniques. One element of this method involves classifying objects in the image using English keywords derived from training datasets. The caption generator was created by combining LSTM and CNN. In this paper, we propose a deep-learning model that uses computer vision and machine translation to characterize images and generate captions. The model successfully recognizes and labels visual items and their relationships. Transfer Learning will be used to demonstrate the suggested experiment, coupled with the Flickr8k dataset and the Python3 programming language. This study will also look into the functions and construction of neural networks. The proposed model achieves a BELU Score of 69.8. © 2023 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

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：