检索结果-内蒙古大学图书馆

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Sunil Kumar, Aithal S Mahesh, Kavitha St Joseph Engineering College Dept. of Computer Science and Engineering Mangalore India Nmam Institute of Technology Nitte Dept. of Computer Science and Engineering India Science and Engineering Nagarjuna College of Engineering & Technology Mudugurki Bengaluru India

ISBN: (纸本)9798350347579

Detection of objects and its recognition in visual sequences are the two critical tasks in the computer vision field. Various real-time applications such as autonomous vehicles, face recognition, health-care systems and space exploration requires highly reliable and precise object detection models. Traditional object detection and recognition algorithms are based on hand crafted and are considered to be erroneous, time consuming and expensive leading to the significant reduction of accuracy rate for object detection in large datasets. Recently, large number of promising deep neural networks models have been emerged for facilitating automated and accurate detection of varying scale objects and its precise recognition across various computer vision applications. Several GPU based neural models thereby incorporating context-aware capabilities have shown effective performance, which overcomes the drawbacks of traditional techniques. This research study provides an investigation of several popular deep learning models that exists for accurate object detection in various forms of visual sequences. Varying scale objects are detected frequently available in popular MS COCO and PASCAL datasets and their performance are evaluated utilizing one stage Yolo family and two stage Faster RCNN deep learning object detectors. At the end of the study, several future research directions for object detection task are discussed. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Telecom Customer Loyalty Through Churn Prediction Models 8

Enhancing Telecom Customer Loyalty Through Churn Prediction ...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Thanam, A. Malchijah Raj, M.S. Joel, M. Robinson Shanthakumar, P. Jacson, J. Joel Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Mathematics Tamil Nadu Chennai602105 India Kcg College of Technology Department of Computer Science and Engineering Chennai India Nehru Institute of Technology Department of Computer Science and Engineering Coimbatore India Kings Engineering College Department of Information Technology Chennai India

ISBN: (纸本)9798350367904

In the rapidly evolving telecommunications sector, maintaining profitability and growth depends on customer retention. With the goal of identifying the critical elements influencing customer attrition and creating a useful predictive model, this study offers a thorough investigation of customer churn prediction using a telecom dataset. This study uses a dataset that contains a variety of client features, such as account details, demographic data, and service consumption trends. Here, the data preparation techniques are used to manage anomalies, missing values, and data normalisation. The study uses a range of machine learning methods to forecast churn, such as support vector machines, random forests, decision trees, logistic regression, and gradient boosting. Metrics including accuracy, then precision, also the recall, then F1 score, and also the area under the curve of receiver operating characteristic are used to assess each model's performance (AUC-ROC). By use of cross-validation and hyperparameter adjustment, we guarantee the models' resilience and generalizability. Significant churn predictors, including contract type, duration, monthly costs, and customer support interactions, are identified by our investigation. According to the research, month-to-month contract holders who have higher monthly fees and frequent contact with customer service are more likely to experience customer attrition. The model with the highest degree of prediction accuracy is the random forest, which has an AUC-ROC of 0.85, making it the best-performing model. This paper offers a useful foundation for putting churn prediction models into practice in addition to highlighting the important variables causing customer churn in the telecom industry. Telecom firms may lower churn rates by creating focused retention tactics, such personalised offers and better customer care, by proactively identifying at-risk clients. The findings highlight how crucial it is to use machine learning and data a

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Unveiling Themes in Judicial Proceedings: A Cross-Country Study Using Topic Modeling on Legal Documents from India and the UK

Unveiling Themes in Judicial Proceedings: A Cross-Country St...

引用

2024 Joint Ontology Workshops - Episode X: The Tukker Zomer of Ontology, and Satellite Events, JOWO 2024

作者： Didwania, Krish Toshniwal, Durga Agarwal, Amit Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Computer Science Indian Institute of Technology Roorkee India

Legal documents are indispensable in every country for legal practices and serve as the primary source of information regarding previous cases and employed statutes. In today’s world, with an increasing number of judicial cases, it is crucial to systematically categorize past cases into subgroups, which can then be utilized for upcoming cases and practices. Our primary focus in this endeavor was to annotate cases using topic modeling algorithms such as Latent Dirichlet Allocation, Non-Negative Matrix Factorization, and BerTopic for a collection of lengthy legal documents from India and the UK. This step is crucial for distinguishing the generated labels between the two countries, highlighting the differences in the types of cases that arise in each jurisdiction. Furthermore, an analysis of the timeline of cases from India was conducted to discern the evolution of dominant topics over the years. © 2024 Copyright for this paper by its authors.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Improving the Autonomous Vehicle Vision with Synthetic Data using Gen AI 3

Improving the Autonomous Vehicle Vision with Synthetic Data ...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Kadiyapu, Durga Chandra Mouli Mangali, Venkata Sai Thummuru, Jaideep Reddy Sattula, Sriya Annapureddy, Sasivardhan Reddy Arunkumar, M.S. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331527549

This research focuses on addressing the challenges associated with training object detection and segmentation models for autonomous vehicles using real-world data, which is often difficult to collect, limited in diversity, and expensive to annotate. To overcome these limitations, we propose a novel framework for generating synthetic datasets using deep learning techniques and generative AI. Specifically, we utilize the Stable Diffusion models to generate synthetic images, and annotate them using a combination of the Segment Anything Model (SAM) and the CVAT tool. The annotations are further refined to produce label files, and the dataset is split into training and validation sets. For evaluation, the YOLOv8 is applied for object detection and segmentation tasks using the synthetic dataset. Additionally, the Salesforce/Blip image-captioning model is integrated to provide descriptive captions for the detected objects. Experimental results demonstrate that synthetic datasets generated by this approach not only provide coverage of complex and rare scenarios but also achieve comparable or superior performance compared to real-world datasets in object detection and segmentation tasks. These findings underscore the potential of synthetic data to serve as a cost-effective and scalable alternative to real-world data for autonomous vehicle training. © 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

Improve Accuracy in Healthcare Data Analysis using Competitive Ensemble Deep Learning Model 18

Improve Accuracy in Healthcare Data Analysis using Competiti...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Sravanthi, Jakkula Reddy, Chada Sampath Mahendar, A. Kumar, V. Ravi Buragadda, Swathi Ghantasala, G. S. Pradeep Gupta, Gaurav Vnr Vignana Jyoti Institute of Engineering and Technology Department of Information Technology Telangana India Sree Chaitanya Institute of Technological Sciences Department of Computer Science Engineering Telangana Karimnagar India Telangana Hyderabad India Ace Engineering College Department of Computer Science Engineering Ghatkesar India Lakireddy Balireddy College of Engineering Department of Computer Science Engineering Kakinada India Alliance University Department of Computer Science and Engineering Bengaluru India Shoolini University Yogananda School of Artificial Intelligence Computers and Data Sciences Solan India

ISBN: (纸本)9789380544519

This paper discusses the significance of Machine Learning (ML) and Deep Learning (DL) techniques for structured and unstructured healthcare data. As healthcare data is increasing tremendously, it is difficult to identify hidden patterns in huge amounts of data. DL handles a massive amount of clinical data and provides better outcomes. A novel competitive ensemble deep learning model has been proposed to improve the classification performance of structured data. However, dealing with unstructured data, the proposed work highlights a competitive DL model for Twitter sentiment analysis. In addition, this paper discusses the proposed Competitive Ensemble Deep Learning (CEPL) algorithm for text data. The proposed model is compared with a traditional model to evaluate the model's performance in the range of 0.2%-0.5%. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Accuracy CEPL Deep Learning Healthcare data Machine learning Methods

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning approach for automated grading of knee osteoarthritis severity

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Kaur, PrabSimran Kohli, Guneet Singh Bedi, Jatin Wasly, Saud Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Electrical and Computer Engineering Department King Abdulaziz University Jeddah22254 Saudi Arabia Center of Excellence in Intelligent Engineering Systems King Abdulaziz University Jeddah22254 Saudi Arabia

Knee Osteoarthritis (OA) is a prevalent musculoskeletal disorder that affects the knee joint that causes pain, stiffness, and reduced mobility. It is also known as "Degenerative Joint Disease" and is caused by the degeneration of cartilage in the knee joint, leading to bone-on-bone contact and further damage. Knee OA is prevalent in the population, affecting around 22% to 39% of people in India, and there is currently no treatment available that can halt the progression of the disease. Therefore, early diagnosis and management of symptoms are essential to reduce its impact on an individual’s quality of life. To address this issue, have introduced a framework that leverages ConvNeXt architecture, a modernization of ResNets (ResNet-50) architecture towards Hierarchical Transformers (Swin Transformers), to provide accurate identification and classification of knee osteoarthritis. The classification of knee osteoarthritis was done using the Kellgren and Lawrence (KL) graded X-ray images. These images of the damaged knees are preprocessed and augmented, creating a scaled, enhanced, and varied version of the features, thus making the data fitter and more significant for classification. The performance estimation of the proposed strategy is conducted on the Osteoarthritis Initiative (OAI), a research project focused on knee osteoarthritis that works in partnership with NIH and other private industries to develop a public domain dataset that can facilitate research and evaluation. It involves training the prepared data using various hyper-tuned versions of ConvNeXt. The different fine-tuned results of the ConvNeXt models on each KL Grade are evaluated against the other state-of-the-art models and vision transformers. The comparative assessment of widely used performance measures shows that the proposed approach outperforms the conventional models by generating the highest score for all the KL grades. Lastly, an approach is employed to statistically confirm the validity of t

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

CHART:Intelligent Crime Hotspot Detection and Real-Time Tracking Using Machine Learning

引用

computers, Materials & Continua 2024年第12期81卷 4171-4194页

作者： Rashid Ahmad Asif Nawaz Ghulam Mustafa Tariq Ali Mehdi Tlija Mohammed AEl-Meligy Zohair Ahmed University Institute of Information Technology PMAS Arid Agriculture UniversityRawalpindi46000Pakistan Industrial Engineering Department College of EngineeringKing Saud UniversityRiyadh11421Saudi Arabia Jadara University Research Center Jadara UniversityIrbid21110Jordan Applied Science Research Center Applied Science Private UniversityAmman11931Jordan School of Computer Science and Engineering Central South UniversityChangsha410083China

Crime hotspot detection is essential for law enforcement agencies to allocate resources effectively,predict potential criminal activities,and ensure public *** methods of crime analysis often rely on manual,time-consuming processes that may overlook intricate patterns and correlations within the *** some existing machine learning models have improved the efficiency and accuracy of crime prediction,they often face limitations such as overfitting,imbalanced datasets,and inadequate handling of spatiotemporal *** research proposes an advanced machine learning framework,CHART(Crime Hotspot Analysis and Real-time Tracking),designed to overcome these *** proposed methodology begins with comprehensive data collection from the police *** dataset includes detailed attributes such as crime type,location,time and demographic *** key steps in the proposed framework include:Data Preprocessing,Feature engineering that leveraging domain-specific knowledge to extract and transform relevant *** Map Generation that employs Kernel Density Estimation(KDE)to create visual representations of crime density,highlighting hotspots through smooth data point distributions and Hotspot Detection based on Random Forest-based to predict crime likelihood in various *** Experimental evaluation demonstrated that CHART shows superior performance over benchmark methods,significantly improving crime detection accuracy by getting 95.24%for crime detection-I(CD-I),96.12%for crime detection-II(CD-II)and 94.68%for crime detection-III(CD-III),*** designing the application with integrating sophisticated preprocessing techniques,balanced data representation,and advanced feature engineering,the proposed model provides a reliable and practical tool for real-world crime *** of crime hotspots enables law enforcement agencies to strategize effectively,focusing resources on high-risk areas and thereby enhanc

关键词： Crime hotspot heat map kernel density estimation(KDE) support vector machine(SVM)

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning in the Development of a Drug Discovery System 15th

Application of Deep Learning in the Development of a Drug Di...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Praveen Kumar, B.V. Nageswara Rao, A. Tummala, Navya Deepthi Bikku, Thulasi Reddy Madhavi, K. Computer Science and Engineering Usha Rama College of Engineering and Technology Andhra Pradesh Telaprolu India Computer Science and Engineering CMR Institute of Technology Telangana Hyderabad India Computer Science and Engineering Vignan’s Nirula Institute of Technology and Science for Women Andhra Pradesh Guntur India Computer Science and Engineering Amrita School of Computing Amaravati Amrita Vishwa Vidyapeetham Andhra Pradesh Amaravati522503 India School of Computing Mohan Babu University Tirupati India

ISBN: (纸本)9783031810824

Efficient drug discovery hinges on the accurate prediction of interactions between potential drugs and target proteins. Deep learning models have shown promise in this domain;however, their adoption can be challenging for individuals not well-versed in both computer science and cheminformatics. In response to this challenge, we present DeepPurpose, an extensive and user-friendly deep learning library tailored for drug-target interaction (DTI) prediction. DeepPurpose offers a range of features, including the ability to customize interaction types through chemical and protein encoders, as well as access to over 50 neural architectures. As the effectiveness of existing aseptic medications diminishes, the identification of viable DTIs becomes pivotal in the drug development process. DeepPurpose employs an encoder-decoder structure to model interactions, taking compound SMILES strings and pairs of protein amino acid sequences as inputs. The system generates a binding affinity score for the given compound-protein pair. To achieve this, DeepPurpose encodes input proteins and compounds using multiple deep learning encoders, combining their deep embeddings and passing them through a deep neural network decoder to determine binding propensity. DeepPurpose represents a valuable tool in the field of drug discovery, providing researchers with accessible and effective means to predict and explore potential drug-target interactions. Its user-friendly design and comprehensive functionality aim to bridge the gap between deep learning and DTI prediction for a wider audience of researchers and practitioners. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

WLARS: Workload-Aware Recharge Scheduling Mechanism for Improving Surveillance Quality in Wireless Rechargeable Sensor Networks

引用

IEEE Sensors Journal 2023年第11期23卷 12237-12250页

作者： Dande, Bhargavi Chang, Chih-Yung Wu, Shih-Jung Roy, Diptendu Sinha National Taiwan University Department of Electrical Engineering Taipei10617 Taiwan Tamkang University Department of Computer Science and Information Engineering New Taipei25137 Taiwan National Institute of Technology Meghalaya Department of Computer Science and Engineering Shillong793003 India

With radio frequency (RF), the mobile charger (MC) can wirelessly transmit energy to the sensor nodes in the network. The wireless energy transfer enhances the lifetime of sensor nodes in wireless rechargeable sensor networks (WRSNs). Most of the studies improved the efficiency of MC or perpetuated the lifetime of WRSNs. At the same time, none of the studies focused on considering the spatial and temporal surveillance qualities (STSQs) of each sensor recharged. Therefore, this article proposed an efficient energy recharge scheduling for MC, aiming to maximize the STSQ of the given network. Initially, sensor routing load (RL) is considered to partition the network to distribute the charging load of the MCs evenly. Second, the busy level of the MC is considered to send the recharging requests to the MC. Based on the busy level of MC, the sensors adjust the sensing rate frequency to manage their energy. Finally, cooperation between the neighboring MCs is proposed to reduce the waiting time for recharging requested sensors. The simulation results present that the proposed work yields the literature in terms of STSQ, traveling distance, average waiting time (AWT), and energy usage efficiency. © 2001-2012 IEEE.

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

LSTDA: Link Stability and Transmission Delay Aware Routing Mechanism for Flying Ad-Hoc Network (FANET)

引用

computers, Materials & Continua 2023年第10期77卷 963-981页

作者： Farman Ali Khalid Zaman Babar Shah Tariq Hussain Habib Ullah Altaf Hussain Daehan Kwak Department of Computer Science and Engineering Sungkyunkwan UniversitySeoul03063South Korea Information Engineering School Chang’an UniversityXi’an710061China College of Technological Innovation Zayed UniversityDubai19282United Arab Emirates School of Computer Science and Technology Zhejiang Gongshang UniversityHangzhou310018China Institute of Computer Science and IT The University of Agriculture PeshawarPeshawer25120Pakistan Department of Computer Science and Technology Kean UniversityUnionNew Jersey07083USA

The paper presents a new protocol called Link Stability and Transmission Delay Aware(LSTDA)for Flying Adhoc Network(FANET)with a focus on network corridors(NC).FANET consists of Unmanned Aerial Vehicles(UAVs)that face challenges in avoiding transmission loss and delay while ensuring stable *** proposed protocol introduces a novel link stability with network corridors priority node selection to check and ensure fair communication in the entire *** protocol uses a Red-Black(R-B)tree to achieve maximum channel utilization and an advanced relay *** paper evaluates LSTDA in terms of End-to-End Delay(E2ED),Packet Delivery Ratio(PDR),Network Lifetime(NLT),and Transmission Loss(TL),and compares it with existing methods such as Link Stability Estimation-based Routing(LEPR),Distributed Priority Tree-based Routing(DPTR),and Delay and Link Stability Aware(DLSA)using MATLAB *** results show that LSTDA outperforms the other protocols,with lower average delay,higher average PDR,longer average NLT,and comparable average TL.

关键词： LSTDA routing protocol Flying Ad-hoc Network link stability unmanned aerial vehicles maxim priority channel

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：