检索结果-内蒙古大学图书馆

IEEE International Conference on Emerging & Sustainable Technologies for Power & ICT in a Developing Society (NIGERCON)

作者： Samuel-Soma M. Ajibade Muhammed Basheer Jasser Angela Lee Siew Hoong Rex V. Culpable Celestino A. Quirante Arvie L. Dacillo Adedotun O. Adetunla Kayode Akinlekan Akintoye Department of Data Science and Artificial Intelligence School of Engineering and Technology Sunway University No. 5 Jalan Universiti Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Sunway University Selangor Malaysia College of Technology Cebu Technological University Moalboal Cebu Philippines Dept. of Mechanical and Mechatronics Engineering Afe Babalola University Ado Ekiti Nigeria Dept. of Mechanical Engineering Science University of Johannesburg Johannesburg South Africa Department of Computer Science The Federal Polytechnic Ado Ekiti Ekiti State Nigeria

ISBN: (数字)9798331542559

ISBN: (纸本)9798331542566

The swift expansion of e-commerce has prompted the creation of advanced recommender systems to augment user experience and boost sales. Machine learning techniques have become fundamental for the development of these systems, allowing firms to provide tailored product recommendations based on customer preferences and habits. This research presents a thorough literature assessment of machine learning methodologies utilized in recommender systems, emphasizing their predictive efficacy in the e-commerce sector. We analyze essential methodologies, including collaborative filtering, content-based filtering, hybrid models, and sophisticated techniques such as deep learning. Through the examination of 38 research in the domain, we elucidate the limitations, advantages, and possibilities of machine learning algorithms in delivering precise and scalable suggestions. Our research indicates that hybrid models, which integrate many recommendation strategies, demonstrate significant potential in addressing challenges like the cold start problem and data sparsity. The report delineates prospective research avenues, underscoring the necessity for continued innovation in the integration of machine learning into recommender systems to improve accuracy and customer happiness in e-commerce settings.

关键词： Deep learning Machine learning algorithms Filtering Collaborative filtering Machine learning data models User experience Electronic commerce Recommender systems Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Context Transformer for Multi-level Semantic Scene Understanding

arXiv

引用

arXiv 2025年

作者： Hao, Luoying Hu, Yan Yue, Yang Wu, Li Fu, Huazhu Duan, Jinming Liu, Jiang Research Institute of Trustworthy Autonomous Systems Dept. of Computer Science and Engineering Southern University of Science and Technology China School of Computer Science University of Birmingham United Kingdom Division of Informatics Imaging and Data Sciences School of Health Sciences University of Manchester United Kingdom MGI Tech Co. Ltd. China Singapore

A comprehensive and explicit understanding of surgical scenes plays a vital role in developing context-aware computer-assisted systems in the operating theatre. However, few works provide systematical analysis to enable hierarchical surgical scene understanding. In this work, we propose to represent the tasks set [phase recognition → step recognition → action and instrument detection] as multi-level semantic scene understanding (MSSU). For this target, we propose a novel hierarchical context transformer (HCT) network and thoroughly explore the relations across the different level tasks. Specifically, a hierarchical relation aggregation module (HRAM) is designed to concurrently relate entries inside multi-level interaction information and then augment task-specific features. To further boost the representation learning of the different tasks, inter-task contrastive learning (ICL) is presented to guide the model to learn task-wise features via absorbing complementary information from other tasks. Furthermore, considering the computational costs of the transformer, we propose HCT+ to integrate the spatial and temporal adapter to access competitive performance on substantially fewer tunable parameters. Extensive experiments on our cataract dataset and a publicly available endoscopic PSI-AVA dataset demonstrate the outstanding performance of our method, consistently exceeding the state-of-the-art methods by a large margin. The code is available at https://***/Aurorahao/HCT. Copyright © 2025, The Authors. All rights reserved.

关键词： Transplantation (surgical)

来源：评论

学校读者我要写书评

暂无评论

Beam Switching with Low Control Overhead for Millimeter-wave Communication

Beam Switching with Low Control Overhead for Millimeter-wave...

引用

Asia-Pacific Conference on Microwave

作者： Ashim Kumar Arghyadip Roy Ratnajit Bhattacharjee Dept. of Electronics and Electrical Engineering IIT Guwahati India Mehta Family School of Data Science and Artificial Intelligence IIT Guwahati India

ISBN: (数字)9784902339567

ISBN: (纸本)9781665451086

Mm-wave communication using massive Multiple-Input Multiple Output (MIMO) is highly directional in nature, hence making beam scanning and alignment a crucial aspect. In high mobility scenarios, frequent beam scanning may incur a performance degradation due to high control overhead. In this paper, we have adopted a supervised learning approach to determine the precoders and combiners for a hybrid beamforming architecture. To avoid frequent beam scanning and switching, we propose an overhead-aware strategy that addresses a trade-off between the spectral efficiency (SE) and the overhead signalling. Simulations are performed using channel data generated using the open source channel simulator NYUSIM.

关键词： Degradation Spectral efficiency Array signal processing Supervised learning Switches Microwave communication Control systems

来源：评论

学校读者我要写书评

暂无评论

Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages 1

Vyākarana: A Colorless Green Benchmark for Syntactic Evalua...

引用

1st Workshop on Multilingual Representation Learning, MRL 2021

作者： Patil, Rajaswa Dhillon, Jasleen Mahurkar, Siddhant Kulkarni, Saumitra Malhotra, Manav Baths, Veeky Cognitive Neuroscience Lab. BITS Pilani Goa Campus India Dept. of CS & IS BITS Pilani Goa Campus India Data Science Institute Columbia University United States Dept. of Computer Engineering PICT Maharashtra India Dept. of Mathematics BITS Pilani Goa Campus India

ISBN: (纸本)9781954085961

While there has been significant progress towards developing NLU resources for Indic languages, syntactic evaluation has been relatively less explored. Unlike English, Indic languages have rich morphosyntax, grammatical genders, free linear word-order, and highly inflectional morphology. In this paper, we introduce Vyākarana: a benchmark of Colorless Green sentences in Indic languages for syntactic evaluation of multilingual language models. The benchmark comprises four syntax-related tasks: PoS Tagging, Syntax Tree-dept. Prediction, Grammatical Case Marking, and Subject-Verb Agreement. We use the datasets from the evaluation tasks to probe five multilingual language models of varying architectures for syntax in Indic languages. Due to its prevalence, we also include a code-switching setting in our experiments. Our results show that the token-level and sentence-level representations from the Indic language models (IndicBERT and MuRIL) do not capture the syntax in Indic languages as efficiently as the other highly multilingual language models. Further, our layer-wise probing experiments reveal that while mBERT, DistilmBERT, and XLM-R localize the syntax in middle layers, the Indic language models do not show such syntactic localization. © 2021 Association for Computational Linguistics.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

New Cloud Service Discovery Mechanisms for Improved Usability

New Cloud Service Discovery Mechanisms for Improved Usabilit...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Ramu K Kavitha Dasari Rakesh Chandrashekar Ginni Nijhawan Ravi Kalra Mohammed Kassim Al-Hussainawy Dept. of CSE Velammal Institute of Technology Chennai TN India Institute of Aeronautical Engineering Dundigal Hyderabad Department of Mechanical Engineering New Horizon College of Engineering Bangalore Lovely Professional University Phagwara Knowledge Park II Lloyd Institute of Engineering & Technology Greater Noida Uttar Pradesh Collage of Dentist National University of Science and Technology Dhi Qar Iraq

ISBN: (数字)9798350373783

ISBN: (纸本)9798350373790

The Adaptive Service Discovery Framework changes cloud service discovery. It uses machine learning and linguistic analysis. ASDF employs three primary algorithms: CSR, SST, and UBM. They collaborate to make service discovery fast, aware, and personalized. UBM tailors service concepts to each person, while SST employs semantics to match correctly. How well a service fits into its environment is considered by CSR. These strategies provide a trustworthy foundation that adapts to users’ changing demands and environments. This study reveals that ASDF is cheaper, more efficient, adaptable, and easier to use than conventional approaches. It performs better than DNS-Based Discovery, LDAP Service Discovery, SOAP-Based Service Discovery, UDDI Registry, and RESTful API Discovery, therefore it may improve cloud service discovery. This proves it can improve cloud service discovery.

关键词： Adaptation models Technological innovation Machine learning algorithms Semantics Restful API Machine learning Transforms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Encrypted Internet Traffic Classification Through Advanced data Augmentation Techniques

arXiv

引用

arXiv 2024年

作者： Zion, Yehonatan Aharon, Porat Dubin, Ran Dvir, Amit Hajaj, Chen Department of Computer Science Ariel Cyber Innovation Center Ariel University Israel Dept. of Computer and Software Eng. Ariel Cyber Innovation Center Ariel University Israel Department of Industrial Engineering and Management Data Science Artificial Intelligence Research Center Ariel University Israel

The increasing popularity of online services has made Internet Traffic Classification a critical field of study. However, the rapid development of internet protocols and encryption limits usable data availability. This paper addresses the challenges of classifying encrypted internet traffic, focusing on the scarcity of open-source datasets and limitations of existing ones. We propose two data Augmentation (DA) techniques to synthetically generate data based on real samples: Average augmentation and MTU augmentation. Both augmentations are aimed to improve the performance of the classifier, each from a different perspective: The Average augmentation aims to increase dataset size by generating new synthetic samples, while the MTU augmentation enhances classifier robustness to varying Maximum Transmission Units (MTUs). Our experiments, conducted on two well-known academic datasets and a commercial dataset, demonstrate the effectiveness of these approaches in improving model performance and mitigating constraints associated with limited and homogeneous datasets. Our findings underscore the potential of data augmentation in addressing the challenges of modern internet traffic classification. Specifically, we show that our augmentation techniques significantly enhance encrypted traffic classification models. This improvement can positively impact user Quality of Experience (QoE) by more accurately classifying traffic as video streaming (e.g., YouTube) or chat (e.g., Google Chat). Additionally, it can enhance Quality of Service (QoS) for file downloading activities (e.g., Google Docs). © 2024, CC BY-NC-ND.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

ECG-based Assessment and Therapeutic Implications of AV Nodal Conduction Dynamics During Atrial Fibrillation

ECG-based Assessment and Therapeutic Implications of AV Noda...

引用

Computers in Cardiology (CinC)

作者： Mattias Karlsson Mikael Wallman Pyotr G Platonov Sara R Ulimoen Frida Sandberg Dept. of Systems and Data Analysis Fraunhofer-Chalmers Centre Gothenburg Sweden Dept. of Biomedical Engineering Lund University Lund Sweden Chalmers Science Park Göteborg Sweden Dept. of Cardiology Clinical Sciences Lund University Lund Sweden Vestre Viken Hospital Trust Bæerum Hospital Rud Norway

The conduction properties of the atrioventricular (AV) node have a significant impact on heart rate during permanent atrial fibrillation (AF), and can be modulated through the use of β-blockers or calcium channel blockers. These drugs have different physiological effects and are often selected empirically. Hence, an improved understanding of how these drugs affect the AV node conduction properties may contribute to personalized treatment of AF. We propose a novel methodology for estimating the refractory period and conduction delay dynamics of the fast and slow pathways of the AV node from 24-hour ambulatory ECG recordings. Our approach comprises a network model of the AV node, a problem-specific genetic algorithm, and an approximate Bayesian computation algorithm for estimating the posterior distribution of the AV node properties. We analyzed 24-hour ambulatory ECG recordings at baseline from 51 patients with permanent AF. Interestingly, a moderate correlation between the short-term variability in the refractory period for the fast pathway and reduction in heart rate during treatment with metoprolol (ρ = 0.48, p < 0.005) was found. Thus, the proposed methodology enables individualized characterization of the AV node and can potentially assist in treatment selection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Activity Detection and Channel Estimation in Massive Machine-Type Communications with Low-Resolution ADC

Joint Activity Detection and Channel Estimation in Massive M...

引用

IEEE International Conference on Communications (ICC)

作者： Ye Xue An Liu Yang Li Qingjiang Shi Vincent Lau Shenzhen Research Institute of Big Data Shenzhen China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Tongji University Shanghai China Dept. of ECE The Hong Kong University of Science and Technology Hong Kong

In massive machine-type communications, data transmission is usually considered sporadic, and thus inherently has a sparse structure. This paper focuses on the joint activity detection (AD) and channel estimation (CE) problems in massive-connected communication systems with low-resolution analog-to-digital converters. To further exploit the sparse structure in transmission, we propose a maximum posterior probability (MAP) estimation problem based on both sporadic activity and sparse channels for joint AD and CE. Moreover, a majorization-minimization-based method is proposed for solving the MAP problem. Finally, various numerical experiments verify that the proposed scheme outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Causal Discovery for Rechargeable Battery Modeling Considering Group-Level DAG Constraints

Causal Discovery for Rechargeable Battery Modeling Consideri...

引用

Annual Conference of Industrial Electronics Society

作者： Yue Wang Sihui Chen Jiang Xu Jiayu Wan Yang Liu Xin Li Microelectronics Thrust The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China Dept. Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen China Global Institute of Future Technology Shanghai Jiao Tong University Shanghai China Data Science Research Center Duke Kunshan University Kunshan China

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

Rechargeable battery has attracted great research popularity in recent years, and numerous data-driven solutions have been proposed for its modeling. While most research works in this domain focus on the statistical correlations among extracted variables, understanding their causal relationships is equally important to provide useful insights, thereby improving the operation in real-world scenarios. In order to reach this goal, causal discovery has been utilized, which learns a directed acyclic graph (DAG) structure, referred to as causal graph, from observation data to represent the causal relationships among variables with specific physical interpretations. However, existing approaches only consider the DAG characteristics between individual variables. It may easily lead to group-level causal conflicts if multiple variables are created from the same source factor, which is a common practice for modeling the degradation of rechargeable batteries. In order to tackle this challenge, a novel group-level DAG constraint is proposed in this paper as a continuous regularization term that discourages cycles among blocks as well as individual elements in the weighted adjacent matrix corresponding to the causal graph. It is efficiently solved using an augmented Lagrangian-based method.

关键词： Lithium-ion batteries Industrial electronics Degradation Directed acyclic graph Correlation Accuracy

来源：评论

学校读者我要写书评

暂无评论

Enhanced Handover Management in 5G Networks using Machine Learning in Fading Scenarios

Enhanced Handover Management in 5G Networks using Machine Le...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Deepak Upadhyay Sreekanth Rallapalli Zakir Hussain Nookala Venu Rashmi Sharma Shipra Shukla Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Department of MCA Nitte Meenakshi Institute of Technology Bengaluru India Centre for Internet of Things Madhav Institute of Technology & Science Deemed University Gwalior India Department of CSE Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India Dept. of CSE (Data Science) G. L. Bajaj Institute of Technology and Management Greater Noida India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

This study explores the use of machine learning (ML) to improve initial handover performance for 5G networks by analysing fading-affected scenarios. In this study, we assess the ability of ML models to predict optimal handover decisions compared with conventional methods. In this study, simulation results show that our ML-based methods can reduce the handover inaccuracy by 50%, decrease latency up to 10 times and stabilize network performance. We accompany our assessment with a series of graphical analyses to show how ML algorithms change their behaviour dynamically in response to deteriorating link intensity due user mobility and increasing h/o frequency, thereby degrading the network performance. The results clearly illustrate that ML enabled handover optimization is significantly more effective than traditional methods in accommodating fading-channel dynamics, thereby improving both the network performance and user experience of future generation wireless networks.

关键词： Fading channels 5G mobile communication Wireless networks Simulation Wires Machine learning Handover User experience Stability analysis Reliability

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：