检索结果-内蒙古大学图书馆

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Shamim Ahmad Khan Rahama Salman Al-Hussein Maysir Majid M. Mythili Malik Bader Alazzam Ponni Valavan M Department of ECE Glocal School of Science & Technology Glocal University U.P India Department of Computer Science College of Engineering and Computer Science Jazan University Jazan KSA Department of Biomedical Engineering Al-Farahidi University Baghdad Iraq Department of English Nandha Engineering College(Autonomous) Erode India Faculty of Information Technology Jadara University Irbid Jordan Department of AI & DS K. Ramakrishnan College of Engineering Trichy Tamil Nadu India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

Human-in-the-Loop (HITL) Machine Learning with Ensemble Learning uses the best of both automated algorithms and human input in making predictions and decision making when it comes to Machine Learning (ML). In HITL frameworks they include human inputs in model training and validation, allowing the resultant models to be built based on actual needs rather than white algorithms, which may be insensitive to some details otherwise. It is more relevant in such areas or applications that involve higher risk such as credit risk applications in today's financial world where predictions form the basis for major loans' approval. Although previous studies that employed fully automated ML models have some shortcomings that include being prone to giving biased predictions, being less interpretable and scalability issues and failure to handle edge cases hence reducing reliability and trustworthiness. To overcome these problems, this study introduces a new approach of combining the HITL with the XGBoost, which is one of the most potent ensemble learning algorithms to develop a balanced model of loan default prediction. Through the analysis of loan data from Lending Club, this method has attained an accuracy of 99.4% along with a high precision and a high recall, thus pointing to well-rounded performance of the model. Expert knowledge in the form of the HITL loop improves the regularization and optimization of the XGBoost model leading to a better, efficient, reliable, and more interpretable model for credit scoring. It was in python the model was developed taking advantage of the powerful ml and data analysis libraries which make it easy to develop, scalable and reusable for real life organizations especially in the financial arena where precision and accuracy are paramount. This approach lays some basis for subsequent innovations in the ICT applications in HITL ML systems in different fields.

关键词： Training Analytical models Machine learning algorithms Accuracy Predictive models Prediction algorithms Human in the loop Data models Ensemble learning Reliability

来源：评论

学校读者我要写书评

暂无评论

SpikingSoft: A Spiking Neuron Controller for Bio-inspired Locomotion with Soft Snake Robots

arXiv

引用

arXiv 2025年

作者： Zhang, Chuhan Wang, Cong Pan, Wei Della Santina, Cosimo The Department of Cognitive Robotics Faculty of Mechanical Engineering Delft University of Technology Delft Netherlands The Department of Computer Science The University of Manchester Manchester United Kingdom

Inspired by the dynamic coupling of moto-neurons and physical elasticity in animals, this work explores the possibility of generating locomotion gaits by utilizing physical oscillations in a soft snake by means of a low-level spiking neural mechanism. To achieve this goal, we introduce the Double Threshold Spiking neuron model with adjustable thresholds to generate varied output patterns. This neuron model can excite the natural dynamics of soft robotic snakes, and it enables distinct movements, such as turning or moving forward, by simply altering the neural thresholds. Finally, we demonstrate that our approach, termed SpikingSoft, naturally pairs and integrates with reinforcement learning. The high-level agent only needs to adjust the two thresholds to generate complex movement patterns, thus strongly simplifying the learning of reactive locomotion. Simulation results demonstrate that the proposed architecture significantly enhances the performance of the soft snake robot, enabling it to achieve target objectives with a 21.6% increase in success rate, a 29% reduction in time to reach the target, and smoother movements compared to the vanilla reinforcement learning controllers or Central Pattern Generator controller acting in torque space. Copyright © 2025, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Eyeballing Combinatorial Problems: A Case Study of Using Multimodal Large Language Models to Solve Traveling Salesman Problems 1st

Eyeballing Combinatorial Problems: A Case Study of Using Mul...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Elhenawy, Mohammed Abdelhay, Ahmed Alhadidi, Taqwa I. Ashqar, Huthaifa I. Jaradat, Shadi Jaber, Ahmed Glaser, Sebastien Rakotonirainy, Andry Accident Research and Road Safety Queensland Queensland University of Technology 130 Victoria Park Rd Kelvin Grove BrisbaneQLD4059 Australia Centre for Data Science Queensland University of Technology 130 Victoria Park Rd Kelvin Grove BrisbaneQLD4059 Australia Computer and Systems Engineering Department Faculty of Engineering Minia University Minia Egypt Civil Engineering Department Al-Ahliyya Amman University Al-Saro Al-Salt Amman Jordan Arab American University Palestine and Columbia University JeninNY United States Department of Transport Technology and Economics Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Műegyetem Rkp. 3. Budapest1111 Hungary

ISBN: (纸本)9783031823763

Multimodal Large Language Models (MLLMs) have demonstrated proficiency in processing diverse modalities, including text, images, and audio. These models leverage extensive pre-existing knowledge, enabling them to address complex problems with minimal to no specific training examples, as evidenced in few-shot and zero-shot in-context learning scenarios. This paper investigates the use of MLLMs’ visual capabilities to ‘eyeball’ solutions for the Traveling Salesman Problem (TSP) by analyzing images of point distributions on a two-dimensional plane. Our experiments aimed to validate the hypothesis that MLLMs can effectively ‘eyeball’ viable TSP routes. The results from zero-shot, few-shot, self-ensemble, and self-refine zero-shot evaluations show promising outcomes. We anticipate that these findings will inspire further exploration into MLLMs’ visual reasoning abilities to tackle other combinatorial problems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

EmoSyn: Adaptive Emotion Framework for Sentiment Analysis and Internet of Medical Things

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Awan, Kamran Ahmad Alqahtani, Abdullah M. Cengiz, Korhan Alshammari, Alya Alrashdi, Ibrahim The University of Haripur Faculty of Information Technology and Numerical Sciences Department of Information Technology Khyber Pakhtunkhwa Pakistan Jazan University Department of Electrical and Electronic Engineering Collage of Engineering and Computer Science Saudi Arabia Prince Mohammad Bin Fahd University Department of Electrical Engineering Al Khobar31952 Saudi Arabia Princess Nourah bint Abdulrahman University Department of Applied Linguistics College of Languages Riyadh11671 Saudi Arabia Jouf University Department of Computer Science College of Computer and Information Sciences Al-Jouf Sakaka73211 Saudi Arabia

Sentiment analysis, or more specifically, the integration of IoMT into healthcare systems, requires frameworks that must adapt at runtime with high precision. Most existing methods have several limitations of either latency or accuracy issues, and therefore perform less effectively in dynamic scenarios. This study aims to address these challenges by proposing EmoSyn, a novel framework that incorporates Emotion Wave Modulation (EWM), Neuro-Cognitive Language Dynamics (NCLD), and the Sentient IoMT Interaction Protocol (SIP). EWM generates dynamic emotional waveforms using high-dimensional feature vectors and kernelized mappings, while NCLD employs synthetic neural mappings and adaptive linguistic modeling to capture semantic transitions. SIP facilitates real-time IoMT recalibration through bidirectional sentiment-driven feedback. Implemented using mathematical frameworks and a custom Emotion-Aware Predictive Synthesis Algorithm (EAPSA), EmoSyn ensures precise sentiment interpretation and efficient IoMT interactions. The framework was evaluated using MOSEI and MIMIC-III datasets in a Python-based simulation environment. The results showed EmoSyn achieving 91% precision for MOSEI and 86% for MIMIC-III, with average latencies of 29 ms and 27 ms. © 2013 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Mapping the Landscape of Personalization: A Comprehensive Review of Prediction and Trends in Recommendation Systems

引用

Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 2025年第2期15卷

作者： Sachdeva, Tamanna Goyal, Lalit Mohan Mittal, Mamta Department of Computer Engineering J.C. Bose University of Science and Technology YMCA Faridabad India Department of Data Analytics Delhi Skill and Entrepreneurship University New Delhi India

Recommendation systems (RSs) have become indispensable features in nearly all web applications. Sifting through data and alleviating information overload, these systems offer more streamlined and personalized recommendations. E-commerce giants such as Amazon, Netflix, and YouTube are offering recommendations to users based on their interests, past experiences, demographic information, etc. hence, increasing the user's engagement on these applications. This study offers a comprehensive review of recommendation systems, covering their types, fundamental techniques, and emerging trends, with a focus on the predictive models and algorithms that power personalization. This study shows how in comparison to traditional collaborative and content-based recommendation systems-building techniques, the novel approaches of deep learning, graph-based techniques, meta-learning, few-shot learning, exploration, and federated learning offer promising prospects to improve recommendation systems' scalability, privacy-preserving abilities, and accuracy. These advanced methods deliver more diverse, context-aware, and personalized recommendations by leveraging large-scale data and complex predictive algorithms. Furthermore, this paper depicts forthcoming trajectories in the field of recommendation systems, including the adoption of graph-based approaches, federated learning, and the exploration of ethical considerations. By mapping the current landscape of prediction-driven personalization and identifying emerging trends, this review serves as a valuable resource for scholars and practitioners seeking to deepen their understanding of the field and drive innovation in recommendation systems. Readers can expect to gain insights into both foundational and cutting-edge techniques and how these can shape the future of personalized recommendations. © 2025 Wiley Periodicals LLC.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

End-to-End triplet loss based fine-tuning for network embedding in effective PII detection

arXiv

引用

arXiv 2025年

作者： Kohli, Rishika Gupta, Shaifu Gaur, Manoj Singh Department of Computer Science and Engineering Indian Institute of Technology Jammu J&K India Indian Institute of Technology Jammu J&K India

There are many approaches in mobile data ecosystem that inspect network traffic generated by applications running on user’s device to detect personal data exfiltration from the user’s device. State-of-the-art methods rely on features extracted from HTTP requests and in this context, machine learning involves training classifiers on these features and making predictions using labelled packet traces. However, most of these methods include external feature selection before model training. Deep learning, on the other hand, typically does not require such techniques, as it can autonomously learn and identify patterns in the data without external feature extraction or selection algorithms. In this article, we propose a novel deep learning based end-to-end learning framework for prediction of exposure of personally identifiable information (PII) in mobile packets. The framework employs a pre-trained large language model (LLM) and an autoencoder to generate embedding of network packets and then uses a triplet-loss based fine-tuning method to train the model, increasing detection effectiveness using two real-world datasets. We compare our proposed detection framework with other state-of-the-art works in detecting PII leaks from user’s device. © 2025, CC BY.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Leveraging the Commerce Graph for Optimizing Digital Commerce

引用

Procedia computer science 2025年 259卷 1072-1081页

作者： Subrata Paul Amartya Chakraborty Stobak Dutta Keya Das Ghosh Anirban Mitra Department of CSE-AI Brainware University Ramkrishnapur Road Barasat 700125 West Bengal India Department of Computer Science and Engineering St Thomas’ College of Engineering and Technology Kolkata Amity College of Commerce & Finance Amity University Kolkata New Town Kolkata 700135 West Bengal India Department of Computer Science and Engineering Amity University Kolkata Kadampukur New Town 700135 West Bengal India

As a dynamic network that links important elements of the commerce ecosystem, including buyers, sellers, products, and transactions, the Commerce Graph is a ground-breaking development in digital commerce. By using advanced centrality metrics, such as degree, betweenness, and closeness, to identify key consumers and products, this study exemplifies its capacity for transformation. The findings show that the most important roles in the network are played by customers with higher centrality ratings (such as IDs 66, 91, and 47) and well-known products (such as IDs 102, 104, and 100). With the top buyers in 2018 displaying noteworthy engagement tendencies, temporal research reveals changing customer behaviours. Additionally, buyer and product clusters are found using community detection employing the Louvain algorithm, allowing segmentation tactics to maximise marketing and consumer engagement. The study offers practical insights that may be used to improve corporate operations and identify targets for customized promotions. This study makes the Commerce Graph an essential tool for tackling issues like scalability and incorporating sophisticated algorithms.

关键词： Commerce Graph digital commerce interconnected data customer experiences conversion rates business models eCommerce

来源：评论

学校读者我要写书评

暂无评论

Dreamer: Dual-RIS-aided Imager in Complementary Modes

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Wang, Fuhai Huang, Yunlong Feng, Zhanbo Xiong, Rujing Li, Zhe Wang, Chun Mi, Tiebin Qiu, Robert Caiming Ling, Zenan Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan430074 China Huazhong University of Science and Technology Institute of Artificial Intelligence Wuhan430074 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200030 China

Reconfigurable intelligent surfaces (RISs) have emerged as a promising auxiliary technology for radio frequency imaging. However, existing works face challenges of faint and intricate back-scattered waves and the restricted field-of-view (FoV), both resulting from complex target structures and a limited number of antennas. The synergistic benefits of multi-RIS-aided imaging hold promise for addressing these challenges. Here, we propose a dual-RIS-aided imaging system, Dreamer, which operates collaboratively in complementary modes (reflection-mode and transmission-mode). Dreamer significantly expands the FoV and enhances perception by deploying dual-RIS across various spatial and measurement patterns. Specifically, we perform a fine-grained analysis of how radio-frequency (RF) signals encode scene information in the scattered object modeling. Based on this modeling, we design illumination strategies to balance spatial resolution and observation scale, and implement a prototype system in a typical indoor environment. Moreover, we design a novel artificial neural network with a CNN-external-attention mechanism to translate RF signals into high-resolution images of human silhouettes. Our approach achieves an impressive structural similarity index (SSIM) score 0.83 surpassing state-of-the-art solutions, validating its effectiveness in broadening perception modes and enhancing imaging capabilities. The code to reproduce our results is available at https://***/fuhaiwang/Dreamer. © 2025 IEEE.

关键词： Radio waves

来源：评论

学校读者我要写书评

暂无评论

Constructions of Covering Sequences and Arrays

arXiv

引用

arXiv 2025年

作者： Chee, Yeow Meng Etzion, Tuvi Ta, Hoang Vu, Van Khu Department of Industrial Systems Engineering and Management National University of Singapore Singapore Department of Computer Science Technion — Israel Institute of Technology Haifa3200003 Israel

An (n, R)-covering sequence is a cyclic sequence whose consecutive n-tuples form a code of length n and covering radius R. Using several construction methods improvements of the upper bounds on the length of such sequences for n ≤ 20 and 1 ≤ R ≤ 3, are obtained. The definition is generalized in two directions. An (n, m, R)covering sequence code is a set of cyclic sequences of length m whose consecutive n-tuples form a code of length n and covering radius R. The definition is also generalized to arrays in which the m × n sub-matrices form a covering code with covering radius R. We prove that asymptotically there are covering sequences that attain the sphere-covering bound up to a constant factor. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User Intent Detection in Persian Text-Based Chatbots: A Comprehensive Review of Methods and Challenges

User Intent Detection in Persian Text-Based Chatbots: A Comp...

引用

International Conference on Web Research (ICWR)

作者： Elham Amiri Abyaneh Rahmat Zolfaghari Alireza Amiri Abyaneh Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran Iran Department of Computer Engineering Hashtgerd Branch Islamic Azad University Alborz Iran Amirkabir University of Technology (Tehran Polytechnic) Tehran Iran

ISBN: (数字)9798331508913

ISBN: (纸本)9798331508920

User Intent Detection is one of the primary tasks in dialogue systems and chatbots, playing a key role in improving human-machine interaction. With the increasing use of chatbots in the Persian language, there is a growing need to develop efficient methods for detecting user intent in this language. This review article provides a comprehensive overview of the methods, challenges, and recent advancements in the field of user intent detection in Persian text-based chatbots. The review discusses deep learning-based methods, pre-trained language models, and language-specific challenges. Additionally, it analyzes existing datasets and data augmentation techniques to improve model performance. The findings of this review indicate that, despite recent advancements, challenges such as the scarcity of labeled data, structural differences between Persian and other languages, and the need for multilingual models persist. Finally, future research directions are proposed to enhance user intent detection in Persian chatbots.

关键词： Deep learning Training Reviews Computational modeling Text categorization Syntactics Chatbots Data models Tokenization Multilingual

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：