检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Agheli, Pouya Pappas, Nikolaos Kountouris, Marios Communication Systems Dept. EURECOM France Dept. of Computer Science and Artificial Intelligence University of Granada Spain Dept. of Computer and Information Science Linköping University Sweden

This paper addresses query scheduling for goal-oriented semantic communication in pull-based status update systems. We consider a system where multiple sensing agents (SAs) observe a source characterized by various attributes and provide updates to multiple actuation agents (AAs), which act upon the received information to fulfill their heterogeneous goals at the endpoint. A hub serves as an intermediary, querying the SAs for updates on observed attributes and maintaining a knowledge base, which is then broadcast to the AAs. The AAs leverage the knowledge to perform their actions effectively. To quantify the semantic value of updates, we introduce a grade of effectiveness (GoE) metric. Furthermore, we integrate cumulative perspective theory (CPT) into the long-term effectiveness analysis to account for risk awareness and loss aversion in the system. Leveraging this framework, we compute effect-aware scheduling policies aimed at maximizing the expected discounted sum of CPT-based total GoE provided by the transmitted updates while complying with a given query cost constraint. To achieve this, we propose a model-based solution based on dynamic programming and model-free solutions employing state-of-the-art deep reinforcement learning (DRL) algorithms. Our findings demonstrate that effect-aware scheduling significantly enhances the effectiveness of communicated updates compared to benchmark scheduling methods, particularly in settings with stringent cost constraints where optimal query scheduling is vital for system performance and overall effectiveness. Copyright © 2025, The Authors. All rights reserved.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

An Ising Machine-Based Hybrid Optimization Method Using Constraint Conversion and Correction

An Ising Machine-Based Hybrid Optimization Method Using Cons...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Kinya Iwata Masashi Tawada Nozomu Togawa Dept. of Computer Science and Communications Engineering Waseda University Green Computing Systems Research Organization Waseda University

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

This paper proposes an Ising machine-based hy-brid optimization method to solve combinatorial optimization problems, which consists of an approximate formulation process, an annealing process with an Ising machine, and a correction process. The approximate formulation and correction aim to improve the performance of the Ising machine. Computational experiments were conducted on the multi-dimensional knapsack problem (MKP) using an Ising machine. We compare the results with those of the proposed method and the conventional method and demonstrate the effectiveness of the proposed approach.

关键词： Annealing Optimization methods Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Quantum Network Routing with Heterogeneous Nodes

Quantum Network Routing with Heterogeneous Nodes

引用

International Communication systems and Networks and Workshops, COMSNETS

作者： Anoop Kumar Pandey Bheemarjuna Reddy Tamma M V Panduranga Rao Dept. of Computer Science and Engineering IIT Hyderabad India

ISBN: (数字)9798331531195

ISBN: (纸本)9798331531201

Deciding a route for the transfer of quantum information (namely, qubits) on a quantum network is a significant problem that is being studied extensively. In this work, we investigate the problem of routing on a quantum network of heterogeneous nodes both with and without fidelity and timing *** propose a Path Request Packet (PRP) based routing scheme for dynamically selecting a path that maximizes the overall probability of transmission success while maintaining fidelity above a threshold and adhering to time constraints. While the proposed scheme can perform suboptimally under fidelity and timing constraints, we discuss a straightforward proof of optimality in the absence of these constraints. Simulations on random graphs demonstrate that the PRP-based scheme performs better, both in terms of reliability and fidelity, than a non-trivial baseline routing algorithm.

关键词： Qubit Routing Timing Error correction Quantum networks Time factors Reliability

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Driven - Pest Classification and Sustainable Agriculture 3

Deep Learning Driven - Pest Classification and Sustainable A...

引用

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

作者： Kumar, M. Sirish Usha, R. Reddy, B. Rama Kantha Ramachandra, S. Prakash, P. Jaya Swetha, B. Mohan Babu University School of Computing Dept. of Data Science India Madanapalle Institute of Technology and Science Madanapalle India Sri Venkateswara College of Engineering Tirupati India Mother Theresa Institute of Engineering and Technology Palamaner India Sri Venkateswara College of Engineering Department of It Tirupati India Mohan Babu University Dept. of Master of Computer Applications India

ISBN: (纸本)9798331509675

This study introduces a system designed to identify pests in crops and classify them as either beneficial or harmful. The project begins by providing a comprehensive overview of various pest identification methods, analyzing their strengths and limitations. To address the problem, a categorization approach is proposed that incorporates convolutional neural networks (CNN) to build the pest identification and classification model. The model was trained using a dataset containing images of different pest species. Extensive testing was conducted on a large dataset, and the system's performance was validated against multiple traditional classification models. The proposed framework achieved a classification accuracy of 90%, outperforming conventional methods. This research highlights agriculture's vital role in the economy and underscores the potential of advanced technologies in supporting sustainable farming practices. © 2025 IEEE.

关键词： Agriculture Sustainability Classification Accuracy Classification Model Convolutional Neural Network (CNN) Pest Classification

来源：评论

学校读者我要写书评

暂无评论

Credit Card Fraud Detection: Data Balancing Techniques and Model Interpretability

Credit Card Fraud Detection: Data Balancing Techniques and M...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Tanveer Kaiser Avishek Chowdhury Umme Humyra Nabila Pantha Singha Mohammad Hasan M. A. Rasel Dept. of Computer Science & Engineering Premier University Chattogram Bangladesh Dept. of Computer Science & Engineering Chittagong University of Engineering and Technology Chattogram Bangladesh Dept. of Artificial Intelligence Universiti Malaya Malaysia

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Credit card fraud detection is a crucial task in fi-nancial institutions to safeguard against fraudulent transactions. This study investigates the performance of Random Forest and Gradient Boosting models on a Nigerian credit card fraud detection dataset. Key features were selected using Chi-Square and Analysis of Variance (ANOVA) tests, and the models were evaluated across four data balancing techniques: no balancing (imbalanced), under-sampling, over-sampling, and hybrid sampling. The primary focus was on recall, as misclassifying fraudulent transactions can have significant financial implications. Gradient Boosting consistently outperformed Random Forest, achieving higher Recall, F1-Score, and AUC-ROC values across all experiments, particularly with over and hybrid sampling. To enhance interpretability, SHapley Additive exPlanations (SHAP) were applied to the Gradient Boosting model. SHAP analysis revealed that the amount of the transaction and average income expenditure were the most influential features in predicting fraud. Local and global explanations highlighted how specific feature values impacted the model’s decisions, while dependency plots uncovered interaction effects between key features. These findings contribute to the advancement of fraud detection methodologies, offering insights into effective strategies for mitigating financial risks associated with fraudulent transactions.

关键词： Analytical models Focusing Credit cards Boosting Prediction algorithms Data models Fraud Security Random forests Analysis of variance

来源：评论

学校读者我要写书评

暂无评论

Classification of Sarcoma Based on Genomic Data Using Machine Learning Models

引用

Procedia computer science 2025年 252卷 317-330页

作者： Pratham Gala Yash Pandloskar Shubham Godbole Fayed Hakim Pratik Kanani Lakshmi Kurup Dept. of Computer Science and Engineering (Data Science) Dwarkadas J. Sanghvi College of Engineering Mumbai India Dept. of Artificial Intelligence and Data Science Dwarkadas J. Sanghvi College of Engineering Mumbai India

The proposed work provides a new machine-learnt classification approach for the various types of soft tissue sarcoma based on genomics data which addresses a considerable gap in sarcoma diagnostics. The previous studies have investigated various aspects of sarcoma but this study is unique in that it targets the predicting sarcoma variant types using genetic information, which has not been done before. Random Forest was used as the meta-estimator and a stacking ensemble model comprising of Random Forest, Extreme Gradient Boosting and LightGBM were used for this study. The model which was trained and validated on a complete dataset of 206 adult soft tissue sarcoma samples containing genomic alterations, transcriptomic, epigenomic and proteomic data achieved an accuracy of 89.44% at a precision level as high as 91%. Stratified k-fold cross validation is employed to ensure that class imbalance is not a hindrance to performance. This innovative approach outmatches single classifiers and traditional single model methods at great length hence making it possible and effective to use machine learning on genomic data for predicting sarcoma variants. Thus, the findings from this research could change cancer diagnosis forever; they promise more accurate classification as well as personalized treatment modalities while also providing a framework for analogous applications in other rare complex cancers.

关键词： Sarcoma Classification Stacking Ensemble Model Genomic Data

来源：评论

学校读者我要写书评

暂无评论

Quantitative Analysis of Error Propagation in Hindi-English Cascaded Speech-to-Speech Translation Models

Quantitative Analysis of Error Propagation in Hindi-English ...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Mahendra Gupta Maitreyee Dutta Chandresh Kumar Maurya Dept. of Computer Science and Engineering NITTTR Chandigarh Chandigarh India Dept. of IMEE NITTTR Chandigarh Chandigarh India Dept. of Computer Science and Engineering IIT Indore Indore India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Speech-to-Speech Translation (S2ST) plays a crucial role in reducing language barriers and enabling seamless communication between people from different linguistic backgrounds. Traditional S2ST systems typically rely on a cascaded design, where components like Automatic Speech Recognition (ASR), Machine Translation (MT), and Text-to-Speech (TTS) work together in sequence to complete the translation process. Cascaded models are widely used S2ST models and are prone to error propagation (EP) across the pipeline, significantly impacting translation quality. EP is discussed in various literature. However, a comprehensive quantitative analysis is not available, particularly for low-resource languages like Hindi and English. This work presents a detailed quantitative study of EP in Hindi-English cascaded S2ST models, bridging this critical research gap. This study utilizes both text-based and textless evaluation metrics such as BLEU, Translation Edit Rate (TER), and BLASER score for translation accuracy to quantify the impact of EP at various stages of the pipeline on the FLEURES dataset. The result analysis shows that due to EP, the translation quality of the S2ST model decreases in BLEU score of 11.55 for English→Hindi and BLEU score of 12.16 for Hindi→English. Similarly, reference-based BLASER decreases by 0.61 and 0.45 for English→Hindi and Hindi→English, respectively.

关键词： Measurement Analytical models Translation Accuracy Statistical analysis Computational modeling Pipelines Linguistics Text to speech Machine translation

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Solutions with CNN and IoT for Enhancing Visual Impairments

AI-Driven Solutions with CNN and IoT for Enhancing Visual Im...

引用

Emerging systems and Intelligent Computing (ESIC), International Conference on

作者： M. Lakshmi Prasad Veeramalli Varshitha A. Praneeth Goud R. Bindu Ch. Srinivasulu S. Janardhana Rao Dept. of Computer Science and Engineering Institute of Aeronautical Engineering Hyderabad India

ISBN: (数字)9798331522100

ISBN: (纸本)9798331522117

Visual impairment is a problem that affects millions of people worldwide, preventing them from walking independently and performing daily tasks. Some of the challenges that blind people face include crossing the street, reading, driving, and socializing. Despite the scientific community’s continuous efforts to treat the eye, these solutions have not yet been found. Traditional aids such as canes are useful but limited. Get in the groove. The main focus of the project is to integrate the YOLOv5 object detection model with a convolutional neural network (CNN). Known for its fast and accurate target detection, YOLOv5, together with CNN, improves the physical ability to detect and classify targets in difficult areas with high accuracy. The eye uses the camera module to continuously monitor the environment and identify various objects in real time; the detected data is converted into speech by text-to-speech (TTS) converters such as Google Text- to-Speech (gTTS) and pyttsx3 This description allows users to get an instant description of their surroundings, unlike helping the blind, it improves their ability to navigate independently rather than just providing references, but there are also good ways to work with better and more reliable assistive technologies.

关键词： YOLO Cloud computing Accuracy Navigation Face recognition Visual impairment Glass Assistive technologies Cameras Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

You Only Look Once Version 8 (YOLOv8)-Driven Emergency Vehicle Detection and Graph Neural Networks (GNNs) based Traffic Signal Prioritization

You Only Look Once Version 8 (YOLOv8)-Driven Emergency Vehic...

引用

Trends in Material science and Inventive Materials (ICTMIM), International Conference on

作者： B. Shyamala Gowri Harini Harisitha S Abishek Kanna M Amirthavarshini N S Dept. of Computer Science & Engineering Easwari Engineering College TN India

ISBN: (数字)9798331501488

ISBN: (纸本)9798331501495

The research develops a traffic management system that integrates You Only Look Once version 8 (YOLOv8) for emergency vehicle detection and Graph Neural Network (GRAPH NEURAL NETWORKS (GNNs))-based traffic signal prioritization to address the inefficiencies of traditional traffic management systems. These systems often fail to detect emergency vehicles accurately and adapt traffic signals in real-time, leading to delayed emergency responses and traffic congestion. The proposed system leverages You Only Look Once version 8 (YOLOv8)'s superior object detection capabilities and GRAPH NEURAL NETWORKS (GNNs)-based reinforcement learning to dynamically adjust traffic signals based on real-time road conditions. Experimental results demonstrate a 40% reduction in emergency vehicle response time and a 35% improvement in traffic flow, showcasing the system's ability to enhance urban traffic performance and emergency response efficiency.

关键词： YOLO Smart cities Vehicle detection Reinforcement learning Traffic control Emergency services Real-time systems Graph neural networks Time factors Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Speech-based Dementia Prediction using Artificial Intelligence

Speech-based Dementia Prediction using Artificial Intelligen...

引用

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

作者： Vivekanand, Chettiyar Vani Nayagam, Shamini Rajeev, Sreena Rajalakshmi Engineering College Dept. Computer Science Engineering Chennai India

ISBN: (纸本)9798331521394

The global healthcare, social, and economic impacts that affect the patient, family, and society as a whole are significantly affected by dementia. This study's objective is to look at how the analysis of speech patterns might support the early diagnosis of dementia. We will create and assess machine learning models to categorize people with and without dementia using acoustic characteristics taken from voice data. In order to determine the best practices for dementia detection, the study will mix a number of conventional machine learning techniques. The goal of using speech data is to help identify the condition early, which can save a lot of money and allow for prompt interventions to stop its progression. Early detection is vital because it makes room for therapeutic methods that work and protect. It looks at important elements such as methods for collecting data, pre-processing strategies, features classifiers, and extraction techniques. The extract of acoustic features in Python modules such as Librosa was utilized for the analysis of speech data. The Praat software's Python interface, Parselmouth, utilized for OpenSMILE, a toolkit for phonetic analysis, and obtaining a variety of acoustic characteristics that are utilized deep acoustic embedding to efficiently record and reflecting essential aspects of speech that are intimately associated with cognitive deficits. The findings of this investigation could help the creation of accessible and noninvasive dementia-related screening tools. © 2025 IEEE.

关键词： Deep learning

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：