检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Gungor, Cagri Eppinger, Derek Kovashka, Adriana Intelligent Systems Program Department of Computer Science University of Pittsburgh United States

Tactile sensing, which relies on direct physical contact, is critical for human perception and underpins applications in computer vision, robotics, and multimodal learning. Because tactile data is often scarce and costly to acquire, generating synthetic tactile images provides a scalable solution to augment real-world measurements. However, ensuring robust generalization in synthesizing tactile images—capturing subtle, material-specific contact features—remains challenging. We demonstrate that overlapping training and test samples in commonly used datasets inflate performance metrics, obscuring the true generalizability of tactile models. To address this, we propose a leakage-free evaluation protocol coupled with novel, reference-free metrics—TMMD, I-TMMD, CI-TMMD, and D-TMMD—tailored for tactile generation. Moreover, we propose a vision-to-touch generation method that leverages text as an intermediate modality by incorporating concise, material-specific descriptions during training to better capture essential tactile features. Experiments on two popular visuo-tactile datasets, Touch and Go and HCT, show that our approach achieves superior performance and enhanced generalization in a leakage-free setting. © 2025, CC BY.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

RAFA-Net: Region Attention Network for Food Items and Agricultural Stress Recognition

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 121-133页

作者： Bera, Asish Krejcar, Ondrej Bhattacharjee, Debotosh Birla Institute of Technology and Science Department of Computer Science and Information Systems Pilani333031 India University of Hradec Kralove Center for Basic and Applied Science Faculty of Informatics and Management Hradec Kralove50003 Czech Republic Skoda Auto University Mlada Boleslav29301 Czech Republic Universiti Teknologi Malaysia Malaysia Japan International Institute of Technology Kuala Lumpur81310 Malaysia Jadavpur University Department of Computer Science and Engineering Kolkata700032 India

Deep convolutional neural networks (CNNs) have facilitated remarkable success in recognizing various food items and agricultural stress. A decent performance boost has been witnessed in solving the agro-food challenges by mining and analyzing region-based partial feature descriptors. Also, computationally expensive ensemble learning schemes fusing multiple CNNs have been studied in earlier works. This work proposes a region attention scheme for modeling long-range dependencies by building a correlation among different regions within an input image. The attention method enhances feature representation by learning the usefulness of context information from complementary regions. Spatial pyramidal pooling and average pooling pairs aggregate partial descriptors into a holistic representation. Both pooling methods establish spatial and channelwise relationships without incurring extra parameters. A context gating scheme is applied to refine the descriptiveness of weighted attentional features, which is relevant for classification. The proposed region attention network for food items and agricultural stress recognition method, dubbed RAFA-Net, has been experimented on three public food datasets, and has achieved state-of-the-art performances with distinct margins. The highest top-1 accuracy of RAFA-Net is 91.69%, 91.56%, and 96.97% on the UECFood-100, UECFood-256, and MAFood-121 datasets, respectively. In addition, better accuracies have been achieved on two benchmark agricultural stress datasets. The best top-1 accuracies on the Insect Pest (IP-102) and PlantDoc-27 plant disease datasets are 92.36%, and 85.54%, respectively;implying RAFA-Net's generalization capability. © 2023 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Childhood Malnutrition Using Survey Data and Machine Learning Approaches 4

Early Detection of Childhood Malnutrition Using Survey Data ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Zumma, Thoufiq Rahaman, Anikur Islam Prova, Nuzhat Noor Haque, Tasriful Joy Bose, Julias Caeser Youki, Ravina Akter Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh Washington University Science and Technology Department of Computer Science New York United States Pace University Department of Seidenberg School of Csis New York United States Victorian Institute of Technology Master of Information Technology and Systems Australia University of Wollongong Faculty of Artificial Intelligence and Science Australia University of Technology Sydney Faculty of Engineering and It Australia

ISBN: (纸本)9798331523923

Children's physical, mental and emotional development depends heavily on sleep, with age-specific sleep needs fluctuating. Malnutrition may result from eating too little, absorbing nutrients poorly, being unwell, living in poverty or not knowing enough about nutrition. Food allergies and iron insufficiency are two examples of illnesses whose onsets might differ depending on environmental exposures and genetics. By providing proper diet, getting medical attention when necessary and encouraging healthy behaviors, parents play a crucial role in supporting their children's health. For children to grow and develop properly, they need meals high in fruits, vegetables, milk, protein, calcium, iron and fiber. Key advantages of a balanced diet include aiding bone formation, improving heart health and encouraging regular bowel motions and digestion. In general, children's general health and wellness depend on caregivers being aware of their dietary requirements and giving them the proper attention. The findings of the research imply that machine learning algorithms may be useful in understanding and predicting the prevalence of malnutrition in children. Furthermore, these algorithms could provide perceptive data that might help politicians create effective policies. In this research, we make use of five different machine learning algorithms. With a decision tree, the accuracy is 0.92%, followed by svm which provides 0.91%, KNN, which provides 0.84%, GBM classifier, which provides 0.79% and random forest, which provides 0.65%. © 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

From Pictures to Prompts: Analyzing and Reconstructing AI-Generated Images with BLIP2 and CLIP 24

From Pictures to Prompts: Analyzing and Reconstructing AI-Ge...

引用

8th International Conference on Natural Language Processing and Information Retrieval, NLPIR 2024

作者： Kuo, Yi-Hsuan Chang, Hsien-Tsung Department of Computer Science and Information Engineering Chang Gung University Taoyuan China Bachelor Program in Artificial Intelligence Chang Gung University Taoyuan China

ISBN: (纸本)9798400717383

This study presents a novel approach to analyzing and reconstructing AI-generated images using BLIP2 and CLIP models, focusing on a dataset of 268,000 Midjourney-generated images and prompts. We introduce a multi-level feature classification system encompassing 11 categories and 1,100 features, and employ BLIP2 for descriptive text generation and CLIP for feature similarity analysis. Our methodology involves image pre-processing, custom feature extraction, and image reconstruction under various conditions. The effectiveness of our approach is demonstrated through similarity scores between original and reconstructed images, ranging from 68.15 to 71.25 across different feature extraction conditions. This research contributes to the fields of natural language processing and information retrieval by offering insights into AI-generated image analysis, proposing new methods for feature extraction and reconstruction, and suggesting avenues for improving image generation models and multi-modal understanding. © 2024 Copyright held by the owner/author(s).

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Tolerant Tracking Control Protocol for PMSM Based on Policy Iteration Algorithm and Fault Compensation 16th

Tolerant Tracking Control Protocol for PMSM Based on Polic...

引用

16th International Conference on Social Robotics, ICSR + InnoBiz 2024

作者： Yan, Shuya Li, Xiaocong Qian, Huaming Ma, Jun Al Mamun, Abdullah College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150001 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Guangzhou China Information Science and Technology Eastern Institute of Technology Ningbo China

ISBN: (纸本)9789819611508

In robotics applications, ensuring reliable performance in the presence of actuator faults is essential for maintaining system safety and reliability. This paper presents a tolerant tracking control method for permanent magnet synchronous motors (PMSMs) based on adaptive dynamic programming and fault compensation. The method simultaneously considers tracking accuracy and energy consumption through a policy iteration algorithm. In the optimality analysis of the algorithm, more relaxed conditions are provided to demonstrate that the performance function can converge to a near-optimal value within a finite number of iterations. In practical implementation, an actor-critic network is used to approximate the performance function and control protocol, alongside a fault detection mechanism based on an expanded time horizon, which achieves fault detection from arbitrary initial values. The effectiveness of the proposed algorithm is verified using a high-fidelity PMSM model in Simulink. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Permanent magnets

来源：评论

学校读者我要写书评

暂无评论

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

引用

Neural Computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Prior-Boosted GRL: Microarchitecture Design Space Exploration via Graph Representation Learning

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年第3期44卷 1141-1154页

作者： Wu, Zheng Shen, Jinyi Yi, Xiaoling Shang, Li Yang, Fan Zeng, Xuan Fudan University State Key Laboratory of Integrated Circuits and Systems The School of Microelectronics Shanghai200433 China Fudan University State Key Laboratory of Integrated Circuits and Systems Shanghai200433 China KU Leuven Department of Electrical Engineering Microelectronics Circuits and Systems Leuven3000 Belgium Fudan University State Key Laboratory of Integrated Circuits and Systems The School of Computer Science Shanghai200433 China

The design space exploration (DSE) of contemporary microprocessors faces a significant challenge of high-computational cost. In this context, we introduce Prior-boosted graph representation learning (GRL), a novel framework for the DSE of the microarchitectures the microprocessors underpinned by graph embeddings. Using GRL, Prior-boosted GRL constructs a compact and continuous vector space for design representation. This framework is further boosted by an efficient sampling algorithm informed by prior knowledge, which is instrumental in generating a superior set of initial designs to accelerate the exploration process. A well-designed ensemble surrogate model is combined with the multiobjective Bayesian optimization to explore the design space holistically within this graph-embedding domain. Rigorous experimental evaluations conducted on the RISC-V Berkeley-Out-of-Order Machine (BOOM) platform demonstrate that Prior-boosted GRL substantially surpasses preceding methods, achieving a 107.79% enhancement in Pareto front quality compared to the state-of-the-art DSE algorithm. It also outstrips manual designs on performance, power, and area metrics. As of this writing, Prior-boosted GRL holds the first place in the ICCAD 2022 CAD Contest evaluation platform. © 2024 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Offsets Reconstruction Method for Clock Skew Measurement Over High-Jitter Communication

引用

SN computer science 2025年第5期6卷 1-14页

作者： Sastra, Nyoman Putra Saputra, Komang Oka Teng, Wei-Chung Study Program of Electrical Engineering Faculty of Engineering Udayana University Jalan Raya Kampus Bukit Jimbaran Bali Badung 80361 Indonesia Department of Computer Science and Information Engineering National Taiwan University of Science and Technology No. 43 Section 4 Keelung Rd Taipei 106 China

Measuring clock skew of devices over a network fully relies on the offsets, the differences between sending and receiving times. Offsets that shape a thick line are the most ideal one as their slope is directly the clock skew sought. When some outliers separate from the thick line due to higher delay jitter, current advanced approaches use the lower bound or the majority of offsets to derive accurate clock skew. However, outliers in offsets that shape parallel dotted lines, reduce the availability of offsets in the lower region, and scatter widely the offsets from their majority zone. These conditions drive the current skew estimation approaches to lose their accuracy. This paper then developed a new method, which reconstructs back the outliers into their origin positions, in order to provide ideal offsets for clock skew measurement. The experimental evaluations have demonstrated that the clock skew accuracy of dotted-lines offsets tampered by outliers was improved from 2.1 to 0.9 ppm by the proposed reconstruction method. For a broader purpose, the reconstruction method has been adjusted to be implemented also on non-dotted-lines offsets. The robustness of the proposed method for this case has also been exhibited by the very ideal reconstructed offsets that shape like a thick line. © The Author(s) 2025.

关键词： Clock skew Delay jitter Dotted lines Hough transform

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of various classification algorithms for providing competency training to workplace risk prevention

引用

Multimedia Tools and Applications 2025年第15期84卷 15123-15149页

作者： Garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Birla Institute of Technology Ranchi Mesra India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Networking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India

In the workplace, risk prevention helps detect the risks and prevent accidents. To achieve this, workers' mental and physical parameters related to their health should be focused on and analyzed. It helps improve the workers' mental health and thus improves organizational performance. There are a lot of mental illnesses due to excess work and a lack of professional knowledge. It affects the performance of the worker. So, the organization needs to conduct competency training programs to improve their professional skills and the mindset to tackle the work pressure. There are several competency training programs given in various organizations to mold the workers, and it considerably reduces workplaces risks. Competency training in the workplace teaches integrity, honesty, managerial skills, and other workers. Developing organizational skills is the primary concern in this competency training. This paper enabled one of the best machine learning algorithms to be chosen to predict the hazards in the workplace and provide a healthy environment to the workers. For that, several classification methods such as Logistic Regression, Decision trees, AdaBoost classifier, Random Forest, Gradient Boosting classifier, and XGBoost classifier are implemented experimented with, and the performance is verified with python software. From the comparison, it has been found that the XGBoost classifier is selected as the best classifier and identified that it is highly suitable for analyzing and predicting workplace risks data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Occupational risks

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adaptation, and Enhanced Predictive Modeling for Diabetes Risk Assessment

AI-Driven Mobile Healthcare: Societal Impact, Workforce Adap...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Hole, Shreyas Rajendra Kolluru, Vinothkumar Gangul, Ranita Kolekar, Sagar Chintakunta, Advaitha Naidu Mungara, Sudeep Bangalore India Institute of Technology Department of Data Science Stevens HobokenNJ07030 United States Delaware State University Computer Science & Engineering Bangalore India Department of Civil Engineering Pune India University of North Carolina at Charlotte Department of Computer Science CharlotteNC28223 United States Masters in Information Systems Stevens Institute of Technology HobokenNJ07030 United States

ISBN: (纸本)9798331508685

With advancements in artificial intelligence, it is natural for the health industry to focus on IOT devices. AI could promote a paradigm shift in how doctors and patients interact through immediate updates, predictive features, and remote access. The focus of this study is the outreach and employment aspects revolving around AI-enabled health care, with special attention to mHealth solutions. We searched through published data and came across 112 relevant studies identifying keywords such as accessibility, empowerment, and workforce. One of the most interesting findings was the fact that AI targeting mobile applications has the possibility of increasing access to health services by approximately 60 percent for rural areas, as well as increasing the patient cooperative rate by approximately 45%, where a predictive health tracking device has been utilized. We proposed two new measures: the Physical Activity and Nutrition Index (PANI) and Health Status Index (HSI), allowing for better diabetes risk predictions with a 0.82 AUC-ROC and better generalizability than traditional baselines, with an improvement of 12%. When identifying the best available ML models, including Logistic Regression, Random Forest, XGBoost, LightGBM, and Bayesian Neural Networks, we found that the hybrid Random Forest + Linear SVC model had the best performance with recall and accuracy of 0.77 and 0.72, respectively. The ability of the model to demonstrate both interpretability and specificity was evident. It was also observed that synthetic data augmentation (SMOTE) increased the recall for minority class predictions by 18% but did not reduce specificity. © 2025 IEEE.

关键词： Risk assessment

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：