检索结果-内蒙古大学图书馆

Gender Classification from Pashto Handwritten Text Images

IEEE Access 2025年 13卷 81736-81754页

作者： Sultan, Khan Ahmad, Riaz Muhammad, Siraj Almutairi, Sulaiman Abohashrh, Mohammed Ullah, Khalil Namoun, Abdallah Hussain, Ibrar Shaheed Benazir Bhutto University Department of Computer Science Dir Upper Khyber Pakhtunkhwa Sheringal75660 Pakistan Qassim University College of Applied Medical Sciences Department of Health Informatics Qassim52571 Saudi Arabia King Khalid University College of Applied Medical Sciences Department of Basic Medical Sciences Abha61421 Saudi Arabia University of Malakand Department of Software Engineering Dir Lower Khyber Pakhtunkhwa Malakand18800 Pakistan Islamic University of Madinah AI Center Faculty of Computer and Information Systems Madinah42351 Saudi Arabia Shaheed Benazir Bhutto University Sheringal Quality Enhancement Cell Khyber Pakhtunkhwa Dir Upper75660 Pakistan

computer vision (CV) is a subfield of computer science that enables machines to perceive, interpret, and understand visual data. It combines image processing, analysis, and machine learning to extract meaningful insights from images and videos. One key application of CV is the classification of gender from handwritten text images-a complex task, especially in languages such as Pashto due to the intricacy of the script and the limited resources. This research presents a novel approach to gender classification using Pashto Handwritten Text Images (PHTI). The study evaluates and compares the performance of traditional machine learning and modern deep learning models: Support Vector Machine (SVM) and You Only Look Once version 8 (YOLO8), a CNN-based object detection framework. The PHTI dataset, introduced in this study, consists of 36,086 text line images written by 200 male and 200 female native Pashto writers. The goal is to assess how effectively SVM and YOLO8 can classify gender based on visual handwriting patterns in the Pashto language. The experimental results reveal that YOLO8 outperforms SVM in classification accuracy. Although SVM, a widely used machine learning model, achieved an accuracy of 61.29%, YOLO8 reached a significantly higher accuracy of 77% in the same data set. This performance gap highlights the advantages of using advanced deep learning models for complex pattern recognition tasks in CV. This research provides a pioneering contribution by focusing on Pashto, a low-resource language, in the context of gender classification using handwritten text images. It opens new pathways for applying CV in regional languages and supports the development of intelligent systems capable of handling various scripts. © 2013 IEEE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Optimizing Heart-Kidney Interaction for Cancer Detection Through Physiological Process Simulation as a Decision Support System

引用

IEEE Access 2025年 13卷 79169-79179页

作者： Jaddi, Najmeh Sadat Abdullah, Salwani Othman, Zalinda Yahya, Yazrina Zakree Ahmad Nazri, Mohd Leng Goh, Say Alvankarian, Fatemeh Alvankarian, Jafar Iranian eUniversity Faculty of Computer Engineering Tehran96351-14578 Iran Universiti Kebangsaan Malaysia Center for Artificial Intelligence Technology Faculty of Information Science and Technology Bangi43600 Malaysia Universiti Kebangsaan Malaysia Center for Software Technology and Management Faculty of Information Science and Technology Bangi43600 Malaysia Universiti Malaysia Sabah Kampus Antarabangsa Labuan Optimisation and Analytics Research Group Faculty of Computing and Informatics Labuan87000 Malaysia University of Maryland Department of Electrical and Computer Engineering College ParkMD20742 United States RayanMiniFab Tehran University Science and Technology Park Tehran*** Iran

A decision support system (DSS) is a computer-based tool used to improve decision-making capabilities for any organization by analyzing the available data. The heart-kidney (HK) model proposed in this paper, as a DSS, simulates the physiological processes of the heart and kidneys in the human body to support cancer detection. The first part of the HK algorithm is inspired by the functions of the heart, where blood molecules (solutions) are sent to the heart, simulating the processes of oxygenation and the pumping of oxygenated blood to the kidneys as a local search. The solutions generated by the heart are then fed into the kidney-inspired algorithm (KA), which performs filtration, reabsorption, secretion, and excretion. The heart component enhances the KA’s local search capability, guiding the algorithm toward optimal solutions. The HK model is evaluated on eight test functions, with results compared to those of the heart algorithm and KA alone. Additionally, the HK algorithm’s effectiveness as a decision support system is tested on benchmark classification and time series prediction problems, with statistical analysis against existing methods in the literature. Finally, the HK algorithm is applied to cancer detection from microRNA data, demonstrating its potential in optimizing decision-making processes in healthcare. © 2013 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Dynamic Channel Allocation via Bandit Learning for WiFi 7 Networks with Multi-Link Operation

Dynamic Channel Allocation via Bandit Learning for WiFi 7 Ne...

引用

IEEE Conference on Wireless Communications and Networking

作者： Shumin Lian Jingwen Tong Liqun Fu School of Informatics Xiamen University Xiamen China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The upcoming IEEE 802.11be standard, termed WiFi 7, introduces multi-link operation (MLO), enabling devices to establish multiple simultaneous connections utilizing different frequencies and channels. While MLO has the potential to boost network throughput, optimizing channel allocation in WiFi 7 networks introduces many challenges. In this paper, we propose a best-arm identification-enabled Monte Carlo tree search (BAI-MCTS) algorithm for efficient channel allocation in WiFi 7 networks. Specifically, we first employ an efficient mechanism to calculate the network throughput by capturing the essential features of the CSMA protocol. We then formulate this channel allocation problem as a multi-armed bandit (MAB) problem. However, solving this MAB problem induces high sample complexity due to the large-arm space. To overcome this challenge, we introduce BAI-MCTS by combining the BAI and MCTS techniques. Notably, BAI-MCTS has a fast convergence rate and low sample complexity. Simulation results demonstrate that the proposed algorithm outperforms the baseline algorithms in terms of the convergence rate, which is about 42.40% faster than the UCT algorithm when reaching 95% of the optimal value.

关键词： Protocols Monte Carlo methods Heuristic algorithms Simulation Channel allocation Throughput Dynamic scheduling Multiaccess communication Wireless fidelity Convergence

来源：评论

学校读者我要写书评

暂无评论

NDAS: Noise-Decomposed Abnormal Segmentation for Robust Medical Image Retrieval

NDAS: Noise-Decomposed Abnormal Segmentation for Robust Medi...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Ju-Chan Kim Pham Van Nguyen Duc-Tai Le Hyunseung Choo College of Computing and Informatics Sungkyunkwan University Suwon South Korea Department of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

This paper presents NDAS (Noise-Decomposed Ab-normal Segmentation), an innovative framework for robust med-ical image retrieval and segmentation. By explicitly decomposing noise and abnormal features, NDAS enhances retrieval accuracy and segmentation precision. Experimental results on the BraTS 2019 dataset validate NDAS's superiority over CBMIR and SBMIR methods, achieving the highest Top-5 accuracy and Dice coefficient. This demonstrates its effectiveness in handling noise, isolating pathological regions, and retrieving diagnostically relevant medical images. NDAS offers a significant advancement in medical imaging analysis, emphasizing its potential for clinical applications requiring precision and reliability.

关键词： Image segmentation Pathology Accuracy Noise Image retrieval Information management Reliability Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

S2L-CM: Scribble-supervised nuclei segmentation in histopathology images using contrastive regularization and pixel-level multiple instance learning

引用

computers in Biology and Medicine 2025年第Pt B期192卷 110293-110293页

作者： Oh, Hyun-Jic Min, Seonghui Jeong, Won-Ki Department of Computer Science and Engineering College of Informatics Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of

Deep learning-based pathology nuclei segmentation algorithms have demonstrated remarkable performance. Conventional methods mostly focus on supervised learning, which requires significant manual effort to generate ground truth labels. Recently, weakly supervised learning has been extensively explored as a method for overcoming this limitation by training models with sparse annotations. However, the performance is inferior compared to that of fully supervised learning schemes. This paper proposes S2L-CM, a scribble-supervised nuclei segmentation framework based on two ideas;first, we leverage self-generated pseudo labels from user-given sparse scribble labels to train the deep learning model without full ground-truth labels, and second, we utilize multiscale contrastive regularization and pixel-level multiple-instance learning to further refine pseudo labels to improve segmentation performance. We demonstrate the effectiveness and robustness of our method on four nuclei datasets by comparing it with existing state-of-the-art methods. Code will be available at: https://***/hvcl/S2L-CMhttps://***/hvcl/S2L-CM. © 2025

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Edge AI Robot Technology Application with YOLOv8, MQTT and MQ-5 Sensors for Realtime Fire and Smoke Detection 14th

Edge AI Robot Technology Application with YOLOv8, MQTT and...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Andriyadi, Anggi Wijaya, Chandra Chen, Shih-Yen Huang, Ding-Hsiang Yang, Chao-Tung Department of Industrial Engineering and Enterprise Information Tunghai University Taichung City Taiwan Department of Computer Science Tunghai University Taichung City Taiwan Department of Information System Institut Informatika dan Bisnis Darmajaya Bandar Lampung Indonesia Department of Informatics Universitas Katolik Parahyangan Bandung Indonesia Research Center for Smart Sustainable Circular Economy Tunghai University Taichung City Taiwan

ISBN: (纸本)9789819623945

Fire incidents pose a significant security threat that requires attention from all stakeholders. For example, Taipei reported 893 fire incidents in 2023 alone. This study aims to enhance security surveillance by promptly detecting fire incidents through the development of a patrol robot. The robot captures sensor signals from the MQ-5 and transmits them via MQTT to the Raspberry Pi control center, delivering real-time reports of smoke and fire to fire officials. Additionally, equipped with a camera, the robot streams footage using RTSP to Jetson for fire and smoke object recognition using the You Look Only Once (YOLO) algorithm. Our robot effectively detected smoke and fire using the MQ5-Sensor and transmitted the signals via MQTT. Furthermore, it analyzed the visual stream to identify fire and smoke patterns with YOLOv8, resulting in a significant increase in accuracy. The evaluation of our model yielded impressive performance metrics, including a precision of 93%, a recall of 97%, a precision-recall of 97.90%, and an F1-Score of 97%. In the future studies we will integrate a mini camera and Large Language Model (LLM) to enable the robot to communicate with humans to warn of early fire incidents. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Smoke detectors

来源：评论

学校读者我要写书评

暂无评论

MRI Prostate and Tumor Segmentation with Fine-tuned SAM: A Path to Enhanced Treatment Planning

MRI Prostate and Tumor Segmentation with Fine-tuned SAM: A P...

引用

Medical Imaging 2025: Clinical and Biomedical Imaging

作者： Chen, Jingchu Hu, Mingzhe Safari, Mojtaba Yang, Xiaofeng Department of Radiation Oncology Winship Cancer Institute Emory University AtlantaGA30322 United States School of Mechanical Engineering Georgia Institute of Technology AtlantaGA30322 United States Department of Computer Science and Informatics Emory University AtlantaGA30322 United States

ISBN: (纸本)9781510685987

Magnetic resonance imaging (MRI) provides high spatial resolution and soft tissue contrast, which is crucial in diagnosing prostate cancer. Accurate segmentation of the prostate and dominant intraprostatic lesions on MRI is essential for guiding dose boost in radiation therapy planning. However, manual segmentation is labor-intensive and time-consuming. While current deep learning models offer automatic segmentation, they often struggle with accurately contouring the smaller, irregularly shaped DILs due to limited patient data. The Segment Anything Model (SAM), a foundation model pre-trained on a large and diverse dataset, has the potential to address these challenges and improve prostate and DIL segmentation on MRI. Studies suggest fine-tuning SAM can help SAM adapt to medical images and improve segmentation outcomes. We obtained T2-weighted MRI slices with manual contours from the Cancer Imaging Archive (TCIA) for training and evaluation. The bounding box method was employed to generate prompts for its intuitive approach and effectiveness in achieving optimal segmentation results. We trained a fine-tuned SAM model to segment the prostate and DIL. The results were compared to the segmentation results of the baseline metrics established by the SAM-only model. The fine-tuned SAM produced the best segmentation results, achieving mean Dice Similarity Coefficients (DSCs) of 0.911±0.044, 95th Percentile Hausdorff Distance (HD95) of 3.58±2.078 mm, and an Intersection over Union (IoU) of 0.862±0.059 for the prostate, and a mean DSC of 0.800±0.088, HD95 of 2.987±3.016 mm, and IoU of 0.708±0.105 for the DIL. © 2025 SPIE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diabetes Prediction Performance Using Feature Selection Based on Grey Wolf Optimizer with Autophagy Mechanism

SSRN

引用

SSRN 2025年

作者： Sirmayanti Prastyo, Pulung Hendro Mahyati Department of Electrical Engineering Politeknik Negeri Ujung Pandang Makassar Indonesia Department of Informatics and Computer Engineering Politeknik Negeri Ujung Pandang Makassar Indonesia Department of Chemical Engineering Politeknik Negeri Ujung Pandang Makassar Indonesia

Diabetes mellitus, often called a silent killer, is a chronic condition characterized by insufficient insulin production and elevated blood sugar levels, leading to complications in vital organs such as the nerves, eyes, and kidneys. Machine learning is a powerful tool for predicting diabetes;however, noisy features can negatively impact its accuracy, making an effective feature selection essential. This study proposes an improved feature selection approach for diabetes prediction, leveraging the Grey Wolf Optimizer with an integrated Autophagy Mechanism (GWO-AM) on the Pima Indian Diabetes Dataset. The autophagy mechanism, inspired by cellular self-degradation and recycling, is incorporated into GWO to enhance exploration and exploitation. Comprehensive experiments show that GWO-AM significantly improves prediction accuracy and reduces the number of selected features. The GWO-AM obtains a notable accuracy of 90.91% and outperforms existing methods, highlighting its potential to improve computational efficiency and model interpretability in medical data analysis. © 2025, The Authors. All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Optimizing Logistics in E-Commerce Using Deep Random Forest for Enhanced User Satisfaction 3

Optimizing Logistics in E-Commerce Using Deep Random Forest ...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Nisha, G.Anne Sreetha, P. Seetha, A. Manickam, K. Jagannathan, Sharath Kumar Sekar, S.D. Kyoto Computer Gakuin Department of Informatics Kyoto Japan Kpr Institute of Engineering and Technology Department of Biomedical Engineering Tamil Nadu India S. A. Engineering College Department of Information Technology Thiruverkadu Chennai India Sona College of Technology Department of Mathematics Tamil Nadu India Data Science Institute Saint Peter's University NJ United States R.M.K.Engineering College Department of Mechanical Engineering TamilNadu Chennai India

ISBN: (纸本)9798331542375

Operational efficiency is one of the most important factors affecting customer satisfaction directly in e-commerce. Still, constant addressing of timely delivery, path simplification, and reduction of delays remains challenging problems. Deep Random Forest (DRF) is a new approach presented in this work to examine and forecast significant logistics metrics including delivery times and satisfaction scores. Development of this approach targeted to solve these issues. The model makes use of e-commerce past performance including order volumes, customer comments, and delivery times. Findings: The suggested approach achieves 10% increase in user satisfaction, 12% cost reduction, and 15% faster delivery times than baseline methods. This is accomplished by means of DRF, applied to examine trends and carry out predictive modifications. Results and Methodology: These results outperform those of the benchmarks established by Gradient Boosting and XGBoost, which displayed respective rises in satisfaction of 9% and 8%. Apart from improving the quality of service, the use of DRF not only strengthened user loyalty but also contributed to improve the transportation efficiency. This approach exposes the transforming opportunities of artificial intelligence in logistics management for e-commerce systems. This approach guarantees operations with a customer-centric concentration benefiting from measurable advantages. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Sustainable energy management in the AI era: a comprehensive analysis of ML and DL approaches

引用

Computing 2025年第6期107卷 1-64页

作者： Javed, Haseeb Eid, Fatma El-Sappagh, Shaker Abuhmed, Tamer Department of Computer Science and Engineering College of Computing and Informatics Sungkyunkwan University Suwon South Korea Technology Management Stony Brook University New York USA Applied Artificial Intelligence College of Computing and Informatics Sungkyunkwan University Suwon South Korea Faculty of Computer Science and Engineering Galala University Suez Egypt Information Systems Department Faculty of Computers and Artificial Intelligence Benha University Banha Egypt

This study comprehensively analyzes the application of innovative deep learning (DL) and machine learning (ML) techniques in smart energy management systems (EMSs), with an emphasis on load forecasting, demand response, and the development of smart energy sectors. The application of various ML and DL models were examined in over 200 studies from 2014 to 2024 in an electrical network's EMS to highlight the key benefits and advances made by each technology for the sustainable management systems in energy sector. The findings emphasize DL and ML models’ enhanced precision and predictive capabilities in load forecasting, their efficacy in enabling efficient demand response mechanisms, and their significance in supporting the development of smart energy sectors. Furthermore, recommendations are made based on the survey results to assist in incorporating these techniques into EMS frameworks, such as investment in data infrastructure, model training and validation, and collaboration between researchers, industry experts, and policymakers. The study also discusses the limitations identified in the literature, such as limited real-world implementations, challenges regarding quality and data availability, and the need for enhanced ML and DL model interpretability. Addressing these limitations can assist in increasing the application and efficacy of ML and DL techniques in EMSs, enabling a more efficient and sustainable energy landscape. Finally, this study facilitates researchers' exploration of ML and DL in energy management, highlighting relevant limitations, strengths, and alternative approaches associated with sustainable energy management. It also indicates potential future research directions for further investigation.

关键词： Power management (telecommunication)

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：