检索结果-内蒙古大学图书馆

Attar: RRAM-based in-memory attention accelerator with software-hardware co-optimization

Science China(information Sciences) 2025年第3期68卷 371-387页

作者： Bing LI Ying QI Ying WANG Yinhe HAN Information Engineering College Capital Normal University Research Center for Intelligent Computing Systems Institute of Computing TechnologyChinese Academy of Sciences

The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate computations lead to substantial inefficiencies when processing long sequences. To address these challenges, we introduce Attar, a resistive random access memory(RRAM)-based in-memory accelerator designed to optimize attention mechanisms through software-hardware co-optimization. Attar leverages efficient Top-k pruning and quantization strategies to exploit the sparsity and redundancy of attention matrices, and incorporates an RRAM-based in-memory softmax engine by harnessing the versatility of the RRAM crossbar. Comprehensive evaluations demonstrate that Attar achieves a performance improvement of up to 4.88× and energy saving of 55.38% over previous computing-in-memory(CIM)-based accelerators across various models and datasets while maintaining comparable accuracy. This work underscores the potential of in-memory computing to enhance the efficiency of attention-based models without compromising their effectiveness.

关键词： RRAM computing-in-memory attention pruning quantization

来源：评论

学校读者我要写书评

暂无评论

Exploring & exploiting high-order graph structure for sparse knowledge graph completion

引用

Frontiers of Computer Science 2025年第2期19卷 31-42页

作者： Tao HE Ming LIU Yixin CAO Zekun WANG Zihao ZHENG Bing QIN Research Center for Social Computing and Information Retrieval Harbin Institute of TechnologyHarbin 150001China Peng Cheng Laboratory Shenzhen 518000China SMU School of Computing and Information Systems Singapore Management UniversitySingapore 178902Singapore

Sparse Knowledge Graph(KG)scenarios pose a challenge for previous Knowledge Graph Completion(KGC)methods,that is,the completion performance decreases rapidly with the increase of graph *** problem is also exacerbated because of the widespread existence of sparse KGs in practical *** alleviate this challenge,we present a novel framework,LR-GCN,that is able to automatically capture valuable long-range dependency among entities to supplement insufficient structure features and distill logical reasoning knowledge for sparse *** proposed approach comprises two main components:a GNN-based predictor and a reasoning path *** reasoning path distiller explores high-order graph structures such as reasoning paths and encodes them as rich-semantic edges,explicitly compositing long-range dependencies into the *** step also plays an essential role in densifying KGs,effectively alleviating the sparse ***,the path distiller further distills logical reasoning knowledge from these mined reasoning paths into the *** two components are jointly optimized using a well-designed variational EM *** experiments and analyses on four sparse benchmarks demonstrate the effectiveness of our proposed method.

关键词： knowledge graph completion graph neural networks reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Document Classification Using Modified Relative Discrimination Criterion and RSS-ELM Techniques

引用

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 824-833页

作者： Anwaar, Muhammad Gilanie, Ghulam Namoun, Abdallah Sharif, Wareesa Department of Artificial Intelligence-Faculty of Computing The Islamia University of Bahawalpur Bahawalpur Pakistan AI Center-Faculty of Computer and Information Systems Islamic University of Madinah Madinah42351 Saudi Arabia

Internet content is increasing daily, and more data are being digitized due to technological advancements. Everincreasing textual data in words, phrases, terms, sentences, and paragraphs pose significant challenges in classifying them effectively and require sophisticated techniques to arrange them automatically. The vast amount of textual data presents an opportunity to organise and extract valuable insights by identifying crucial pieces of information using feature selection techniques. Our article proposes "a Modified Relative Discrimination Criterion (MRDC) Technique and Ringed Seal Search-Extreme Learning Machine (RSS-ELM) to improve document classification", which prioritizes key data and fits corresponding documents into appropriate classes. The proposed MRDC and RSS-ELM techniques are compared with several existing techniques, such as the Relative Discrimination Criterion (RDC), the Improved Relative Discrimination Criterion (IRDC), GA-EM, and CS-ELM. The MRDC technique produced superior classification results with 91.60% accuracy compared to existing RDC and IRDC for feature selection. Moreover, the RSS-ELM optimization technique improved predictions significantly, with 98.9% accuracy compared to CS-ELM and GA-ELM on the Reuter21578 dataset. © (2025), (Science and information Organization). All rights reserved.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Agricultural consumer Internet of Things devices: Methods for optimizing data aggregation

引用

Alexandria Engineering Journal 2025年 125卷 692-699页

作者： Mengash, Hanan Abdullah Mahgoub, Hany Alshuhail, Asma Darem, Abdulbasit A. Majdoubi, Jihen Yafoz, Ayman Alsini, Raed Alghushairy, Omar Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Engineering and Technology Unit Applied College Majmaah University Al Majmaah11952 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Department of Information Systems and Technology College of Computer Science and Engineering University of Jeddah Jeddah21589 Saudi Arabia

With the advent of state-of-the-art computer and digital technology, modern civilisation has been immensely facilitated and optimised. The Internet of Things (IoT) has grown in importance in recent years, allowing us to monitor our physical environments and broadening our horizons. The "practice, science, or art" of farming is defined as tending to land, growing crops with the use of different tools and techniques, and then selling the harvested food. If farmers optimise their operations with the help of a Wireless Sensor Network (WSN), they will be able to work much more efficiently and effectively. Data aggregation involves collecting information from multiple sensors. The data aggregation process is optimised by applying metaheuristic techniques. A Genetic Algorithm (GA) is a method for modelling evolution that uses mutation, crossover, and natural selection as its building blocks. The key benefit of the Artificial Bee Colony (ABC) approach is that it simultaneously considers local and global search, and it doesn't get trapped calculating its local minima. Naturalistic algorithms like ALO model their hunting behaviour after that of ant-lions and doodlebugs. It manages to find a happy medium between exploration and exploitation with just one operator. Experimental evidences show that the proposed metaheuristic technique, ABC-ALO, which combines the best elements of Artificial Bee Colony and Ant Lion Optimisation, is superior to existing metaheuristic approaches in terms of lifetime computation, or the number of alive nodes at different round counts. © 2025

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Synthetic Time Series Data Generation for Healthcare Applications: A PCG Case Study 59

Synthetic Time Series Data Generation for Healthcare Applica...

引用

59th Annual Conference on information Sciences and systems, CISS 2025

作者： Jamshidi, Ainaz Arif, Muhammad Kalhoro, Sabir Ali Gelbukh, Alexander University of Maryland Baltimore County Dept. of Information Systems United States Colorado State University Dept. of Information Systems United States North Dakota State University Dept. of Electrical Engineering United States Instituto Politécnico Nacional Dept. of Computing Research Center Mexico

ISBN: (纸本)9798331513269

The generation of high-quality medical time series data is essential for advancing healthcare diagnostics and safeguarding patient privacy. Specifically, synthesizing realistic phonocardiogram (PCG) signals offers significant potential as a cost-effective and efficient tool for cardiac disease pre-screening. Despite its potential, the synthesis of PCG signals for this specific application received limited attention in research. In this study, we employ and compare three state-of-the-art generative models from different categories - WaveNet, DoppelGANger, and DiffWave - to generate high-quality PCG data. We use data from the George B. Moody PhysioNet Challenge 2022. Our methods are evaluated using various metrics widely used in the previous literature in the domain of time series data generation, such as mean absolute error and maximum mean discrepancy. Our results demonstrate that the generated PCG data closely resembles the original datasets, indicating the effectiveness of our generative models in producing realistic synthetic PCG data. In our future work, we plan to incorporate this method into a data augmentation pipeline to synthesize abnormal PCG signals with heart murmurs, in order to address the current scarcity of abnormal data. We hope to improve the robustness and accuracy of diagnostic tools in cardiology, enhancing their effectiveness in detecting heart murmurs. © 2025 IEEE.

关键词： Cardiology

来源：评论

学校读者我要写书评

暂无评论

Chemical environment adaptive learning for optical band gap prediction of doped graphitic carbon nitride nanosheets

引用

Neural computing and Applications 2025年第5期37卷 3287-3301页

作者： Chen, Chen Xu, Enze Yang, Defu Yan, Chenggang Wei, Tao Chen, Hanning Wei, Yong Chen, Minghan Intelligent Information Processing Laboratory Hangzhou Dianzi University Hangzhou China Department of Computer Science Wake Forest University Winston-SalemNC United States Department of Chemical Engineering Howard University WashingtonDC United States Texas Advanced Computing Center University of Texas at Austin AustinTX United States Department of Computer Science & Information Systems University of North Georgia DahlonegaGA United States

This study presents a new machine learning algorithm, named Chemical Environment Graph Neural Network (ChemGNN), designed to accelerate materials property prediction and advance new materials discovery. Graphitic carbon nitride (g-C3N4) and its doped variants have gained significant interest for their potential as optical materials. Accurate prediction of their band gaps is crucial for practical applications;however, traditional quantum simulation methods are computationally expensive and challenging to explore the vast space of possible doped molecular structures. The proposed ChemGNN leverages the learning ability of current graph neural networks (GNNs) to satisfactorily capture the characteristics of atoms' chemical environment underlying complex molecular structures. Our experimental results demonstrate more than 100% improvement in band gap prediction accuracy over existing GNNs on g-C3N4. Furthermore, the general ChemGNN model can precisely foresee band gaps of various doped g-C3N4 structures, making it a valuable tool for performing high-throughput prediction in materials design and development. © The Author(s) 2024.

关键词： Graphitic Carbon Nitride

来源：评论

学校读者我要写书评

暂无评论

MMH-FE:AMulti-Precision and Multi-Sourced Heterogeneous Privacy-Preserving Neural Network Training Based on Functional Encryption

引用

Computers, Materials & Continua 2025年第3期82卷 5387-5405页

作者： Hao Li Kuan Shao Xin Wang Mufeng Wang Zhenyong Zhang The State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science CenterQilu University of Technology(Shandong Academy of Sciences)Jinan250014China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model ***,dishonest clouds may infer user data,resulting in user data *** schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing *** address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training ***,we design a multi-precision functional encryption computation based on Euclidean ***,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced ***,we conduct experiments on three *** results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.

关键词： Functional encryption multi-sourced heterogeneous data privacy preservation neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Cacao Pods Ripeness Using Convolutional Neural Networks

引用

Procedia Computer Science 2025年 257卷 1197-1204页

作者： Karl O. Borromeo Melbert R. Bonotan Archie P. Llagas Joana Marie O. Juan Philip Donald C. Sanchez Nathan Kit A. Berro Department of Computer Science College of Computing and Information Sciences Caraga State University Butuan City Philippines Department of Information Technology College of Computing and Information Sciences Caraga State University Butuan City Philippines Center for Resource Assessment Analytics and Emerging Technologies College of Engineering and Geo-Sciences Caraga State University Butuan City Philippines Department of Information Systems College of Computing and Information Sciences Caraga State University Butuan City Philippines

This paper presents methods for the development of Ripeness Identification of Cacao Pods using Convolutional Neural Network (CNN) and precision agriculture employed in a Mobile Application. This research explores if there is a correlation between the color dynamics of cacao pods and its physiological characteristics, and the possibility of using this correlation to develop Artificial Intelligence (AI) model for ripeness and variety identification, which conventional eye estimation resulted to unripe and overripe harvesting of Cacao Pods. Data analysis and correlation was developed, integrating detection and classification models based on the Single Shot Detection (SSD) MobileNet and Visual Geometry Group (VGG) 16 or VGG16 layers network architectures, respectively. The mobile application utilizes the TensorFlow template for object detection and incorporates image preprocessing techniques for enhanced accuracy. The successful integration of the model into a mobile application demonstrates its potential for practical applications in the cacao industry.

关键词： Cacao Physiological Properties Convolutional Neural Network CNN Deep Learning Ripeness Identification Precision Agriculture

来源：评论

学校读者我要写书评

暂无评论

Segmentation Techniques Applied to CNNs for Cervical Cancer Classification

引用

IEEE Access 2025年 13卷 74678-74688页

作者： Ortiz-Gonzalez, Ana Martinez-Espana, Raquel Morales-Garcia, Juan Imbernon, Baldomero Martinez-Mas, Jose Alvarez, Mauricio A. Romero, Oscar D. Martinez-Cendan, Juan Pedro Bueno-Crespo, Andres University Hospital Complex of Cartagena Pathology Department Spain University of Murcia Information and Communications Engineering Department Spain University of Alicante Department of Software and Computing Systems Spain Spain Catholic University of Murcia Faculty of Medicine Spain CIAGO Gynecological Center Obstetrics and Gynecology Department Spain University of Manchester Computer Science Department United Kingdom University General Hospital Santa Lucía Obstetrics and Gynecology Department Spain

Cervical cancer continues to be a significant global health issue, ranking as the fourth most prevalent cancer affecting women. Enhancing population screening programs by refining the examination of cervical samples conducted by skilled pathologists offers a compelling alternative for early detection of this disease. Deep Learning facilitates the development of automatic classification models to aid experts in this task. However, it is increasingly important to bring explainability to the model both to understand how the network learns to identify pathology and to bring confidence to the diagnosis. In this paper, we design an automatic segmentation masks for the classification of cervicovaginal cell images. This automatic segmentation is combined in a classification model that allows the models to improve their performance thanks to the morphological information provided by the combined segmentation in a Global Average Pooling layer with the convolutional network analysis of the original image. The models will be trained with real data so that learning can recognize the diversity of colors, shapes and sizes of human cell nuclei. The results show a robust and explainable model with satisfactory results, obtaining an F1 Score value of 0.935 in binary classification of revisable and non-revisable cell. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

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：