检索结果-内蒙古大学图书馆

Towards optimized tensor code generation for deep learning on sunway many-core processor

Frontiers of computer science 2024年第2期18卷 1-15页

作者： Mingzhen LI Changxi LIU Jianjin LIAO Xuegui ZHENG Hailong YANG Rujun SUN Jun XU Lin GAN Guangwen YANG Zhongzhi LUAN Depei QIAN State Key Laboratory of Software Development Environment Beijing 100191China School of Computer Science and Engineering Beihang UniversityBeijing 100191China National University of Singapore Singapore 119077Singapore State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214000China Science and Technology on Special System Simulation Laboratory Beijing Simulation Center Beijing 100854China Department of Computer Science and Technology Tsinghua UniversityBeijing 100084China

The flourish of deep learning frameworks and hardware platforms has been demanding an efficient compiler that can shield the diversity in both software and hardware in order to provide application *** the existing deep learning compilers,TVM is well known for its efficiency in code generation and optimization across diverse hardware *** the meanwhile,the Sunway many-core processor renders itself as a competitive candidate for its attractive computational power in both scientific computing and deep learning *** paper combines the trends in these two ***,we propose swTVM that extends the original TVM to support ahead-of-time compilation for architecture requiring cross-compilation such as *** addition,we leverage the architecture features during the compilation such as core group for massive parallelism,DMA for high bandwidth memory transfer and local device memory for data locality,in order to generate efficient codes for deep learning workloads on *** experiment results show that the codes generated by swTVM achieve 1.79x improvement of inference latency on average compared to the state-of-the-art deep learning framework on Sunway,across eight representative *** work is the first attempt from the compiler perspective to bridge the gap of deep learning and Sunway processor particularly with productivity and efficiency in *** believe this work will encourage more people to embrace the power of deep learning and Sunwaymany-coreprocessor.

关键词： sunway processor deep learning compiler code generation performance optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Text Augmentation for Robust Sentiment Analysis: Enhancing Model Performance with EDA and Multi-Channel CNN

引用

IEEE Access 2025年 13卷 31978-31991页

作者： Wahyu Trisna, Komang Huang, Jinjie Chen, Yuanjian Gede Juliana Eka Putra, I. Harbin University of Science and Technology School of Computer Science and Technology Harbin150080 China Primakara University Department of Informatic Engineering Denpasar Bali80226 Indonesia Harbin University of Science and Technology Key Laboratory of Advanced Manufacturing and Intelligence Technology Harbin150080 China

The rapid growth of social media has revolutionized the way individuals share and access opinions, generating vast amounts of textual data containing diverse sentiments. Sentiment analysis enables organizations to derive valuable insights from this data, facilitating improved decision-making. However, the limited availability of labeled datasets and challenges related to data imbalance often hinder the development of robust sentiment analysis models. In this study, we propose a novel framework dynamic Easy Data Augmentation (EDA) technique with a Multi-Channel Convolutional Neural Network (MCNN) to address these issues. The EDA techniques including synonym replacement (SR), random insertion (RI), random deletion (RD), and random swap (RS), enrich the training data by introducing diversity, thereby enhancing model robustness. The MCNN architecture effectively captures local patterns in text using multiple filter sizes, enabling comprehensive feature extraction with low computational overhead. Furthermore, the integration of Word2Vec embeddings ensures meaningful text representation, leveraging context-independent word relationships for improved sentiment analysis. Experimental evaluations demonstrate the effectiveness of the proposed approach, highlighting significant improvements in F1-score compared to baseline models. The findings underscore the potential of dynamic text augmentation and efficient deep learning architectures to overcome the challenges of limited training data, offering a scalable solution for sentiment analysis in real-world applications. Additionally, the proposed model achieves an average performance improvement of 11.34% over previous models. © 2025 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Provable Data Possession with Outsourced Tag Generation for AI-Driven E-Commerce

引用

computers, Materials & Continua 2025年第5期83卷 2719-2734页

作者： Yi Li Wenying Zheng Yu-Sheng Su Meiqin Tang School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science and Technology(School of Artificial Intelligence) Zhejiang Sci-Tech UniversityHangzhou310018China Department of Computer Science and Information Engineering National Chung Cheng UniversityChiayi621301TaiwanChina Advanced Institute of Manufacturing with High-tech Innovations National Chung Cheng UniversityChiayi621301TaiwanChina Department of Computer Science and Engineering National Taiwan Ocean UniversityKeelung202301TaiwanChina School of Integrated Circuits Wuxi Vocational College of Science and TechnologyWuxi214028China

AI applications have become ubiquitous,bringing significant convenience to various *** e-commerce,AI can enhance product recommendations for individuals and provide businesses with more accurate predictions for market strategy ***,if the data used for AI applications is damaged or lost,it will inevitably affect the effectiveness of these AI ***,it is essential to verify the integrity of e-commerce *** existing Provable Data Possession(PDP)protocols can verify the integrity of cloud data,they are not suitable for e-commerce scenarios due to the limited computational capabilities of edge servers,which cannot handle the high computational overhead of generating homomorphic verification tags in *** address this issue,we propose PDP with Outsourced Tag Generation for AI-driven e-commerce,which outsources the computation of homomorphic verification tags to cloud servers while introducing a lightweight verification method to ensure that the tags match the uploaded ***,the proposed scheme supports dynamic operations such as adding,deleting,and modifying data,enhancing its ***,experiments show that the additional computational overhead introduced by outsourcing homomorphic verification tags is acceptable compared to the original PDP.

关键词： Provable data possession data auditing cloud computing e-commerce bloom filter

来源：评论

学校读者我要写书评

暂无评论

Energy-aware resource management in fog computing for IoT applications: A review, taxonomy, and future directions

引用

Software - Practice and Experience 2024年第2期54卷 109-148页

作者： Hashemi, Sayed Mohsen Sahafi, Amir Rahmani, Amir Masoud Bohlouli, Mahdi Department of Computer Engineering Qeshm Branch Islamic Azad university Qeshm Iran Department of Computer Engineering South Tehran Branch Islamic Azad University Tehran Iran Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou Taiwan Department of Computer Science and Information Technology Institute for Advanced Studies in Basic Sciences Zanjan Iran Research and Innovation Department Petanux GmbH Bonn Germany Zanjan Iran

The energy demand for Internet of Things (IoT) applications is increasing with a rise in IoT devices. Rising costs and energy demands can cause serious problems. Fog computing (FC) has recently emerged as a model for location-aware tasks, data processing, fast computing, and energy consumption reduction. The Fog computing model assists cloud computing in fast processing at the network's edge, which also exerts a vital role in cloud computing. Due to the fast computing in fog servers, different quality of service (QoS) approaches have been proposed in various sections of the fog system, and several quality factors have been considered in this regard. Despite the significance of QoS in Fog computing, no extensive study has focused on QoS and energy consumption methods in this area. Therefore, this article investigates previous research on the use and guarantee of Fog computing. This article reviews six general approaches that discuss the published articles between 2015 and late May 2023. The focal point of this paper is evaluating Fog computing and the energy consumption strategy. This article further shows the advantages, disadvantages, tools, types of evaluation, and quality factors according to the selected approaches. Based on the reviewed studies, some open issues and challenges in Fog computing energy consumption management are suggested for further study. © 2023 John Wiley & Sons Ltd.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Fraud Detection in Financial Transactions using Machine Learning - A Comparative Study 3

Fraud Detection in Financial Transactions using Machine Lear...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Jayanthkumar, Avati Sathwik, Mayakuntla Sai Reddy, Shagam Srinivasa Kumar, Donadula Mounish Samir, Chougule Saish Patni, Jagdish Chandra Bahadure, Nilesh Kumar, Rohit Alliance School of Advanced Computing Alliance University Dept. of Computer Science Bengaluru India School of Technology Gsfc University Department of Computer Science and Engineering Vadodara India

ISBN: (纸本)9798331518592

Data analysis techniques using machine learning approaches are the most prominent when we are considering the online fraud, it may be a credit card fraud or any other online fraud in the banking system. Using Machine Learning techniques, we can easily manage the information of fake transactions by extensive data analysis of time, location and amount in the real time. This paper gives the comprehensive study of the changing scene of the fraud discovery in monetary exchanges, investigating the most recent patterns, advances, and techniques utilized by financial institutions and other administrative bodies. An extensive review of various machine learning techniques has been done to find out the effective solution to protect the online fraud. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images for Crop Prediction using Machine and Deep Learning Models 3

Hyperspectral Images for Crop Prediction using Machine and D...

引用

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

作者： Mahalakshmi, R. Kumutha, K. Sakthivanitha, M. Lakshmi, R. Bagavathi Sirajudeen, Mohamed Padmanabhan, Sankar Vels Institute of Science Technology & Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Application Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Information Technology Tamil Nadu Chennai India Nilgiri College of Arts and Science Pg and Research Department of Computer Science Tami Nadu The Nilgiris India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data. © 2025 IEEE.

关键词： Classification Deep Learning(DL) Hyperspectral Images(HSI) Machine Learning(ML)

来源：评论

学校读者我要写书评

暂无评论

Anisotropic leaky-like perturbation with subwavelength gratings enables zero crosstalk

引用

Light(science & Applications) 2023年第6期12卷 1153-1161页

作者： Md Faiyaz Kabir Md Borhan Mia Ishtiaque Ahmed Nafiz Jaidye Syed Z.Ahmed Sangsik Kim Department of Electrical and Computer Engineering Texas Tech UniversityLubbockTX 79409USA Department of Physics and Astronomy Texas Tech UniversityLubbockTX 79409USA School of Electrical Engineering Korea Advanced Institute of Science and TechnologyDaejeon 34141South Korea

Electromagnetic coupling via an evanescent field or radiative wave is a primary characteristic of light,allowing optical signal/power transfer in a photonic circuit but limiting integration density.A leaky mode,which combines both evanescent field and radiative wave,causes stronger coupling and is thus considered not ideal for dense *** we show that a leaky oscillation with anisotropic perturbation rather can achieve completely zero crosstalk realized by subwavelength grating(SWG)*** oscillating fields in the SWGs enable coupling coefficients in each direction to counteract each other,resulting in completely zero *** experimentally demonstrate such an extraordinarily low coupling between closely spaced identical leaky SWG waveguides,suppressing the crosstalk by≈40 dB compared to conventional strip waveguides,corresponding to≈100 times longer coupling *** leaky-SWG suppresses the crosstalk of transverse–magnetic(TM)mode,which is challenging due to its low confinement,and marks a novel approach in electromagnetic coupling applicable to other spectral regimes and generic devices.

关键词： crosstalk coupling enable

来源：评论

学校读者我要写书评

暂无评论

Efficient Method For Automatic Irrigation System using IOT 10

Efficient Method For Automatic Irrigation System using IOT

引用

10th International Conference on Electrical Energy Systems, ICEES 2024

作者： Rajagopal, R. Senbagavalli, M. Sampath, P.V.V.S.S. Sanjeevi Kumar, V. Alliance School of Advanced Computing Alliance University Department of Computer Science and Engineering Bangalore India Alliance School of Advanced Computing Alliance University Department of CSE Bangalore India

ISBN: (纸本)9798350353778

The precise and effective management of water using Internet of Things (IoT) technology in Automatic Irrigation Systems (AIS) has revolutionized agricultural practices. The primary objective is to enhance the watering methods, reduce labor costs, and conserve water. Through the literature review, various components are used in this automatic irrigation system. Identifying gaps in existing approaches leads to the proposal of an integrated framework. This process encompasses the availability and cost-effectiveness of the product. The testing and evaluation of the system will be conducted by testing trails with different soil moisture levels. As a result, we can see an improvement in the quality of the product. The purpose of this project is to show the importance of water conservation in the modern deforested environment. Future work will focus on integrating based on weather conditions by getting the datasets from the weather station. © 2024 IEEE.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

A Simulation Study of n-ZnO/Perovskite/p-Cu2SnS3 Based Self-Powered Photodetector: Design and optimisation

引用

Materials Research Innovations 2023年第7期27卷 503-510页

作者： Yadav, Sanjeev Mani Pandey, Amritanshu Department of Electronics and Computer Science National Institute of Advanced Manufacturing Technology Jharkhand Ranchi India Centre for Research in Microelectronics Department of Electronics Engineering IIT-BHU Varanasi India

Perovskite has been widely used in the field of optoelectronics owing to its superb optoelectronic properties. The simplest fabrication along with low-temperature handling of perovskite-based planner structures (p-i-n or n-i-p) has drawn their potential impact in organic–inorganic lead halide optoelectronic devices. The poor conductivity, stability, and high processing cost of absorber materials hinder the optical performance of the device. The sandwiching of the perovskite as absorber materials between two inorganic materials working as electron transport layer (ETL) and hole transport layer (HTL) may be a possible solution. An active absorber perovskite (CH3NH3PbI3) assisted by two n-ZnO and p-CTS materials working as an ETL and HTL, respectively, has been used to maximize the overall performance of the proposed device. The resultant optimized device shows the maximum responsivity of ∼0.35 (A/W) for a broad visible spectrum (300–900 nm), while the EQE (%) reported in the range of 25–80%. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Photodetectors

来源：评论

学校读者我要写书评

暂无评论

Optimized quantum circuit implementation of SATURNIN for Grover’s algorithm

引用

International Journal of Information Technology (Singapore) 2024年第5期16卷 2955-2964页

作者： Allu, Swamy Naidu Naidu, T. Appala Rao, K. Gangadhara Department of Computer Science and Engineering Acharya Nagarjuna University Andhra Pradesh Guntur 522510 India CR Rao Advanced Institute of Mathematics Statistics and Computer Science UoH Campus Telangana Hyderabad 500046 India

In 2019, SATURNIN a light-weighted block cipher was proposed for post-quantum security. In this research, we try to examine the security strength of SATURNIN by implementing its quantum circuit to apply Grover’s algorithm for brute-force key search from classical complexity O(N) to quantum complexity O(N/2). We present SATURNIN’s novel quantum structure resource calculation, implementation, and security hardness evaluation based on the NIST proposal for post-quantum security strength. Our proposed quantum circuit implementation requires 872 qubits. As per our evaluation, increasing the number of iterations in this algorithm doesn’t adequately increase its security hardiness against quantum assaults on the IBM QISKIT quantum computer simulator. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Grover’s algorithm Post-quantum Quantum computing SATURNIN block cipher

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：