检索结果-内蒙古大学图书馆

22nd IEEE International Symposium on parallel and Distributed Processing with Applications, ISPA 2024

作者： Feng, Hao Xu, Xinren Chen, Lin Li, Jie Hainan University School of Computer Science and Technology Haikou570100 China South China Normal University School of Software Foshan528225 China

ISBN: (纸本)9798331509712

With the rise of cloud computing and artificial intelligence, the resource utilization rate of data centers is soaring, resulting in significant power consumption and electricity costs. Traditional inappropriate resource placement methods cannot match the local electricity pricing form well, leading to data centers consuming a large amount of energy and requiring large electricity bills. In this paper, firstly, this paper study a global electricity-cost-minimization model, which takes into account both IT and non-IT resource usage. Secondly, We introduce a two-step algorithm (SAT-GAV) to solve the NP-hard TVMP problem. The first step of SAT-GAV uses the simulated annealing algorithm to arrange task placements to reduce electricity costs. In the second step, we uses the greedy algorithm to place virtual machines by leveraging of minimizing data center electricity costs. We conduct extensive experiments to evaluate the effectiveness of SAT-GAV. And compare the performance of our SAT-GAV with other state-of-art algorithms. Experimental results indicate that, compared to other algorithms, our VMP strategy can reduce the electricity costs by 8.9% compared to the best-performing PDGA algorithm and by 33.34% compared to the earlier XINT-GA algorithm. © 2024 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Pakistan Rice Plant Disease Detection: A Highly Effective Pre-Trained CNN Model 25

Enhancing Pakistan Rice Plant Disease Detection: A Highly Ef...

引用

25th International Multi Topic Conference, INMIC 2023

作者： Arshed, Muhammad Asad Akram, Zeeshan Bajwa, Haroon Zahid Azeem, Muhammad Huzaifa Dawood, Muhammad Ahmad Riaz, Faisal Department of Software Engineering Lahore Pakistan Department of Computer Science Lahore Pakistan Department of Infs Lahore Pakistan

ISBN: (纸本)9798350317701

Rice, a crucial global food source, faces numerous challenges impacting its quality and quantity. Pakistan is a significant rice producer and needs more agricultural technological advancements. Conventional disease detection methods for rice plants are time-consuming and ineffective. However, recent progress in agricultural technology, particularly machine learning & deep learning, holds great promise for improved disease identification. In this study, different datasets were considered for preparing a dataset that is specifically related to Pakistan's environmental rice diseases. This study uses a prepared dataset to train the proposed fine-tuned ResNet101V2 model and for the robustness of the proposed model comparison with ResNet101, ResNet50V2, and DenseNet121 also performed in this study. Among the models evaluated, ResNet101V2 exhibited superior performance with a test accuracy of 81%, demonstrating high accuracy in identifying six distinct classes, including five rice leaf diseases (Leaf Blight, Leaf Smut, Hispa, Leaf Blast, and Brown Spot) and one healthy category specific to Pakistan environments. This study represents a significant advancement toward developing more efficient disease detection and management systems in rice farming, ultimately leading to reduced financial losses and improved agricultural practices. © 2023 IEEE.

关键词： Agricultural technology

来源：评论

学校读者我要写书评

暂无评论

Attention-Based BiLSTM for Malware Family Classification 23

Attention-Based BiLSTM for Malware Family Classification

引用

4th International Conference on Computing, Networks and Internet of Things, CNIOT 2023

作者： Liao, Yonglin Luktarhan, Nurbol Wang, Yue Chen, Qinlin School of Software Xinjiang University Urumqi China College of Information Science and Engineering Xinjiang University Urumqi China

ISBN: (纸本)9798400700705

Due to API calls being the most prominent characteristic of malicious software, this paper uses Windows API call sequences as features to classify malware families. A BiLSTM model based on attention mechanism is proposed. First, to address the problem of significantly different sample lengths, an algorithm for preprocessing Windows API call sequences of different lengths is improved, referred to as RD in this paper. RD can effectively remove duplicate APIs and reduce the length of API call sequences, and experimental results show that this preprocessing algorithm can improve the classification accuracy. Then, considering the temporal nature of API calls, this paper uses a BiLSTM model that can perceive contextual information and integrates an attention mechanism to improve the model's performance. Experimental results show that the attention-based BiLSTM model outperforms other models. © 2023 ACM.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Focus-Driven Contrastive Learning for Medical Question Summarization

arXiv

引用

arXiv 2022年

作者： Zhang, Ming Dou, Shuai Wang, Ziyang Wu, Yunfang MOE Key Laboratory of Computational Linguistics Peking University China School of Software and Microelectronics Peking University China School of Computer Science Peking University China

Automatic medical question summarization can significantly help the system to understand consumer health questions and retrieve correct answers. The Seq2Seq model based on maximum likelihood estimation (MLE) has been applied in this task, which faces two general problems: the model can not capture well question focus and and the traditional MLE strategy lacks the ability to understand sentence-level semantics. To alleviate these problems, we propose a novel question focus-driven contrastive learning framework (QFCL). Specially, we propose an easy and effective approach to generate hard negative samples based on the question focus, and exploit contrastive learning at both encoder and decoder to obtain better sentence-level representations. On three medical benchmark datasets, our proposed model achieves new state-of-the-art results, and obtains a performance gain of 5.33, 12.85 and 3.81 points over the baseline BART model on three datasets respectively. Further human judgement and detailed analysis prove that our QFCL model learns better sentence representations with the ability to distinguish different sentence meanings, and generates high-quality summaries by capturing question focus. © 2022, CC0.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

VDDL: A Deep Learning-Based Vulnerability Detection Model for Smart Contracts 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Jiang, Fan Cao, Yuanlong Xiao, Jianmao Yi, Hui Lei, Gang Liu, Min Deng, Shuiguang Wang, Hao School of Software Jiangxi Normal University Nanchang China College of Computer Science Zhejiang University Hangzhou China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

With the widespread use of smart contracts in various fields, the research on smart contract vulnerability detection has increased yearly. Most of the previous research work is based on symbol detection and comparison with expert-defined error patterns to analyze the possible vulnerabilities of smart contracts. The accuracy and performance of such methods are generally low. In response to this problem, this paper proposes an efficient smart contract vulnerability detection model VDDL (Vulnerability Detection Based on Deep Learning). VDDL uses a multi-layer bidirectional Transformer architecture as the model architecture, involving a multi-head attention mechanism and a masking mechanism. A multi-head attention mechanism is applied in the encoder-decoder layer. The masking mechanism randomly masks the input tokens and combined with the context to predict the masked tokens, a deep bidirectional representation for training is realized. Furthermore, VDDL incorporates CodeBERT, a large bimodal pre-trained model for natural and programming languages, to improve training performance. We collected 47,038 smart contracts as datasets for model training and testing. In the end, the accuracy of VDDL reached 92.35%, the recall reached 81.43%, and the F1-score reached 86.38%, which can efficiently detect possible loopholes in smart contracts. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

On Global Controllability of Nonlinear Composite Systems

On Global Controllability of Nonlinear Composite Systems

引用

第43届中国控制会议

作者： Huiling GU Yimin SUN School of Mathematics Sun Yat-sen University Guangdong Province Key Laboratory of Computational Science School of MathematicsSun Yat-sen University

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

In this paper,we study the global controllability of the parallel,the tandem and the feedback connection composite systems which are formed by two planar globally controllable nonlinear systems. Some sufficient conditions are obtained for the global controllability of the tandem and the feedback connection composite systems and some necessary conditions are obtained for the global controllability of the parallel connection composite systems.

关键词： Global controllability composite systems nonlinearity planar systems

来源：评论

学校读者我要写书评

暂无评论

Duplicate Data Elimination Optimization Strategy Based on Edge Service Management

Duplicate Data Elimination Optimization Strategy Based on Ed...

引用

Cyber science and Technology Congress (CyberSciTech), IEEE

作者： Yonglin Pu Xiaolong Xu Lianyong Qi Wanchun Dou Jiong Yu Ziyang Li School of Software Nanjing University of Information Science and Technology Nanjing China College of Computer Science and Technology China University of Petroleum (East China) Dongying China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Software Xinjiang University Urumqi China

ISBN: (数字)9798331532093

ISBN: (纸本)9798331532109

Due to the absence of duplicate data elimination technologies in edge architectures, the interaction experience with mobile users suffers. In response to this issue, an optimized strategy for duplicate data elimination, based on edge service management (DDE-ESM), is proposed. Initially, a model for the placement of edge devices and a model for the collection of cache data are established. Subsequently, a caching device placement algorithm is designed; this not only undertakes comprehensive data collection and cache storage but also forms the basis for querying duplicate data within the architecture. Following this, a model for querying duplicate data in the cache is created, identifying duplicates by segmenting data blocks and generating data fingerprints via hash functions. Ultimately, a model for eliminating duplicate data at the edge is developed, which leads to the creation of an algorithm that rationally deletes duplicate data in accordance with device resource constraints. Experimental results indicate that this optimization strategy for duplicate data elimination not only saves resources on edge devices but also significantly enhances data management efficiency and the utilization of architectural resources.

关键词： Hash functions Fingerprint recognition Data collection Data models Cache storage Optimization

来源：评论

学校读者我要写书评

暂无评论

POPA: Expressing High and Portable Performance across Spatial and Vector Architectures for Tensor Computations 24

POPA: Expressing High and Portable Performance across Spatia...

引用

32nd ACM International Symposium on Field-Programmable Gate Arrays, FPGA 2024

作者： Hao, Xiaochen Rong, Hongbo Zhang, Mingzhe Sun, Ce Jiang, Hong Liang, Yun Peking University China Parallel Computing Lab Intel United States Tsinghua University China University of Science and Technology of China China Intel United States Peking University & Beijing Advanced Innovation Center for Integrated Circuits China

ISBN: (纸本)9798400704185

This paper aims at high and portable performance for tensor computations across spatial (e.g., FPGAs) and vector architectures (e.g., GPUs). The state-of-the-art usually address performance portability across vector architectures (CPUs and GPUs). However, they either miss FPGAs or do not achieve high performance. Without a common architectural abstraction, they program and optimize spatial and vector devices separately, causing low portability. We propose a unified programming framework, POPA, which achieves portability via architectural abstraction and performance via specialization. A parallel dataflow machine is proposed as a unified, abstract hardware target that hides differences of concrete architectures. The machine consists of software-defined systolic arrays and a tensor-specific cache hierarchy, which captures pipeline parallelism and customizable memories on FPGAs, as well as multithreading parallelism on GPUs. The machine is specified in a unified programming model as two dataflow graphs for scheduling compute and data movement, respectively. A compiler then specializes the abstract machine to exploit the properties of FPGAs and GPUs, bridging the gap between the abstract machine and a concrete architecture. We evaluate POPA on several Intel FPGAs and GPUs with high-profile tensor kernels, and this is the first system that achieves >=80% performance of expert-written code or machine peak across architectures, to the best of our knowledge. © 2024 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

A Priori Lane Selection Strategy for Reinforcement Learning of Dynamic Expressway Tolling

A Priori Lane Selection Strategy for Reinforcement Learning ...

引用

2023 International Conference on Pattern Recognition, Machine Vision and Intelligent Algorithms, PRMVIA 2023

作者： Zhang, Xi Wang, Wei Chen, Jing Yunnan University School of Software Kunming China Yunnan University School of Information Science and Engineering Kunming China

ISBN: (纸本)9798350346596

Dynamic tolling of toll roads is a way to dynamically adjust the toll rates according to the changing road traffic conditions in order to alleviate traffic congestion and improve commuting efficiency. Aiming at the dynamic toll collection problem of Chinese expressway, we design a reinforcement learning simulation environment for China's expressway network and propose a reinforcement learning dynamic toll model based on a priori lane selection strategy that adapts to the characteristics of the network and travelers' travel habits. Experiments show that the reinforcement learning-based dynamic tolling can increase the total revenue by more than 10% compared with the fixed- rate tolling scheme and keep the congestion rate at a low level. In addition, the ablation experiments demonstrate that the priori knowledge-based lane selection model can better weigh the "total revenue", "system throughput"and "total system travel time"of the optimized road network under the joint optimization objective © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Handwriting Analysis for Classification of Human Personality 2

Handwriting Analysis for Classification of Human Personality

引用

2nd IEEE International Conference on Advances in Information Technology, ICAIT 2024

作者： Bipin Nair, B.J. Koushik, K.S. Suraj, Ankitha Nithya, K. Venkitesan, Pranav Department of Computer Science Amrita School of Computing Amrita Vishwa Vidyapeetham Mysuru India Software Engineer Frontend Zenloop GMBH Berlin Germany

ISBN: (纸本)9798350383867

This paper explores handwriting analysis for personality classification, leveraging machine learning algorithms like KNN, SVM, Naive Bayes, Decision Trees, and Random Forest. We have Extracted features such as stroke pressure, letter size, slant, and spacing from a diverse dataset, the study compares algorithm performance, showing promising results in accuracy, precision, recall, and F1-score. Implications for psychology, machine learning, and handwriting analysis are discussed. In our study, the results show that models such as SVM achieved over 95% accuracy, followed closely by KNN with more than 94% accuracy, indicating significant progress in data analysis and Classification modeling. © 2024 IEEE.

关键词： Random forests

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：