检索结果-内蒙古大学图书馆

OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Ni, Liwei Wang, Rui Liu, Miao Meng, Xingyu Lin, Xiaoze Liu, Junfeng Luo, Guojie Chu, Zhufei Qian, Weikang Yang, Xiaoyan Xie, Biwei Li, Xingquan Li, Huawei Chinese Academy of Sciences State Key Lab of Processors Institute of Computing Technology Beijing100190 China Pengcheng Laboratory Shenzhen518055 China University of Chinese Academy of Sciences Beijing101408 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China University of Chinese Academy of Sciences School of Computer Science and Technology Beijing100049 China Peking University School of Computer Science Center for Energy-Efficient Computing and Applications Beijing100871 China Ninbo University Faculty of Electrical Engineering and Computer Science Ninbo315211 China Shanghai Jiao Tong University University of Michigan-Shanghai Jiao Tong University Joint Institute MoE Key Laboratory of Artificial Intelligence Shanghai200240 China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou311121 China

This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning (ML) applications within the logic synthesis process. Previous dataset generation flows were tailored for specific tasks or lacked integrated ML capabilities. While OpenLS-DGF supports various machine learning tasks by encapsulating the three fundamental steps of logic synthesis: Boolean representation, logic optimization, and technology mapping. It preserves the original information in both Verilog and ML-friendly GraphML formats. The Verilog files offer semi-customizable capabilities, enabling researchers to insert additional steps and incrementally refine the generated dataset. Furthermore, OpenLS-DGF includes an adaptive circuit engine that facilitates the final dataset management and downstream tasks. The generated OpenLS-D-v1 dataset comprises 46 combinational designs from established benchmarks, totaling over 966,000 Boolean circuits. OpenLS-D-v1 supports integrating new data features, making it more versatile for new tasks. This paper demonstrates the versatility of OpenLS-D-v1 through four distinct downstream tasks: circuit classification, circuit ranking, quality of results (QoR) prediction, and probability prediction. Each task is chosen to represent essential steps of logic synthesis, and the experimental results show the generated dataset from OpenLSDGF achieves prominent diversity and applicability. The source code and datasets are available at https://***/Logic-Factory/ACE/blob/master/OpenLS-DGF. © 1982-2012 IEEE.

关键词： information management

来源：评论

学校读者我要写书评

暂无评论

A WiVi Based IoT Framework for Detection of Human Trafficking Victims Kept in Hideouts 1

引用

5th International Conference on Internet of Things, ICIOT 2020, held as part of the Services Conference Federation, SCF 2020

作者： Samanta, Sidharth Singhar, Sunil Samanta Gandomi, A.H. Ramasubbareddy, Somula Sankar, S. Department of Computer Science and Applications Utkal University BhubaneswarOdisha India Department of Computer Science and Engineering IIIT Bhubaneswar BhubaneswarOdisha India Faculty of Engineering and Information Technology University of Technology Sydney Ultimo Australia Department of Information Technology VNRVJIET HyderabadTelangana500090 India Department of Computer Science Engineering Sona College of Technology SalemTamilnadu636005 India

ISBN: (数字)9783030596156

ISBN: (纸本)9783030596149

Human trafficking is the trade of humans for the purpose of forced labor, sexual slavery, or commercial sexual exploitation for the trafficker or others. The traffickers often trick, defraud, or physically force victims into selling sex and forced labor. In others, victims are lied to, assaulted, threatened, or manipulated into working under inhumane, illegal, or otherwise unacceptable conditions. According to the estimation of the International Labor Organization, there are more than 40.3 million victims of human trafficking globally. It is a threat to the Nation as well as to humanity. There have been many efforts by government agencies & NGOs to stop human trafficking and rescuing victims, but the traffickers are getting smarter day by day. From multiple sources, it is observed that the traffickers generally hide humans in hidden rooms, sealed containers, and boxes disguised as goods. This congestion results in Critical mental and physical damages in some cases. It is practically impossible to physically go and check each box, containers or rooms. So in this paper, we propose an Wireless Vision based IoT framework, which uses the reflection of WiFi radio waves generated by WiFi to detect the presence of humans inside a cement or metal enclosure from outside. © 2020, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Hybrid GRU-Transformer Model for Financial Forecasting and Risk Management

A Hybrid GRU-Transformer Model for Financial Forecasting and...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Rahul Pradhan Malik Bader Alazzam Sarika Keswani Narinder Kumar Bhasin Nadhema Ahmed Jaff S Muthuperumal Department of Computer Engineering & Applications GLA University Mathura India Faculty of Information Technology Jadara University Irbid Jordan Symbiosis Centre for Management Studies Nagpur (SCMS Nagpur) Symbiosis International (Deemed University) Pune India Indian Institute of Banking and Finance Mumbai India Department of Business Administration College of Administrative and Financial Sciences Knowledge University Erbil Iraq Department of Mathematics K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Financial sector demands precise forecasting models to mitigate risk and optimize asset management. This study presents a novel Hybrid GRU-Transformer Model that integrates Gated Recurrent Units (GRUs) for capturing local temporal patterns and the Transformer T5 architecture for modeling global dependencies. Financial datasets sourced from Kaggle, including stock prices and trading volumes, were preprocessed through normalization and categorical encoding, followed by an 80:20 dataset split for training and testing. The proposed model outperformed existing methods such as ARFIMA-LSTM and EMD-CNN-LSTM, achieving superior metrics, including a Mean Squared Error of 0.08 and an $\mathbf{R^{2}}$ of 0.95. Results underline the model's accuracy and robustness in predicting financial risks and trends. By enhancing predictive performance and risk management strategies, this model addresses the dynamic complexities of financial markets. Future research will explore its adaptability across diverse instruments and markets to further its application in real-time forecasting scenarios. The system is implemented using Python integrated with MATLAB.

关键词： Training Adaptation models Predictive models Transformers Robustness Real-time systems Risk management Integrated circuit modeling Forecasting Testing

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Different Cryptocraphy Techniques and the Role of Coding and information Theories in Overcoming Security Threats

An Analysis of Different Cryptocraphy Techniques and the Rol...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Mohammed Shakeel A. Sirisha Ankita Joshi R. Ushasree M. Vaishnavi Devvret Verma Faculty of Computer Applications Invertis University Bareilly Rajau Paraspur Uttar Pradesh Department of Information technology Vignan’s Institute of information technology (Autonomous) Visakhapatnam Andra Pradesh Uttaranchal University Dehradun Uttarakhand India Department of MCA Dayananda Sagar Academy of Technology & Management VTU CSE Bannari Amman Institute of Technology Erode Tamil Nadu India Department of Biotechnology Graphic Era Deemed to be University Dehradun Uttarakhand India

In order to maintain the privacy and secrecy of information, security is essential. There are numerous encryption techniques available to safeguard data while it is being transmitted or stored. Communication security benefits greatly from encryption algorithms. These encryption strategies vary with regards to their solidarity, snappiness, and asset needs (CPU use, memory, and power). This study’s goal is to list the most famous and fascinating calculations as of now being used and to present the ideas of cryptography, cryptography in history, and modern cryptography. This investigation focused on a number of existing cryptography calculations, including DES, IDEA, 3DES, AES, ECC, RSA, homomorphic and blowfish, among others. It was determined that the RSA algorithm takes the longest amount of time to encrypt data, whereas the AES approach uses the fewest text files. We also demonstrated that the AES algorithm decryption is superior to other methods. According to the analytical findings, the AES algorithm is superior to the DES and RSA algorithms. This study recommended further developing a consolidate encipherment calculation, which joins different encipherment calculations in light of every single relevant trademark, to expand the general wellbeing and security of encipherment strategies.

关键词： Privacy Three-dimensional displays information security Trademarks Elliptic curve cryptography Encoding Encryption

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Feature Selection Method Based on Rankability

SSRN

引用

SSRN 2024年

作者： Kong, Lingping Velasquez, Juan D. Perfilieva, Irina Pant, Millie Pan, Jeng-Shyang Snášel, Václav Department of Computer Science VSB-Technical University of Ostrava Ostrava Czech Republic Department of Industrial Engineering University of Chile Santiago Chile Santiago Chile Institute for Research and Applications of Fuzzy Modeling Centre of Excellence IT4Innovations division of The University of Ostrava Ostrava Czech Republic Department of Applied Mathematics and Scientific Computing Indian Institute of Technology Uttarakhand Roorkee247667 India School of Artificial Intelligence Nanjing University of Information Science and Technology China Instituto Sistemas Complejos de Ingeniería Santiago Chile Santiago Chile Faculty of Computer Science and Telecommunications Cracow University of Technology Kraków Poland Mehta Family School of Data Science and Artificial Intelligence Indian Institute of Technology Uttarakhand Roorkee247667 India College of Computer Science and Engineering Shandong University of Science and Technology China

Within the realm of data mining and machine learning, feature selection stands out as an essential technique for dimensionality reduction, presenting both popularity and complexity. Feature selection involves a nuanced trade-off that results in information loss. This distinction underscores the necessity for the development of lightweight, efficient, and practical methods capable of minimizing information loss while executing dimensional reduction. In this paper, we introduce a rankability-based feature selection method. The concept of rankability, proposed in 2019 and similar to the entropy concept, remains relatively unexplored. Our proposed method distinguishes itself by its lightweight complexity, eliminating the need for iterative *** evaluate the effectiveness of our approach, we conducted experiments on forty-one datasets and compared the results with four other algorithms using refined data with 10\%, 30\%, and 50\% feature dimension reduction. The findings reveal that our rankability-based feature selection method consistently outperforms the other four methods across a majority of datasets in terms of accuracy, precision, recall, and F1-macro performance. Specifically, the classification score exceeds 0.9 on accuracy for 50\% feature dimension reduction in twelve datasets, with nine datasets achieving scores over 0.9 in recall, F1-macro, and precision. Overall, our proposed feature selection method demonstrates promising performance. © 2024, The Authors. All rights reserved.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Blockchain Technique to Achieve Secure and Reliable Sharing of IoT Data

引用

computers, Materials & Continua 2020年第10期65卷 87-107页

作者： Bao Le Nguyen E.Laxmi Lydia Mohamed Elhoseny Irina V.Pustokhina Denis A.Pustokhin Mahmoud Mohamed Selim Gia Nhu Nguyen K.Shankar Faculty of Information Technology Duy Tan UniversityDa Nang550000Vietnam Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Faculty of Computers and Information Mansoura UniversityMansoura35516Egypt Department of Entrepreneurship and Logistics Plekhanov Russian University of EconomicsMoscow115093Russia Department of Logistics State University of ManagementMoscow109542Russia Department of Mathematics College of Science&Humanities in AlaflajPrince Sattam bin Abdulaziz UniversityAlaflaj16278Saudi Arabia Graduate School Duy Tan UniversityDa Nang550000Vietnam Department of Computer Applications Alagappa UniversityKaraikudi630003India

In present digital era,an exponential increase in Internet of Things(IoT)devices poses several design issues for business concerning security and *** studies indicate that the blockchain technology is found to be a significant solution to resolve the challenges of data security exist in *** this view,this paper presents a new privacy-preserving Secure Ant Colony optimization with Multi Kernel Support Vector Machine(ACOMKSVM)with Elliptical Curve cryptosystem(ECC)for secure and reliable IoT data *** program uses blockchain to ensure protection and integrity of some data while it has the technology to create secure ACOMKSVM training algorithms in partial views of IoT data,collected from various data ***,ECC is used to create effective and accurate privacy that protects ACOMKSVM secure learning *** this study,the authors deployed blockchain technique to create a secure and reliable data exchange platform across multiple data providers,where IoT data is encrypted and recorded in a distributed *** security analysis showed that the specific data ensures confidentiality of critical data from each data provider and protects the parameters of the ACOMKSVM model for data *** examine the performance of the proposed method,it is tested against two benchmark dataset such as Breast Cancer Wisconsin Data Set(BCWD)and Heart Disease Data Set(HDD)from UCI AI *** simulation outcome indicated that the ACOMKSVM model has outperformed all the compared methods under several aspects.

关键词： Blockchain optimization elliptical curve cryptosystem security ant colony optimization multi kernel support vector machine

来源：评论

学校读者我要写书评

暂无评论

Brain computer Interaction Framework for Speech and Motor Impairment Using Deep Learning

Brain Computer Interaction Framework for Speech and Motor Im...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Abhijit T. Somnathe Iftikhar Aslam Tayubi Pundru Chandra Shaker Reddy Nipun Sharma Vikas Sharma Mannava Yesubabu Electronics and Telecommunication Engineering Smt. Kashibai Navale College of Engineering Pune India Faculty of Computing and Information Technology Rabigh King Abdulaziz University Jeddah Saudi Arabia School of Computer Sicence and Engineering Manipal University Jaipur Jaipur Rajasthan India Electronics and Communication Engineering Presidency University Bangalore Karnataka India School of Computer Science & Applications IIMT University Meerut Uttar Pradesh India Computing Science and Engineering Vardhaman College of Engineering Hyderabad Telangana India

Some people may have trouble communicating with others because of motor and speech difficulties brought on by accidents, strokes, or diseases. Paralyzed people often struggle to communicate their demands, which can make even the simplest tasks challenging. People with disorders like dysarthria and amyotrophic lateral sclerosis may have trouble following conversations. The proposed method for automatic detection of everyday basic desires will help those with dysarthria and quadriplegic paralysis has more fulfilling lives. The device accomplishes this by monitoring brain impulses, which it then converts into either perceptible voice commands or messages that can be delivered to a healthcare provider's smart devices, depending on the user's preferences. The suggested method randomly displays an image of one of six basic requirements while using event-related-potentials(ERPs) detected from the Electroencephalogram (EEG) data to determine which need to fulfill. The dataset utilized for train, test, &validation was built using input from 10 participants. The proposed method had a 96.3|% success rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Module Placement Scheme Using MPC4.5 with Markov Chain Process for Mobile Fog Computing Environment

Module Placement Scheme Using MPC4.5 with Markov Chain Proce...

引用

International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

作者： Rasmita Patro Sudhansu Shekhar Patra Lalbihari Barik Ajaya Dev Prusty Rabindra K. Barik School of Computer Engineering KIIT Deemed to be University Bhubaneswar India School of Computer Applications KIIT Deemed to be University Bhubaneswar India Faculty of Computing and Information Technology in Rabigh King Abdul Aziz University Kingdom of Saudi Arabia

ISBN: (数字)9781728185293

ISBN: (纸本)9781728185309

Mobile Fog computing (MFC) is an elongation to cloud computing in which the processing is performed near the IoT devices. It reduces latency and energy consumption in the system and the idle choice for healthcare applications, smart cities, etc. In MFC, the mobile devices (MDs) select the best fog device (FD) and offload FDs' task. The submitted applications to the system are divided into modules, and the best FD has been selected for the module using the Module Placement C4.5 (MPC45) algorithm. If the MD's power consumption is more than that the power consumption of Wi-Fi, then only offloading has been performed. There are many factors, such as authenticity, confidentiality, availability, capacity, integrity, cost, and speed are used as the decision parameters for selecting the best FD. In the present research paper, a novel module placement scheme has proposed for optimizing the MPC45 with the Markov chain. The proposed approach is compared with the state of art algorithms in terms of power consumption, performance, and response time, which shows that the proposed method of task offloading is better compared to the other existing ones.

关键词： Power demand Smart cities Markov processes Time factors Task analysis Wireless fidelity Edge computing

来源：评论

学校读者我要写书评

暂无评论

A New-fangled Classification Algorithm for Medical Heart Diseases Analysis using Wavelet Transforms

引用

Open Public Health Journal 2024年 17卷

作者： Nayak, Soumya Ranjan Selvarasu, Sivakumar Sripathy, B. Singh, Prabhishek Diwakar, Manoj Gupta, Indrajeet Ravi, Vinayakumar Mazroa, Alanoud Al School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar 751024 India Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology Kattankulathur Chennai 603203 India Department of Mathematics School of Advanced Sciences Vellore Institute of Technology (VIT) Vellore 632 014 India School of Computer Science Engineering & Technology Bennett University Greater Noida India CSE Department Graphic Era deemed to be University Uttarakhand Dehradun India Graphic Era Hill University Uttarakhand Dehradun India School of Computer Science & AI SR University Telangana Warangal 506371 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 (PNU) P.O. Box 84428 Riyadh 11671 Saudi Arabia

Background: In this article, the Mixed Mode Database Miner (MMDBM) algorithm is introduced for the classification of data. This algorithm depends on the decision tree classifier, which handles the numerical and categorical attributes. For the experimental analysis in a well-explored heart disease data set collected from the UCI Repository. Aims: Understanding the fundamentals of every classification method and how to apply them to CUDA is the aim of this study. After reviewing the literature, the approach that is most suited is selected for implementing the suggested algorithm in the MMDM classifier along with the discrete wavelet decomposition. From this experimental analysis, we observed that the use of the wavelet technique in the MMDBM algorithm provides better and more accurate results for data classification. Objective: The main objective of the manuscript is to identify the early stage of heart attack that was caused either by smoking, smoking with tobacco, or non-smoking. Additionally, this study aims to check the validity of the MMDM classifier along with the discrete wavelet decomposition. From this experimental analysis, we observed that the use of the wavelet technique in the MMDBM algorithm provides better and more accurate results for data classification. Methods: In the modern digital world today, data has a major impact on everyone’s life. Every database contains a lot of information hidden either in the form of numerical data, characteristic data, or a mixture of both. Moreover, to accurately decode every dataset, a fast and efficient classifier is essential.. Moreover, by using this hybrid technique based on both MMDBM and Wavelet processes, it compresses the data with minimum storage capacity. Results: The experimental results are compared with the classified data to wavelet data output. These results prove that our presented technique is more prominent and robust in an analysis of heart diseases. Conclusion: This algorithm is based on a decision

关键词： Big data Classification Algorithms Data mining Haar wavelets Healthcare Tobacco

来源：评论

学校读者我要写书评

暂无评论

An Effective Evaluation of SONARS using Arduino and Display on Processing IDE

An Effective Evaluation of SONARS using Arduino and Display ...

引用

computer, Power and Communications (ICCPC), International Conference on

作者： R.G. Vidhya B Kezia Rani Kamlesh Singh D. Kalpanadevi Jyothi Prasad Patra T. Aditya Sai Srinivas Department of ECE HKBK College of Engineering Bangalore India Department of information Technology Vasavi College of Engineering Hyderabad India Department of Computer Science and Engineering GraphicbEra Hill University Dehradun India Department of Computer Applications Kalasalingam Academy of Research and Education Krishnan koil Tamilnadu India Faculty of Electrical Odisha university of Technology and Research OUTR Bhubaneswar odisha India Department of Computer Science and Engineering G. Pulla Reddy Engineering college Kurnool Andhra pradesh India

Sonars are used by SAR teams to identify and retrieve submerged objects like cars and planes. In the event of extensive searches, where sonar operators may become fatigued and overlook the possible item, strategies for the programmable characterisation or identification of the object may be invaluable. Current sonar technology may be used for more than just navigation; it can also be used to locate fish, townships, and create maps of the ocean floor. The power of the transmitter, the quality of the transducer, the sensitivity of the collector, and the design of the acoustic correspondence are the four key aspects that affect the appearance of a sonar system. While current sonar frameworks have limited functionality-such as a two-layered screen and a view of less than 360 degrees of the surrounding environment improved sonar frameworks with a three-layered screen, joined to new PC frameworks, and a 360-degree view of the surrounding environment are on the horizon. Companies now face substantial challenges while attempting oceanic research and inspections. To keep up with the requirements of current maritime businesses, better underwater devices and more precise estimations are always being created and modified.

关键词： Transducers Sensitivity Ultrasonic variables measurement Transmitters Sonar Sonar navigation Acoustics

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：