检索结果-内蒙古大学图书馆

Sustainable Computing and Data Communication Systems (ICSCDS), International Conference on

作者： Amit Kumar Mishra Neha Tripathi Musheer Vaqur Sugandha Sharma Dept. of Computer Science & Engineering Graphic Era Hill University Dehradun Uttarakhand India Dept. of Computer Science & Engineering Graphic Era (Deemed to be University) Dehradun Uttarakhand India Department of Computer Science & Engineering Uttaranchal Institute of Technology Uttaranchal University Dehradun Uttarakhand India School Of Computer Science UPES Bidholi Dehradun Uttarakhand India

The Internet of Things (IoT) has a significant impact on the transportation industry. Autonomous vehicles (AVs) were created to make daily activities easier by hauling goods, distributing packages, and easing traffic. The AVs had a wide range of uses and comprised land vehicles, aerial vehicles, and maritime vehicles. The Cyber Security (CS) enabled data transfer autonomous driving was set up by them to facilitate the solution of this challenge. A network acts as the mediator, downloading data of the transmitter to the autonomous car. For additional safety, the CS -based method Advanced Encryption Standard (AES) is involved to decrypt the data, which is transferable to cypher text. The encryption content could be deciphered by the secret key which is given by the transmitter to the peculiar AV. Customized particle swarm efficiency would be used to modify a conventional neural network. The researchers proposed product’s final stage should be to decrypt the document using dual encryption technology. After the dual cryptography, steganography techniques are used to improve the retention safety of the proposed solution. Their proposed approach was implemented in the Java work area using Internet simulation.

关键词： Steganography Transmitters Transportation industry Machine learning Safety Encryption Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Can Large Language Models Predict the Outcome of Judicial Decisions?

arXiv

引用

arXiv 2025年

作者： Kmainasi, Mohamed Bayan Shahroor, Ali Ezzat Al-Ghraibah, Amani Computer Science and Engineering Dept. Qatar University Doha Qatar School of Computing and Data Science OUC in partnership with LJMU Doha Qatar Biomedical Engineering Dept. Jordan University of Science and Technology Irbid Jordan

Large Language Models (LLMs) have shown exceptional capabilities in Natural Language Processing (NLP) across diverse domains. However, their application in specialized tasks such as Legal Judgment Prediction (LJP) for low-resource languages like Arabic remains underexplored. In this work, we address this gap by developing an Arabic LJP dataset, collected and preprocessed from Saudi commercial court judgments. We benchmark state-of-the-art open-source LLMs, including LLaMA-3.23B and LLaMA-3.1-8B, under varying configurations such as zero-shot, one-shot, and fine-tuning using LoRA. Additionally, we employed a comprehensive evaluation framework that integrates both quantitative metrics (such as BLEU, ROUGE, and BERT) and qualitative assessments (including Coherence, Legal Language, Clarity, etc.) using an LLM. Our results demonstrate that fine-tuned smaller models achieve comparable performance to larger models in task-specific contexts while offering significant resource efficiency. Furthermore, we investigate the impact of fine-tuning the model on a diverse set of instructions, offering valuable insights into the development of a more human-centric and adaptable LLM. We have made the dataset, code, and models publicly available to provide a solid foundation for future research in Arabic legal NLP1 Copyright © 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

Echo State Network Control Based Power Quality Enhancement in Grid-Interactive Solar Photovoltaic System

Echo State Network Control Based Power Quality Enhancement i...

引用

2023 IEEE International Conference on Energy Technologies for Future Grids, ETFG 2023

作者： Morey, Meghraj Gupta, Nitin Garg, Man Mohan Kumar, Ajay Gali, Vijay Kumar Malaviya National Institute of Technology Department of Electrical Engineering Jaipur302 017 India Nazarbayev University Dept. of Electrical and Computer Engineering Nur-Sultan010 000 Kazakhstan Punjab Engineering College Department of Electrical Engineering Chandigarh160 012 India

ISBN: (纸本)9781665471640

This study applies an echo-state network (ESN)-based technique to enhance the utility power quality performance in a grid-integrated solar photovoltaic (PV) system supplying a specially non-linear load. The proposed system serves multiple functionalities, such as improvement of power quality parameters, which includes harmonics suppression, load balancing, neutral current compensation, source reactive power reduction and correcting low power factor, simultaneously managing the solar PV power generated for supplying the load. The proposed control algorithm extracts the contaminated source currents' active and non-active harmonic free fundamental weight components. These weights are further used to estimate the source current reference signals and generate the switching signals for the voltage source inverter (VSI) that integrates the grid with the solar PV system. A small-scale two-stage PV power unit linked with a grid is developed in the laboratory. A DSP-dSPACE 1104 controller is used to implement the ESN controller for the grid-integrated PV system. In a three-phase, four-wire distribution system, the suggested algorithm has been evaluated and demonstrated to effectively address multiple power quality issues while managing solar energy. © 2023 IEEE.

关键词： echo state network grid-integrated PV system harmonics power quality solar photovoltaic (PV) system

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Effect of Nickel Tetraphenylporphyrin Doping on the Crystallite Parameters of ZnO Nanoparticles

Analyzing the Effect of Nickel Tetraphenylporphyrin Doping o...

引用

2022 International Conference on Innovations in science, engineering and technology, ICISET 2022

作者： Chowdhury, Md Al Saeid Hossain, Amran Islam, Mohammad Rafiqul Alam, M. Shafiul Soga, Tetsuo Choudhury, Md. Shamimul Haque International Islamic University Chittagong Dept. of Electrical and Electronic Engineering Chattogram Bangladesh Manarat International University Dept. of Computer Science and Engineering Dhaka Bangladesh King Fahad University of Petroleum and Minerals Dept. of Electrical and Electronic Engineering Dhahran Saudi Arabia Nagoya Institute of Technology Dept. of Electrical and Mechanical Engineering Nagoya Japan

ISBN: (纸本)9781665483971

In this study, we report on crystallite parameters of Zinc Oxide nanoparticles doped with different concentrations of Nickel tetraphenylporphyrin. The films were made by dr. blade coating method and a hot compression technique. Physical characteristics such as crystal size and strain were evaluated more unerringly for all of the XRD reflection peaks resembling to the wurtzite hexagonal phase of ZnO using the Halder Wagner, modified Scherrer method, the SSP and Wagner Agua technique. The results indicate that the mean NiTPP doped ZnO crystalize size and lattice strain determined by all the methods were very interconnected. SSP and Wagner-Agua shows more accurate results than other strategies. Lattice strain decreases and crystallite size increases with increase in doping percentage. © 2022 IEEE.

关键词： X ray diffraction

来源：评论

学校读者我要写书评

暂无评论

NPC Behavior in Games Using Unity ML-Agents: A Reinforcement Learning Approach

NPC Behavior in Games Using Unity ML-Agents: A Reinforcement...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Revat Meshram Sachith Krishna Omkaresh Kulkarni Rutuja Rajendra Patil Gagandeep Kaur Shruti Maheshwari Dept. of Computer Science Engineering (Artificial Intelligence and Machine Learning) Vishwakarma Institute of Information Technology Pune India Symbiosis Institute of Technology Pune Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

Machine learning is having a significant impact on video games, from speeding up the development of new games to the development of new methods in gaming. This study discusses the impact of using ML models in the development and improvement of video games. Examples cited in this paper relate to the ways in which NPCs behave. With the aid of Unity's ML-Agents toolkit, developers can create NPCs that respond to different strategies in real time. This makes the games more exciting and complex. The paper also outlines the possibilities of single-player games, such as first-person shooters and a role-playing game, to notice NPC behavior during the gameplay. In these gaming styles, RL frameworks can be applied to NPCs to enable them to learn and adapt to the environment to create an interactive experience for the player. The conclusions put an emphasis on the evolution of video games with the advent of ML tools; as predicted, NPC behavior becomes more intuitive and less expected.

关键词： Industries Procedural generation Automation Role playing games Games Reinforcement learning Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Two-Stage Reversible Data Hiding in Encrypted Images using Prediction Error Expansion

Adaptive Two-Stage Reversible Data Hiding in Encrypted Image...

引用

International Conference on Secure Cyber Computing and Communication (ICSCCC)

作者： Ankur Rajeev Kumar Ajay K Sharma Dept. of Computer Science and Engg. Delhi Technological University Delhi India Dept. of Computer Science and Engg. National Institute of Technology Delhi India

Over the past few years, reversible data hiding in encrypted images (RDHEI) has gained traction a popular method for securely hiding sensitive data within encrypted images. However, the method has its own limitations, as it cannot directly employ existing reversible data hiding (RDH) methods that exploit the spatial correlation of natural images, because of the high entropy of the encrypted images. To address this concern, this paper presents a novel adaptive two-stage (ATS)-RDHEI method based on prediction error(PE) expansion to enhance security and adaptability across a range of applications. The image encryption procedure entails transforming the image into two images based on bit-plane division, followed by block scrambling, pixel shuffling, and encryption while maintaining the correlation of the blocks. In the data hiding phase, a two-stage embedding process hides the secret data while managing probable overflow/underflow issues. Experimental assessments reveal that the ATS-RDHEI method outperforms existing works in terms of EC while maintaining reversibility and visual security. Furthermore, the flexibility and confidentiality of the proposed method is enhanced by its ability to separately extract data and recover images depending on key availability. As a result, the method finds utility in a variety of domains, including secure image storage on the cloud, medical imaging, and multimedia communication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UniFaaS: Programming across Distributed Cyberinfrastructure with Federated Function Serving

arXiv

引用

arXiv 2024年

作者： Li, Yifei Chard, Ryan Babuji, Yadu Chard, Kyle Foster, Ian Li, Zhuozhao Dept. of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Data Science and Learning Division Argonne National Laboratory LemontIL United States Dept. of Computer Science University of Chicago ChicagoIL United States

Modern scientific applications are increasingly decomposable into individual functions that may be deployed across distributed and diverse cyberinfrastructure such as supercomputers, clouds, and accelerators. Such applications call for new approaches to programming, distributed execution, and function-level management. We present UniFaaS, a parallel programming framework that relies on a federated function-as-a-service (FaaS) model to enable composition of distributed, scalable, and high-performance scientific workflows, and to support fine-grained function-level management. UniFaaS provides a unified programming interface to compose dynamic task graphs with transparent wide-area data management. UniFaaS exploits an observe-predict-decide approach to efficiently map workflow tasks to target heterogeneous and dynamic resources. We propose a dynamic heterogeneity-aware scheduling algorithm that employs a delay mechanism and a re-scheduling mechanism to accommodate dynamic resource capacity. Our experiments show that UniFaaS can efficiently execute workflows across computing resources with minimal scheduling overhead. We show that UniFaaS can improve the performance of a real-world drug screening workflow by as much as 22.99% when employing an additional 19.48% of resources and a montage workflow by 54.41% when employing an additional 47.83% of resources across multiple distributed clusters, in contrast to using a single cluster. Copyright © 2024, The Authors. All rights reserved.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Analysis of Decentralized Pharmaceutical Supply Chain: A Systematic Review

Analysis of Decentralized Pharmaceutical Supply Chain: A Sys...

引用

Artificial Intelligence and Smart Communication (AISC), International Conference on

作者： Prakhar Patel Hitanshu Samantaray Rahul Mansharamani Deepali Vora Ankur Goyal Anurag Gupta Dept. of Computer Science Symbiosis Institute of Technology Symbiosis International Deemed University Pune India Dept. of Computer Science G.L. Bajaj Institute of Technology and Management Greater Noida India

Supply chain optimization has recently emerged as a key research area in process operations and management. There has been a great deal of research done on facility sites and layouts, inventory and distribution planning, capacity and production planning, and complex scheduling. This information only briefly and infrequently addresses issues unique to the pharmaceutical sector. Moreover, effective supply chain management is a problem in any industry, but there is added complexity and risk in healthcare due to the direct impact that a supply chain disruption might have on patient security and health outcomes. One solution for improving the security, authenticity, data provenance, and utility of the health supply chain is blockchain technology. Our goal is to present an overview of the potential problems connected with the adoption and use of blockchain in the medical supply chain, with a focus on the public health, medical device, and pharmaceutical supply sectors.

关键词： Drugs Systematics Supply chain management Scalability Supply chains Smart contracts Blockchains

来源：评论

学校读者我要写书评

暂无评论

FogMedX-Transform: A Transformer-Based Task Interoperability Framework for Energy-Efficient Fog-Enabled IoMT

FogMedX-Transform: A Transformer-Based Task Interoperability...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： R Jayakarthik Sajja Suneel Jayendra Gopal Thatipudi V. Jaganraja Minesh Vohra Gopinath D Dept of Computer science Saveetha College of Liberal Arts and Sciences SIMATS Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dept. of Computer Science University of North Texas Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India School of Mechanical Engineering Lovely Professional University Phagwara Department of Computer Science Kristu Jayanti College (Autonomous) Bengaluru Karnataka India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The increasing speed of Internet of Medical Things (IoMT) development requires framework approaches that secure, efficient, and scalable for healthcare data management. The study presents FogMedX-Transform as a Transformer-based task interoperability framework purposebuilt for energy-efficient fog-enabled IoMT systems. A customized Transformer design utilizing multi-head selfattention allows the framework to deliver timely critical healthcare data processing alongside optimized energy usage. This model demonstrated a 98.7% task interoperability success rate coupled with a 97.5% anomaly detection accuracy that exceeded results from conventional models based in fog environments and the cloud. The framework improved performance through latency reduction between 50% and 70% and energy consumption minimization reached between 25% to 40% thus proving its effectiveness in resource administration. The scalability tests proved steady system functionality when dealing with different device quantities and built-in security features blocked data breaches and had a false positive rate of 2.3% during testing. FogMedX-Transform demonstrates the capability for healthcare transformation through its union of fog computing and deep learning technology integration according to test results.

关键词： Deep learning Performance evaluation Internet of Medical Things Data breach Transformers Data processing Energy efficiency Real-time systems Interoperability Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Current Sensorless Deadbeat Predictive Control for Permanent-Magnet Synchronous Motor Drives

Current Sensorless Deadbeat Predictive Control for Permanent...

引用

IEEE Student Conference on Electric Machines and Systems

作者： Zhemin Hu Ming Yang Dianguo Xu Dept. of Electrical & Computer Engineering Texas A&M University College Station USA Dept. of Electrical Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350366945

ISBN: (纸本)9798350366952

This paper proposes a current sensorless permanent magnet synchronous motor (PMSM) drive scheme based on deadbeat predictive control in which a space vector pulse modulator is introduced for feedback currents to track reference currents accurately. Current sensors are omitted by replacing actual currents with predicted currents, thus only a position sensor is needed and a low-cost servo system is achieved. PI control is adopted for the speed loop. Simulation comparisons between control with current sensors and current sensorless control under external disturbances or parameter inconsistency are conducted to indicate that the performance of current sensorless control is almost the same as that of control with current sensors when the prediction model is accurate.

关键词： Couplings Measurement errors Magnetic sensors Sensorless control Stators Predictive models Synchronous motors Sensor systems Steady-state Predictive control

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：