检索结果-内蒙古大学图书馆

Information technology (ACIT)

作者： Bambang Dwi Wijanarko Bachtiar Rosilah Binti Hassan Dina Fitria Murad Ridho Bramulya Ihsan Yaya Heryadi Engkos Achmad Kuncoro Eka Julianti Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Master of English Education Graduate School Universitas Terbuka Jakarta Indonesia Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor Malaysia Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Manajemen Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Information System Department Universitas Terbuka Jakarta Indonesia

This research is ongoing research into the student learning process which aims to develop artificial intelligence-based technology to calculate essay exam scores automatically, based on the textual proximity of students' answers to the answer key. This research uses an approach based on natural language processing (NLP) and text analysis. Feature extraction was carried out using the BERT model and similarity comparison using the Cosine distance method. Model evaluation was carried out using sensitivity and specificity tests. The model evaluation results show a sensitivity of 98.21%, which means this assessment model is able to detect positive cases well.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The State of AI-Empowered Backscatter Communications: A Comprehensive Survey

TechRxiv

引用

TechRxiv 2023年

作者： Ahmed, Manzoor Hussain, Touseef Ali, Khurshed Mirza, Muhammad Ayzed Khan, Wali Ullah Ihsan, Asim Xu, Fang Han, Zhu The School of Computer and Information Science Institute for AI Industrial Technology Research Hubei Engineering University Xiaogan City432000 China The with College of Computer Science and Technology Qingdao University Qingdao266071 China The DTU Compute Technical University of Denmark Denmark The BUPT-QMUL EM Theory and Application International Research Lab Beijing University of Posts and Telecommunications Beijing100876 China University of Luxembourg Luxembourg City1855 Luxembourg The School of Computer Science and Electronic Engineering Bangor University BangorLL57 1UT United Kingdom The University of Houston TX77004 United States The Department of Computer Science and Engineering Kyung Hee University Seoul Korea Republic of

The Internet of Things (IoT) is undergoing significant advancements, driven by the emergence of Backscatter Communication (BC) and Artificial Intelligence (AI). BC is an energy-saving and cost-effective communication method where passive backscatter devices communicate by modulating ambient Radio-Frequency (RF) carriers. AI has the potential to transform our way of communicating and interacting and represents a powerful tool for enabling the next generation of IoT devices and networks. By integrating AI with BC, we can create new opportunities for energy-efficient and low-cost communication and open the door to a range of innovative applications that were previously not possible. This paper brings these two technologies together to investigate the current state of AI-powered BC. We begin with an introduction to BC and an overview of the AI algorithms employed in BC. Then, we delve into the recent advances in AI-based BC, covering key areas such as backscatter signal detection, channel estimation, and jammer control to ensure security, mitigate interference, and improve throughput and latency. We also explore the exciting frontiers of AI in BC using B5G/6G technologies, including backscatter-assisted relay and cognitive communication networks, backscatter-assisted MEC networks, and BC with RIS, UAV, and vehicular networks. Finally, we highlight the challenges and present new research opportunities in AI-powered BC. This survey provides a comprehensive overview of the potential of AI-powered BC and its insightful impact on the future of IoT. © 2023, CC BY.

关键词： Backscattering

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Low-Power Wireless MEMS Lead-Free Piezoelectric Accelerometer System

引用

IEEE Transactions on Instrumentation and Measurement 2023年 72卷

作者： Li, Cheng-Ying Chen, Ze-Hui Kao, Hsueh-Yu Chang, Sheng-Kai Hsiao, Po-Yu Huang, Yen-Hsiang Huang, Yu-Chieh Chu, Sheng-Yuan Wei, Chia-Ling Liu, Yun-Hui Cheng, Kuang-Wei Tsai, Cheng-Che National Cheng Kung University Department of Electrical Engineering Tainan701 Taiwan National Cheng Kung University Nano-Integrated-Circuit Engineering Program Tainan701 Taiwan Southern Taiwan University of Science and Technology Department of Mechanical Engineering Tainan71005 Taiwan National Cheng Kung University College of Electrical Engineering & Computer Science Department of Electrical Engineering Tainan701 Taiwan Tung Fang Design University School of Application Design Department of Digital Game and Animation Design Kaohsiung82941 Taiwan

In this article, a complete 3-D integrated sensing system intended for practical applications was presented on a printed circuit board (PCB) board, starting with lead-free piezoelectric films deposited using an RF sputtering system, an MEMS structure design/simulation, device fabrication, and a signal processing chip design, including charge- to-voltage transformation, signal amplification, 60-Hz noise rejection, and low-power RF wireless transmission chip for remote monitoring. Both the signal processing chips and the RF wireless transmitter chips were manufactured using the Taiwan Semiconductor Manufacturing Company (TSMC) CMOS process. The piezoelectric coefficient d33 was measured as 27.21 pm/V of the proposed ZnO:Li doped Mg (MLZO) films. To meet the frequency specifications of industrial applications, the ring-structure devices with a 7730-Hz resonance frequency were designed using ANSYS simulation software. There was only a 0.39% deviation compared to the simulation results with the actual experimental data. The measurement results of the proposed system showed that the acceleration detection range was approximately 137 mV/ g (p-p). The voltage-controlled oscillator (VCO) adopted in the wireless transmitter chip had a four-leaf clover structure inductor with two symmetrical axes resulting in better suppression of magnetic field radiation. Finally, this system was applied to industrial spindles, and the normal and abnormal operation information of spindles was successfully and wirelessly monitored. © 1963-2012 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Real-Time Medical Diagnostics with Adaptive AI Algorithm

Optimizing Real-Time Medical Diagnostics with Adaptive AI Al...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Zahid Ahmed Abha Pandey Ashish Sharma Anisha Tandon Teena Sujeet Kumar Department of Computer Science and Application Vivekananda Global University Jaipur Rajasthan India Jagannath International Management School Vasant Kunj New Delhi India Department Of Technology JIET Jodhpur Rajasthan India Maharishi University (MUIT) Noida Uttar Pradesh India GL Bajaj Institute of Management Greater Noida Uttar Pradesh India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

Early diagnosis and treatment of disease are key in concentrations done for medical diagnostics. technology is moving fast and with that, there are always new methods for diagnosing patients being created, the improvement of accuracy and speed even in medical diagnostics. Unfortunately, the abundance of data collected by these tools makes it prohibitively difficult to accurately interpret and analyse real-time results. This is where Adaptive AI (Artificial Intelligence) algorithms are useful. This flexibility of adaptive AI systems makes them well-suited to the real-time medical diagnostics that are required. In addition, through the use of machine learning techniques these algorithms are capable to process and analyse large scale datasets at a speed that is orders faster than any human expert. They can also detect patterns and feature outliers within the data that traditional diagnostic methods may overlook. Using adaptive AI algorithms is anticipated to optimize the diagnostic process of medical conditions and increase accuracy thus allowing faster diagnosis. It could mean finding diseases earlier, and therefore treating they better as well as costing healthcare less. These algorithms are able to constantly learn from new data which allow them not only to improve with time, but also adapt in order effectively combat changing disease patterns.

关键词： Accuracy Machine learning algorithms Machine learning Radiology Real-time systems Planning Medical diagnosis Artificial intelligence Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency

arXiv

引用

arXiv 2022年

作者： Zhang, Dan Zheng, Rui Gadeng, Luosang Yang, Pei School of Information and Engineering Minzu University of China Beijing100081 China Department of Information Science and Technology Tibet University Lhasa850012 China Department of Computer Technology and Application Qinghai University Xining810016 China

This paper addresses the task of semantic segmentation in computer vision, aiming to achieve precise pixel-wise classification. We investigate the joint training of models for semantic edge detection and semantic segmentation, which has shown promise. However, implicit cross-task consistency learning in multi-task networks is limited. To address this, we propose a novel "decoupled cross-task consistency loss" that explicitly enhances cross-task consistency. Our semantic segmentation network, TriangleNet, achieves a substantial 2.88% improvement over the Baseline in mean Intersection over Union (mIoU) on the Cityscapes test set. Notably, TriangleNet operates at 77.4% mIoU/46.2 FPS on Cityscapes, showcasing real-time inference capabilities at full resolution. With multi-scale inference, performance is further enhanced to 77.8%. Furthermore, TriangleNet consistently outperforms the Baseline on the FloodNet dataset, demonstrating its robust generalization capabilities. The proposed method underscores the significance of multi-task learning and explicit cross-task consistency enhancement for advancing semantic segmentation and highlights the potential of multitasking in real-time semantic segmentation. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Kerr effect in ultra-compact hybrid plasmonic metal-insulator-metal nano-focusing structure

引用

Chinese Optics Letters 2022年第3期20卷 106-110页

作者： Kejian Zhu Pengfei Sun F|engfei Xu Xingpeng Liu Tangyou Sun Haiou Li Zhiping Zhou State Key Laboratory of Advanced Optical Communication Systems and Networks Department of ElectronicsSchool of Electronics Engineering and Computer SciencePeking UniversityBeijing 100871China Guangxi Key Laboratory of Precision Navigation Technology and Application Guilin University of Electronic TechnologyGuilin 541004China Shanghai Institute of Optics and Fine Mechanics Chinese Academy of SciencesShanghai 201800China

Nano-focusing structures based on hybrid plasmonic waveguides are likely to play a key role in strong nonlinear optical *** the insertion loss is considerable,a significant nonlinear phase shift may be achieved by decreasing the nano-focusing device footprint and careful parameter ***,we study the Kerr effect in hybrid plasmonic waveguides by analyzing the mode effective area,energy velocity,and insertion ***,by utilizing plasmonics to manipulate the effective index and mode similarity,the TM mode is reflected and absorbed,while the TE mode passes through with relatively low propagation *** providing a deep understanding of hybrid plasmonic waveguides for nonlinear applications,we indicate pathways for their future optimization.

关键词： silicon photonics plasmonics nonlinear optics nano-focusing

来源：评论

学校读者我要写书评

暂无评论

ZuantuSet: A Collection of Historical Chinese Visualizations and Illustrations

arXiv

引用

arXiv 2025年

作者： Mei, Xiyao Zhang, Yu Yang, Chaofan Shi, Rui Yuan, Xiaoru National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Beijing China Department of Computer Science University of Oxford Oxford United Kingdom Center for Research on Ancient Chinese History Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Application Peking University Beijing China PKU-WUHAN Institute for Artificial Intelligence Wuhan China

Historical visualizations are a valuable resource for studying the history of visualization and inspecting the cultural context where they were created. When investigating historical visualizations, it is essential to consider contributions from different cultural frameworks to gain a comprehensive understanding. While there is extensive research on historical visualizations within the European cultural framework, this work shifts the focus to ancient China, a cultural context that remains underexplored by visualization researchers. To this aim, we propose a semi-automatic pipeline to collect, extract, and label historical Chinese visualizations. Through the pipeline, we curate ZuantuSet, a dataset with over 71K visualizations and 108K illustrations. We analyze distinctive design patterns of historical Chinese visualizations and their potential causes within the context of Chinese history and culture. We illustrate potential usage scenarios for this dataset, summarize the unique challenges and solutions associated with collecting historical Chinese visualizations, and outline future research directions. Copyright © 2025, The Authors. All rights reserved.

关键词： Data collection

来源：评论

学校读者我要写书评

暂无评论

Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler

arXiv

引用

arXiv 2023年

作者： Lin, Shaohui Huang, Wenxuan Xie, Jiao Zhang, Baochang Shen, Yunhang Yu, Zhou Han, Jungong Doermann, David The School of Computer Science and Technology East China Normal University Shanghai China The Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education China The Department of Automation School of Aerospace Engineering Xiamen University Xiamen China The Institute of Artificial Intelligence Beihang University Beijing China Zhongguancun Laboratory Beijing China The Youtu Lab Tencent Shanghai China The School of Statistics East China Normal University Shanghai China The Department of Computer Science University of Sheffield United Kingdom The University at Buffalo BuffaloNY United States

Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs, which can be effectively applied to edge devices and cloud services. In this paper, we propose a novel Knowledge-driven Differential Filter Sampler (KDFS) with Masked Filter Modeling (MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization. Specifically, we design a differential sampler with learnable sampling parameters to build a binary mask vector for each layer, determining whether the corresponding filters are redundant. To learn the mask, we introduce masked filter modeling to construct PCA-like knowledge by aligning the intermediate features from the pre-trained teacher model and the outputs of the student decoder taking sampling features as the input. The mask and sampler are directly optimized by the Gumbel-Softmax Straight-Through Gradient Estimator in an end-to-end manner in combination with global pruning constraint, MFM reconstruction error, and dark knowledge. Extensive experiments demonstrate the proposed KDFS’s effectiveness in compressing the base models on various datasets. For instance, the pruned ResNet-50 on ImageNet achieves 55.36% computation reduction, and 42.86% parameter reduction, while only dropping 0.35% Top-1 accuracy, significantly outperforming the state-of-the-art methods. The code is available at https://***/Osilly/KDFS. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

DRL-Based Pricing-Driven for Task Offloading and Dynamic Resource in Vehicle Edge Computing

引用

IEEE Transactions on mobile Computing 2025年

作者： Wu, Sijun Yang, Liang Li, Junjie Guo, Hongzhi Ahmad, Ishtiaq Da Costa, Daniel Benevides Jiang, Hongbo Niyato, Dusit Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Cybersecurity Shaanxi Xi'an710072 China Czech Technical University in Prague Department of Telecommunication Engineering Faculty of Electrical Engineering Prague166 27 Czech Republic Interdisciplinary Research Center for Communication Systems and Sensing Department of Electrical Engineering Dhahran31261 Saudi Arabia Nanyang Technological University School of Computer Science and Engineering Singapore639798 Singapore

Vehicle Edge Computing (VEC) assists vehicles in performing latency-sensitive tasks by deploying resources near the vehicle. Designing an incentive mechanism for vehicles and VEC is crucial for realizing an intelligent transmission system. Considering the rationality of resource allocation, we model the utility functions of the VEC and the vehicle, which are used as optimization objectives. Specifically, the VEC allocates resources through pricing to maximize revenue under resource-constrained conditions, and the vehicle weighs payments against energy consumption to determine offloading and resource allocation. Given the vehicle movement and the variable channel state, we use the Deep Reinforcement Learning (DRL) algorithm to solve these optimization problems. To reduce the learning difficulty of the DRL algorithm in complex VEC scenarios with multiple optimization variables, we propose a Pricing-Driven Resource Allocation (PDRA) algorithm that performs mobility-aware task offloading and calculates the optimal values of the optimization variables in the utility function of the vehicle to reduce the decision dimension. Furthermore, we also propose a DRL-based Pricing-Driven Dynamic Resource Allocation (DPDDRA) algorithm to achieve efficient resource allocation. Extensive experimental results show that the proposed algorithms can reduce the learning difficulty while maximizing VEC and vehicle revenue in complex VEC scenarios. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Predicting the Risk of Illegal Activity and Evaluating Law Enforcement Using WideDeep SGRU Model

A Novel Approach to Predicting the Risk of Illegal Activity ...

引用

Electronics, Computing, Communication and Control technology (ICECCC), International Conference on

作者： Prativa Mishra Anusha P Arvind Kumar Subharun Pal Jyoti Prasad Patra Amit Chauhan Computer Science and Application Reva University Bangalore Karnataka India Department of ECE R.M.K. Engineering College Kavaraipettai Tamilnadu India SCA Manav Rachna International Institute of Research and Studies Faridabad Haryana Computer Science and Engineering Indian Institute of Technology Jammu Jagti Jammu & Kashmir (UT) India EE And EEE Krupajal Engineering College-KEC Puri Odisha India Department of Life sciences School of Sciences CHRIST (Deemed to be University) Bengaluru Karnataka India

ISBN: (数字)9798350371802

ISBN: (纸本)9798350371819

The main reaction to the illicit extraction of natural resources in protected areas around the world is law enforcement patrols headed by rangers. On the other hand, research on patrols' efficacy in reducing criminal behavior is lacking. Similarly, tactics to enhance the effectiveness of patrol organization and monitoring have received very little attention. Sequencing is crucial for model training, feature selection, and preprocessing. Preprocessing steps include cleaning, discretizing, duplicating, and normalizing data. Feature selection makes use of genetic algorithms, which are basically search algorithms with an evolutionary bent that factor in natural selection and genetics. Training stacked GRU models necessitates meticulous feature management. Even the most cutting-edge algorithms, GRU and BiGRU, are no match for the suggested technique. An astounding 97.24% accuracy grade was disclosed by the results, showcasing exceptional growth.

关键词： Training Sequential analysis Accuracy Law enforcement Computational modeling Feature extraction Cleaning

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：