检索结果-内蒙古大学图书馆

Automation and Computation (AUTOCOM), International Conference on

作者： Upender Reddy Chityala Ammar H. Shnain Manoj Govindaraj Prashant Johri T. Kuppuraj N.Lavanya Devi Equinox IT Solutions LLC (Senior ServiceNow Developer - IHG) Department Of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Management Studies Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India School of Computing Science and Engineering Galgotias University Greater Noida India Department of Computer Applications Karpagam Academy of Higher Education Coimbatore India Department of ECE PSNA College of Engineering and Technology India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

This research explores the integration of big data technologies and machine learning to enhance cybersecurity in enterprise environments focusing on proactive threat detection and prevention. Traditional security systems often struggle to keep up with the growing complexity and volume of cyber threats, necessitating a more advanced, data-driven approach. The proposed methodology leverages real-time data processing, predictive modeling, and anomaly detection to improve threat detection accuracy, reduce response times, and enhance system scalability. By collecting and analyzing data from various network sources, including logs from security devices and endpoint protection software, the system detects potential threats more efficiently than conventional methods. Machine learning algorithms such as supervised and unsupervised learning, along with big data platforms like Apache Spark, enable real-time analysis of large volumes of data, ensuring timely identification of both known and unknown cyber threats. The results demonstrate significant improvements in detection accuracy, system scalability, and incident resolution time, with the proposed methodology outperforming traditional security systems in key performance metrics. This research highlights the potential of big data-driven cybersecurity solutions in addressing modern challenges and offers a framework for organizations to implement more effective, scalable, and proactive security measures to safeguard their digital assets.

关键词： Scalability Prevention and mitigation Machine learning Organizations Big Data Predictive models Data processing Threat assessment Real-time systems computer security

来源：评论

学校读者我要写书评

暂无评论

A Dynamic-Static Weighted Network with Diverse-Token Fusion Attention for Rhexis Margin Recognition in Microscopic Surgery

A Dynamic-Static Weighted Network with Diverse-Token Fusion ...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Zhen Li Wen-Qian Yue Gui-Bin Bian Shuai Zhang Wei-Peng Liu Shuo Li School of Electronic and Information Engineering Tongji University Shanghai China Institute of Automation Chinese Academy of Sciences Beijing China School of Health Sciences and Biomedical Engineering Hebei University of Technology Tianjin China School of Artificial Intelligence and Data Science Hebei University of Technology Tianjin China Departments Biomedical Engineering and Computer and Data Science Case Western Reserve University

In microscopic cataract surgery, capsulorhexis is the first, most critical step. However, recognizing the boundary of the rhexis during capsulorhexis is challenging and has rarely been studied due to its intraoperative invisibility, variable shape, and lack of a proprietary labeled dataset, especially in the robot-sssisted surgery. To solve the problems, this paper proposes a creative dynamic boundary recognition solution, which includes a novel segmentation network, DCTNet, and a compensation block. First, the dilated HRNet is designed to constrain the over-compression while maintaining high-resolution representation for better detail preservation. Second, the cascaded transformer block is proposed: The decoupling transformer (DET) is developed to assign dynamic-static weights thus learning the variation pattern for segmented targets decoupling. The coupling transformer(COT) with redistributed embeddings is then developed to fuse diverse-resolution tokens for multi-scale prediction coupling. Moreover, the compensation block compensates for inter-frame movement by key-point registration and recovers a more realistic boundary by a smoothing process. Creatively, we mathematically estimate the uncertainty of framework to eliminate the misidentifications due to aleatoric uncertainty in data. Finally, to evaluate the proposed framework, we establish the first known capsulorhexis dataset, CapSeg. Our proposed DCTNet achieves superior performance to state-of-the-art networks with a lower computational cost, and the feasibility experiment shows its great potential in medical surgical robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Built-In Self-Repair for Manufacturing and Runtime TSV Defects in 3D ICs

Built-In Self-Repair for Manufacturing and Runtime TSV Defec...

引用

IEEE International Test Conference on India (ITC India)

作者： Dilip Kumar Maity Surajit Kumar Roy Chandan Giri Dept. of Computer Science and Engineering Academy of Technology Adisaptagram Hooghly India Department of Information Technology Indian Institute of Engineering Science and Technology Shibpur India

ISBN: (数字)9781728174587

ISBN: (纸本)9781728174594

Three-dimensional Integrated Circuit (3DIC) based on Through Silicon Vias (TSVs) has various benefits of wire length, power consumption, heterogeneous integration as compared to 2DIC. However, defects in TSVs due to manufacturing processes reduce the reliability of the 3DIC. Several state-of-art approaches have proposed to overcome these defects. However, TSVs can be failed during field operation due to Electromigration (EM), which becomes a major reliability concern in 3DICs. Therefore, detection and repair are crucial in the presence of EM failures. This paper presents a runtime dynamic Built-In Self-Repair (BISR) approach to enhance runtime reliability. BISR consists of a test scheme to pinpoint runtime defects as well as manufacturing defects and a repair scheme that replace defective TSVs with neighbor fault-free TSVs. Experimental results demonstrate that the proposed method reduces the overall cost in terms of test time and area overhead significantly. The delay overhead of the repair solution is reasonable for 0.5 ns critical path latency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Automated Calibration Scheme for PLL in Time-to-Digital Converters

An Automated Calibration Scheme for PLL in Time-to-Digital C...

引用

IEEE International Conference on Circuits and Systems (ICCS)

作者： Jiayuan Xu Hang Yu Yan Li Daoming Xi Binjie Ge Hongzhao Liu Shenzhen Laboratory of IC Design for IOT College of Computer Science and Software Engineering Shenzhen University Shenzhen China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Dept. of Electronics and Computer Engineering SHENZHEN MSU-BIT University Shenzhen China Quality and Standards Academy Shenzhen Technology University Shenzhen China

In high performance Time-to-Digital Converters (TDCs), PLL can be adopted to generate the required reference clock, which is in $\sim 100 \ \text{MHz}$ range. In order to improve the phase noise performance, the full VCO frequency range in such a PLL is generally divided into multiple sectors, which can be selected by digital code. This paper proposes an automated calibration scheme to set the digital code for optimized VCO performance. Primarily based on successive approximation algorithm, the proposed scheme completes the automated calibration with only minimal steps. By co-simulating with a typical PLL, the efficacy of the proposed scheme is fully validated. Tentatively synthesized using CMOS 180nm technology, the automated calibration scheme only occupies $100\times 100\text{um}^{2}$ of silicon area, and consists of 144 logical gates. The power consumption is only $\sim 100\ \text{uW}$ .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unknown Word Detection for English as a Second Language (ESL) Learners Using Gaze and Pre-trained Language Models

arXiv

引用

arXiv 2025年

作者： Ding, Jiexin Zhao, Bowen Wang, Yuntao Liu, Xinyun Hao, Rui Chatterjee, Ishan Shi, Yuanchun Institute Tsinghua University Beijing China Electrical & Computer Engineering University of Washington SeattleWA United States Groundlight AI SeattleWA United States Department of Computer Science and Technology Tsinghua University Beijing China Rice University HoustonTX United States School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Paul G. Allen School of Computer Science and Engineering University of Washington SeattleWA United States Qinghai University Xining China

English as a Second Language (ESL) learners often encounter unknown words that hinder their text comprehension. Automatically detecting these words as users read can enable computing systems to provide just-in-time definitions, synonyms, or contextual explanations, thereby helping users learn vocabulary in a natural and seamless manner. This paper presents EyeLingo, a transformer-based machine learning method that predicts the probability of unknown words based on text content and eye gaze trajectory in real time with high accuracy. A 20-participant user study revealed that our method can achieve an accuracy of 97.6%, and an F1-score of 71.1%. We implemented a real-time reading assistance prototype to show the effectiveness of EyeLingo. The user study shows improvement in willingness to use and usefulness compared to baseline methods. © 2025, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Physical Anomalies in IoT Networks Using Machine Learning Techniques

Detection of Physical Anomalies in IoT Networks Using Machin...

引用

Advancement in Renewable Energy and Intelligent Systems (AREIS), International Conference on

作者： M. A. Mukunthan Jose Anand A. Stalin Kesavan Malini Mutyala R. Kesavan R. Geetha Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of ECE KCG College of Technology Chennai Tamil Nadu India Department of Marine Engineering Academy of Maritime Education and Training Chennai Tamil Nadu Department of CSBS Vignana Bharathi Institute of Technology Hyderabad Telangana India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Tamilnadu Department of Computing Technologies SRM Institute of Science and Technology Chennai Tamilnadu

ISBN: (数字)9798350387230

ISBN: (纸本)9798350387247

This work focuses on the implementation of a Machine Learning (ML) algorithm for detecting physical anomalies in Internet of Things (IoT) networks. A Wireless Sensor Network (WSN) was deployed, collecting data under two scenarios: normal operation and an altered state exhibiting physical anomalies. The WSN, composed of humidity, Hall effect, barometer, and temperature sensors, communicated using the MQTT protocol with an Edge node for data capture. Data profiling and preprocessing were conducted to clean and optimize the dataset for ML. The K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF) algorithm were employed to classify network traffic, with hyperparameters tuned using Randomized Search CV. The dataset was split into training (75%) and testing (25%) sets, with performance metrics such as accuracy, precision, recall, F1 score, and ROC curve analyzed. The final model achieved high accuracy (99.53 %) and showed excellent precision (1) with a classification time of 0.0012 seconds per packet. These results demonstrate the RF model's effectiveness in detecting physical anomalies in IoT networks, although further optimization may be needed for real-world scalability.

关键词： Support vector machines Radio frequency Performance evaluation Wireless sensor networks Accuracy Computational modeling Scalability Nearest neighbor methods Reliability Internet of Things

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: A multi-scale and rotation-invariant phase pattern (MRIPP) and a stack of restricted Boltzmann machine (RBM) with preprocessing for facial expression classification (Journal of Ambient Intelligence and Humanized Computing, (2021), 12, 3, (3447-3463), 10.1007/s12652-020-02517-7)

引用

Journal of Ambient Intelligence and Humanized Computing 2024年

作者： Sherly Alphonse, A. Shankar, K. Jeyasheela Rakkini, M.J. Ananthakrishnan, S. Athisayamani, Suganya Singh, A. Robert Gobi, R. Department of Information Technology Ponjesly College of Engineering Nagercoil India Department of Computer Applications Alagappa University Karaikudi India School of Computing Sastra Deemed To Be University Thanjavur India School of Computing Kalasalingam Academy of Research and Education Anand Nagar India Department of Computer Science Christ University Bengalore India

The Publisher has retracted this article in agreement with the Editor-in-Chief. The article was submitted to be part of a guest-edited issue. An investigation by the publisher found a number of articles, including this one, with a number of concerns, including but not limited to compromised editorial handling and peer review process, inappropriate or irrelevant references or not being in scope of the journal or guest-edited issue. Based on the investigation’s findings the publisher, in consultation with the Editor-in-Chief therefore no longer has confidence in the results and conclusions of this article. S. Ananthakrishnan, A. Robert Singh, and R. Gobi disagree with this retraction. M. J. Jeyasheela Rakkini did not explicitly state whether they agree or disagree with this retraction. The remaining authors did not respond to correspondence from the Publisher regarding this retraction. © Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The use of ML Algo Techniques in Translational Way of HC System (Medicine)

The use of ML Algo Techniques in Translational Way of HC Sys...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： S Ganga M. Maheswaran Mohanarathinam Krishna Kant Dixit Anil Pratap Singh V. Diana Earshia Department of Information Technology (IT) Prince Shri Venkateshwara Padmavathy Engineering College Department of Mechatronics Engineering (ME) Nehru Institute of Engineering and Technology T.M. Palayam Tamil Nadu India Department of Biomedical Engineering Karpagam Academy of Higher Education Coimbatore TN Department of Electrical Engineering GLA University Mathura Department of Computer Science & Engineering (CS & E) IES Insititute of Technology and Management IES University Bhopal M.P. India Electronics and Communication Engineering Dept Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology (Deemed To Be University) Avadi Chennai Tamil Nadu India

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

In recent years, the rate of expansion in our ability to handle multi-dimensional biology and clinical data, covering laboratory to real-world situations, has greatly changed the face of pharmaceutical development and research. The introduction of artificially intelligent technology (AI) and ML, or machine learning, into these areas has been crucial. The discipline of precision medicine, at its core emphasize on patient-centric SYSTEMATIC SEQUENCE wise forward and backward translation, has appeared as a central theme to the entire range of the development and discovery of drugs, spanning target confirmation to medication optimization. The merging of cutting-edge analytics into therapeutic practices has become a basic aid, especially in pulling useful insights from extensive enormous data sets, involving “omics” data. This includes in-depth studies of the genome, a transcriptome, proteome, metabolome, all, microbiome, and exposome. This article gives a thorough review of ML uses within drug development, matching with Translational Medicine’s primary objectives (target, patient, dose). Furthermore, it studies the groundbreaking possibilities of ML in changing the science and performance of this field. The talk also dives into the possibilities for adding ML methods into Pharmacometrics, expecting a new effect on model-informed drug finding and development. Lastly, the paper underscores the crucial teamwork of specialists from Clinical Pharmacology, and Bioinformatics, while Biomarker Technologies within cross-functional teams, stressing their combined role in realizing the promise of AI/ML-enabled Translational while Precision Medicine.

关键词： Drugs Systematics Reviews Precision medicine Biological system modeling Merging Medical services

来源：评论

学校读者我要写书评

暂无评论

Where Precision Meets Efficiency: Transformation Diffusion Model for Point Cloud Registration 39

Where Precision Meets Efficiency: Transformation Diffusion M...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Yuan, Yongzhe Wu, Yue Fan, Xiaolong Gong, Maoguo Miao, Qiguang Ma, Wenping MoE Key Lab of Collaborative Intelligence Systems Xidian University China School of Computer Science and Technology Xidian University China School of Electronic Engineering Xidian University China Academy of Artificial Intelligence College of Mathematics Science Inner Mongolia Normal University China School of Artificial Intelligence Xidian University China

ISBN: (纸本)157735897X

We propose a transformation diffusion model for point cloud registration to balance precision and efficiency. Our method formulates point cloud registration as a denoising diffusion process from noisy transformation to object transformation, which is represented by quaternion and translation. Specifically, in training stage, object transformation diffuses from ground-truth transformation to random distribution, and the model learns to reverse this noising process. In sampling stage, the model refines randomly generated transformation to the optimal transformation in a progressive way. We derive the variational bound in closed form for training and provide instantiation of the model. Our diffusion model maps transformation into latent space, and splits the transformation into two components (rotation and translation) based on the fact that they belong to different solution spaces. In addition, our work provides the following crucial findings: (i) Point cloud registration, one of the representative discriminative tasks, can be solved by a generative way and mapped into latent space to obtain new unified probabilistic formulation. (ii) Our model, Transformation Diffusion Model (TDM) can be a plug-and-play agent for point cloud registration, making our method applicable to different deep registration networks. Experimental results on synthetic and real-world datasets demonstrate that, in correspondence-free and correspondence-based scenarios, TDM can both achieve exceeding 60% performance improvements and higher efficiency simultaneously. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of autonomous production using deep neural network for complex job

Design of autonomous production using deep neural network fo...

引用

2020 International Virtual Conference on Sustainable Materials, IVCSM 2k20

作者： Sara, S. Belina V.J. Anand, M. Silvia Priscila, S. Yuvaraj, N. Manikandan, R. Ramkumar, M. Department of Computer Science Srmist Ramapuram Campus Chennai India Department of Information Technology College of Engineering and Technology Srm Institute of Science and Technology Chennai India Department of Ug Computer Science Mohamed Sathak Arts and Science College Chennai India Training and Research Ict Academy Chennai India Department of Cs TheQuaideMilleth College for Men Chennai India AP/CSE Gnanamani College of Technology Rasipuram Namakkal Dt. India

Deep Neural Network (DNN) in recent era offers new opportunities to manage the production systems with increasing complexity. In this paper, DNN is trained with discrete event simulation and a process based association to make the job shop an autonomous one. This intelligent system operates well in complex environment with constrained time limits while making optimal decisions. The DNN is henceforth combined with constrained time limits for the process of production control. The system is implemented typically in semiconductor manufacturing industries on complex job shops of a wafer fab case. The DNN is trained in such a way that it operates in complex environment with timing constraints that ships the job in accurate way without flaws in operation. The DNN rewards the selection with reduced time constraint, which tends to operates with most critical batch list. The study therefore shows that the DNN manages well the timing constraints than the standard benchmark technique. © 2021 Elsevier Ltd. All rights reserved.

关键词： Deep neural networks

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：