检索结果-内蒙古大学图书馆

1st IEEE International Conference on Electronics, Computing, Communication and Control Technology, ICECCC 2024

作者： Aishwarya, D. Sandeep, Ponduru Akhilesh Varma, Penmatsa V.P.S. Sathyabama Institute of Science and Technology Dept. of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350371802

This study introduces a novel facial deconstruction method for face emotion identification. After identifying facial landmarks with the IntraFace algorithm, seven regions of interest (ROI) are extracted, representing the principal featuresof the face: the mouth, nose, an area between the eyebrows, right and left eyes, and eyebrows. Next, a variety of local descriptors, such as Local Binary Patterns, Completed Local Binary Patterns. Local Ternary Patterns, and Dynamic Local Ternary Patterns, are employed to capture distinctive features. Inputting the feature vector which represents a face image into a multi-class support vector machine completes the recognition process. The suggested method outperforms previous facial deconstruction techniques, according on experimental findings on two publicly available datasets. © 2024 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Techniques Optimised LSTM Network for Improved Weather Prediction 2

Metaheuristic Techniques Optimised LSTM Network for Improved...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Mittal, Shweta Sangwan, Om Prakash Guru Jambheshwar University of Science and Technology Dept. of Computer Science and Engineering Hisar India

ISBN: (纸本)9798350360523

Tremendous amount of meteorological data is being generated on a daily basis from a number of sources such as weather stations, balloons, satellites, sensors etc. Timely weather prediction helps people plan everyday life events. Long Short Term Memory (LSTM) networks perform extremely well for capturing dependencies in time series datasets. Number of neurons in hidden layer highly impacts the performance of the LSTM network. The hit and Trial method for selecting the neurons consumes a lot of time and resources and might not lead to a global optimum solution. In this research work, two techniques, i.e. Genetic Algorithm optimized LSTM (LSTM-GA) and Artificial Bee Colony optimized LSTM (LSTM-ABC) have been proposed and implemented to automate the selection of the hidden layer's neurons for improved weather prediction. Proposed techniques have been implemented using DeepLearning4j library making the techniques scalable on clusters of machines. For evaluating the performance of proposed techniques, 15 years Brazil's weather dataset has been used. The experimental results proved that the proposed LSTM-GA and LSTM-ABC techniques have the reduced MAE value of 0.0074 and 0.0075 respectively while the LSTM network without any optimization has a relatively higher MAE value of 0.0086. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Robust Line-Convex Polygon Intersection Computation in E2 using Projective Space Representation

引用

Machine Graphics and Vision 2023年第3-4期32卷 3-16页

作者： Skala, Vaclav Dept. of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic

This paper describes modified robust algorithms for a line clipping by a convex polygon in E2 and a convex polyhedron in E3. The proposed algorithm is based on the Cyrus-Beck algorithm and uses homogeneous coordinates to increase the robustness of computation. The algorithm enables computation fully in the projective space using the homogeneous coordinates and the line can be given in the projective space, in general. If the result can remain in projective space, no division operation is needed. It supports the use of vector-vector operations, SSE/AVX instructions, and GPU. © 2023 Institute of Information Technology, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

Direct Torque Control of IPMSMs for Fast Dynamic Response with Constant Switching Frequency

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第3期72卷 395-401页

作者： Shin, Eun-Kyeol Lee, Kyo-Beum Dept. of Electrical and Computer Engineering Ajou University Korea Republic of

This paper proposes the direct torque control (DTC) of interior permanent magnet synchronous motors (IPMSMs) for fast dynamic response with constant switching frequency. The conventional DTC is constructed based on the hysteresis flux and torque controllers with the flux and torque errors as input. The switching frequency of DTC is not constant. In the DTC with constant switching frequency, a torque regulator with a constant switching frequency is applied to overcome this problem, instead of the hysteresis torque controller for the conventional DTC. The DTC with constant switching frequency uses a torque regulator with a proportional-integral (PI) torque controller and a triangular carrier to realize a constant switching frequency. Compared to the conventional DTC, the DTC with constant switching frequency has the poor dynamic response because both voltage vectors increasing and decreasing torque are selected in the transient state. In this paper, the bandwidth of PI torque controller is varied to improve the dynamic response of the DTC with constant switching frequency. The effectiveness of the proposed method is verified through simulation results. Copyright © The Korean Institute of Electrical Engineers.

关键词： Torque

来源：评论

学校读者我要写书评

暂无评论

Optimal Channel Selection for EEG-Based Enhanced Brain Robot Interface for Autonomous Wheelchair 12

Optimal Channel Selection for EEG-Based Enhanced Brain Robot...

引用

12th International Conference on Awareness science and Technology, iCAST 2023

作者： Sibli, Sabbir Ahmed Kabir, Raihan Jannat, Nuray Watanobe, Yutaka Islam, Md Rashedul Dept. of Computer Science and Engineering Fareast International University Banani Dhaka1213 Bangladesh Dept. of Computer Science and Engineering University of Aizu Aizuwakamatsu Fukushima Japan Dept. of Computer Science and Engineering BRAC University Dhaka1212 Bangladesh Dept. of Computer Science and Engineering University of Asia Pacific Dhaka1216 Bangladesh

ISBN: (纸本)9798350324693

Creating an autonomous wheelchair system based on EEG (electroencephalogram) signals is a fascinating and challenging concept. In non-invasive Brain robot Interface (BRI), scalp EEG signals acquired from the multiple channels come with different artifact types, majorly as an electrooculogram (EoG). Also, all the channels don't carry equally important information regarding the particular motor activities. The primary contribution of this paper is to denoise the EEG signal and then find the optimal channels to achieve the most informative EEG signals for the motor activity recognition. Thus, this research proposes a model where firstly t he E oG a rtifacts h ave b een removed from EEG signals with the regression method and other noises with Discrete Wavelet Transform (DWT). Secondly, It proposes a model of selecting optimal channels using a hybrid feature selection process, which includes a filter a nd w rapper method using sequential floating forward search (SFFS). Maximum Class Separability (MCS) and Support Vector Machine (SVM), both have been used for evaluating the channels. Then again SVM has been applied for classifying the motor activities by the signals recorded from the optimal channels. A dataset with four classes of human motor activities has been used for evaluating the whole proposed model. This proposed model shows the highest accuracy of 84.15% for the optimal channel set with Standard Deviation (STD) feature among other optimal channel sets of features. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

IEEE Vehicular Technology Society Bylaws Changes [Society News]

引用

IEEE VEHICULAR TECHNOLOGY MAGAZINE 2025年第1期20卷 111-112页

作者： Rubinstein, Tom Dept. of Electrical & Computer Engineering Auburn University Auburn AL USA

Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robot Vision-Based Autonomous Navigation Method Using Sim2Real Domain Adaptation 22

Robot Vision-Based Autonomous Navigation Method Using Sim2Re...

引用

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

作者： Zhang, Mengjiao Duan, Shihong Xu, Cheng Dept. Computer Science Beijing China

ISBN: (纸本)9798331509712

Vision-based autonomous navigation is pivotal in mobile robot technology, involving autonomous movement, path planning, obstacle avoidance, and target reaching in unknown environments. Reinforcement Learning (RL) offers a trial-and-error-driven learning method for autonomous navigation. However, training RL models directly on physical robots is time-intensive and poses potential risks. Simulators accelerate RL training efficiency and reduce costs, but they typically provide only approximate models of robot dynamics and their interactions with the environment. This leads to a simulation-to-reality gap (Sim2Real Gap), where strategies trained in simulation under-perform in real-world applications, sometimes resulting in task failures. To address the issue of reducing the Sim2Real Gap in visual sampling training, this paper establishes a bridging plugin between the simulator and ROS, enabling the subscription to interaction data between the ROS-based robot and its real-world environment. We propose a Sim2Real domain adaptation method based on CycleGAN, which generates effective visual observations for autonomous navigation learning. The experimental results demonstrate that this domain adaptation-based method, by utilizing minimal real-world data, significantly reduces the Sim2Real Gap compared to approaches relying solely on simulation data, achieving a performance improvement of 62.38%. © 2024 IEEE.

关键词： Robot vision

来源：评论

学校读者我要写书评

暂无评论

The Homie - An Application For Tenants and Owners 2

The Homie - An Application For Tenants and Owners

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Vishnu, S. Shri Hari Nagappan, G. Dept of Computer Science and Engineering Chennai India Computer Science and Engineering Chennai India

ISBN: (纸本)9798350360523

An innovative Android platform called Homie to help apartment owners and tenants communicate more easily and provide better services. Its main purpose is to make it easier for renters to share important papers with apartment owners directly, such as monthly receipts and utility invoices. It also allows tenants to file complaints online and guarantees that owners will respond to them promptly. Furthermore, Homiee lets renters easily reserve features like game rooms, function halls, and pool areas... Homiee uses Java and Android Visual Studio for programming, and Google Firebase is utilized for effective data management. This combination guarantees efficient tenant and owner information extraction and storage for effective data management, facilitating faultless tenant activity tracking and monitoring. With the help of an enclosed platform for tracking tenant activity and data tracking as well as security, Homiee bridges the communication gap that frequently exists between property owners and tenants. Tenant satisfaction and unit managing efficiency are improved as a result. By enhancing the tenant-owner relationship and offering a fully functioning platform for processes, Homiee provides a useful answer to the problems associated with apartment management. © 2024 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Balancing Safety and Security in Autonomous Driving Systems: A Machine Learning Approach with Safety-First Prioritization 40

Balancing Safety and Security in Autonomous Driving Systems:...

引用

40th Annual computer Security Applications Conference Workshops, ACSACW 2024

作者： Hasani, Afshin Nia, Mehran Alidoost Atani, Reza Ebrahimi University of Guilan Dept. of Computer Engineering Rasht Iran Shahid Beheshti University Faculty of Computer Science and Engineering Tehran Iran

ISBN: (纸本)9798331532819

In the era of autonomous vehicles (AVs), ensuring the safety and security of the system is an ongoing challenge, particularly when faced with increasingly cyber-Attacks such as GPS spoofing and man-in-The-middle. This paper presents a novel reinforcement learning (RL)-based framework that prioritizes safety over security concerns in AVs, ensuring that life-critical tasks such as collision avoidance and speed control are always maintained, even in the presence of security threats. Our system leverages the MAPE-K loop to dynamically adapt to changing conditions, using RL in the Analyzing phase to make real-Time decisions that maximize cumulative safety rewards while addressing security risks that directly affect operational integrity. We demonstrate how our RL-based self-Adaptive system mitigates security threats while maintaining safe driving behaviors through various simulations and experiments. The proposed system shows significant improvements in collision avoidance and threat detection, ultimately ensuring that the AV's safety is preserved in even the most challenging scenarios. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Ransomware Threats Using Machine Learning Approach 8

Detecting Ransomware Threats Using Machine Learning Approach

引用

8th IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics, DISCOVER 2024

作者： Guruprasad, Sunitha Rao, Arnav G. Shetty, Sanmitha Chitharanjan Bastian, Rose Khader, Sarah Abdul St Joseph Engineering College Dept. of Computer Science & Engineering Mangaluru India Visvesvaraya Technological University Karnataka Belagavi India Ramaiah Institute of Technology Dept. of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798350350593

The rise of ransomware-related cyber-attacks poses a severe threat to organizations across various sectors. This research addresses the urgent need for robust detection mechanisms using advanced machine learning (ML) models. Ransomware, characterized by irreversible encryption of user data, demands proactive strategies for identification and prevention. This study leverages publicly available ransomware and benign executable files from sources such as VirusTotal which are run in a sandboxed environment to obtain a dataset to train an ML model capable of differentiating between diverse ransomware samples and classifying them based on specific characteristics. The process begins with meticulous data preprocessing ensuring the dataset's quality. Feature extraction algorithms are employed to identify relevant characteristics, streamlining the dataset and optimizing model performance. The model is trained on the dataset to effectively learn patterns. Evaluation metrics, including accuracy, precision, recall, F1-score, and the ROC curve, provide comprehensive insights into the model's effectiveness. © 2024 IEEE.

关键词： Adversarial machine learning

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：