检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Ebrahimi, Amirhosein Vafaeisefat, Hoda Asghari, Mohsen Rahmati, Dara School of Computer Science Institute for Research in Fundamental Sciences Farmanieh Campus Tehran Iran Faculty of Computer Science and Software Engineering Concordia University Montreal Canada Faculty of Computer Science and engineering Shahid Beheshti University Tehran Iran

Nowadays, with the ever-growing advancement in neural networks, many of today's needs have been resolved. However, the processing speed of neural network applications might be challenging and take too long to execute. This is especially true for real-time and embedded systems, which must guarantee a response within limited time constraints. It is relatively straightforward to observe the blurred line between the real-time system and biologically inspired applications. For instance, the bio-SFA algorithm learns slow-varying features by inspiration from the human brain, and the bio-NICA algorithm, a biologically plausible neural network for non-negative independent component analysis, separates mixtures of unknown signals into their distinct sources by understanding how the brain solves blind source separation. These algorithms stem from the human brain's functionality;therefore, the processing speed should be reasonable. In this work, we will leverage the high capability of hardware performance by using field-programmable gate arrays (FPGAs) to accelerate both the bio-SFA and bio-NICA algorithms. We have compared our approach with a software implementation running on two popular embedded boards' processors, ARM Cortex-A53 SoC and ARM Cortex-A72. We have run the standard algorithm on both boards and calculated the number of cycles it takes. Generally, the designed accelerator performs around 38x speedup for Bio-SFA and 4x speedup for Bio-NICA over Cortex-A53. Similarly, compared to Cortex-A72, it achieves 9x speedup for Bio-SFA and 2x for Bio-NICA. Moreover, the accelerator consumes only 0.34 Watts for Bio-SFA and 0.85 Watts for Bio-NICA of power. © 2023, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Multi Layered Rule-Based Technique for Explicit Aspect Extraction from Online Reviews

引用

computers, Materials & Continua 2022年第12期73卷 4641-4656页

作者： Mubashar Hussain Toqir A.Rana Aksam Iftikhar M.Usman Ashraf Muhammad Waseem Iqbal Ahmed Alshaflut Abdullah Alourani School of Systems and Technology University of Management and TechnologyLahore54770Pakistan Department of Computer Science and It The University of LahoreLahore54000Pakistan School of Computer Sciences Universiti Sains Malaysia(USM)Penang11800Malaysia Department of Computer Science Comsats University IslamabadLahore54000Pakistan Department of Computer Science GC Women University SialkotPakistan Department of Software Engineering The Superior UniversityLahore53700Pakistan Faculty of Computing and It Albaha UniversityAlbahaSaudi Arabia Department of Computer Science Majmaah UniversitySaudi Arabia

In the field of sentiment analysis,extracting aspects or opinion targets fromuser reviews about a product is a key *** the polarity of an opinion is much more useful if we also know the targeted Aspect or *** based approaches,like dependency-based rules,are quite popular and effective for this ***,they are heavily dependent on the authenticity of the employed parts-of-speech(POS)tagger and dependency *** popular rule based approach is to use sequential rules,wherein the rules formulated by learning from the user’s ***,in general,the sequential rule-based approaches have poor generalization ***,existing approaches mostly consider an aspect as a noun or noun phrase,so these approaches are unable to extract verb *** this article,we have proposed a multi-layered rule-based(ML-RB)technique using the syntactic dependency parser based rules along with some selective sequential rules in separate layers to extract noun ***,after rigorous analysis,we have also constructed rules for the extraction of verb *** verb rules primarily based on the association between verb and opinion *** proposed multi-layer technique compensates for the weaknesses of individual layers and yields improved results on two publicly available customer review *** F1 score for both the datasets are 0.90 and 0.88,respectively,which are better than existing *** improved results can be attributed to the application of sequential/syntactic rules in a layered manner as well as the capability to extract both noun and verb aspects.

关键词： Explicit aspect aspect extraction opinion mining rule-based verb aspects

来源：评论

学校读者我要写书评

暂无评论

Optimizing Gammatone Cepstral Coefficients for Gear Fault Detection

引用

IEEE Access 2025年 13卷 101711-101720页

作者： Zrar Kh Abdul Abdulbasit K. Al-Talabani Wisam Hazim Gwad Entisar Alkayal Halgurd S. Maghdid Safar Maghdid Asaad Computer Department College of Science Charmo University Sulaymaniyah Iraq Department of Software Engineering Faculty of Engineering Koya University Koya Iraq Department of Artificial Intelligence Engineering College of Engineering Alnoor University Ninavah Iraq Information Technology Department Faculty of Computing and Information Technology-Rabigh King Abdulaziz University Jeddah Saudi Arabia Department of Engineering Research Center Deanship of Research and Development Centers Koya University Erbil Governorate Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil Iraq

Cepstral features, such as Gammatone Cepstral Coefficients (GTCC), have recently been applied in fault detection and diagnosis. However, GTCC was originally designed for speech feature extraction rather than fault detection, which limits its ability to capture relevant features for fault identification effectively. In this research, three key parameters of GTCC, namely, the number of coefficients, maximum frequency, and minimum frequency, are optimized using two metaheuristic algorithms: Fitness Dependent Optimizer (FDO) and Grey Wolf Optimization (GWO). These parameters are vital for enhancing the effectiveness of GTCC in extracting relevant features from the vibration signal for gear defect identification. Specifically, the maximum and minimum frequency values are critical for capturing the Gear Mesh Frequency (GMF), a common indicator of gear faults. Furthermore, optimizing the number of GTCC coefficients helps reduce model complexity. Experimental results demonstrate that optimizing GTCC parameters with GWO improves fault detection performance using an SVM classifier, achieving over 1% and 3% accuracy improvements on the PHM09 and DDS datasets, respectively.

关键词： Feature extraction Fault detection Optimization Gears Metaheuristics Mel frequency cepstral coefficient Mathematical models Filter banks Support vector machines Cepstrum

来源：评论

学校读者我要写书评

暂无评论

Robust Feature engineering Techniques for Designing Efficient Motor Imagery-Based BCI-Systems

arXiv

引用

arXiv 2024年

作者： Gardezi, Syed Saim Jawed, Soyiba Khan, Mahnoor Bukhari, Muneeba Khan, Rizwan Ahmed Department of Biomedical Engineering Faculty of Engineering Salim Habib University Karachi Pakistan Department of Computer Software Engineering College of Electrical and Mechanical Engineering NUST Islamabad Pakistan Department of Physics Faculty of Applied Sciences Riphah International University Islamabad Pakistan Department of Biomedical Engineering Faculty of Engineering NED University Karachi Pakistan Department of Computer Science School of Mathematics and Computer Science Institute of Business Administration Karachi Pakistan

A multitude of individuals across the globe grapple with motor disabilities. Neural prosthetics utilizing Brain-computer Interface (BCI) technology exhibit promise for improving motor rehabilitation outcomes. The intricate nature of EEG data poses a significant hurdle for current BCI systems. Recently, a qualitative repository of EEG signals tied to both upper and lower limb execution of motor and motor imagery tasks has been unveiled. Despite this, the productivity of the Machine Learning (ML) Models that were trained on this dataset was alarmingly deficient, and the evaluation framework seemed insufficient. To enhance outcomes, robust feature engineering (signal processing) methodologies are implemented. A collection of time domain, frequency domain, and wavelet-derived features was obtained from 16-channel EEG signals, and the Maximum Relevance Minimum Redundancy (MRMR) approach was employed to identify the four most significant features. For classification K Nearest Neighbors, Support Vector Machine, Decision Tree, and Naïve Bayes models were implemented with these selected features, evaluating their effectiveness through metrics such as testing accuracy, precision, recall, and F1 Score. By leveraging SVM with a Gaussian Kernel, a remarkable maximum testing accuracy of 92.50% for motor activities and 95.48% for imagery activities is achieved. These results are notably more dependable and gratifying compared to the previous study, where the peak accuracy was recorded at 74.36%. This research work provides an in-depth analysis of the MI Limb EEG dataset and it will help in designing and developing simple, cost-effective and reliable BCI systems for neuro-rehabilitation. © 2024, CC BY-NC-ND.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

ETHACA - A Container-Based Cyber Range for Research and Education 29

ETHACA - A Container-Based Cyber Range for Research and Educ...

引用

29th IEEE International Workshop on computer Aided Modeling and Design of Communication Links and Networks, CAMAD 2024

作者： Chouliaras, Nestoras Kantzavelou, Ioanna Pantziou, Grammati Maglaras, Leandros Chouliara-Sidera, Panagiota Adamakos, Antonis Chalatsakos, Panagiotis University of West Attica Department of Informatics and Computer Engineering Athens Greece School of Computing Edinburgh Napier University EdinburghEH10 5DT United Kingdom University of Thessaly Department of Computer Science and Biomedical Infromatics Lamia Greece Senior Software Engineer at *** Athens Greece Open University of Cyprus Faculty of Pure and Applied Sciences Nicosia Cyprus

ISBN: (纸本)9798350377644

The advent of Industry 4.0 and the Industrial Internet of Things (IIoT) has revolutionized manufacturing and production systems, enhancing efficiency and communication through the integration of advanced technologies such as IoT devices and AI. However, this increased digitization has also led to heightened cybersecurity risks, with a notable rise in the frequency and complexity of cyber-attacks. Cyber Ranges emerges as a critical solution in addressing these challenges, offering a controlled environment for simulating cyber-attack scenarios, training cybersecurity teams, and developing robust defense strategies. The escalating demand for cybersecurity professionals has highlighted the crucial need for effective training solutions. This article presents an open-source Cyber Range constructed on container-based architecture, meticulously engineered for efficient operation with minimal resource consumption. In response to the scarcity of cybersecurity experts, this platform prioritizes extensive scalability and robust isolation between exercises, ensuring secure learning environments, and also integrates a complex developed exercise series aimed at strengthening cybersecurity learning experiences. These exercises encompass a variety of scenarios and challenges, catering to professionals at different skill levels. Each exercise replicates real-world cyber threats, offering practical, hands-on learning opportunities. Additionally, a comprehensive questionnaire accompanies these exercises, designed to gather feedback on participants' experiences. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Improving Code Coverage for Structural Testing by using Parametric Inter-procedural Slicing

Improving Code Coverage for Structural Testing by using Para...

引用

computer Applications (ICCA), IEEE Conference on

作者： Myint Myitzu Aung Kay Thi Win Software Engineering Lab University of Computer Studies Mandalay Mandalay Myanmar Faculty of Information Science University of Computer Studies Mandalay Mandalay Myanmar

Structural testing is one of the testing techniques in software testing. It is the testing process of internal structure in the given source code by comparing the expected result and real results and finding out faults. To complete the structural testing, it takes a long time and needs to improve code coverage. Thus, this paper focus on improving code coverage of structural testing by using parametric inter-procedural slicing with backward slicing technique. In program slicing, there are two types of slicing: forward and backward slicing depending on the slicing direction. In this paper, backward slicing is used and it starts at the criteria for the slice consideration. The parametric inter-procedural slicing is one of the program slicing techniques which is an algorithm that takes the slice criteria as a parameter and work to handle inter-procedural data flow by considering many possible dependence relations. By slicing the original input program before measuring code coverage, the input program is simplified and excluded unexecutable statements. Therefore, the proposed system in this paper can reduce the complexity of the source code and improve code coverage for structural testing. Moreover, the used dataset in experiment is benchmark dataset in C and it is converted to Java for the improvement of language oriented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluating and transforming you and your colleagues' assessments in an age of generative AI 52

Evaluating and transforming you and your colleagues' assessm...

引用

52nd Annual Conference of the European Society for engineering: Educating Responsible Engineers, SEFI 2024

作者： Neal, P.R. Daniel, S. Hassan, G.M. Grundy, S. Haque, R. Nikolic, S. Belkina, M. Lyden, S. Sandison, C. School of Chemical Engineering University of New South Wales Sydney Australia School of Professional Practice and Leadership University of Technology Sydney Sydney Australia School of Computer Science and Software Engineering University of Western Australia Perth Australia School of Science Technology and Engineering University of the Sunshine Coast Sippy Downs Australia Faculty of Engineering and Information Sciences University of Wollongong Wollongong Australia College Western Sydney University Sydney Australia School of Engineering University of Tasmania Hobart Australia

ISBN: (纸本)9782873520274

ChatGPT and other Generative AI tools (GenAI) have generated much commotion and confusion within academic circles. Many academics still need to understand the risk such tools pose on current assessment practices and how students can use them for improved grades/outcomes. Unfortunately, most studies are very generic, do not go into much detail, and are outside of the engineering education context. In addition, GenAI provides many opportunities to construct novel, authentic and/or personalised learning experiences for students. The workshop's facilitators have completed two comprehensive studies evaluating ChatGPT's impact on engineering education assessment (Nikolic et al. 2023;Nikolic et al. 2024). While strengths, weaknesses and opportunities were outlined, it is only the starting point for much-needed conversations. This workshop introduced participants to various GenAI tools in the context of a variety of engineering assessment types and engaged participants with a range of experience levels. We guided and engaged participants in exploring GenAI capabilities, in applying a framework for evaluating security and opportunities in assessment and through this demonstrated a model for professional development that they can adapt to their own institutions. © 2024 SEFI 2024 - 52nd Annual Conference of the European Society for engineering, Proceedings: Educating Responsible Engineers. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Analyses of Parametric Relation in Ant Colony Approach for Robot Path Planning Problem

Analyses of Parametric Relation in Ant Colony Approach for R...

引用

IEEE Workshop on Advanced Robotics and its Social Impacts, ARSO

作者： Sudeep Sharan Anh Tong Ngoc Minh Juan José Domínguez-Jiménez Peter Nauth Faculty of Computer Science and Engineering Frankfurt University of Applied Sciences Frankfurt am Main Germany UCASE Software Engineering Group School of Engineering University of Cádiz Cádiz Spain

ISBN: (数字)9798350344639

ISBN: (纸本)9798350344646

One of the most challenging areas of robotics research is the mobile robot vehicle in a complicated obstacle environment. Recently, algorithms for autonomous mobile vehicles have largely been influenced by nature-based algorithms. The swarm behavior of many different organisms, such as ants, fireflies, honey bees, and foxes, is simulated by several algorithms in mobile robot research, and the results are highly interesting and inspiring. In this paper, we took the inspired algorithm as an ant colony which is used to solve the path planning problems for any mobile vehicle/robots. While studying and using the ant colony approaches to solve the problem, we found that the parameter selections are one of the important expects to make the results of any application worse or better. Therefore, we decided to perform the study on the parametric relation in an ant colony approach. The importance of utilization of the Ant Colony optimization (ACO) approach is to control the parameters. In this paper, we analysed/investigated the relationship between the different control parameters of the ACO algorithm and their performance in the resolution of path planning problem. Simulation is performed with different parameter values and by the result analysis, a selection of parameter is presented.

关键词： Ant colony optimization Path planning Organisms Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Exact Quantum Sensing Limits for Bosonic Dephasing Channels

引用

PRX Quantum 2024年第2期5卷 020354-020354页

作者： Zixin Huang Ludovico Lami Mark M. Wilde School of Mathematical and Physical Sciences Centre for Quantum Software and Information Faculty of Engineering and Information Technology Science Park 123 Amsterdam 1098 XG the Netherlands Korteweg–de Vries Institute for Mathematics Institute for Theoretical Physics School of Electrical and Computer Engineering

Dephasing is a prominent noise mechanism that afflicts quantum information carriers, and it is one of the main challenges toward realizing useful quantum computation, communication, and sensing. Here, we consider discrimination and estimation of bosonic dephasing channels, when using the most general adaptive strategies allowed by quantum mechanics. We reduce these difficult quantum problems to simple classical ones based on the probability densities defining the bosonic dephasing channels. By doing so, we rigorously establish the optimal performance of various distinguishability and estimation tasks and construct explicit strategies to achieve this performance. To the best of our knowledge, this is the first example of a non-Gaussian bosonic channel for which there are exact solutions for these tasks.

关键词： Non-gaussian quantum states Quantum channels Quantum fluctuations & noise Quantum information theory Quantum parameter estimation Quantum sensing

来源：评论

学校读者我要写书评

暂无评论

Accurate Real-World Co-ordinate Finding and the Object Classification for the Robot Manipulator

Accurate Real-World Co-ordinate Finding and the Object Class...

引用

Embedded Systems and Artificial Intelligence (ESAI), International Conference on

作者： Sudeep Sharan Hung Do Thanh Peter Nauth Juan José Domínguez-Jiménez Faculty of Computer Science and Engineering Frankfurt University of Applied Sciences Frankfurt am Main Germany UCASE Software Engineering Group School of Engineering University of Cádiz Cádiz Spain

ISBN: (数字)9798331522056

ISBN: (纸本)9798331522063

This paper presents an object detection and classification of the objects using Deep Learning (DL). The integration of object detection algorithms and depth camera developed is capable of providing robots, such as self developed assistive intelligent robot called “ROSWITHA” (RObot System WITH Autonomy) with the ability to detect an object and interpret their surrounding environment. It also provides the real-world coordinates/position of the object in that environment, which helps the robot to perform some applications, such as grabbing and serving, etc. You Only Look Once (YOLO) is one of the most popular object detection algorithms which is treated as a single regression problem and is processed by a single neural network. In this work, the YOLOv5 (YOLO version 5) network is implemented on a depth camera “RealSense” for processing object detection and estimating the position of the objects. The model is trained on reduced/filtered application-required objects (e.g. bottle and cup) from the available COCO dataset, and the training outcome alongside the performance of the overall system was evaluated. The results exhibited a satisfactory performance of the model in accurately detecting and classifying the objects with a high confidence score ranging from the least to $\mathbf{7 2 \%}$ to the highest of $\mathbf{9 0 \%}$. The confidence score could also be adjusted by the user on the developed GUI to attain the most certain predictions.

关键词： YOLO Training Accuracy Robot kinematics Current measurement Robot vision systems Cameras Manipulators Distance measurement Robots

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：