检索结果-内蒙古大学图书馆

A conceptual framework for SPI evaluation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Unterkalmsteiner, Michael Gorschek, Tony Islam, A.K.M. Moinul Cheng, Chow Kian Permadi, Rahadian Bayu Feldt, Robert Software Engineering Research Lab School of Computing Blekinge Institute of Technology KarlskronaSE-371 79 Sweden Software Engineering: Process and Measurement Research Group Department of Computer Science University of Kaiserslautern PO Box 3049 Kaiserslautern67653 Germany General Electrics Healthcare Healthcare IT. Munzinger Straße 5 Freiburg79111 Germany Amadeus S.A.S. Product Marketing and Development 485 Route du Pin Montard Boite Postale 69 Sophia Antipolis06902 Cedex France

software Process Improvement (SPI) encompasses the analysis and modification of the processes within software development, aimed at improving key areas that contribute to the organizations’ goals. The task of evaluating whether the selected improvement path meets these goals is challenging. Based on the results of a systematic literature review on SPI measurement and evaluation practices, we developed a framework (SPI-MEF) that supports the planning and implementation of SPI evaluations. SPI-MEF guides the practitioner in scoping the evaluation, determining measures and performing the assessment. SPI-MEF does not assume a specific approach to process improvement and can be integrated in existing measurement programs, refocusing the assessment on evaluating the improvement initiative’s outcome. Sixteen industry and academic experts evaluated the framework’s usability and capability to support practitioners, providing additional insights that were integrated in the application guidelines of the framework. Copyright © 2013 John Wiley & Sons, Ltd. © 2023, CC BY-NC-SA.

关键词： software design

NLP for Sentiment Analysis in Social Media Posts to Detect Suspicious Behaviour

学校读者我要写书评

暂无评论

NLP for Sentiment Analysis in Social Media Posts to Detect S...

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： Abhishek Awasthi Mohammad Bdair A. Nandha Kumar Sanjog Thapa Nalini Devi S Bharathi Ramesh Kumar Software Developer Sporta Technology pvt Ltd Maharashtra India School of Architecture Computing & Engineering University of East London London United Kindom Department of EEE Bannari Amman Institute of Technology Sathyamangalam India Department of Information System and Analysis Lamar University Texas USA Department of Management Studies St. Joseph's Institute of Technology Chennai India Department of Mathematics Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

In an era where social media is an almost omnipresent means of communication, online safety is crucial. Still, conventional sentiment analysis methods sometimes fall short of accurately spotting dubious conduct. A novel approach utilizing advanced Natural Language Processing (NLP) techniques, especially Deep Learning (DL) models like BERT (Bidirectional Encoder Representations from Transformers), is proposed to overcome these challenges. DL is used by the suggested method to identify nuanced attitudes in social media posts, which raises the accuracy of identifying suspicious activities. That is not the case with conventional systems that depend on basic algorithms. With detection rates of 88%, 85%, and 90% for hate speech, violent statements, and extreme opinions, respectively, the system accomplishes remarkable outcomes via meticulous data gathering, preprocessing, and model training. Through comparison, it outperforms existing systems in terms of F1 score (0.92), recall (0.91), precision (0.94), and accuracy (0.92). The proposed system effectively reduces potential risks and encourages a safer online environment by utilizing the effective analysis of sentiment in social media posts, therefore indicating a major advancement in online security.

关键词： Training Sentiment analysis Accuracy Social networking (online) Hate speech Bidirectional control Transformers Encoding Data models Security

Latent fingerprint enhancement and segmentation technique based on hybrid edge adaptive DTV model 2

学校读者我要写书评

暂无评论

Latent fingerprint enhancement and segmentation technique ba...

2nd International Conference on Smart computing and Electronic Enterprise, ICSCEE 2021

作者： Hilles, Shadi M S Liban, Abdilahi Miaikil, Othman A.M. Mahmoud Altrad, Abdullah Baker El-Ebiary, Yousef A. Hilles, Mohanad M Contreras, Jennifer Istanbul OKAN University Software Engineering Department Istanbul Turkey Hargeisa University Computer Science Department Hargeisa Somalia Al-Madinah International University Computer Science Department Kuala Lumpur Malaysia Universiti Sultan Zainal Abidin Faculty of Informatics and Computing Trengganu Malaysia University College of Applied Science Information Technology Department Gaza Palestine FEU Institute of Technology Department of Information Technology Manila Philippines

ISBN: (纸本)9781665432221

Image enhancement and segmentation is widely used for fingerprint identification and authorization in biometrics devices, criminal scene is most challenges due to low quality of fingerprint, the most significant efforts is to develop algorithm for latent fingerprint enhancement which become challenging problem due to the complex and existing problem for instance, developing algorithms of latent fingerprint is able to extract features of image blocks and removing overlapping and isolate the poor and noisy background. however, it's still challenging and interested problem specifically latent fingerprint enhancement and segmentation. The aim study of this paper is to propose latent fingerprint enhancement and segmentation based on hybrid model and Chan-Vese method for segmentation, in order to reduce low image quality and increase the accuracy of fingerprint. The desired characteristics of intended technique are adaptive, effective and accurate, hybrid model of edge adaptive direction achieves accurate latent fingerprint enhancement and segmentation, the target needs to improve feature detection and performance, this research has proposed system architecture of research method in fingerprint enhancement and segmentation where is the method content two stages, the first is normalization and second is reconstruction, using EDTV model is required for adaptive noise, in addition Chan-vase technique contributed for identification of fingerprint image features, the result and testing using RMSE with three categories of fingerprint images good, bad and ugly show better performance for all three categories, as well RMSE shows the average of good latent fingerprint before and after enhancement. Latent Fingerprint Enhancement and Segmentation Technique Based on Hybrid Model Edge Adaptive Directional Total Variation © 2021 IEEE.

关键词： Image enhancement

Explainable Semantic Federated Learning Enabled Industrial Edge Network for Fire Surveillance

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dong, Li Peng, Yubo Jiang, Feibo Wang, Kezhi Yang, Kun School of Computer Science Hunan University of Technology and Business Changsha410205 China Xiangjiang Laboratory Changsha410205 China School of Intelligent Software and Engineering Nanjing University Suzhou China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China Department of Computer Science Brunel University London United Kingdom

In fire surveillance, Industrial Internet of Things (IIoT) devices require transmitting large monitoring data frequently, which leads to huge consumption of spectrum resources. Hence, we propose an Industrial Edge Semantic Network (IESN) to allow IIoT devices to send warnings through Semantic communication (SC). Thus, we should consider (1) Data privacy and security. (2) SC model adaptation for heterogeneous devices. (3) Explainability of semantics. Therefore, first, we present an eXplainable Semantic Federated Learning (XSFL) to train the SC model, thus ensuring data privacy and security. Then, we present an Adaptive Client Training (ACT) strategy to provide a specific SC model for each device according to its Fisher information matrix, thus overcoming the heterogeneity. Next, an Explainable SC (ESC) mechanism is designed, which introduces a leakyReLU-based activation mapping to explain the relationship between the extracted semantics and monitoring data. Finally, simulation results demonstrate the effectiveness of XSFL. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

CaRE: Finding Root Causes of Configuration Issues in Highly-Configurable Robots

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hossen, Md Abir Kharade, Sonam Schmerl, Bradley Cámara, Javier O’Kane, Jason M. Czaplinski, Ellen C. Dzurilla, Katherine A. Garlan, David Jamshidi, Pooyan College of Engineering and Computing University of South Carolina SC United States School of Computer Science Carnegie Mellon University PA United States ITIS Software Universidad de Málaga Málaga Spain Department of Computer Science and Engineering Texas A&M University TX United States Jet Propulsion Laboratory California Institute of Technology CA United States

Robotic systems have subsystems with a combinatorially large configuration space and hundreds or thousands of possible software and hardware configuration options interacting non-trivially. The configurable parameters are set to target specific objectives, but they can cause functional faults when incorrectly configured. Finding the root cause of such faults is challenging due to the exponentially large configuration space and the dependencies between the robot’s configuration settings and performance. This paper proposes CARE—a method for diagnosing the root cause of functional faults through the lens of causality. CARE abstracts the causal relationships between various configuration options and the robot’s performance objectives by learning a causal structure and estimating the causal effects of options on robot performance indicators. We demonstrate CARE’s efficacy by finding the root cause of the observed functional faults and validating the diagnosed root cause by conducting experiments in both physical robots (Husky and Turtlebot 3) and in simulation (Gazebo). Furthermore, we demonstrate that the causal models learned from robots in simulation (e.g., Husky in Gazebo) are transferable to physical robots across different platforms (e.g., Husky and Turtlebot 3). © 2023, CC BY.

关键词： Robots

Adaptive latent fingerprint image segmentation and matching using Chan-vese technique based on EDTV model 2

学校读者我要写书评

暂无评论

Adaptive latent fingerprint image segmentation and matching ...

2nd International Conference on Smart computing and Electronic Enterprise, ICSCEE 2021

作者： Hilles, Shadi M S Liban, Abdilahi Altrad, Abdullah Mahmoud Miaikil, Othman A.M. El-Ebiary, Yousef A. Baker Contreras, Jennifer Hilles, Mohanad M Istanbul OKAN University Software Engineering Department Istanbul Turkey Hargeisa University Computer Science Department Hargeisa Somalia Al-Madinah International University Computer Science Department Kuala Lumpur Malaysia Universiti Sultan Zainal Abidin Faculty of Informatics and Computing Trengganu Malaysia FEU Institute of Technology Department of Information Technology Manila Philippines University College of Applied Science Information Technology Department Gaza Palestine

ISBN: (纸本)9781665432221

Biometrics such as face, fingerprint, iris, voice and palm prints are the most widely used, and as well the fingerprints are one of the most frequently used biometrics to identify individuals and authenticate their identity. commonly categorized into three different categories which are rolled, plain and latent fingerprints. The reliability of image segmentation for latent fingerprint which is used in criminal issues still challenges, The difficulty of latent fingerprint image segmentation mainly lies in the poor quality of fingerprint patterns and the presence of the noise in the background, This research has investigated the fingerprint segmentation and matching based on EDTV and presented Chan-vese active contour segmentation technique, in addition, presented NIST SD27 for grayscale dataset of latent fingerprint which is standard by National Institute of Standard and Technology, where is dataset have varieties of fingerprint image samples, a total about 258 of latent fingerprint, those samples collected from crime scenes and matching fingerprint and shown the performance of matching accuracy ROC and CMC curves, To evaluate the performance of the matching ROC and CMC curves has been deployed, The area under curve (AUC) of the ROC of the good images performance is 72% with CMC rank1-idnetification of 42% and rank-20 identification of 79%. the result shows that the latent fingerprint method performance is better for good latent fingerprint images compare to bad and ugly images, while there is no much difference for bad and ugly image. © 2021 IEEE.

关键词： Biometrics

Non-Hemolytic Peptide Classification Using A Quantum Support Vector Machine

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhuang, Shengxin Tanner, John Wu, Yusen Huynh, Du Q. Liu, Wei Cadet, Xavier F. Fontaine, Nicolas Charton, Philippe Damour, Cedric Cadet, Frederic Wang, Jingbo Department of Physics The University of Western Australia Australia Department of Computer Science and Software Engineering The University of Western Australia Australia Department of Computing Imperial College London London United Kingdom PEACCEL Artificial Intelligence Department AI for Biologics Paris France University of Paris City University of Reunion BIGR Inserm UMR S1134 Paris France Laboratory of Excellence GR-Ex Paris France EnergyLab EA 4079 Faculty of Sciences and Technology University of Reunion Saint-Denis France

Quantum machine learning (QML) is one of the most promising applications of quantum computation. However, it is still unclear whether quantum advantages exist when the data is of a classical nature and the search for practical, real-world applications of QML remains active. In this work, we apply the well-studied quantum support vector machine (QSVM), a powerful QML model, to a binary classification task which classifies peptides as either hemolytic or non-hemolytic. Using three peptide datasets, we apply and contrast the performance of the QSVM, numerous classical SVMs, and the best published results on the same peptide classification task, out of which the QSVM performs best. The contributions of this work include (i) the first application of the QSVM to this specific peptide classification task, (ii) an explicit demonstration of QSVMs outperforming the best published results attained with classical machine learning models on this classification task and (iii) empirical results showing that the QSVM is capable of outperforming many (and possibly all) classical SVMs on this classification task. This foundational work paves the way to verifiable quantum advantages in the field of computational biology and facilitates safer therapeutic development. Copyright © 2024, The Authors. All rights reserved.

关键词： Support vector machines

Technical Debt Management: The Road Ahead for Successful software Delivery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Avgeriou, Paris Ozkaya, Ipek Chatzigeorgiou, Alexander Ciolkowski, Marcus Ernst, Neil A. Koontz, Ronald J. Poort, Eltjo Shull, Forrest Dept. of Computing Science University of Groningen Groningen Netherlands Software Engineering Institute Carnegie Mellon University PittsburghPA United States Dept. of Applied Informatics University of Macedonia Thessaloniki Greece QAware GmbH München Germany Department of Computer Science University of Victoria Victoria Canada The Boeing Company MesaAZ United States CGI Rotterdam Netherlands

Technical Debt, considered by many to be the 'silent killer' of software projects, has undeniably become part of the everyday vocabulary of software engineers. We know it compromises the internal quality of a system, either deliberately or inadvertently. We understand Technical Debt is not all derogatory, often serving the purpose of expediency. But, it is associated with a clear risk, especially for large and complex systems with extended service life: if we do not properly manage Technical Debt, it threatens to "bankrupt" those systems. software engineers and organizations that develop softwareintensive systems are facing an increasingly more dire future state of those systems if they do not start incorporating Technical Debt management into their day to day practice. But how? What have the wins and losses of the past decade of research and practice in managing Technical Debt taught us and where should we focus next? In this paper, we examine the state of the art in both industry and research communities in managing Technical Debt;we subsequently distill the gaps in industrial practice and the research shortcomings, and synthesize them to define and articulate a vision for what Technical Debt management looks like five years hence. © 2024, CC BY-NC-ND.

关键词： Industrial research

Federated Reinforcement Learning for Electric Vehicles Charging Control on Distribution Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qian, Junkai Jiang, Yuning Liu, Xin Wang, Qiong Wang, Ting Shi, Yuanming Chen, Wei The MoE Engineering Research Center of Software/Hardware Co-design Technology and Application The Shanghai Key Lab. of Trustworthy Computing East China Normal University China The Automatic Control Laboratory EPFL Switzerland The School of Information Science and Technology ShanghaiTech University China The State Grid Beijing Electric Power Company China The Department of Electronic Engineering Tsinghua University China

With the growing popularity of electric vehicles (EVs), maintaining power grid stability has become a significant challenge. To address this issue, EV charging control strategies have been developed to manage the switch between vehicle-to-grid (V2G) and grid-to-vehicle (G2V) modes for EVs. In this context, multi-agent deep reinforcement learning (MADRL) has proven its effectiveness in EV charging control. However, existing MADRL-based approaches fail to consider the natural power flow of EV charging/discharging in the distribution network and ignore driver privacy. To deal with these problems, this paper proposes a novel approach that combines multi-EV charging/discharging with a radial distribution network (RDN) operating under optimal power flow (OPF) to distribute power flow in real time. A mathematical model is developed to describe the RDN load. The EV charging control problem is formulated as a Markov Decision Process (MDP) to find an optimal charging control strategy that balances V2G profits, RDN load, and driver anxiety. To effectively learn the optimal EV charging control strategy, a federated deep reinforcement learning algorithm named FedSAC is further proposed. Comprehensive simulation results demonstrate the effectiveness and superiority of our proposed algorithm in terms of the diversity of the charging control strategy, the power fluctuations on RDN, the convergence efficiency, and the generalization ability. © 2023, CC BY-NC-SA.

关键词： Reinforcement learning