检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Waseem, Muhammad Liang, Peng Shahin, Mojtaba Salle, Amleto Di Márquez, Gastón School of Computer Science Wuhan University Wuhan430072 China Department of Software Systems and Cybersecurity Faculty of Information Technology Monash University Melbourne3800 Australia Department of Information Engineering Computer Science and Mathematics University of L’Aquila L’AquilaI-67100 Italy Department of Electronics and Informatics Federico Santa María Technical University Concepción4030000 Chile

Context: Microservices Architecture (MSA) has received significant attention in the software industry. However, little empirical evidence exists on design, monitoring, and testing of microservices systems. Objective: This research aims to gain a deep understanding of how microservices systems are designed, monitored, and tested in the industry. Method: A mixed-methods study was conducted with 106 survey responses and 6 interviews from microservices practitioners. Results: The main findings are: (1) a combination of domain-driven design and business capability is the most used strategy to decompose an application into microservices, (2) over half of the participants used architecture evaluation and architecture implementation when designing microservices systems, (3) API gateway and Backend for frontend patterns are the most used MSA patterns, (4) resource usage and load balancing as monitoring metrics, log management and exception tracking as monitoring practices are widely used, (5) unit and end-to-end testing are the most used testing strategies, and (6) the complexity of microservices systems poses challenges for their design, monitoring, and testing, for which there are no dedicated solutions. Conclusions: Our findings reveal that more research is needed to (1) deal with microservices complexity at the design level, (2) handle security in microservices systems, and (3) address the monitoring and testing challenges through dedicated solutions. © 2021, CC BY.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Optimizing heat transfer in turbulent impinging jets array: A computational fluid dynamics investigation and machine learning approach for predicting the average Nusselt number

引用

Physics of Fluids 2025年第5期37卷

作者： Hnaien, Nidhal Neffati, Syrine Abdullah, Nermeen Hassen, Walid Aoudia, Mouloud Kolsi, Lioua Department of Energy Engineering College of Engineering University of Monastir Monastir5000 Tunisia College of Computer Sciences and Software Engineering University of Ha'il Ha'il Saudi Arabia Department of Industrial and Systems Engineering College of Engineering Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Laboratory of Metrology and Energy Systems University of Monastir Monastir5000 Tunisia Department of Industrial Engineering College of Engineering Northern Border University P.O. Box 1321 Arar91431 Saudi Arabia Department of Mechanical Engineering College of Engineering University of Ha'il Ha'il City81451 Saudi Arabia

In this study, a computational fluid dynamics analysis is performed to explore how the number of nozzles (N) and the impingement height (H) influence heat transfer (HT) within an impinging jets array (IJA). To simulate the dynamic flow and the HT characteristics, the two-equation k-ω turbulence model was used. The results show that as the number of nozzles increases and impingement height decreases, local and mean Nusselt numbers increase. The greatest enhancement in the average Nusselt number (Nuavg) when reducing the impact height from H = 8 to 2 (57.4%) is noted for a maximum number of nozzles (N = 9). On the other hand, choosing a minimum impact height (H = 2) ensures a maximum improvement in (Nuavg) by 127% following the variation in the number of nozzles from 1 to 9. The streamlines contours of the turbulent flow indicate the presence of two types of vortices, simple vortices and counter-rotating vortices of different dimensions depending on (N) and (H) values. Non-dimensional velocity and static pressure contours highlight the complex interactions between the impingement plate and the flow, and the considerable effects of the number of nozzles and impingement height on the HT and turbulence levels. The linear regression method is adopted to estimate the average Nusselt number along the plate, and correlation given by this method shows moderate agreement with the numerical results. To improve the accuracy of the estimated values, artificial intelligence techniques are applied to find an optimal machine learning model for predicting the average Nusselt number based on a set of input features, including (N) and engineered polynomial transformations of (H). Modeling was accomplished using deep learning through a multi-layer neural network to capture complex relationships. The Adam optimizer and the mean squared error loss function were used to train the model, comparing predictions with actual simulation results. This research offers important insights into the d

关键词： Linear regression

来源：评论

学校读者我要写书评

暂无评论

Loss Functions in Deep Learning: A Comprehensive Review

arXiv

引用

arXiv 2025年

作者： Elharrouss, Omar Mahmood, Yasir Bechqito, Yassine Serhani, Mohamed Adel Badidi, Elarbi Riffi, Jamal Tairi, Hamid Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Department of Information Systems College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Informatics Faculty of Sciences Dhar El Mahraz Sidi Mohamed Ben Abdellah University Fez Morocco

Loss functions are at the heart of deep learning, shaping how models learn and perform across diverse tasks. They are used to quantify the difference between predicted outputs and ground truth labels, guiding the optimization process to minimize errors. Selecting the right loss function is critical, as it directly impacts model convergence, generalization, and overall performance across various applications, from computer vision to time series forecasting. This paper presents a comprehensive review of loss functions, covering fundamental metrics like Mean Squared Error and Cross-Entropy to advanced functions such as Adversarial and Diffusion losses. We explore their mathematical foundations, impact on model training, and strategic selection for various applications, including computer vision (Discriminative and generative), tabular data prediction, and time series forecasting. For each of these categories, we discuss the most used loss functions in the recent advancements of deep learning techniques. Also, this review explore the historical evolution, computational efficiency, and ongoing challenges in loss function design, underlining the need for more adaptive and robust solutions. Emphasis is placed on complex scenarios involving multi-modal data, class imbalances, and real-world constraints. Finally, we identify key future directions, advocating for loss functions that enhance interpretability, scalability, and generalization, leading to more effective and resilient deep learning models. © 2025, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Flow-Based Programming For Machine Learning

Research Square

引用

Research Square 2021年

作者： Mahapatra, Tanmaya Banoo, Syeeda Nilofer Lehrstuhl für Software und Systems Engineering Fakultät für Informatik Technische Universität München Boltzmannstraße 03 Garching b München85748 Germany Birla Institute of Technology and Science Department of Computer Science and Information Systems Vidya Vihar Pilani333031 India

Machine Learning (ML) has gained prominence and has tremendous applications in fields like medicine, biology, geography and astrophysics, to name a few. Arguably, in such areas it is used by domain experts, who are not necessarily skilled-programmers. Thus, it presents a steep learning curve for such domain experts in programming ML applications. To overcome this and foster widespread adoption of ML techniques, we propose to equip them with domain-specific graphical tools. Such tools, based on the principles of flow-based programming paradigm, would support the graphical composition of ML applications at a higher level of abstraction and auto-generation of target code. Accordingly, (i) we have modelled ML algorithms as composable components;(ii) described an approach to parse a flow created by connecting several such composable components and use an API-based code generation technique to generate the ML application. To demonstrate the feasibility of our conceptual approach, we have modelled the APIs of Apache Spark ML as composable components and validated it in three use-cases. The use-cases are designed to capture the ease of program specification at a higher abstraction level, easy parametrisation of ML APIs, auto-generation of the ML application and auto-validation of the generated model for better prediction accuracy. © 2021, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Towards the hierarchical state machine oriented proteus systems programming language

Towards the hierarchical state machine oriented proteus syst...

引用

Accelerating Space Commerce, Exploration, and New Discovery Conference, ASCEND 2020

作者： Tellier, Daniel Millman, Meyer McClelland, Brian Go, Kate Beatrix Balayan, Alice Munje, Michael J. Dewey, Kyle Ho, Nhut Havelund, Klaus Ingham, Michel Department of Computer Science California State University Northridge NorthridgeCA91330 United States Department of Electrical and Computer Engineering California State University Northridge NorthridgeCA91330 United States Department of Mechanical Engineering California State University Northridge NorthridgeCA91330 United States Laboratory for Reliable Software Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States Systems Engineering Division Jet Propulsion Laboratory California Institute of Technology PasadenaCA91109 United States

ISBN: (纸本)9781624106088

In space applications, hierarchical state machines (HSMs) are often used for writing simulation and control software, including that of the Curiosity rover. At the Jet Propulsion Lab (JPL), multiple programming languages have been developed specifically for writing HSM-based software, and these have been used in practice. However, we observe that the existing languages developed have significant issues with one or more of usability, performance, and safety, making them problematic for HSM-based development. To address these concerns, we are taking lessons learned from these languages and developing a new programming language named Proteus. Proteus builds HSM support directly into the language, and permits complex HSMs to be defined which communicate with each other. Proteus is designed with a look and feel similar to C/C++, making it usable and overall approachable for use by JPL systems engineers. Proteus itself compiles to C++, allowing it to fit easily into existing development toolchains, and making it amenable to embedded real-time systems. To ensure that Proteus will be of use to its target audience, it is being developed iteratively through a series of prototypes which are regularly evaluated by key stakeholders at JPL, allowing us to refine its design if we go off course. While Proteus is still very young in its development, we demonstrate its basic viability on an example utilizing multiple independent HSMs communicating with each other, and relevant execution traces. In the future, we plan to apply Proteus to larger HSMs taken from real space applications, and many additional relevant features are planned. © 2020 The MITRE Corporation. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Gamma Imaging in Proton Therapy by Sanitizing Compton Camera Simulated Patient Data using Neural Networks through the BRIDE Pipeline

Improving Gamma Imaging in Proton Therapy by Sanitizing Comp...

引用

IEEE International Conference on Big Data

作者： Michael O. Chen Julian Hodge Peter L. Jin Ella Protz Elizabeth Wong Ruth Obe Ehsan Shakeri Mostafa Cham Matthias K. Gobbert Carlos A. Barajas Vijay R. Sharma Sina Mossahebi Lei Ren Stephen W. Peterson Jerimy C. Polf Departments of Mathematics Dartmouth College USA Dept. of Mathematics and Statistics U. of Maryland USA James M. Bennett High School Salisbury MD USA Department of Mathematics and Sciences Florida Atlantic University USA Department of Mathematics Brookdale Community College USA Dept. of Computer Science and of Software Engineering U. of Houston Clear Lake USA Dept. of Information Systems U. of Maryland USA Dept. of Radiation Oncology U. of Maryland School of Medicine USA Dept. of Physics U. of Cape Town South Africa M3D Inc. USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Precision medicine in cancer treatment increasingly relies on advanced radiotherapies, such as proton beam radiotherapy, to enhance efficacy of the treatment. When the proton beam in this treatment interacts with patient matter, the excited nuclei may emit prompt gamma ray interactions that can be captured by a Compton camera. The image reconstruction from this captured data faces the issue of mischaracterizing the sequences of incoming scattering events, leading to excessive background noise. To address this problem, several machine learning models such as Feedfoward Neural Networks (FNN) and Recurrent Neural Networks (RNN) were developed in PyTorch to properly characterize the scattering sequences on simulated datasets, including newly-created patient medium data, which were generated by using a pipeline comprised of the GEANT4 and Monte-Carlo Detector Effects (MCDE) softwares. These models were implemented using the novel ‘Big-data REU Integrated Development and Experimentation’ (BRIDE) platform, a modular pipeline that streamlines preprocessing, feature engineering, and model development and evaluation on parallelized GPU processors. Hyperparameter studies were done on the novel patient data as well as on water phantom datasets used during previous research. Patient data was more difficult than water phantom data to classify for both FNN and RNN models. FNN models had higher accuracy on patient medium data but lower accuracy on water phantom data when compared to RNN models. Previous results on several different datasets were reproduced on BRIDE and multiple new models achieved greater performance than in previous research.

关键词： Particle beams Recurrent neural networks Accuracy Pipelines Phantoms Scattering Cameras Data models software Radiation therapy

来源：评论

学校读者我要写书评

暂无评论

Context-aware virtual adversarial training for anatomically-plausible segmentation

arXiv

引用

arXiv 2021年

作者： Wang, Ping Peng, Jizong Pedersoli, Marco Zhou, Yuanfeng Zhang, Caiming Desrosiers, Christian Department of Software IT Engineering Ecole de technologie supérieure MontrealH3C1K3 Canada Department of Systems Engineering Ecole de technologie supérieure MontrealH3C1K3 Canada School of Computer Science and Technology Shandong University Jinan250101 China

Despite their outstanding accuracy, semi-supervised segmentation methods based on deep neural networks can still yield predictions that are considered anatomically impossible by clinicians, for instance, containing holes or disconnected regions. To solve this problem, we present a Context-aware Virtual Adversarial Training (CAVAT) method for generating anatomically plausible segmentation. Unlike approaches focusing solely on accuracy, our method also considers complex topological constraints like connectivity which cannot be easily modeled in a differentiable loss function. We use adversarial training to generate examples violating the constraints, so the network can learn to avoid making such incorrect predictions on new examples, and employ the REINFORCE algorithm to handle non-differentiable segmentation constraints. The proposed method offers a generic and efficient way to add any constraint on top of any segmentation network. Experiments on two clinically-relevant datasets show our method to produce segmentations that are both accurate and anatomically-plausible in terms of region connectivity. Copyright © 2021, The Authors. 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

Case study of designing and evaluating an independent open learner model tool

引用

Higher Education Pedagogies 2023年第1期8卷

作者： Check-Yee Law John Grundy Karola V. Baggo Andrew Cain Rajesh Vasa a Faculty of Information Science and Technology Multimedia University Melaka Malaysia b Department of Software Systems & Cybersecurity Monash University Clayton Australia c Department of Computer Sci and Software Engineering Swinburne University of Technology Hawthorn Australia d Faculty of Sci Eng & Built Env Deakin University Burwood Australia

ABSTRACTOpen Learner Model (OLM) visualisations capture and display a learner’s learning state such as knowledge levels, learning progress, and misconceptions. Exposing learners to their own models offers learners a perspective about their learning state. Numerous benefits have been reported include providing more opportunities for learners to collaborate, enhancing learning outcomes, and prompting learners to be more self-regulated. We describe a new independent OLM tool, Doubtfire++ that we have designed to support Task-Oriented Portfolio teaching to raise student awareness of their progress and achievements, and to encourage self-regulated learning. The results of our evaluation show that Doubtfire++ helped the teaching staff in creating a supportive learning environment and students felt supported and rewarded for learning in a self-regulated manner. We have identified several OLM visualizations that were perceived to assist self-regulated learning. We also have gained insightful inputs and feedback that lead to expanding its application to a broader context.

关键词： Constructive alignment learning outcome open learner model portfolio teaching self-regulated learning visualization

来源：评论

学校读者我要写书评

暂无评论

Technical debt and agile software development practices and processes: An industry practitioner survey

arXiv

引用

arXiv 2021年

作者： Holvitie, Johannes Licorish, Sherlock A. Spínola, Rodrigo O. Hyrynsalmi, Sami MacDonell, Stephen G. Mendes, Thiago S. Buchan, Jim Leppänen, Ville Turku Centre for Computer Science Software Development Laboratory Turku Finland University of Turku Department of Information Technology Turku Finland University of Otago Department of Information Science Otago Dunedin New Zealand Salvador University Graduate Program in Systems and Computer Bahia Salvador Brazil Federal University of Bahia Fraunhofer Project Center for Software and System Engineering Salvador Brazil Tampere University of Technology Pori Campus Pori Finland Federal Institute of Bahia Information Technology Department Bahia Santo Amaro Brazil Auckland University of Technology School of Engineering Computer and Mathematical Sciences Auckland New Zealand

Context: Contemporary software development is typically conducted in dynamic, resource-scarce environments that are prone to the accumulation of technical debt. While this general phenomenon is acknowledged, what remains unknown is how technical debt specifically manifests in and affects software processes, and how the software development techniques employed accommodate or mitigate the presence of this debt. Objectives: We sought to draw on practitioner insights and experiences in order to classify the effects of agile method use on technical debt management, given the popularity and perceived success of agile methods. We explore the breadth of practitioners' knowledge about technical debt;how technical debt is manifested across the software process;and the perceived effects of common agile software development practices and processes on technical debt. In doing so, we address a research gap in technical debt knowledge and provide novel and actionable managerial recommendations. Method: We designed, tested and executed a multi-national survey questionnaire to address our objectives, receiving 184 responses from practitioners in Brazil, Finland, and New Zealand. Results: Our findings indicate that: 1) Practitioners are aware of technical debt, although, there was under utilization of the concept, 2) Technical debt commonly resides in legacy systems, however, concrete instances of technical debt are hard to conceptualize which makes it problematic to manage, 3) Queried agile practices and processes help to reduce technical debt;in particular, techniques that verify and maintain the structure and clarity of implemented artifacts (e.g., Coding standards and Refactoring) positively affect technical debt management. Conclusions: The fact that technical debt instances tend to have characteristics in common means that a systematic approach to its management is feasible. However, notwithstanding the positive effects of some agile practices on technical debt management, comp

关键词： Legacy systems

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2024 Quality Assessment of AI-Generated Content Challenge

arXiv

引用

arXiv 2024年

作者： Liu, Xiaohong Min, Xiongkuo Zhai, Guangtao Li, Chunyi Kou, Tengchuan Sun, Wei Wu, Haoning Gao, Yixuan Cao, Yuqin Zhang, Zicheng Wu, Xiele Timofte, Radu Gankhuyag, Ganzorig Yoon, Kihwan Xu, Yifang Fan, Haotian Kong, Fangyuan Zhao, Shiling Dong, Weifeng Yin, Haibing Zhu, Li Wang, Zhiling Huang, Bingchen Peng, Fei Fu, Huiyuan Ming, Anlong Wang, Chuanming Ma, Huadong He, Shuai Dou, Zifei Chen, Shu Yu, Zihao Guan, Fengbin Motamednia, Hossein Hosseini-Benvidi, S. Farhad Mahmoudi-Aznaveh, Ahmad Mansouri, Azadeh Saha, Avinab Mishra, Sandeep Gupta, Shashank Sureddi, Rajesh Saha, Oindrila Celona, Luigi Bianco, Simone Napoletano, Paolo Schettini, Raimondo Yang, Junfeng Fu, Jing Zhang, Wei Cao, Wenzhi Liu, Limei Peng, Han Yuan, Weijun Li, Zhan Cheng, Yihang Deng, Yifan Zhang, Huacong Xie, Haiyi Wang, Chengwei Chen, Baoying Zeng, Jishen Yang, Jianquan Wang, Weigang Fang, Xi Lv, Xiaoxin Yan, Jun Li, Haohui Qu, Bowen Li, Yao Luo, Shuqing Wang, Shunzhou Gao, Wei Lu, Zihao Conde, Marcos V. Timofte, Radu Lu, Yiting Li, Xin Wang, Xinrui Guan, Fengbin Chen, Zhibo Liao, Ruling Ye, Yan Wang, Qiulin Li, Bing Zhou, Zhaokun Geng, Miao Chen, Rui Tao, Xin Liang, Xiaoyu Sun, Shangkun Fang, Xi Wang, Weigang Yan, Jun Ma, Xingyuan Li, Jiaze Yang, Mengduo Xu, Haoran Zhou, Jie Zhu, Shiding Yu, Bohan Zhi, Tianwu Zhang, Yabin Li, Yaohui Li, Yang Xu, Jingwen Liu, Jianzhao Liao, Yiting Li, Junlin Chen, Baoying Zeng, Jishen Xie, Haiyi Wang, Chengwei Yang, Jianquan Chen, Pengfei Xu, Xinrui Shen, Jiabin Duan, Zhichao Liu, Jiahe Yan, Qi Qu, Youran Zeng, Xiaohui Wang, Lele Liao, Renjie Shanghai Jiao Tong University China Nanyang Technological University Singapore ETH Zürich Switzerland University of Würzburg Germany Korea Electronics Technology Institute Korea Republic of ByteDance China Hangzhou Dianzi University China Sankuai China Beijing University of Posts and Telecommunications China Beijing Xiaomi Mobile Software Co. Ltd. China University of Science and Technology of China China High Performance Computing Laboratory School of Computer Science Institute for Research in Fundamental Sciences Tehran Iran Department of Electrical and Computer Engineering Faculty of Engineering Kharazmi University Tehran Iran Cyber Research Institute Shahid Beheshti University Tehran Iran University of Texas Austin United States University of Massachusetts Amher United States Department of Informatics Systems and Communication Xiangjiang Laboratory Hunan University of Technology and Business China Jinan University China Sun Yat-sen University China Alibaba Group China Cisco Systems Inc. United States DP Technology Ltd. Shopee Pte. Ltd Tongji University China School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China University of Würzburg Germany Kuaishou Technology China Peking University China Zhejiang University China Bytedance Inc China Xidian University China University of British Columbia Canada University of Toronto Canada

This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

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：