检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Perera, Judith Tempero, Ewan Tu, Yu-Cheng Blincoe, Kelly Galster, Matthias School of Computer Science The University of Auckland Auckland1010 New Zealand Department of Electrical Computer and Software Engineering The University of Auckland Auckland1010 New Zealand Department of Computer Science and Software Engineering College of Engineering University of Canterbury Christchurch1010 New Zealand

software practitioners can make sub-optimal decisions concerning requirements during gathering, documenting, prioritizing, and implementing requirements as software features or architectural design decisions - this is captured by the metaphor 'Requirements Technical Debt (RTD).' In our prior work, we developed a conceptual model to understand the quantification of RTD and support its management. In this paper, we present our perspective and the vision to apply the lens of RTD to software requirements concerning veracity, i.e., requirements related to truth, trust, authenticity, and demonstrability in software-intensive systems. Our goal is to cultivate awareness of veracity as an important concern and eventually support the management of RTD for software requirements concerning veracity, what we term as 'Veracity Debt,' through its quantification. Copyright © 2024, The Authors. All rights reserved.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

How Propense Are Large Language Models at Producing Code Smells? A Benchmarking Study

arXiv

引用

arXiv 2024年

作者： Velasco, Alejandro Rodriguez-Cardenas, Daniel Alif, Luftar Rahman Palacio, David N. Poshyvanyk, Denys Department of Computer Science William & Mary United States Department of Software Engineering University of Dhaka Bangladesh

Large Language Models (LLMs) have shown significant potential in automating software engineering tasks, particularly in code generation. However, current evaluation benchmarks, which primarily focus on accuracy, fall short in assessing the quality of the code generated by these models, specifically their tendency to produce code smells. To address this limitation, we introduce CodeSmellEval, a benchmark designed to evaluate the propensity of LLMs for generating code smells. Our benchmark includes a novel metric: Propensity Smelly Score (PSC), and a curated dataset of method-level code smells: CodeSmellData. To demonstrate the use of CodeSmellEval, we conducted a case study with two state-of-the-art LLMs, CodeLlama and Mistral. The results reveal that both models tend to generate code smells, such as simplifiable-condition and consider-merging-isinstance. These findings highlight the effectiveness of our benchmark in evaluating LLMs, providing valuable insights into their reliability and their propensity to introduce code smells in code generation tasks. © 2024, CC BY-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Statistical Data Mining with Slime Mould Optimization for Intelligent Rainfall Classification

引用

computer Systems science & engineering 2023年第10期47卷 919-935页

作者： Ramya Nemani G.Jose Moses Fayadh Alenezi K.Vijaya Kumar Seifedine Kadry Jungeun Kim Keejun Han Department of Mathematics Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science and Engineering University Institute of Engineering and Technology(UIET)Guru Nanak UniversityHyderabadIndia Department of Electrical Engineering College of EngineeringJouf UniversitySaudi Arabia Department of Computer Science and Engineering GITAM School of TechnologyVishakhapatnam CampusGITAM(Deemed to be a University)VishakhapatnamIndia Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea Division of Computer Engineering Hansung UniversitySeoul02876Korea

Statistics are most crucial than ever due to the accessibility of huge counts of data from several domains such as finance,medicine,science,engineering,and so *** data mining(SDM)is an interdisciplinary domain that examines huge existing databases to discover patterns and connections from the *** varies in classical statistics on the size of datasets and on the detail that the data could not primarily be gathered based on some experimental strategy but conversely for other ***,this paper introduces an effective statistical Data Mining for Intelligent Rainfall Prediction using Slime Mould Optimization with Deep Learning(SDMIRPSMODL)*** the presented SDMIRP-SMODL model,the feature subset selection process is performed by the SMO algorithm,which in turn minimizes the computation *** rainfall *** neural network with long short-term memory(CNN-LSTM)technique is *** last,this study involves the pelican optimization algorithm(POA)as a hyperparameter *** experimental evaluation of the SDMIRP-SMODL approach is tested utilizing a rainfall dataset comprising 23682 samples in the negative class and 1865 samples in the positive *** comparative outcomes reported the supremacy of the SDMIRP-SMODL model compared to existing techniques.

关键词： Statistical data mining predictive models deep learning rainfall prediction parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Microfluidic chip foreign body detection based on improved YOLOx

Microfluidic chip foreign body detection based on improved Y...

引用

2022 International Conference on Artificial Intelligence, Virtual Reality, and Visualization, AIVRV 2022

作者： Yan, Hao-Dong Liao, Li-Min Liu, Xiao-Dong School of Computer Science and Artificial Intelligence Zhengzhou University Zhengzhou450001 China Software Professional Department Guangdong Foshan Lianchuang Graduate School of Engineering Foshan528311 China

ISBN: (纸本)9781510662988

To solve the problem of identifying the presence of foreign objects in microfluidic chip images, an improved model is proposed for the feature of small foreign object targets. The attention mechanism is introduced to enhance the perceptiveness of the model in channel and space. The ResUnit module in the network is modified to enhance the feature information. Also choose diou as the loss function to improve the edge accuracy. The experimental results show that the improved YOLOx target detection algorithm has a significant improvement in foreign object detection in terms of accuracy, and the average precision (AP) reaches 99.12% on YOLOx, which is 0.7% higher than the original network. The results show that the improved algorithm based on YOLOx in this study can achieve foreign object detection in microfluidic chip images. © 2023 SPIE. All rights reserved.

关键词： Microfluidic chips

来源：评论

学校读者我要写书评

暂无评论

Aspect-Based Sentiment Analysis on Amharic Text for Evaluating Ethio-Telecom Services 2

Aspect-Based Sentiment Analysis on Amharic Text for Evaluati...

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Tesfa, Tarikwa Belete, Befikadu Abera, Samuel Mohapatra, Sudhir Kumar Das, Tapan Kumar Addis Ababa Science and Technology University Department of Software Engineering Addis Ababa Ethiopia Ethio Telecom Services Addis Ababa Ethiopia Sri Sri University Faculty of Emerging Technologies Cuttack India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

ISBN: (纸本)9798350328202

People are increasingly expressing their views and opinions about a company's goods or service on social media these days. For all types of businesses and organizations, sentiment analysis in text can be used to find prospective customers and obtain quick feedback on the services or goods they provided. As a result, the organization has a better chance and opportunity to meet the needs of the consumer. Using sentiment analysis, we may extract important information from the thoughts and emotions of an organization's supporters and clients. It examines natural language content produced about services and goods. Detailed opinion mining at the aspect/feature level to serve consumer and organizational needs. In this study, three different machine learning algorithms, these are Naïve Bayes (NB), Support Vector Machine (SVM), and K- Nearest Neighbor (KNN) are used to build the proposed aspect-based sentiment analysis model from the customer comments in Amharic text which is collected from Ethio-telecom official Facebook page. The collected data is annotated into sentiment polarity and aspect-based sentiment classes by the help of five annotators. After data annotation, different preprocessing tasks were implemented. Bag of words and TF-IDF word representation techniques were used to represent each unique word to their vector representation. The experiment was conducted on those three models and the result was validated. The labeled aspects were not balanced so that a SMOTE class imbalance handling technique was employed to the dataset. Finally, SVM model trained with TF-IDF word representation technique with SMOTE oversampled dataset has achieved the highest accuracy result of 98% as compared to NB and KNN. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Method for Detecting Jute Pests Using Deep Convolutional Neural Networks 5

An Intelligent Method for Detecting Jute Pests Using Deep Co...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Vignesh, S. Prabhu, S. Sampathkumar, R. Rani, M. Thillai Rejina Parvin, J. Maheswari, G. Uma Saravanakumar, R. Karpagam Academy of Higher Education Department of Computer Applications Tamil Nadu Coimbatore India KPR Institute of Engineering and Technology Department of Mechatronics Engineering Tamil Nadu Coimbatore India Sri Krishna College of Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Sri Krishna College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India RMK College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Iconix Software Solution Tamil Nadu Tirunelveli India

ISBN: (纸本)9798331518097

Pest attacks pose a serious threat to the production of jute and other significant crops. Jute farmers often utilize their visual sense and hands-on expertise to distinguish between multiple diseases that seem to be identical. The intelligent model we built for the identification of jute pests was based on a deep convolutional neural network (DCNN). This practical difficulty led to the development of this concept. The proposed DCNN model can automatically identify jute pest concerns with high speed and accuracy based on image recognition. In addition, images of the four most common jute bugs are included in an organized image graphics collection. Our model yields a DCNN accuracy is 96.72% for the four most significant jute pest kinds. Further proof of the model's effectiveness is provided by the accuracy, recall, F1-score, and confusion matrix metrics. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Partial Permutations Comparison, Maintenance and Applications 33

Partial Permutations Comparison, Maintenance and Application...

引用

33rd Annual Symposium on Combinatorial Pattern Matching, CPM 2022

作者： Levy, Avivit Porat, Ely Shalom, B. Riva Department of Software Engineering Shenkar College Ramat-Gan Israel Department of Computer Science Bar-Ilan University Ramat-Gan Israel

ISBN: (纸本)9783959772341

This paper focuses on the concept of partial permutations and their use in algorithmic tasks. A partial permutation over Σ is a bijection πpar : Σ1 7→ Σ2 mapping a subset Σ1 ⊂ Σ to a subset Σ2 ⊂ Σ, where |Σ1| = |Σ2| (|Σ| denotes the size of a set Σ). Intuitively, two partial permutations agree if their mapping pairs do not form conflicts. This notion, which is formally defined in this paper, enables a consistent as well as informatively rich comparison between partial permutations. We formalize the Partial Permutations Agreement problem (PPA), as follows. Given two sets A1, A2 of partial permutations over alphabet Σ, each of size n, output all pairs (πi, πj), where πi ∈ A1, πj ∈ A2 and πi agrees with πj. The possibility of having a data structure for efficiently maintaining a dynamic set of partial permutations enabling to retrieve agreement of partial permutations is then studied, giving both negative and positive results. Applying our study enables to point out fruitful versus futile methods for efficient genes sequences comparison in database or automatic color transformation data augmentation technique for image processing through neural networks. It also shows that an efficient solution of strict Parameterized Dictionary Matching with One Gap (PDMOG) over general dictionary alphabets is not likely, unless the Strong Exponential Time Hypothesis (SETH) fails, thus negatively answering an open question posed lately. © Avivit Levy, Ely Porat, and B. Riva Shalom;licensed under Creative Commons License CC-BY 4.0

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Optimizing MEMS Optical Arrays with Silicon Micro Mirrors using Machine Learning Techniques 3

Optimizing MEMS Optical Arrays with Silicon Micro Mirrors us...

引用

3rd International Conference on Computational Modelling, Simulation and Optimization, ICCMSO 2024

作者： Joshi, Vilas Ramrao Sharma, Surender Kumar Galande, Vijay Agatrao Sachin Patil, Pallavi Patil, Ushadevi Suttarwala, Hussain Sharma, Deepak K. Savitribai Phule Pune University Department of Computer Engineering Pune India Poornima University Department of Electrical Engineering Jaipur India KJEI's Trinity Academy of Engineering Department of Engineering Science Pune India Genba Sopanrao Moze College of Engineering Department of Civil Engineering Pune India American Express Senior Software Engineer PhoenixAZ85054 United States University of Technology Jaipur India

ISBN: (纸本)9798350361391

In the rapidly evolving landscape of optical microsystems, the infusion of Machine Learning (ML) techniques stands out as a catalyst for unprecedented progress. This research paper delves into the intricate interplay between Micro-Electro-Mechanical Systems (MEMS), optical arrays, and silicon micro mirrors, shedding light on the transformative prowess unleashed by Machine Learning in optimizing these intricate components. Focusing on the limitations posed by conventional designs, the paper not only illuminates the challenges encountered but also presents a compelling narrative of how ML algorithms emerge as formidable allies, poised to surmount these hurdles with ingenuity and precision. The exploration extends beyond a mere technical discourse;it unfolds as a narrative of innovation, where the convergence of MEMS, optical arrays, and silicon micro mirrors, guided by the intelligence of Machine Learning, transcends traditional boundaries, propelling optical microsystems into an era of unparalleled efficiency and adaptability. This research beckons a new epoch, where the intricate dance of silicon micro mirrors and the intricate mechanics of MEMS find harmony through the symphony of Machine Learning, reshaping the landscape of optical microsystems and inspiring future possibilities that were once deemed beyond reach. © 2024 IEEE.

关键词： Microchannels

来源：评论

学校读者我要写书评

暂无评论

The Art of Deception: Black-box Attack Against Text-to-Image Diffusion Model 29

The Art of Deception: Black-box Attack Against Text-to-Image...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Lu, Yuetong Xu, Jingyao Li, Yandong Lu, Siyang Wei, Xiang Lu, Wei Beijing Jiaotong University School of Software Engineering Beijing China Beijing Jiaotong University School of Computer and Information Technology Beijing China University of Central Florida Department of Computer Science OrlandoFL United States

ISBN: (纸本)9798350330717

With the rise of Foundation models, Text-to-Image models, as one of its important branches, have been increasingly applied. While focusing on the impressive generation capabilities of these models, it is also crucial to pay attention to the robustness of the models against attacks. In this paper, we shift our focus towards studying the vulnerability of Text-to-Image (T2I) models. To this end, we propose a black-box attack method and demonstrate that T2I models are susceptible to adversarial text attacks. Specifically, this method can disrupt T2I models by making subtle modifications to the model's input (i.e., prompt) without accessing the model parameters, resulting in the generation of incorrect images. It is worth mentioning that we discovered the ability to switch different types of tokenizers within this black-box framework to handle text, furthermore, this attack framework can be applied to target different versions of T2I models. The experiments indicate that the images generated through adversarial text exhibit noticeable errors. We also employ CLIP score, a metric used to evaluate the similarity between images and image descriptions, to assess the results. The findings demonstrate a significant decrease in the visual-textual similarity after the model is subjected to attacks. Additionally, we have identified a specific type of error that T2I models tend to make when facing attacks - when confronted with unrecognizable text, the model often interprets it as human-related content. This paper not only highlights the vulnerability of T2I models to adversarial text attacks but also further discusses potential methods that could enhance the robustness of these attack techniques. This provides a valuable reference for future research directions in this field. © 2023 IEEE.

关键词： Diffusion ModelAdversarial Attack Foundation Model Text-to-Image

来源：评论

学校读者我要写书评

暂无评论

Automatic Repeat Request Design in AoI-Aware Broadcast With Heterogeneous Direct and Relay-Assisted Users

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Xueer Pan, Haoyuan Chan, Tse-Tin Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China The Education University of Hong Kong Department of Mathematics and Information Technology Hong Kong Shenzhen University National Engineering Laboratory for Big Data System Computing Technology The College of Computer Science and Software Engineering Shenzhen China

This paper investigates the design of automatic repeat request (ARQ) protocols in age of information (AoI)-aware broadcast systems with heterogeneous users, including both direct and relay-assisted users. In this setup, a direct user receives status updates directly via a single-hop link, while a relay-assisted user can receive status updates through either a direct single-hop link or a two-hop relay-assisted link. While ARQ is commonly used to ensure reliable transmission in error-prone wireless networks, previous studies suggest that ARQ does not improve the average AoI in single-hop networks. However, its impact on AoI in systems with relays, particularly those involving heterogeneous users, remains unclear. We address this gap by analyzing the average AoI under different ARQ strategies, introducing a transmission limit k ≥ 0 at the relay. Here, k = 0, k = 1, and k > 1 correspond to non-relay, non-ARQ-at-relay, and truncated-ARQ-at-relay strategies, respectively. Utilizing a unified Markov chain framework that models the transmission processes for each user type, we derive the theoretical average AoI. Our results show that the direct user benefits most from non-relay and non-ARQ strategies, similar to single-hop systems. In contrast, the relay-assisted user achieves optimal performance with truncated-ARQ-at-relay, leveraging both direct and relay-assisted links. For the overall system, applying a non-ARQ-at-relay approach strikes a balance in AoI between the direct and relay-assisted users, leading to a more stable and lower system-wide average AoI. © 2014 IEEE.

关键词： Mobile telecommunication systems

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：