检索结果-内蒙古大学图书馆

IAENG International Journal of Computer Science 2025年第1期52卷 171-186页

作者： Ignaim, Karam Fernandes, João M. Department of Software Engineering Al Balqa’ Applied University Salt Jordan Centro ALGORITMI/Department of Informatics University of Minho Braga Portugal

Successful product development is mostly dependent on how well contributions from stakeholders are taken into account. There are signs that the way stakeholders are involved in a project is directly linked to how well software products are delivered. Engagement of stakeholders enables organisations to proactively consider the requirements and expectations of anyone with a stake in the product under development. For a given stakeholder management process (SMP) to work well, it is recommended that all stakeholders be listed in a reference document, and their involvement in the process to be kept up-to-date. For this purpose, this study presents a solution to this problem by coming up with a feature-modelling-based stakeholder management process (FM-SMP) for capturing and documenting the right stakeholders during the SMP. The FMSMP supports ongoing monitoring of the status and attributes of stakeholders during this process. This manuscript includes the description of a case study on smart homes, where the proposed FM-SMP was adopted and evaluated successfully. The result of the case study reveals that the use of FM-SMP improves the ability of software engineers to effectively and precisely identify the appropriate stakeholders, thereby enhancing enduser satisfaction in software product development. © (2025), (International Association of Engineers). All rights reserved.

关键词： Product development

来源：评论

学校读者我要写书评

暂无评论

Bias analysis of AI models for undergraduate student admissions

引用

Neural Computing and Applications 2025年第12期37卷 7785-7795页

作者： Van Busum, Kelly Fang, Shiaofen Department of Computer Science and Software Engineering Butler University IndianapolisIN United States Computing and Engineering Indiana University Luddy School of Informatics Indiana University Indianapolis IndianapolisIN United States

Bias detection and mitigation is an active area of research in machine learning. This work extends previous research done by the authors Van Busum and Fang (Proceedings of the 38th ACM/SIGAPP Symposium on Applied Computing, 2023) to provide a rigorous and more complete analysis of the bias found in AI predictive models. Admissions data spanning six years was used to create an AI model to determine whether a given student would be directly admitted into the School of Science under various scenarios at a large urban research university. During this time, submission of standardized test scores as part of a student’s application became optional which led to interesting questions about the impact of standardized test scores on admission decisions. We developed and analyzed AI models to understand which variables are important in admissions decisions, and how the decision to exclude test scores affects the demographics of the students who are admitted. We then evaluated the predictive models to detect and analyze biases these models may carry with respect to three variables chosen to represent sensitive populations: gender, race, and whether a student was the first in his/her family to attend college. We also extended our analysis to show that the biases detected were persistent. Finally, we included several fairness metrics in our analysis and discussed the uses and limitations of these metrics. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

software Development for Text Processing in Mapping Architecturally Significant Requirements Towards Quality Attributes 10

Software Development for Text Processing in Mapping Architec...

引用

10th International Conference on Smart Computing and Communication, ICSCC 2024

作者： Seba, Monica Dewi Priyadi, Yudi Darwiyanto, Eko Telkom University Department of Informatics Bandung Indonesia Telkom University Department of Software Engineering Bandung Indonesia

ISBN: (纸本)9798350363104

Understanding Architecturally Significant Requirements (ASRs) and Quality Attributes (QAs) is crucial to improving software quality. A system's mismatch problem between ASRs and QAs can have serious consequences. System performance can be negatively affected, resulting in poor user experience and decreased operational efficiency. This research will focus on developing software to process text information derived from mapping ASRs against QAs in the documentation artifacts of an application called IdVar4CL, which is the object of the case study. The purpose of this research is to develop software that can map ASRs to QAs through text processing based on a Requirement Specification to contribute to the development of datasets, adopting the stages of the agile-Scrum model in conducting text extraction as well as in semantic similarity, and validity-reliability of the mapping results. This research has successfully identified 10 ASR documents and 11 QA documents. In addition, the results of adopting the stages of the agile model with the Scrum method are four sprint stages accompanied by Retrospective: Data preprocessing, Term Frequency Inverse Document Frequency (TF-IDF) Vectorization, Work embedding, and Semantic Similarity. Invalidity and reliability activities, this research has also managed to get 5 ASR documents with values below 0.8, namely D1(0.77), D2(0.775), D4(0.785), D5(0.79), and D7(0.765). © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning GPT-4o-Mini for Programming Questions Generation

Fine-Tuning GPT-4o-Mini for Programming Questions Generation

引用

2024 International Conference on Computer and Applications, ICCA 2024

作者： Hesham, Alaa Hamdy, Abeer The British University in Egypt Faculty of Informatics and Computer Science Department of Software Engineering Cairo Egypt

ISBN: (纸本)9798350367560

Creating programming questions that are both meaningful and educationally relevant is a critical task in computer science education. This paper introduces a fine-tuned GPT4o-mini model (C2Q). It is designed to generate meaningful questions by leveraging semantic feature extraction and well- crafted prompts. The approach addresses the limitations of traditional generative models, offering a deeper understanding of programming code and producing questions that are precise, diverse, and relevant to a given code snippets. The proposed framework incorporates essential code elements, such as control structures and method attributes, to generate questions that align with programming concepts. Evaluation metrics used were BLEU, ROUGE-1, and ROUGE-L to evaluate the model's performance. The findings reveal that the model achieves better structural coherence and conceptual relevance while focusing on contextual understanding over exact term matching. This work highlights the potential of the proposed approach to advance teaching and assessment methods in computer science. © 2024 IEEE.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

A fuzzy method of recognizing color label for controlling the movement of actuators the mechatronic complex

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 16949-16959页

作者： Bobyr, Maxim Milostnaya, Natalia Department of Software Engineering Faculty of Fundamental and Applied Informatics Southwest State University 50 let Oktyabrya Kursk305000 Russia

The hardware and software model for controlling the movement of actuators in the mechatronic complex based on a fuzzy method of recognizing the color label is presented in the article. The main task of this complex is to capture moving objects in real-time. Fixation of objects is carried out in two modes: manual and automatic. In manual mode, the grip is carried out by the operator. In automatic mode, a set of magnetic sensors is used for fixation, which monitors the location of the actuators of the mechatronic complex and a laser sensor or technical vision system that determines the location of the moving object. The main problem in the automatic mode is to determine the moment at which the axes of the moving object and the gripper are aligned. A fuzzy model for determining the time of the moment of alignment of two axes was developed in the article to solve this problem. Also, a fuzzy method of recognizing a color label based on the approach of area’s ratio is shown in the article. The novel contribution of a proposed method is the fuzzy segmentation scheme used for detecting the colored mark by image processing. A distinctive feature of a defuzzification model is the usage of a universal formula to find the area of geometric shapes. As a result, the time of defuzzification was reduced to 65 ns. It allows to use the proposed method in real-time systems, for example, in video processing systems with resolutions 1024 × 768 and 25 fps. The article presents a numerical simulation of the process of fixing a moving object, which confirms the effectiveness of the proposed solution. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intent Detection Through ChatGPT-Driven Data Augmentation 5th

Enhancing Intent Detection Through ChatGPT-Driven Data Augme...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Tesfagergish, Senait Gebremichael Damasevicius, Robertas Kapociute-Dzikiene, Jurgita Department of Software Engineering Kaunas University of Technology Kaunas Lithuania Department of Applied Informatics Vytautas Magnus University Kaunas Lithuania

ISBN: (纸本)9789819771776

This study investigates the improvement of intent detection tasks, focusing on the Facebook Multilingual Task Oriented Dataset, which encompasses 12 classes, including specific intents like weather and alarms. To address the scarcity of datasets in the Amharic language for intent detection, we first translated the English dataset into Amharic using Google Translator. Additionally, we expanded the dataset to include Lithuanian, German, French, and Czech languages. Next, we balance the dataset through data augmentation using ChatGPT, particularly targeting the four least-covered classes by adding 50 sentences to each. For text vectorization, the language-agnostic BERT sentence embedding model was used for its multilingual capabilities and Amharic language support. The classification was based on Cosine similarity, incorporating a majority voting mechanism from the most similar training instances. We conducted multilingual experiments to evaluate the performance of intent detection across various languages, both before and after data augmentation. Our findings highlight the effectiveness of using ChatGPT for data augmentation in intent detection tasks across all investigated languages, particularly in enhancing underrepresented languages and specific intents. We achieved improvement in intent detection performance for minority classes. This shows the benefit of using ChatGPT with imbalanced datasets for multilingual tasks and applications. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Translation (languages)

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Extraction of Pap Smear Images Based on Convolutional Neural Network and Vision Transformer for Cervical Cancer Classification

Deep Feature Extraction of Pap Smear Images Based on Convolu...

引用

2024 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IAICT 2024

作者： Sholik, Mohammad Fatichah, Chastine Amaliah, Bilqis Department of Informatics Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Software Engineering Universitas Telkom Surabaya Indonesia

ISBN: (纸本)9798350353464

Cervical cancer is a malignant disease that women commonly experience. This cancer can be prevented if screening is carried out early using the pap smear method. The pap smear technique yields a subjective diagnosis. An appropriate decision-making method is needed to overcome this obstacle, such as using a computer-based diagnosis method and applying machine learning. We apply a combination of deep feature extraction using transfer learning from convolutional neural network models and vision transformers to obtain local and global features. Local and global features can represent an image's more comprehensive variety of features. The combined features are then reduced using two steps, principal component analysis and linear discriminant analysis, to obtain a representation of the essential features of the data. The reduced features are then analyzed using several classifiers, including SVM, K-NN, MLP, and LR. The proposed framework was evaluated on three publicly accessible datasets, namely Herlev, Mendeley LBC, and SIPaKMeD, achieving classification accuracies of 97.83% (SVM, K-NN, MLP, and LR), 100% (SVM, K- NN, MLP, and LR), and 98.52% (SVM, K-NN, and LR) respectively. ©2024 IEEE.

关键词： Cervical Cancer Classification Deep Feature Extraction Feature Reduction

来源：评论

学校读者我要写书评

暂无评论

Influence of Human Skills on Scrum Teams: A Case Study of Junior Team software Development 15

Influence of Human Skills on Scrum Teams: A Case Study of Ju...

引用

15th International Conference on Information Technology and Electrical engineering, ICITEE 2023

作者： Phakdee, Nuttaporn Saengsai, Apisit Burapha University. Faculty of Informatics Department of Software Engineering Chonburi Thailand

ISBN: (纸本)9798350304466

Agile software development methodologies, including Scrum, have become popular for their flexibility and collaborative approach. However, the success of Scrum teams heavily depends on the dynamics among team members. This study explores the challenges related to Agile software development, specifically focusing on the influence of human skills on the Scrum team. While Scrum encompasses various well-defined aspects, it does not explicitly address personality traits. Consequently, this study seeks to explore how teams' performance is influenced by the human skills possessed by their members during the implementation of Agile methodologies. This study investigated eight teams of software engineering students engaged in software development projects by observing impacted team processes in each iteration. The results show that soft skills and J/P significantly influence team processes. However, their impact on the team's product varies across cycles. Additionally, soft skills interact with the Feeling (F)/ Thinking (T) and Judging (J)/Perceiving (P), affecting team processes and products. © 2023 IEEE.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

Classification of Privacy Preserved Medical Data with Fractional Tuna Sailfish Optimization Based Deep Residual Network in Cloud

引用

Annals of Data Science 2024年 1-26页

作者： Shikalgar, Shabanam K. Kumar, N. V. S. Pavan Singh, Gavendra Rashid, Faizur Sharad Institute of Technology College of Engineering Yadrav India Koneru Lakshmiah Education Foundation Vijayawada India Department of Software Engineering College of Computing and Informatics Haramaya University Dire Dawa138 Ethiopia College of Computing and Informatics Haramaya University Dire Dawa138 Ethiopia

Nowadays, with the growth of emerging technologies, increased attention has been paid to the classification of privacy-preserved medical data and development of various privacy-preserving models for the promotion of online medical pre-diagnosis systems. Medical data is highly sensitive and it is essential to ensure privacy of medical records from third-party users to increase service quality, satisfy patients and earn trust. The classification of medical preserved data is helpful to build a clinical decision system by classifying patients based on their disease and symptoms. In this article, a hybrid optimization-based deep learning model named Fractional Tuna Sailfish Optimization–Deep Residual Network (FractionalTSFO-DRN) is designed to precisely classify the privacy preserved medical data. A privacy utility coefficient matrix is used to ensure the privacy of medical data by generating a key matrix using Tuna Sailfish Optimization (TSFO) algorithmic technique. The privacy-preserved medical data is allowed for the classification process using DRN and the introduced Fractional TSFO is used to optimize and enhance the classification in DRN. The assessment followed by using heart disease prediction databases proved that the employed classification technique recorded an accuracy of 94.67%, a True Positive Rate of 93.56%, and a True Negative Rate of 89.68% respectively. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Chatbots and Social Robots in Education: FEPER Framework for Efficiency, Pedagogical and Ethical Requirements 15

Artificial Intelligence Chatbots and Social Robots in Educat...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Virvou, Maria Tsihrintzis, George A. University of Piraeus Software Engineering Laboratory Department of Informatics Piraeus Greece Machine Learning Image Processing and Multimedia Applications Laboratory University of Piraeus Department of Informatics Piraeus Greece

ISBN: (纸本)9798350368833

Artificial Intelligence (AI) chatbots and social robots, when incorporated into educational settings, have the potential to significantly transform the learning experience, particularly by providing more personalised, one-on-one attention to students. However, deploying such technology in classrooms also presents challenges. These include unresolved issues related to human-AI interaction, pedagogy and theories, human oversight, data privacy, transparency, accuracy and trust. This paper explores the development of a comprehensive framework aimed at enhancing the efficiency, pedagogical effectiveness, and ethical use of AI-driven educational tools, focusing on social robots and chatbots. The framework addresses important factors such as interaction quality, requirements engineering strategies, and the alignment of AI functionalities with educational goals. It also examines ethical concerns, including data security, user transparency, and trustworthiness. By reviewing recent literature on social robots and chatbots and incorporating emerging ethical considerations alongside long-standing educational objectives, this research aims at establishing a holistic framework, FEPER, of best practices and requirements. The findings offer valuable insights for educators, policymakers, and developers aiming to create more dynamic, personalised, and ethical educational environments using AI technology. © 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：