Context and motivation: Artificial intelligence (AI) provides computer systems problem-solving and decision-making features mimicking human behavior. As AI becomes widely adopted, AI-powered systems become increasingl...
详细信息
ISBN:
(纸本)9783031573262;9783031573279
Context and motivation: Artificial intelligence (AI) provides computer systems problem-solving and decision-making features mimicking human behavior. As AI becomes widely adopted, AI-powered systems become increasingly ubiquitous. Requirements engineering (RE) is fundamental to system development, including AI-powered systems, which provide novel RE challenges. Question/problem: Developing means for addressing these challenges, which include increased need and importance of specifying and addressing social requirements, (e.g., responsibility, ethics, and trustworthiness);achieving a comprehensive understanding of all RE aspects, given the substantial growth in the diversity and complexity of requirements and the emergence of newand often contradictory ones;and, employing relevant methods and techniques that are suited for addressing these challenges. Principal ideas/results: We propose anRE4AI ontology as a first step toward addressing the above challenges. The development of the ontology was based on a meta-synthesis of relevant publications for identifying recurring themes and patterns, resulting in a set of themes categorized into RE stages, topics, stakeholders' roles, and constraints that formed the developed ontology. Contribution: The ontology provides a systematic and unambiguous representation of the accumulated RE knowledge about the system, including requirement themes, relationships between requirements, constraints, and stakeholders needed in the RE process. This ontology provides the basis for a complete AI RE methodology (AI-REM) framework that will incorporate methods to develop and manage AI-powered system requirements.
software-defined networking (SDN) decouples control and data planes of network devices to manage network services and determine forwarding paths in a centralized manner. In order to reduce the occurrence of path rerou...
详细信息
Nursing informatics (NI) integrates nursing knowledge with IT, making a difference in patient outcomes as well as better healthcare processes. softwareengineering (SE) principles deliver quality, efficiency, and opti...
详细信息
This paper presents a synthesis method of decision-making systems based on Agents forming multiple coalitions. The condition for coalition formation is defined by a mathematical model that solves the problem of global...
详细信息
Massive Open Online Courses (MOOCs) are widely receiving attention from learners because of their ability to recommend personalized courses to learners. While existing course recommendation methods have shown good per...
详细信息
ISBN:
(纸本)9789819755004;9789819755011
Massive Open Online Courses (MOOCs) are widely receiving attention from learners because of their ability to recommend personalized courses to learners. While existing course recommendation methods have shown good performance, they still overlook the learning sequence from easy to difficult and the correlation between different disciplinary categories, resulting in unsatisfactory performance. To tackle these, we propose a GAT-based Category-aware Course Recommendation system, named GCCR. Specifically, we integrate the learner-course-category tripartite graph and course sequence graph into a unified large-scale graph, and then introduce a learner-centered graph sampling strategy within this unified graph, optimizing GAT-based propagation. Besides, we utilize the genetic algorithm to adaptively search for a locally optimal assignment plan based on the correlation between disciplinary categories. Finally, to improve model convergence stability, we introduce the weighted dual prediction, assigning distinct weights to the losses of GCCR and its GAT-less variant to train simultaneously, named GCCR + D. Extensive experiments on real-world datasets from two different periods demonstrate the effectiveness of our model compared to prevailing baseline methods.
Fault localization is one of the most important activities in software debugging. Among various fault localization techniques, mutation-based fault localization (MBFL) has been commonly studied with its promising perf...
详细信息
A truss member is an essential component for supporting roofs and bridge construction. While steel is the primary or most common material used, the industry faces various challenges today, such as product shortages an...
详细信息
This paper present a novel blockchain CP-ABE (Ciphertext-Policy Attribute-based Encryption) data ciphertext sharing scheme, leveraging decentralized proxy re-encryption. It utilizes Ethereum blockchain and zero-knowle...
详细信息
Under the background of engineering education accreditation, the analog electronic technology course, with the comprehensive cultivating goal of knowledge, ability and quality, adopts students-centered and online merg...
详细信息
Improving the performance of predicting student performance by transfer learning has become a new research focus in the field of education datamining. However, most works concentrate on homogeneous transfer learning, ...
详细信息
ISBN:
(纸本)9789819754946;9789819754953
Improving the performance of predicting student performance by transfer learning has become a new research focus in the field of education datamining. However, most works concentrate on homogeneous transfer learning, therefore they cannot solve the feature heterogeneity between source and target domains. A heterogeneous transfer learning algorithm with feature matching based on correlation coefficients and fine-tuning (FMBCC-FT) is proposed. FMBCC-FT first normalizes the source and target domain data, then selects and matches features according to the correlation coefficients between the features and the labels, finally trains the logistic regression model with source domain data and fine-tunes with target domain labeled data. The experiments are carried out with the open datasets of edX as the source domain and the learning data from Jilin University as the target domain. The results show that the proposed method outperforms the related works and confirm its effectiveness and competitiveness.
暂无评论