Journal of Cases on Information Technology

In this article, we discuss the stagnation problem related to circulating digital course resources (DCRs) in China. Using information ecology theory, questionnaires and practical tests, we learn that universities in China are embodied with information isolation, and hence circulating the associated DCRs is inhibited. Our results show that the original simple mechanical construction no longer meets the current needs of teaching and learning. Consequently, coordination is essential among relevant subjects and circulating DCRs. In doing so, we further reoptimise the current circulating system of DCRs in Chinese universities through the use of information ecology theory and in turn provide a new solution for the sustainable construction and application of DCRs.

Support vector data description (SVDD) inspires us in data analysis, adversarial training, and machine unlearning. However, collecting support vectors requires pricey computation, while the alternative boundary selection with O(N2) is still a challenge. The authors propose an indispensable edge pattern selection method (IEPS) for data description with direct SVDD model building. IEPS suggests a double local analysis to select the global edge patterns. Edge patterns belong to a subset of the target problem of SVDD and its variants, and neighbor analysis becomes pivotal. While an excessive number of participating data result in redundant computations, an insufficient number may impede data separability or compromise the model’s quality. Consequently, a data-adaptive sampling strategy has been devised to ascertain an optimal ratio of retained data for edge pattern selection. Extensive experiments indicate that IEPS keeps indispensable edge patterns for data description while reducing the interference in the norm vector generation to guarantee the effectiveness for clustering analysis.

A dynamic mutation probability formula is utilized to optimize the model. In order to solve the logistics warehouse path problem, the ant colony optimization algorithm, optimized by a genetic algorithm, is employed to construct a logistics warehouse path optimization model. This model effectively optimizes the logistics warehouse paths. Test results comparing the convergence and distribution of non-inferior solutions demonstrated that the proposed model outperforms others in terms of convergence and non-inferior solution distribution. In practical logistics warehouse optimization, applying the proposed model to optimize cargo locations can significantly enhance the effectiveness of the objective function. The optimization resulted in improvements for all four objective functions related to cargo location, with reduction rates of 10.38%, 30.88%, 51.78%, and 88.49%, respectively. For the optimization of logistics warehouse paths, the original distance was 47.6m, which was reduced to 27.8m after optimization. Consequently, the picking distance decreased by 41.60%.

Implementing mental health education (MHE) in schools is vital for students' psychological well-being. Subject infiltration integrates psychological factors into subject learning, promoting healthy development. However, English learning can introduce issues like self-confidence and language anxiety. Early identification of mental health problems (MHP) is crucial. This study, rooted in humanistic psychology and constructivism, explores affective factors, strategies, teaching, and English listening. The algorithm, based on the DeepPsy model, shows promise, identifying 75% of students with MHP. This research aids universities in offering timely support to high-risk students, minimizing long-term harm. The algorithm contributes to a healthier learning environment by enhancing English teaching and addressing mental health issues early.

Traditional customer segmentation methods cannot obtain more effective information from massive customer data, which affects the formulation of marketing strategies. Based on this, this study constructs a customer segmentation marketing strategy model that integrates support vector machines and clustering algorithms. This model first utilizes support vector machines to segment existing customer data, and then integrates support vector machines and clustering algorithms to construct a customer segmentation model. Finally, simulation experiments are conducted using the dataset. The results show that the model algorithm obtains the optimal solution when the quantity of iterations is 50. Meanwhile, the average error rate of the model algorithm in the customer segmentation process is 6.82%, the average recall rate is 91.28%, and the average profit predicted by the impact strategy developed by the segmentation model is 29.88%, which is 2.53% different from the true value.

With the advent of the information age, the traditional pavement management technology of operating expressways can no longer meet the higher requirements for the improvement of engineering quality in the information age. This paper proposes a method of integrated analysis based on BIM (building information modeling) and GIS (geographic information system), builds an intelligent platform for highway operation and maintenance, and solves the problem of data islands in highway maintenance and management.

With the continuous progress of information technology, distance English teaching is becoming a practical choice. The introduction of 5G technology has improved the English classroom experience and provided innovation for modern teaching. With the help of wireless communication technology, teachers can effectively impart cognitive skills. Compared with traditional English teaching methods, it obviously enhances the two-way communication between students and professors. Teaching students in accordance with their aptitude uses the reformed Best Available Technology Optimization Algorithm (RBOA) to optimize the transmission process and evaluate students' cognitive ability. This study shows that the proposed method seems to be more effective than the traditional college English course and can significantly improve students' language ability. This optimization scheme has a potential wide application prospect in teaching practice, which has injected new vitality and possibility into English education.

When a cyber incident occurs, organizations need to identify the attack's impacts. They have to investigate potentially infected devices as well as certainly infected devices. However, as an organization's network expands, it is difficult to investigate all devices. In addition, the cybersecurity workforce shortage has risen, so organizations need to respond to incidents efficiently with limited human resources. To solve this problem, this paper proposes a tool to assist an incident response team. It can visualize ATT&CK techniques attacker used and, furthermore, detect lateral movements efficiently. The tool consists of two parts: a web application that extracts ATT&CK techniques from logs and a lateral movement detection system. The web application was implemented and could map the collected logs obtained from an actual Windows device to the ATT&CK matrix. Furthermore, actual lateral movements were performed in an experimental environment that imitated an organizational network, and the proposed detection system could detect them.

ICAO has emphasized that aeronautical information agencies should provide digitized aeronautical data and information, and realize that aeronautical data exchanging internationally in AIM. The AIXM structured aeronautical information dataset will be the main source of aeronautical basic data in the aeronautical information exchange network. In this article, the authors first analyze the spatio-temporal attributes of AIXM dataset and design the query method of AIXM structured obstacle data based on the research of AIXM coding specification. Secondly, the helicopter path planning is taken as the research scenario. Using the AIXM obstacle dataset and route dataset, combining the helicopter performance constraints to construct the envelope frame for collision judgment, and a new path planning method with improving the classical A* algorithm based on the AIXM dataset is proposed. The proposed method is validated and visualized. The validation results show that the proposed method reduces the frequency of helicopter turning, and ensures the safe distance between the flight path and the obstacles.

This article conducts a series of research on computer network courses based on “flipped classroom.” Teaching reform will be carried out for computer networks, but the results are mediocre. The author of this article has carefully considered and summarized computer network teaching based on his years of teaching experience and has put forward suggestions for widespread application. This article discusses the application of translation. The necessity and connotation of transitioning to classroom mode were emphasized, and the design of this teaching method was emphasized, adopting a three-step approach of “consolidating and improving knowledge after class.” Therefore, teachers should start from their own perspective, based on process preview, in class learning, and after class review, find the connection point between flipped classroom and computer network courses, reflect on the problems in teaching, and adopt targeted teaching methods to solve problems. This article provides guidance for improving teachers' teaching level.

The green credit policy has significantly influenced the growth of green industries in China. This study evaluates its impact on reducing bank credit risk using data from 26 Chinese banks from 2015 to 2021. The authors discovered that the policy's primary effect is linked to banks' financial leverage. Notably, green credit's influence on insolvency risk is most evident in leverage risk. However, despite governmental support for green credit collaboration, prevalent information gaps between banks and green enterprises lead to misjudgments and subsequent credit losses. To address the balance between credit risk mitigation and privacy, the authors investigated vertical joint learning for a precise risk control model grounded in commercial banks' practices. Experiments revealed that this joint model outperforms the sole “bank internal model” in presenting green credit data, underscoring the potential of machine learning to refine green credit systems and bolster banks' credit risk management.

The Internet's rapid growth has led to information overload, necessitating recommender systems for personalized suggestions. While content-based and collaborative filtering have been successful, data sparsity remains a challenge. To address this, this article presents a novel social recommender system based on convolutional neural networks (SRSCNN). This approach integrates deep learning and contextual information to overcome data sparsity. The SRSCNN model incorporates user and item factors obtained from a neural network architecture, utilizing features from item titles and tags through a CNN. The authors conducted extensive experiments with the MovieLens 10M dataset, demonstrating that the SRSCNN approach outperforms state-of-the-art baselines. This improvement is evident in both rating prediction and ranking accuracy across recommendation lists of varying lengths.

Enterprise resource planning (ERP) implementations often encounter multifaceted challenges, leading to failures. Success relies on technical competence, management support, and user engagement. Unique organizational processes significantly influence outcomes. Failures can disrupt operations, highlighting the need to identify critical success factors (CSFs) for effective ERP implementation. This study employed analytic hierarchy process (AHP) methodology to analyze CSFs. Data collection involved surveys administered to a social insurance company's ERP project team in Indonesia. This study revealed 15 success factors, categorized into organization, process, and technology dimensions. Organization emerged as the most crucial, followed by technology and process. Among these, five CSFs stood out: project team competence, vendor and consultant quality, ERP fit, top management support, and hardware and software selection.

In the realm of physical education in college, the traditional classroom teaching approach primarily relies on paper textbooks and demonstrations by the teacher. However, in today's physical education classrooms, there is a need to change these traditional teaching methods. Utilizing multimedia technology and interactive interfaces, teachers can demonstrate the essential actions and intricate details through multimedia videos and other formats such as push-pull and shaking. This chapter introduces a multi-segment human body tracking algorithm that focuses on real-time tracking. The human body target is divided into multiple segments, and an online learning method based on Hough Forests is used to learn the overall appearance of the human body and the appearance model of each segment. The research findings indicate that when the merged area exceeds 82.36% of the pre-segmentation area using watershed analysis, smaller areas lead to faster segmentation speed, while larger areas result in slower segmentation speed. Compared to other methods, this approach yields better recognition results.

These days, the problem of fake news has grown to be a major social and personal concern. With the amount of information generated through social media, it is very crucial to be able to detect and properly take care of that fake information. Previous studies proposed a machine learning model to detect fake news in online Thai health and medical articles. Still, the problem of detecting fake news with similar content but different objectives exists, and the accuracy of the model needs improvement. Therefore, this study aims to solve these problems by adding 33 new features, including textual features, sentiment-based features, and lexicon features, i.e., herbs, fruits, and vegetables, to identify the objective of an article. We trained and tested the model’s prediction accuracy on a new dataset containing 582 reliable and 435 unreliable (fake news) articles from eight Thai websites. Our improved classification model using XGBoost with Lasso, the best feature selection method, achieved an accuracy of 97.76% without over-fitting, reflecting a 7.16% improvement over our earlier model.

This paper aims to explore Kuwaiti users’ perspectives and experiences with Shlonik, the mandatory contact tracing application that was used during the COVID-19 pandemic. A sample of 2,450 tweets about users’ experiences was collected and thematically analyzed. The analysis used DeLone and McLean’s information system success model to explore aspects of the degree to which this app can be judged a “success,” using parameters of system quality and service quality. A novel finding identified by this qualitative study was the significance of themes identified in the analysis such as social privacy (timing, privacy, and female privacy, which are related to the cultural and religious norms of Kuwait) and technical privacy (related to data protection). The research identified significant conflict with cultural and social norms in users’ experience of the Shlonik app – factors not normally identified or discussed in existing literature. This research supports a need for improved strategies and designs in future m-government applications in developing countries.

In the geographical field, the studies have been on service areas using the Voronoi diagram and its derived models is extensive, but there is a lack of effective methods to achieve a good area-weight proportionality between generators and their exclusive regions. As a famous visualizing method, adaptive multiplicatively weighted Voronoi diagrams are able to achieve it, but are limited to displaying non-spatial data. The approach of the area-weight proportional multiplicatively weighted Voronoi diagram is proposed to solve these problems by allowing for spatial division with a point-fixed iteration approach and a vector-based multiplicatively weighted Voronoi diagram construction method from point features with spatial coordinates and references in GIS environments. It enables one to create a set of regions that is proportional to the weights of the generators. The method is successfully tested on a series of cases. The approach aims to establish a kind of spatial data model to represent demand and supply situations in real life.

Financial domains are suffering from organized fraudulent activities that are inflicting the world on a larger scale. Basel Anti-Money Laundering (AML) index enlists 146 countries, which are impacted by criminal acts like money laundering, and represents the country's risk level with a notable deteriorating trend over the last five years. Despite AML being a substantially focused area, only a fraction of such activities has been prevented. Because financial data related to this field is concealed, access is limited and protected by regulatory authorities. This paper aims to study a graph-based machine-learning model to identify fraudulent transactions using the financial domain's synthetic dataset (100K nodes, 5.3M edges). Graph-based machine learning with financial datasets resulted in promising 77-79% accuracy with a limited feature set. Even better results can be achieved by enriching the feature vector. This exploration further leads to pattern detection in the graph, which is a step toward AML detection.

This paper aims to visualise three financial distress outlooks using computer simulations. The financial distress exposure for airport operations in Malaysia between 1991 and 2021 is given by Altman Z”-score and modelled by the multivariate generalized linear model (MGLM). Seven determinants contributing to the financial distress from literature are examined. The determinant series are fitted individually by using linear model with time series components and autoregressive integrated moving average models to forecast values for the next 10 financial years. Future short- to long-term memory effects following COVID-19 are apparent in time series plots. In the simulations, the MGLM procedure utilised Gaussian, gamma, and Cauchy probability distributions associated with expectations and challenges of doing business as well as uncertainties in the economy. The underlying trends of realistic, optimistic, and pessimistic financial distress outlooks insinuate that the increasing risk of financial distress of airport operations in Malaysia is expected to continue for the next decade.

Due to the differences of students' English proficiency and the rapid changes in reading interests, online personalized English reading recommendation is a highly challenging problem. Although some works have been proposed to address the dynamic change of recommendation, there are two issues with these methods. First, it only considers whether students have read the recommended articles. Second, these methods often fail to capture the real-time changing interests of users. To address the above challenges, a deep Q-network based recommendation framework was proposed. The authors further use the user's behavior and scores as reward information to get more user’s feedback. In addition, a personalized adaptive module was introduced to capture the short-term interests on the fly and utilized the consistent loss of KL divergence to distill the knowledge from the online model. Extensive experiments on the offline and online dataset in the IWiLL website demonstrate the superior performance of the method.

With the advancement of technology, the metaverse image is used to improve the success rate of surgical. The purpose of this study was to understand the acceptance of extended reality surgery by different populations of medical experts and patients. The main reason for using a triangular mixed model for the study is because of the small amount of relevant research data for this study, quantitative research, exploratory research, and cross-sectional research can avoid some human interference and reduce error. The results of the study data showed that the image model, interaction design, surgeon, and clarity of use of the head-mounted display with metaverse technology by the expert group were conducive to improved surgical success rates. Metaverse surgery offers opportunities for modern digital surgery and can effectively improve the expert's ability to promote the smoothness of physical indicators during the procedure. This study is pioneering the role of a metaverse in facilitating surgery from the dual perspective of medical experts and patients.

As governments, education departments, and academic accreditation bodies have begun to encourage schools to develop evidence-based decision-making and innovation systems, learning analysis techniques have shown great advantages in decision-making aid and teaching evaluation. After integrating relevant algorithms and technologies in artificial intelligence and machine learning, learning analysis has achieved higher analysis accuracy. In order to realize the recognition of students' classroom behaviors such as standing up, sitting up, and raising hands and improve the recognition accuracy and recall rate, multi-modal data such as human key point information and RGB images are used for experiments. To further improve the feature extraction capability of the model, features are extracted from the improved ResNet-50 and EfficientNet-B0 models, and bilinear fusion is performed to further improve the recognition accuracy of the models.

The literature emphasizes the crucial role of state-owned enterprises (SOEs) in fostering economic growth and addressing public demands. However, ensuring the sustainable development of SOEs requires further research to investigate sustainable project management with a focus on value creation. Accordingly, the authors conducted a case study of a prominent real estate SOE in China to examine how SOEs can alter their project management practices and achieve a more sustainable business model. The findings reveal that adopting a whole life-cycle management system can promote value refinement, optimization, and co-creation, enabling SOEs to achieve value creation through sustainable management. This study offers useful insights for policymakers and business executives in China and contributes to the literature on sustainable project management and value creation.

Log anomaly detection holds great significance in computer systems and network security. A large amount of log data is generated in the background of various information systems and equipment, so automated methods are required to identify abnormal behavior that may indicate security threats or system malfunctions. The traditional anomaly detection methods usually rely on manual statistical discovery, or match by regular expression which are complex and time-consuming. To prevent system failures, minimize troubleshooting time, and reduce service interruptions, a log template-based anomaly detection method has been proposed in this context. This approach leverages log template extraction, log clustering, and classification technology to timely detect abnormal events within the information system. The effectiveness of this method has been thoroughly tested and compared against traditional log anomaly detection systems. The results demonstrate improvements in log analysis depth, event recognition accuracy, and overall efficiency.

The present work proposed an improved switch migration method (ISMM) for balancing the controller load to migrate the switch from overloaded to under-loaded controller. This method is used on each controller during controller load balance in order to decide the state of controllers. The implementation was conducted using the Mininet simulation tool. The performance of the proposed solution has been evaluated by using throughput, response time, and packet loss metrics. Accordingly, the simulation results indicated that this method has improved throughput by 7.6% over SSMS and 1.8% over CAMD, improved response time 8.3% over SSMS and 4% over CAMD, and improved the packet loss 8% over SSMS and 1.3% over CAMD during the incoming traffic load between 501p/s and 5000p/s. Thus, the performance of ISMM has shown efficient results over SSMS and CAMD among all assessed metrics by balancing the load between controllers.