Artificial intelligence is one of the key technologies for progression to the fourth industrial revolution. This technology also has a significant impact on software professionals who are continuously striving to achieve high-quality software development by fixing various types of software bugs. During the software development and maintenance stages, software bugs are the major factor that can affect the cost and time of software delivery. To efficiently fix a software bug, open bug repositories are used for identifying bug reports and for classifying and prioritizing the reports for assignment to the most appropriate software developers based on their level of interest and expertise. Owing to a lack of resources such as time and manpower, this bug report triage process is extremely important in software development. To improve the bug report triage performance, numerous studies have focused on a latent Dirichlet allocation (LDA) using the k-nearest neighbors or a support vector machine. Although the existing approaches have improved the accuracy of a bug triage, they often cause conflicts between the combined techniques and generate incorrect triage results. In this study, we propose a method for improving the bug report triage performance using multiple LDA-based topic sets by improving the LDA. The proposed method improves the existing topic sets of the LDA by building two adjunct topic sets. In our experiment, we collected bug reports from a popular bug tracking system, Bugzilla, as well as Android bug reports, to evaluate the proposed method and demonstrate the achievement of the following two goals: increase the bug report triage accuracy, and satisfy the compatibility with other state-of-the-art approaches.

Mobile apps, used by many people worldwide, have become an essential part of life. Before using a mobile app, users judge the reliability of apps according to their reviews. Therefore, app reviews are essential components of management for companies. Unfortunately, some fake reviewers write negative reviews for competing apps. Moreover, artificial intelligence (AI)-based macro bot programs that generate app reviews have emerged and can create large numbers of reviews with malicious purposes in a short time. One notable AI technology that can generate such reviews is Generative Pre-trained Transformer-2 (GPT-2). The reviews generated by GPT-2 use human-like grammar; therefore, it is difficult to detect them with only text mining techniques, which use tools like part-of-speech (POS) tagging and sentiment scores. Thus, probability-based sampling techniques in GPT-2 must be used. In this study, we identified features to detect reviews generated by GPT-2 and determined the optimal feature combination for improving detection performance. To achieve this, based on the analysis results, we built a training dataset to find the best feature combination for detecting the generated reviews. Various machine learning models were then trained and evaluated using this dataset. As a result, the model that used both text mining and probability-based sampling techniques detected generated reviews more effectively than the model that used only text mining techniques. This model achieved a top classification accuracy of 90% and a macro F1 of 0.90. We expect the results of this study to help app developers maintain a more stable mobile app ecosystem. Graphical abstract

The development of information and communication technology has created many positive outcomes, including convenience for people; however, cases of unsolicited communication, such as spam, also occur frequently. Spam is the indiscriminate transmission of unwanted information by anonymous users, called spammers. Spam content is indiscriminately transmitted to users in various forms, such as SMS, e-mail, and social network service posts, causing negative experiences for users of the service, while also creating costs, such as unnecessarily large amounts of network traffic. In addition, spam content includes phishing, hype or false advertising, and illegal content. Recently, spammers have also used images that contain stimulating content to effectively attract users’ curiosity and attention. Image spam contains more complex information than text, making it more difficult to analyze and to generalize its properties compared to text. Therefore, existing text-based spam detectors are vulnerable to spam image attacks, resulting in a decline in service quality. In this paper, a “hybrid features by combining visual and text information to improve spam filtering performance” method is proposed to reduce the occurrence of misclassification. The proposed method employs three sub-models to extract features from spam images and a classifier model to output the results using the features. Each sub-model extracts topic-, word-, and image-embedding-based features from spam images. In addition, the sub-models use optical character recognition, latent Dirichlet allocation, and word2Vec techniques to extract features from images. To evaluate spam image classification performance, the spam classifiers were trained using the extracted features and the results were measured using a confusion matrix. Our model achieved an accuracy of 0.9814 and a macro-F1 score of 0.9813. In addition, the application of OCR evasion techniques resulted in a decrease in recognition performance. Using the proposed model, a mean macro-F1 score of 0.9607 was obtained.

Ophthalmology is a core medical field that is of interest to many. Retinal examination is a commonly performed diagnostic procedure that can be used to inspect the interior of the eye and screen for any pathological symptoms. Although various types of eye examinations exist, there are many cases where it is difficult to identify the retinal condition of the patient accurately because the test image resolution is very low because of the utilization of simple methods. In this paper, we propose an image synthetic approach that reconstructs the vessel image based on past retinal image data using the multilayer perceptron concept with artificial neural networks. The approach proposed in this study can convert vessel images to vessel-centered images with clearer identification, even for low-resolution retinal images. To verify the proposed approach, we determined whether high-resolution vessel images could be extracted from low-resolution images through a statistical analysis using high- and low-resolution images extracted from the same patient.

In recent years, large data centers have increased significantly as data usage has increased because of digital innovations. However, data centers are 24-hour operation facilities that consume large amounts of power, thus causing environmental problems. Recently, research has been conducted using deep learning methods from various perspectives to predict traffic and reduce power consumption in data centers and servers. However, the traffic processed by servers is highly variable, which is a factor that makes server management difficult. Thus, the traffic processed by servers is irregular, and more research is required on dynamic server management. This study proposes Customized Dynamic Server Management (CDSM) based on Long-Term Short Memory (LSTM), a neural network that is effective in predicting time-series data, to address the aforementioned problem. The proposed method can more effectively save the power used by servers, thereby managing servers more reliably and efficiently than before in the current operating environment. To validate the proposed model, we collected the traffic data at six Wikipedia data centers. We then analyzed the relationship between each traffic data using statistical analysis and conducted experiments. Furthermore, we calculated the server power consumption based on the actual power consumption according to the CPU usage of different servers provided by SPECpower, a benchmark for evaluating server power efficiency. Additionally, we calculated the amount of computation required for the program and deep learning model of the proposed. Based on this, practical results were derived considering the trade-off between the server’s power saving and computation performance. Based on these results, the performance of the method proposed in this study was validated in a statistically significant manner, which showed that server management can be performed reliably and efficiently.