Бидний тухай
Багш ажилтан
Software defect prediction in the early stages of the Software Development Life Cycle (SDLC) is crucial to reducing project cost and ensuring the implementation’s success. Existing methods for software defect detection in a project rely on the implementation or testing phases of the SDLC, based on the source code. While relatively few studies have focused on identifying defects in the design phase of the SDLC, these approaches primarily employ machine learning or deep learning methods to detect and classify suspect code segments or classes in static diagrams as defective or clean. This study utilizes 24 model-based metrics extracted via SDMetrics, including structural and object oriented design features derived from UML class diagrams. To enhance classification performance, this study introduces an ensemble machine learning model with different techniques (stacking, voting) that combine multiple machine learning models. Specifically, wecompare ensemble models with different ensemble techniques to the individual models in terms of accuracy, precision, recall, F-measure, and AUC by utilizing a large dataset called the Unified Bug Dataset, comprising five publicly available sub-datasets. Experimental results show that the ensemble model with the stacking ensemble method outperformed other ensemble models and the individual classifiers (RF, XGBoost, ET) in terms of AUC.
Early and accurate detection of software defects is crucial for improving software quality and reducing development costs. While significant research has focused on defect prediction using source code, investigations at the design level, particularly with UML class diagrams, remain less explored. Graphs are widely used to represent the network structure of connected data, and graph learning methods leverage machine learning algorithms to extract meaningful features. As a result, they have attracted significant attention from researchers for tasks such as classification, prediction, and matching. In this study, we created a graph-based dataset from a UML class diagram to support predicting software defects, since the diagram represents connected data. Furthermore, we used a typical graph neural network method to show the capabilities of the dataset in software defect prediction at the design stage of the software development life cycle. Finally, we found that there are insignificant improvements from machine learning methods.
Виртуал бодит байдал (VR) технологи нь боловсрол, зугаа цэнгэл, соёлын өвийг сурталчлахад илүү гүнзгий, бодит мэдрэмжийг хэрэглэгчдэд олгодог хүчирхэг хэрэгсэл болон хөгжиж байна. Гэвч өнөөдөр ашиглагдаж буй виртуал аяллууд ихэвчлэн гара ар эсвэл удирдлага ашиглан хийгддэг учир хэрэглэгчийн оролцоо, мэдрэмжийг хязгаарладаг. Энэхүү судалгаагаар веб камерын тусламжтайгаар хүний нүдний хөдөлгөөнийг бодит цаг хугацаанд хянаж, ямар ч нэмэлт мэдрэгч төхөөрөмж ашиглахгүйгээр виртуал аяллыг илүү бодитой, хэрэглэгчид тааламжтай хэлбэрээр удирдах шинэлэг аргыг танилцууллаа. Энэхүү систем нь хүний нүдний харц болон физиологийн бусад үзүүлэлтүүдийг 360 градусын виртуал орчинтой холбон, хэрэглэгчийн анхаарал төвлөрөлд нийцүүлэн орчныг өөрчилдөг. Энэхүү аргыг олон түвшний дүрслэл, нүдний хөдөлгөөний загварчлал, анхааралд тулгуурласан динамик тохируулгаар баяжуулсан. Туршилтын үр дүнгээр веб камер ашигласан энэхүү технологи нь уламжлалт аргуудаас илүү хүртээмжтэй, хэрэглэгчийн танин мэдэхүйн ачааллыг багасгаж, илүү гүнзгий мэдрэмжийг төрүүлсэн нь тогтоогдсон. Иймд энэхүү судалгаагаар веб камерт суурилсан харааны хяналтын систем нь VR төхөөрөмж ашиглах боломжгүй эсвэл зардал өндөртэй орчинд илүү тохиромжтой, үр ашигтай шийдэл болохыг онцоллоо.
This paper presents a study of a new action, wiping operation, to accelerate human activities for a type of hidden object game (HOG). So far, aesthetical image composition and mysterious stories have been mainly used to make an HOG enjoyable. However, there have been insufficient studies to explore game elements such as the efficiency of game effects on an HOG to accelerate human activities. An HOG is a game in which a player is given a task to find target objects, such as a jewel, a tulip, and a bicycle, existing in a scene image, such as a room, a garden, and a park, by a given hint. The hint is given by the names of the objects in most cases, although other types are sometimes used such as the silhouettes of the objects. The wiping operation is used in an HOG in which a scene image is transformed into a triangulated image and a player finds target objects existing in it. The player applies the wiping operation to the triangulated image to change the level of detail of it by an action like “wiping the image” interactively and intuitively. The wiping operation stirs the player’s imagination, activates human brain, and accelerates human activities. In general, the effect of an action is often evaluated by a questionnaire. However, using only questionnaire data to measure the human activities is inaccurate because the result depends on the subjectiveness of participants. Therefore, it is desirable to measure brain activities to evaluate the efficiency of human activities on HOG. A brain sensor is one of the solutions to measure human activities. This paper shows the experimental results by both of questionnaire and brain sensor data to verify the effectiveness of the wiping operation.
An aesthetical image composition and mysterious stories are the main components of a hidden object game (HOG) to make it enjoyable. In an HOG, players find objects hidden in an image and inquired by a list. As far as we know, there have been insufficient studies to explore game elements such as the efficiency of game effects on an HOG to accelerate human activities. In this paper, we propose “wiping operation” to accelerate human activities for an HOG. In an HOG that we developed, first, an original image is transformed into a triangulated image. Then, during game play, the quickness of the wiping action by a player makes the level of detail of the triangulation finer and rougher. We did an experiment to investigate the performance of the wiping operation. Each player in the experiment wore a brain activity sensor to obtain a brain activity value during game play and answered a questionnaire after game play. We show the experimental results by the questionnaire and brain activity value to verify the effectiveness of the wiping operation.
