Continual revelations of academic fraud have raised concerns regarding the detection of forged experimental images in the public domain. To address this issue, we introduce a multiscale attention-based deep (MAD) descriptor scheme for detecting copy-move image forgery in biomedical research scenarios. Our method utilizes the common object detection network as a backbone and incorporates the positional embedding module, the channel-attention module, and the self-attention module to generate a dense feature field for input images. The proposed method demonstrates robustness against common attacks encountered during research manuscript preparation, low-contrast biomedical images featuring small foreground objects, and unseen or unlearned object patterns. Extensive experiments substantiate that our approach outperforms previous copy-move forgery methods when applied to real-world cases across various domains. Our proposed method can serve as an efficient screening tool for the rapid identification of biomedical image forgeries.

With the booming development of autonomous vehicles (AV) in recent years, a vehicle needs to have the ability to detect changes in the environment in real-time. If the vehicle can be decelerated in advance according to the traffic signs, it can effectively reduce fuel consumption and improve overall comfort. This paper uses the Kaggle data set for training based on marking the common traffic signs in foreign countries, adds the local data set in Taiwan to the testing data set, and uses the You Only Look Once v4 (YOLOv4) neural network to detect the traffic signs in real time. The experimental results show that YOLOv4 still has a good generalization ability in the case of slight differences in different national sign types, and the mean Average Precision (mAP) can reach more than 87.6%.

Eco-driving is an effective and immediate environmental protection and energy saving method. This research assists occupational driving license training to achieve eco-driving at two parts: 1. Combine g-sensor with on board diagnostics (OBD-II) and add parameters to improve the data analysis. 2. Through two kinds of neural network models, predict fuel consumption to analyze driving style, and provide reports to display evaluation and behavior suggestions. The experimental configuration designed in this research includes user interface, OBD-II system, neural network model, and is applied to public institutions to provide assistance. The results of this study show that the accuracy of predicting fuel consumption exceeds 97%, which verifies the practicability of the system. The system will also help extend other related applications, such as achieving a driving behavior model that compares energy saving and safety.

Traumatic Brain Injury (TBI) is most commonly accident injury in modern society. The deterioration of cognition and memory is a common phenomenon caused by TBI. Most of the basic experiments used rats for pathological research. Moreover, an eight-arm maze was often used to test the spatial learning behavior of brain diseases, such as Alzheimer’s disease and TBI. However, most of maze experimental data were collected in manual records. This process would take a lot of manpower and time. Therefore, the research built an automatic tracking trajectory system of the eight-arm maze to collect experiment data. Furthermore, the path trajectory of the rat can be recorded in time. Finally, these path trajectory data were used to analysis behavior feature of TBI animals. The results showed that TBI rats have a 40%~80% chance of having a trajectory to the right.

Virtual reality (VR) has huge potential to enable radically new applications, behind which spherical panoramic video processing is one of the backbone techniques. However, current VR systems reuse the techniques designed for processing conventional planar videos, resulting in significant energy inefficiencies. Our characterizations show that operations that are unique to processing 360° VR content constitute 40% of the total processing energy consumption.

Recently, a new wave of business opportunities has emerged by integrating social media and commerce. Although many hospitality organizations have considered online social communities as potential channels for promotion, most of them have failed to obtain sales from community members. Therefore, the purpose of this study was to propose and examine a new research model that can capture cognitive- and affective-based trust elements influencing fans' behavioral intention to purchase by affecting their firm commitment. A survey of 393 Facebook participants found strong support for the model. The results indicated that Facebook fans' perceptions of firm commitment could be a strong predictor of their buying intention. Factors of building cognitive trust (i.e. perceived reputation, perceived ability, and information quality) as well as affective trust (i.e. perceived benevolence, perceived integrity and perceived social presence) were the critical components significantly influencing fans' firm commitment. Theoretical and practical implications of the results are discussed.