Explore the vast range of titles available.

An important technique for converting 2D videos into 3D is depth image-based rendering (DIBR), which creates virtualized perspectives with textured images and corresponding depth maps. Yet, the majority of the currently used methods struggle in handling the disocclusion holes in warped virtual images. This research presents a unique deep learning-based disocclusion hole-filling approach in stereoscopic vision synthesis as a solution to this issue. Firstly, we explicitly take into account some particular limitations of the synthesized virtual views and designate them as scene influence maps in the network, which might offer some significant extra scene cues to lessen hallucinated content mixing among various layers. Then, an enhanced directional scene influence map, which diffuses using a novel anisotropic diffusion equation under consistent stereoscopic constraints, is further investigated for efficient disocclusion hole filling. Empirical analyses and comparisons on the Middlebury and KITTI datasets confirmed that our approach outperforms previous deep learning-based generative inpainting algorithms for disocclusion hole filling in the warped views.

This study presents a multivariate regression-based analysis aimed at quantifying the influence of key vibration-generating components in two types of grain combines—C110H (with straw walker) and CASE IH (axial flow)—on the operator’s seat (OS). Using triaxial accelerometers, vibrational measurements were performed under both stationary and operational working mode. RMS acceleration values were recorded for major subsystems (engine, threshing unit, chassis, chopper/header) and processed via multiple linear regression. The models generated for each combine and axis (Ox, Oy, Oz) revealed high coefficients of determination (R2 > 0.85), confirming the linear model’s validity. Influence maps and standardized coefficients were used to rank the sources of vibration. Results indicate that the straw walker dominates vibration transmission in the C110H, while the header and threshing system are more significant in the CASE IH. The findings support the development of predictive algorithms for real-time vibration monitoring and ergonomic improvements in combine design. Moreover, the proposed methodology provides a cost-effective diagnostic tool for early fault detection, targeted maintenance, and the long-term reduction of operator fatigue and injury risks.

Vessel trajectory prediction plays a crucial role in ensuring the safety and efficiency of maritime transportation. This study proposes an innovative sequence-to-sequence model, called the Vessel Influence Long Short-Term Memory (VI-LSTM), which introduces a novel Vessel Influence Map (VIM) to quantitatively model the dynamic effects of surrounding vessels. To enhance reliability, VI-LSTM incorporates Gaussian distribution predictions combined with Monte Carlo dropout techniques to estimate prediction uncertainty. Additionally, a temporally weighted hybrid loss function is designed to balance prediction accuracy and uncertainty. Furthermore, this study systematically categorizes and models factors influencing vessel trajectory prediction. Experimental results demonstrate that VI-LSTM achieves a mean distance error of 330.66 m on the standard test set and 480.30 m on an unseen subject test set, outperforming other comparative models, particularly in complex navigation scenarios and high-density maritime environments. These innovations significantly improve the accuracy and generalizability of vessel trajectory predictions, leading to enhanced safety, increased efficiency, and more effective collision avoidance in maritime navigation.

With the development of artificial intelligence, techniques such as machine learning, object detection, and trajectory tracking have been applied to various traffic fields to detect accidents and analyze their causes. However, detecting traffic accidents using closed-circuit television (CCTV) as an emerging subject in machine learning remains challenging because of complex traffic environments and limited vision. Traditional research has limitations in deducing the trajectories of accident-related objects and extracting the spatiotemporal relationships among objects. This paper proposes a traffic accident detection method that helps to determine whether each frame shows accidents by generating and considering object trajectories using influence maps and a convolutional neural network (CNN). The influence maps with spatiotemporal relationships were enhanced to improve the detection of traffic accidents. A CNN is utilized to extract latent representations from the influence maps produced by object trajectories. Car Accident Detection and Prediction (CADP) was utilized in the experiments to train our model, which achieved a traffic accident detection accuracy of approximately 95%. Thus, the proposed method attained remarkable results in terms of performance improvement compared to methods that only rely on CNN-based detection.

With the rapid development in technology in recent years, the use of cameras and the production of video and image data have similarly increased. Therefore, there is a great need to develop and improve video surveillance techniques to their maximum extent, particularly in terms of their speed, performance, and resource utilization. It is challenging to accurately detect anomalies and increase the performance by minimizing false positives, especially in crowded and dynamic areas. Therefore, this study proposes a hybrid video anomaly detection model combining multiple machine learning algorithms with pixel-based video anomaly detection (PBVAD) and frame-based video anomaly detection (FBVAD) models. In the PBVAD model, the motion influence map (MIM) algorithm based on spatio–temporal (ST) factors is used, while in the FBVAD model, the k-nearest neighbors (kNN) and support vector machine (SVM) machine learning algorithms are used in a hybrid manner. An important result of our study is the high-performance anomaly detection achieved using the proposed hybrid algorithms on the UCF-Crime data set, which contains 128 h of original real-world video data and has not been extensively studied before. The AUC performance metrics obtained using our FBVAD-kNN algorithm in experiments were averaged to 98.0%. Meanwhile, the success rates obtained using our PBVAD-MIM algorithm in the experiments were averaged to 80.7%. Our study contributes significantly to the prevention of possible harm by detecting anomalies in video data in a near real-time manner.

Almost all recent deep reinforcement learning algorithms use four consecutive frames as the state space to retain the dynamic information. If the training state data constitute an image, the state space is used as the input of the neural network for training. As an AI-assisted decision-making technology, a dynamic influence map can describe dynamic information. In this paper, we propose the use of a frame image superimposed with an influence map as the state space to express dynamic information. Herein, we optimize Ape-x as a distributed reinforcement learning algorithm. Sparse reward is an issue that must be solved in refined intelligent decision making. The use of an influence map is proposed to generate the intrinsic reward when there is no external reward. The experiments conducted in this study prove that the combination of a dynamic influence map and deep reinforcement learning is effective. Compared with the traditional method that uses four consecutive frames to represent dynamic information, the score of the proposed method is increased by 11–13%, the training speed is increased by 59%, the video memory consumption is reduced by 30%, and the memory consumption is reduced by 50%. The proposed method is compared with the Ape-x algorithm without an influence map, DQN, N-Step DQN, QR-DQN, Dueling DQN, and C51. The experimental results show that the final score of the proposed method is higher than that of the compared baseline methods. In addition, the influence map is used to generate an intrinsic reward to effectively resolve the sparse reward problem.

In edge computing, diverse kinds of data are handled in real-time. An increasing number of researches have been carried out to improve the performance of data handling for agent-based data control technology. An important application for edge computing is to control the distributed agents in real-time strategy (RTS) games. One of the key approaches for agent control is the grouping of agents; however, it is difficult to group them in a reasonable cluster. This paper proposes a recommendation method for the best grouping of agents and edge computing devices to reduce the time of handling data and obtaining optimal results for RTS game agent selecting. The proposed method used K-means, influence mapping, and Bayesian probability, and was evaluated by utilizing a game environment in which the performance of handling data is easily evaluated. The comparison result between the recommendation and random modes shows that our method has ability to increase 47% of the percentage the wins.

PurposeRemote and isolated indigenous communities in Nunavik (Canada) currently face a number of housing related challenges. This paper proposes a conceptual framework to identify the factors affecting value creation within the supply chain of social housing construction in that region. The term “social” refers to the fact that governments subsidise construction and operation of these buildings intended for low-income households.Design/methodology/approachThe research used a literature review and information collected from 3 semi-structured interviews with key stakeholders to identify the desired features of improvement or solutions (e.g. prefabrication) with respect to value creation. A SWOT analysis, an influence/dependence map and a causal loop diagram were developed to represent the supply chain.FindingsLocal job creation and the number of buildings to build were identified as the key factors that can roughly represent value creation. Energy resources, construction time, type and amount of labour force, shipping constraints, number of replacement parts and waste disposal were identified as the main factors constraining the range of solutions to implement.Practical implicationsThe framework can be used to support the decision-making in supply chain management and the design of solutions for remote areas such as Nunavik.Originality/valueThis paper is the first to analyse value creation in social building construction in remote and isolated communities such as those from Nunavik. Conceptual models achieved within the framework allowed identifying the factors that could roughly represent this value creation, as well as logical relationships that link them with other factors.

While CPA (Certified Public Accountant) firms utilize cloud auditing technologies to generate auditing reports and convey information to their clients in the Internet of Things (IoT) Era, they often cannot determine whether cloud auditing is a secure and effective form of communication with clients. Strategies related to cloud auditing provider evaluation and improvement planning are inherently multiple attribute decision making (MADM) issues and are very important to the auditor industry. To overcome these problems, this paper proposes an evaluation and improvement planning model to be a reference for CPA firms selecting the best cloud auditing provider, and illustrates an application of such a model through an empirical case study. The DEMATEL (decision-making trial and evaluation laboratory) approach is first used to analyze the interactive influence relationship map (IIRM) between the criteria and dimensions of cloud auditing technology. DANP (DEMATEL-based ANP) is then employed to calculate the influential weights of the dimensions and criteria. Finally, the modified VIKOR method is utilized to provide improvement priorities for performance cloud auditing provider satisfaction. Based on expert interviews, the recommendations for improvement priorities are privacy, security, processing integrity, availability, and confidentiality. This approach is expected to support the auditor industry to systematically improve their cloud auditing provider selection.