Roads make a huge contribution to the economy and act as a platform for transportation. Potholes in roads are one of the major concerns in transportation infrastructure. A lot of research has proposed using computer vision techniques to automate pothole detection that include a wide range of image processing and object detection algorithms. There is a need to automate the pothole detection process with adequate accuracy and speed and implement the process easily and with low setup cost. In this paper, we have developed efficient deep learning convolution neural networks (CNNs) to detect potholes in real-time with adequate accuracy. To reduce the computational cost and improve the training results, this paper proposes a modified VGG16 (MVGG16) network by removing some convolution layers and using different dilation rates. Moreover, this paper uses the MVGG16 as a backbone network for the Faster R-CNN. In addition, this work compares the performance of YOLOv5 (Large (Yl), Medium (Ym), and Small (Ys)) models with ResNet101 backbone and Faster R-CNN with ResNet50(FPN), VGG16, MobileNetV2, InceptionV3, and MVGG16 backbones. The experimental results show that the Ys model is more applicable for real-time pothole detection because of its speed. In addition, using the MVGG16 network as the backbone of the Faster R-CNN provides better mean precision and shorter inference time than using VGG16, InceptionV3, or MobilNetV2 backbones. The proposed MVGG16 succeeds in balancing the pothole detection accuracy and speed.

Due to the massive surge in the world population, the agriculture cycle expansion is necessary to accommodate the anticipated demand. However, this expansion is challenged by weed invasion, a detrimental factor for agricultural production and quality. Therefore, an accurate, automatic, low-cost, environment-friendly, and real-time weed detection technique is required to control weeds on fields. Furthermore, automating the weed classification process according to growth stages is crucial for using appropriate weed controlling techniques, which represents a gap of research. The main focus of the undertaken research described in this paper is on providing a feasibility study for the agriculture community using recent deep-learning models to address this gap of research on classification of weed growth stages. For this paper we used a drone to collect a dataset of four weed (Consolida regalis) growth stages. In addition, we developed and trained one-stage and two-stage models YOLOv5, RetinaNet (with Resnet-101-FPN, Resnet-50-FPN backbones) and Faster R-CNN (with Resnet-101-DC5, Resnet-101-FPN, Resnet-50-FPN backbones), respectively. The results show that the generated Yolov5-small model succeeds in detecting weeds and classifying weed growth stages in real time with the highest recall of 0.794. RetinaNet with ResNet-101-FPN backbone shows accurate results in the testing phase (average precision of 87.457). Although Yolov5-large showed the highest precision in classifying almost all weed growth stages, Yolov5-large could not detect all objects in tested images. Overall, RetinaNet with ResNet-101-FPN backbones shows accurate and high precision, whereas Yolov5-small shows the shortest inference time in real time for detecting a weed and classifying its growth stages.

With the exponential growth of large data produced by IoT applications and the need for lowcost computational resources, new paradigms such as volunteer cloud computing (VCC) have recently been introduced. In VCC, volunteers do not disclose resource information before joining the system. This leads to uncertainties about the level of trust in the system. The majority of available trust models are suitable for peer-to-peer (P2P) systems, which rely on direct and indirect interaction, and might cause memory consumption overhead concerns in large systems. To address this problem, this paper introduces ProTrust, a probabilistic framework that defines the trust of a host in VCC. We expand the concept of trust in VCC and develop two new metrics: (1) trustworthiness based on the priority of a task, named loyalty, and (2) trustworthiness affected by behavioral change. We first utilized a modified Beta distribution function, and the behavior of resources are classified into different loyalty levels. Then, we present a behavior detection method to reflect recent changes in behavior. We evaluated ProTrust experimentally with a real workload trace and observed that the framework's estimation of the trust score improved by approximately 15% and its memory consumption decreased by more than 65% compared to existing methods.

Additive manufacturing is an emerging and crucial technology that can overcome the limitations of traditional manufacturing techniques to accurately manufacture highly complex parts. X-ray Computed Tomography (XCT) is a widely used method for non-destructive testing of AM parts. However, detection and segmentation of defects in XCT images of AM have many challenges due to contrast, size, and appearance of defects. This study developed deep learning techniques for detecting and segmenting defects in XCT images of AM. Due to a large number of required defect annotations, this paper applied image processing techniques to automate the defect labeling process. A single-stage object detection algorithm (YOLOv5) was applied to the problem of defect detection in image data. Three different variants of YOLOv5 were implemented and their performances were compared. U-Net was applied for defect segmentation in XCT slices. Finally, this research demonstrates that deep learning techniques can improve the automatic defect detection and segmentation in XCT data of AM.

No abstract