Rice, a staple food crop worldwide, is pivotal in agricultural productivity and public health. Automatic classification of typical rice pests and diseases is crucial for optimizing rice yield and quality in practical production. However, infrequent occurrences of specific pests and diseases lead to uneven dataset samples and similar early-stage symptoms, posing challenges for effective identification methods. In this study, we employ four image enhancement techniques—flipping, modifying saturation, modifying contrast, and adding blur—to balance dataset samples throughout the classification process. Simultaneously, we enhance the basic RepVGG model by incorporating the ECA attention mechanism within the Block and after the Head, resulting in the proposal of a new classification model, RepVGG_ECA. The model successfully classifies six categories: five types of typical pests and diseases, along with healthy rice plants, achieving a classification accuracy of 97.06%, outperforming ResNet34, ResNeXt50, Shufflenet V2, and the basic RepVGG by 1.85%, 1.18%, 3.39%, and 1.09%, respectively. Furthermore, the ablation study demonstrates that optimal classification results are attained by integrating the ECA attention mechanism after the Head and within the Block of RepVGG. As a result, the classification method presented in this study provides a valuable reference for identifying typical rice pests and diseases.

In this paper, we propose vehicle detection and classification in a real road environment using a modified and improved AlexNet. Among the various challenges faced, the problem of poor robustness in extracting vehicle candidate regions through a single feature is solved using the YOLO deep learning series algorithm used to propose potential regions and to further improve the speed of detection. For this, the lightweight network Yolov2-tiny is chosen as the location network. In the training process, anchor box clustering is performed based on the ground truth of the training set, which improves its performance on the specific dataset. The low classification accuracy problem after template-based feature extraction is solved using the optimal feature description extracted through convolution neural network learning. Moreover, based on AlexNet, through adjusting parameters, an improved algorithm was proposed whose model size is smaller and classification speed is faster than the original AlexNet. Spatial Pyramid Pooling (SPP) is added to the vehicle classification network which solves the problem of low accuracy due to image distortion caused by image resizing. By combining CNN with SVM and normalizing features in SVM, the generalization ability of the model was improved. Experiments show that our method has a better performance in vehicle detection and type classification.

In football or soccer, a referee controls the game based on the set rules. The decisions made by the referee are final and can’t be appealed. Some of the decisions, especially after a handball event, whether to award a penalty kick or a yellow/red card can greatly affect the final results of a game. It is therefore necessary that the referee does not make an error. The objective is therefore to create a system that can accurately recognize such events and make the correct decision. This study chose handball, an event that occurs in a football game (Not to be confused with the game of Handball). We define a handball event using object detection and robotic perception and decide whether it is intentional or not. Intention recognition is a robotic perception of emotion recognition. To define handball, we trained a model to detect the hand and ball which are primary objects. We then determined the intention using gaze recognition and finally combined the results to recognize a handball event. On our dataset, the results of the hand and the ball object detection were 96% and 100% respectively. With the gaze recognition at 100%, if all objects were recognized, then the intention and handball event recognition were at 100%.

Current traffic light systems follow predefined timing sequences, causing the light to turn green even when no cars are waiting, while the side road with waiting vehicles may still face a red light. Reinforcement learning can help by training an intelligent model to analyze real-time traffic conditions and dynamically adjust signal lights based on actual demand and necessity. If the traffic light becomes intelligent and autonomous then it can significantly reduce the time wasted everyday commuting due to previously determined traffic light timing sequences. In our previous work, we used fuzzy logic to control the traffic light where the time was fixed but in this paper, the waiting time becomes a variable that changes depending on other road variables like vehicles, pedestrians, and times. Moreover, we trained an agent in this work using reinforcement learning to optimize the traffic flow in junctions with traffic lights. The trained agent worked using the greedy method to improve traffic flow to maximize the rewards by changing the signals appropriately. We have two states and there are only two actions to take for the agent. The results of the training of the model are promising. In normal situations, the average waiting time was 9.16 seconds. After applying our fuzzy rules, the average waiting time was reduced to 026 seconds, and after applying reinforcement learning, it was 0.12 seconds in a simulator. The average waiting time was reduced by 97~98%. These models have the potential to improve real-world traffic efficiency by approximately 67~68%.

Providing enough health caregivers due to an aging population has recently been challenging. To alleviate this problem, there's a growing demand for certain household monitoring tasks to be automated especially for elderly persons living independently to reduce the number of scheduled visits by caregivers. Moreover, gathering crucial data using AI technology about functional, cognitive, and social health status, is essential for monitoring daily physical activities at home. This paper proposes a system that determines a room's cleanliness (degree of clutter) to decide whether a caregiver visit is required. A Yolov5-based method is applied to recognize objects in the room including clothes, utensils, clothes, etc. However, due to background noise interference in the rooms and the insufficient feature extraction in YOLOv5, an improvement regime is proposed to improve the detection accuracy. The ECA (Efficient Channel Attention) is added to the network's backbone to focus on feature information, reducing the missed detection rate. The initial anchor box clustering algorithm is improved by replacing K-means with the K-means++ algorithm, enabling more effective adaptation to changing room views. The regression loss function EIoU (Enhanced Intersection over Union) is introduced to optimize the convergence speed and improve the accuracy. The room clutter is determined using set rules by comparing the detection results and prior information from the clean room using IOU. In 31 rooms, 9 subjects' evaluation was used to prove the effectiveness of the proposed system. Compared to the original Yolov5 algorithm, the method proposed in this paper achieved better performance