Humans depend heavily on agriculture, which is the main source of prosperity. The various plant diseases that farmers must contend with have constituted a lot of challenges in crop production. The main issues that should be taken into account for maximizing productivity are the recognition and prevention of plant diseases. Early diagnosis of plant disease is essential for maximizing the level of agricultural yield as well as saving costs and reducing crop loss. In addition, the computerization of the whole process makes it simple for implementation. In this paper, an intelligent method based on deep learning is presented to recognize nine common tomato diseases. To this end, a residual neural network algorithm is presented to recognize tomato diseases. This research is carried out on four levels of diversity including depth size, discriminative learning rates, training and validation data split ratios, and batch sizes. For the experimental analysis, five network depths are used to measure the accuracy of the network. Based on the experimental results, the proposed method achieved the highest F1 score of 99.5%, which outperformed most previous competing methods in tomato leaf disease recognition. Further testing of our method on the Flavia leaf image dataset resulted in a 99.23% F1 score. However, the method had a drawback that some of the false predictions were of tomato early light and tomato late blight, which are two classes of fine-grained distinction.

Many accidents occurred in highway uphill sections. Changes in the vehicle speed may cause accidents. The driver’s psychological state is closely related to the control of speed. In this paper, 16 participants were selected for a field driving experiment, where the speed change data of a single vehicle traveling in highway uphill sections and the corresponding participants’ physiological performance data during the experiment were all collected. Then the instantaneous speed, eye movement parameters, and heart rate (HR) of each participant were analyzed with statistical methods. The results reveal that deceleration (or stop acceleration) events before the uphill crest occur in more than 80% of the uphill sections when there is no other interference. This phenomenon occurs because the participant’s sight distance is restricted in these segments. The location of the slow-down segment was closely dependent on the slope gradient and the driving speed. In the slow-down segments, the participants have the longest fixation time and the lowest saccade and blink time compared with those in front of and behind the slow-down segments. Moreover, the driver’s HR increase is the highest. These results can serve as guidance for highway designers who develop safety measures for uphill sections.