YOLO-DD:Improved YOLOv5 for Defect Detection

As computer technology continues to advance,factories have increasingly higher demands for detecting defects.However,detecting defects in a plant environment remains a challenging task due to the presence of complex backgrounds and defects of varying shapes and sizes.To address this issue,this paper proposes YOLO-DD,a defect detectionmodel based on YOLOv5 that is effective and robust.To improve the feature extraction process and better capture global information,the vanilla YOLOv5 is augmented with a new module called Relative-Distance-Aware Transformer(RDAT).Additionally,an Information Gap Filling Strategy(IGFS)is proposed to improve the fusion of features at different scales.The classic lightweight attention mechanism Squeeze-and-Excitation(SE)module is also incorporated into the neck section to enhance feature expression and improve the model’s performance.Experimental results on the NEU-DET dataset demonstrate that YOLO-DDachieves competitive results compared to state-of-the-art methods,with a 2.0% increase in accuracy compared to the original YOLOv5,achieving 82.41% accuracy and38.25FPS(framesper second).Themodel is also testedon a self-constructed fabric defect dataset,and the results show that YOLO-DD is more stable and has higher accuracy than the original YOLOv5,demonstrating its stability and generalization ability.The high efficiency of YOLO-DD enables it to meet the requirements of industrial high accuracy and real-time detection.

Behavioral problems and related factors in children of different aged patients with schizophrenia: A cross-sectional study

BACKGROUND： With the age growing, changes of behavioral problems in children whose parents had schizophrenia, differences of related factors and ways for particular intervention should be further studied. OBJECTIVE： To survey the behavioral problems in children of different aged patients with chizophrenia and investigate the correlation between behavioral problems and related factors in different aged groups. DESIGN： Cross-sectional study. SETTING： Shandong Mental Health Center. PARTICIPANTS： A total of 364 patients with schizophrenia were selected from eleven psychiatric hospitals from June 1999 to June 2000. There were 179 males and 185 females, and their ages ranged from 28 to 45 years. All patients met modified diagnostic criteria of schizophrenia （the second edition）, China Classification of Mental Diseases and Diagnostic Criteria. Meanwhile, children of the 364 patients were grouped based on their ages, including 6 - 1 l years old group [n -217; 114 males and 103 females; mean age of （9±2） years] and 12 - 16 years old group [n = 147; 99 males and 48 females; mean age of （14±1） years]. The Chinese norms of Achenbach＇s Child Behavior Check List were regarded as the normal control group. METHODS： Children who received self-made mental health related factors inventory and Achenbach＇s Child Behavior Check List were involved in this study. All children and their parents provided the confirmed consent. Achenbach＇s Child Behavior Check List was used for parents to mainly evaluate children, and the results manifested various behavioral problems based on different sexes and different ages. Self-made mental health related factors inventory contained questionnaires for parents and children, respectively. In this study, home situation of parents as well as personality characteristics and educational styles of children were mainly evaluated. MAIN OUTCOME MEASURES： ① Scores of Achenbach＇s Child Behavior Check List in different aged children; ② Scores of self-made mental health related factors inventory based on different home situations and educational styles. RESULTS： Children of 364 patients were involved in the final analysis. ① There were no significant differences in total score of Achenbach＇s Child Behavior Check List and sex in the two groups （P 〉 0.05）. There were significant differences in schizoid, body recount, aggression, depression, hyperactivity, violating discipline, compulsion and total abnormal rate of boys between the 6 - 11 years old group and the normal control group （P 〈 0.05 - 0.01）. In addition, there were also significant differences in poor communication, depression, hyperactivity, violating discipline, compulsion and total abnormal rate of girls between the 6 - 11 years old group and the normal control group （P 〈 0.05 - 0.01）. ② As compared with normal control group,scores of home environment in the two aged groups demonstrated that educational level was low; interpersonal relationship was poor; relation to children was not closed; relationship between husband and wife was not harmonious; positive rate of family history was high; economic status was poor; family atmosphere was poor. Therefore, there was significant difference （P 〈 0.01）. Educational level in parental generation and single parent family in the 6 - 11 years old group were higher than that in the 12 - 16 years old group, with significant difference （P 〈 0.05）. As compared with the normal control group, results of education demonstrated that children in the two aged groups had poor communication with other children; they had poor behaviors in schools; most of them were boarded and had poor relationship with their parents; teaching styles for children were different. CONCLUSION： All children of different aged patients with schizophrenia had poor home environment and education; and they were often affected by other factors. Behavioral problems were changed with the age growing; in addition, these changes were related to home environment, education and society. Therefore, comprehensive intervention may be an ideal method.