An object detection algorithm combining self-attention and YOLOv4 in traffic scene.

Automobile intelligence is the trend for modern automobiles, of which environment perception is the key technology of intelligent automobile research. For autonomous vehicles, the detection of object information, such as vehicles and pedestrians in traffic scenes is crucial to improving driving safety. However, in the actual traffic scene, there are many special conditions such as object occlusion, small objects, and bad weather, which will affect the accuracy of object detection. In this research, the SwinT-YOLOv4 algorithm is proposed for detecting objects in traffic scenes, which is based on the YOLOv4 algorithm. Compared with a Convolutional neural network (CNN), the vision transformer is more powerful at extracting vision features of objects in the image. The CNN-based backbone in YOLOv4 is replaced by the Swin Transformer in the proposed algorithm. The feature-fusing neck and predicting head of YOLOv4 is remained. The proposed model was trained and evaluated in the COCO dataset. Experiments show that our method can significantly improve the accuracy of object detection under special conditions. Equipped with our method, the object detection precision for cars and person is improved by 1.75%, and the detection precision for car and person reach 89.04% and 94.16%, respectively.

Comparative study on nitrogen removal and functional genes response between surface flow constructed wetland and floating treatment wetland planted with Iris pseudacorus.

Excessive nitrogen accumulated from wastewater with low C/N ratio is a new threat to water ecosystem. In this study, surface flow constructed wetland (SFCW) and floating treatment wetland (FTW) planted with Iris pseudacorus were set in parallel for nitrogen removal. The nitrogen removal efficiencies and pathways, as well as the abundance and functional diversities of the microbial community, were investigated. The results demonstrated that SFCW generally had better nitrogen removal performance than FTW did over four seasons. The average total nitrogen removal efficiency was 66.0% and 43.8% in SFCW and FTW, respectively. The plant uptake played a vital role in nitrogen reduction, which accounted for 29.3% and 7.7% of the total removed nitrogen in SFCW and FTW, respectively. A combination of high-throughput sequencing and quantitative polymerase chain reaction analysis revealed that the two wetland systems had complete nitrogen cycling, and the narG gene was the dominant nitrogen-transformation functional gene in both systems. More abundant denitrifying genes in SFCW than in FTW were also responsible for higher removal capacity of nitrogen. The results suggest that the planting pattern of wetland vegetation has an important impact on nitrogen removal efficiency by influencing the plant absorption and the development of microbial communities.

Comparison of Inferior and Superior Conjunctival Autograft for Primary Pterygium.

PURPOSE: To determine the postoperative symptom by using inferior conjunctival autografting (ICA) rather than superior conjunctival autografting (SCA) after excision of pterygium. METHODS: This prospective randomized control study evaluated 80 eyes of 80 consecutive patients undergoing primary pterygium surgery. Patients in each subgroup were then randomized into the ICA (n = 40) or SCA (n = 40) group. All patients were asked to return for follow up on days 1, 2, 3, 5, 7, and 14 then at months 1, 3, 6, and 12 postoperatively. Outcome measures were postoperative patient discomfort, corneal epithelial healing time, complications and recurrence rate. RESULTS: Fluorescein staining revealed complete corneal epithelial healing time was 3.1 ± 0.5 d (range 2-4) in the ICA group and 3.3 ± 0.6 d (range 2-4) in the SCA group (p = 0.11). Pain scores were significantly less in the ICA group than the SCA group on follow-up days 3 and 5 (p < 0.05). Postoperative foreign body sensation scores on follow-up days 5 and 7 were significantly lower in the ICA group than the SCA group (p < 0.05). Epiphora scores were significantly less in the ICA group than the SCA group on follow-up days 3, 5, and 7 (p < 0.05). No statistically significant differences between two groups were found for the overall (conjunctival and corneal) recurrence rates (5% versus 7.5%, p = 0.64). No serious complications were encountered. CONCLUSION: Pterygium excision with ICA led to less postoperative discomfort for patients with primary pterygium.

A novel technique of sutureless and glueless conjunctival autografting in pterygium surgery by electrocautery pen.

PURPOSE: To compare the efficacy and safety of electrocautery pen (ECP) with nylon 10-0 sutures in conjunctival autografting for the treatment of primary pterygium. METHODS: A prospective, randomized, clinical trial was carried out in 80 patients (80 eyes) with primary pterygium. Patients were randomized to undergo pterygium surgery using either ECP (40 eyes) or nylon 10-0 sutures (40 eyes) to attach the conjunctival autograft. All the patients were followed up postoperatively on postoperative days 1, 2, 3, 5, 7, and 14 and then at months 1, 3, 6, and 12. Outcome measures were surgery time, postoperative patient discomfort, complications, and recurrence rate. RESULTS: The mean surgical time for the glue group was significantly shorter at 20.4 minutes compared with the suture group at 27.1 minutes (P < 0.001). Postoperative pain, irritation, and epiphora were significantly less at postoperative days 5 and 7 (P < 0.05). Postoperative foreign body sensation was significantly less at postoperative days 2, 3, 5, and 7 (P < 0.05). Two patients in the ECP group had partial graft dehiscence; 2 patients in the suture group developed granulomas. During the follow-up period, conjunctival recurrence (grade 3) developed in 1 (2.5%) eye in the ECP group, and in 2 (5%) eyes in the suture group. Both groups had 1 (2.5%) corneal recurrence (grade 4). CONCLUSION: Using ECP for the attachment of conjunctival autograft in pterygium surgery is safe, fast, simple, and economical with less postoperative discomfort.

Weighted frequent gene co-expression network mining to identify genes involved in genome stability.

Gene co-expression network analysis is an effective method for predicting gene functions and disease biomarkers. However, few studies have systematically identified co-expressed genes involved in the molecular origin and development of various types of tumors. In this study, we used a network mining algorithm to identify tightly connected gene co-expression networks that are frequently present in microarray datasets from 33 types of cancer which were derived from 16 organs/tissues. We compared the results with networks found in multiple normal tissue types and discovered 18 tightly connected frequent networks in cancers, with highly enriched functions on cancer-related activities. Most networks identified also formed physically interacting networks. In contrast, only 6 networks were found in normal tissues, which were highly enriched for housekeeping functions. The largest cancer network contained many genes with genome stability maintenance functions. We tested 13 selected genes from this network for their involvement in genome maintenance using two cell-based assays. Among them, 10 were shown to be involved in either homology-directed DNA repair or centrosome duplication control including the well-known cancer marker MKI67. Our results suggest that the commonly recognized characteristics of cancers are supported by highly coordinated transcriptomic activities. This study also demonstrated that the co-expression network directed approach provides a powerful tool for understanding cancer physiology, predicting new gene functions, as well as providing new target candidates for cancer therapeutics.

k-Neighborhood decentralization: a comprehensive solution to index the UMLS for large scale knowledge discovery.

The Unified Medical Language System (UMLS) is the largest thesaurus in the biomedical informatics domain. Previous works have shown that knowledge constructs comprised of transitively-associated UMLS concepts are effective for discovering potentially novel biomedical hypotheses. However, the extremely large size of the UMLS becomes a major challenge for these applications. To address this problem, we designed a k-neighborhood Decentralization Labeling Scheme (kDLS) for the UMLS, and the corresponding method to effectively evaluate the kDLS indexing results. kDLS provides a comprehensive solution for indexing the UMLS for very efficient large scale knowledge discovery. We demonstrated that it is highly effective to use kDLS paths to prioritize disease-gene relations across the whole genome, with extremely high fold-enrichment values. To our knowledge, this is the first indexing scheme capable of supporting efficient large scale knowledge discovery on the UMLS as a whole. Our expectation is that kDLS will become a vital engine for retrieving information and generating hypotheses from the UMLS for future medical informatics applications.