Search

In order to deal with the target recognition in the complex underwater environment, we carried out experimental research. This includes filtering noise in the feature extraction stage of underwater images rich in noise, or with complex backgrounds, and improving the accuracy of target classification in the recognition process. This paper discusses our contribution to improving the accuracy of underwater target classification. This paper proposes an underwater target classification algorithm based on the improved flow direction algorithm (FDA) and search agent strategy, which can simultaneously optimize the weight parameters, bias parameters, and super parameters of the extreme learning machine (ELM). As a new underwater target classifier, it replaces the full connection layer in the traditional classification network to build a classification network. In the first stage of the network, the DenseNet201 network pre-trained by ImageNet is used to extract features and reduce dimensions of underwater images. In the second stage, the optimized ELM classifier is trained and predicted. In order to weaken the uncertainty caused by the random input weight and offset of the introduced ELM, the fuzzy logic, chaos initialization, and multi population strategy-based flow direction algorithm (FCMFDA) is used to adjust the input weight and offset of the ELM and optimize the super parameters with the search agent strategy at the same time. We tested and verified the FCMFDA-ELM classifier on Fish4Knowledge and underwater robot professional competition 2018 (URPC 2018) datasets, and achieved 99.4% and 97.5% accuracy, respectively. The experimental analysis shows that the FCMFDA-ELM underwater image classifier proposed in this paper has a greater improvement in classification accuracy, stronger stability, and faster convergence. Finally, it can be embedded in the recognition process of underwater targets to improve the recognition performance and efficiency.

The progressive neurodegenerative disease, amyotrophic lateral sclerosis (ALS), is characterized by muscle weakness and atrophy owing to selective motoneuron degeneration. The anti-glutamatergic drug, riluzole (RZ), is the standard-of-care treatment for ALS. Bojungikgi-tang (BJIGT), a traditional herbal formula, improves motor function and prolongs the survival of mice with ALS. As ALS is a multicomplex disease, effective therapies must target multiple mechanisms. Here, we evaluated the efficacy of a BJIGT/RZ combination (5-week treatment) in 2-month-old hSOD1G93A mice with ALS. We performed quantitative polymerase chain reaction, Western blotting, immunohistochemistry, and enzyme activity assays. BJIGT/RZ significantly attenuated inflammation, autophagy, and metabolic and mitochondrial dysfunctions in the gastrocnemius (GC) compared with the control. It reduced the mRNA and protein levels of muscle denervation-related proteins and creatine kinase levels. The total creatine level was significantly higher in the BJIGT/RZ-treated GC. Moreover, after BJIGT/RZ treatment, the number of Nissl-stained motoneurons and choline acetyl transferase-positive neurons in the spinal cord significantly increased via the regulation of proinflammatory cytokines. Collectively, the BJIGT/RZ treatment was superior to single-drug treatments in alleviating multiple ALS-related pathological mechanisms in the ALS mouse model. Overall, BJIGT can serve as a dietary supplement and be combined with RZ to achieve superior therapeutic effects against ALS.

Hochu-ekki-to (Bojungikgi-Tang (BJIGT) in Korea, Bu-Zhong-Yi-Qi Tang in Chinese), a traditional herbal prescription, has been widely used in Asia. Hochu-ekki-to (HET) is used to enhance the immune system in respiratory disorders, improve the nutritional status associated with chronic diseases, enhance the mucosal immune system, and improve learning and memory. Amyotrophic lateral sclerosis (ALS) is pathologically characterized by motor neuron cell death and muscle paralysis, and is an adult-onset motor neuron disease. Several pathological mechanisms of ALS have been reported by clinical and in vitro/in vivo studies using ALS models. However, the underlying mechanisms remain elusive, and the critical pathological target needs to be identified before effective drugs can be developed for patients with ALS. Since ALS is a disease involving both motor neuron death and skeletal muscle paralysis, suitable therapy with optimal treatment effects would involve a motor neuron target combined with a skeletal muscle target. Herbal medicine is effective for complex diseases because it consists of multiple components for multiple targets. Therefore, we investigated the effect of the herbal medicine HET on motor function and survival in hSOD1G93A transgenic mice. HET was orally administered once a day for 6 weeks from the age of 2 months (the pre-symptomatic stage) of hSOD1G93A transgenic mice. We used the rota-rod test and foot printing test to examine motor activity, and Western blotting and H&amp, E staining for evaluation of the effects of HET in the gastrocnemius muscle and lumbar (L4&ndash, 5) spinal cord of mice. We found that HET treatment dramatically inhibited inflammation and oxidative stress both in the spinal cord and gastrocnemius of hSOD1G93A transgenic mice. Furthermore, HET treatment improved motor function and extended the survival of hSOD1G93A transgenic mice. Our findings suggest that HET treatment may modulate the immune reaction in muscles and neurons to delay disease progression in a model of ALS.