Forest Fire Detection via Feature Entropy Guided Neural Network.

Forest fire detection from videos or images is vital to forest firefighting. Most deep learning based approaches rely on converging image loss, which ignores the content from different fire scenes. In fact, complex content of images always has higher entropy. From this perspective, we propose a novel feature entropy guided neural network for forest fire detection, which is used to balance the content complexity of different training samples. Specifically, a larger weight is given to the feature of the sample with a high entropy source when calculating the classification loss. In addition, we also propose a color attention neural network, which mainly consists of several repeated multiple-blocks of color-attention modules (MCM). Each MCM module can extract the color feature information of fire adequately. The experimental results show that the performance of our proposed method outperforms the state-of-the-art methods.

Exploring the association between epilepsy and depression: A systematic review and meta-analysis.

OBJECTIVE: This study offers meta-analytic data on the potential association between epilepsy and depression especially for the prevalence of depression in epilepsy or vice versa. METHODS: The relevant studies were searched and identified from nine electronic databases. Studies that mentioned the prevalence and/or incidence of epilepsy and depression were included. Hand searches were also included. The search language was English and the search time was through May 2022. Where feasible, random-effects models were used to generate pooled estimates. RESULTS: After screening electronic databases and other resources, 48 studies from 6,234 citations were included in this meta-analysis. The period prevalence of epilepsy ranged from 1% to 6% in patients with depression. In population-based settings, the pooled period prevalence of depression in patients with epilepsy was 27% (95% CI, 23-31) and 34% in clinical settings (95% CI, 30-39). Twenty studies reported that seizure frequency, low income, unemployment of the patients, perception of stigma, anxiety, being female, unmarried status, disease course, worse quality of life, higher disability scores, and focal-impaired awareness seizures were risk factors for depression. CONCLUSION: Our study found that epilepsy was associated with an increased risk of depression. Depression was associated with the severity of epilepsy.

Baicalin regulates depression behavior in mice exposed to chronic mild stress via the Rac/LIMK/cofilin pathway.

BACKGROUND: Depression is a common disease that endangers people's physical and mental health. Traditional Chinese medicine has advantages in treating the emotional and cognitive symptoms of depressive disorders. OBJECTIVE: To study the effects of baicalin on the behavior and to clarify the underlying mechanism through evaluation of the Rac1-LIMK1-cofilin pathway. METHODS: A chronic mild stress (CMS) model of depression was used. Baicalin was administered to the mice for the intervention, and the positive control group was treated with fluoxetine. Behavioral tests were conducted to observe the degree of depressive disorders. Synaptophysin (SYP), postsynaptic density protein-95 (PSD95), brain-derived neurotrophic factor (BDNF), tyrosine kinase receptors (TrkB), Rac1 and cofilin expression was determined using Western blot analysis, and mRNA was quantified using real-time PCR. RESULTS: Mice in the CMS group showed an increase in depression-like behavior (p < 0.01), while mice in the baicalin and fluoxetine groups showed a decrease in depression-like behavior (p < 0.01), compared with the control group. Electron microscopy showed ultrastructural changes in the hippocampal CA3 area of the CMS group, which were alleviated by baicalin treatment. SYP, PSD95, BDNF, TrkB, Rac1 and cofilin protein expression levels were decreased in the CMS group compared with the control group, while these levels were increased in the baicalin and fluoxetine groups (p < 0.01). There was no significant difference among the baicalin and fluoxetine groups (p > 0.05). CONCLUSION: Baicalin markedly alleviated depression-like behavioral changes, exerted effects on SYP, PSD95, BDNF, and TrkB expression, activated the Rac1-cofilin pathway, and subsequently improve synaptic plasticity.

Characterization of duplicated Dunaliella viridis SPT1 genes provides insights into early gene divergence after duplication.

The sodium-dependent phosphate transporter gene from unicellular green algae Dunaliella viridis, DvSPT1, shares similarity with members of Pi transporter family. Sequencing analysis of D. viridis BAC clone containing the DvSPT1 gene revealed two inverted duplicated copies of this gene (DvSPT1 and DvSPT1-2 respectively). The duplication covered most of both genes except for their 3' downstream region. The duplicated genomic sequences exhibited 97.9% identity with a synonymous divergence of Ks=0.0126 in the coding region. This data indicated very recent gene duplication in D. viridis genome, providing an excellent opportunity to investigate sequence and expression divergence of duplicated genes at an early stage. Scattered point mutations and length polymorphism of simple sequence repeats (SSRs) were predominant among the sequence divergence soon after gene duplication. Due to sequence divergence in the 5' regulatory regions and a swap of the entire 3' downstream regions (3'-UTR), DvSPT1 and DvSPT1-2 showed expression divergence in response to extra-cellular NaCl concentration changes. According to their expression patterns, the two diverged gene copies would provide better adaptation to a broader range of extra-cellular NaCl concentration. Furthermore, Southern blot analysis indicated that there might be a large phosphate transporter gene family in D. viridis.