Feature Interaction Learning Network for Cross-Spectral Image Patch Matching.

Recently, feature relation learning has attracted extensive attention in cross-spectral image patch matching. However, most feature relation learning methods can only extract shallow feature relations and are accompanied by the loss of useful discriminative features or the introduction of disturbing features. Although the latest multi-branch feature difference learning network can relatively sufficiently extract useful discriminative features, the multi-branch network structure it adopts has a large number of parameters. Therefore, we propose a novel two-branch feature interaction learning network (FIL-Net). Specifically, a novel feature interaction learning idea for cross-spectral image patch matching is proposed, and a new feature interaction learning module is constructed, which can effectively mine common and private features between cross-spectral image patches, and extract richer and deeper feature relations with invariance and discriminability. At the same time, we re-explore the feature extraction network for the cross-spectral image patch matching task, and a new two-branch residual feature extraction network with stronger feature extraction capabilities is constructed. In addition, we propose a new multi-loss strong-constrained optimization strategy, which can facilitate reasonable network optimization and efficient extraction of invariant and discriminative features. Furthermore, a public VIS-LWIR patch dataset and a public SEN1-2 patch dataset are constructed. At the same time, the corresponding experimental benchmarks are established, which are convenient for future research while solving few existing cross-spectral image patch matching datasets. Extensive experiments show that the proposed FIL-Net achieves state-of-the-art performance in three different cross-spectral image patch matching scenarios.

A YOLOv7 incorporating the Adan optimizer based corn pests identification method.

Major pests of corn insects include corn borer, armyworm, bollworm, aphid, and corn leaf mites. Timely and accurate detection of these pests is crucial for effective pests control and scientific decision making. However, existing methods for identification based on traditional machine learning and neural networks are limited by high model training costs and low recognition accuracy. To address these problems, we proposed a YOLOv7 maize pests identification method incorporating the Adan optimizer. First, we selected three major corn pests, corn borer, armyworm and bollworm as research objects. Then, we collected and constructed a corn pests dataset by using data augmentation to address the problem of scarce corn pests data. Second, we chose the YOLOv7 network as the detection model, and we proposed to replace the original optimizer of YOLOv7 with the Adan optimizer for its high computational cost. The Adan optimizer can efficiently sense the surrounding gradient information in advance, allowing the model to escape sharp local minima. Thus, the robustness and accuracy of the model can be improved while significantly reducing the computing power. Finally, we did ablation experiments and compared the experiments with traditional methods and other common object detection networks. Theoretical analysis and experimental result show that the model incorporating with Adan optimizer only requires 1/2-2/3 of the computing power of the original network to obtain performance beyond that of the original network. The mAP@[.5:.95] (mean Average Precision) of the improved network reaches 96.69% and the precision reaches 99.95%. Meanwhile, the mAP@[.5:.95] was improved by 2.79%-11.83% compared to the original YOLOv7 and 41.98%-60.61% compared to other common object detection models. In complex natural scenes, our proposed method is not only time-efficient and has higher recognition accuracy, reaching the level of SOTA.

Epidemiology of Blastocystis infection from 1990 to 2019 in China.

BACKGROUND: Blastocystis is ubiquitous presence in animals and humans worldwide and has a high level genetic diversity. The aim of this study was to conduct a summary of Blastocystis prevalence, subtypes (STs) in humans and animals in China and depict their distribution. METHODS: We searched for the articles related to epidemiology of Blastocystis in humans and animals throughout China which published from January 1, 1990, to July 31, 2019 in the following databases: PubMed, China National Knowledge Infrastructure (CNKI) and Wanfang database. The keywords were Blastocystis and one of the following ones: STs, subtypes, distribution, epidemiology, prevalence, infection, molecular, geographic, intestinal parasites, genetic diversity and characterization. RESULTS: In recent years, various molecular epidemiological studies have been carried out in some provinces/regions of China to identify subtypes of Blastocystis. Infants and young children, school students, hospitalized diarrhea patients, HIV/AIDS patients, tuberculosis patients, and cancer patients as respondents had been included. ST1-ST7 and ST12 were the main subtypes in Chinese population. Moreover, surveys of Blastocystis infection in animal were also conducted in some provinces of China. A variety of animals were investigated including pigs, cattle, sheep, yak, giant panda, and crested ibis (Nipponia nippon) with the main subtypes of ST1-ST8, ST10, ST12-ST14. CONCLUSIONS: In recent years, some provinces/regions in China have conducted various molecular epidemiological studies to identify the Blastocystis subtypes. It is important to focus on new subtypes and mixed subtypes of infection, while increasing data on ribosomal alleles. We encourage the scientific community to start research on humans and surrounding animals (including domestic and wild animals) to better understand the possibility of Blastocystis transmission between humans and animals. We call for action among researchers studying intestinal parasitic diseases (Blastocystis), start drawing the subtype of Blastocystis and increase the subtype related to its clinical symptoms.

A method overview in smart aquaculture.

Aquaculture is an important part of agricultural economy. In the past, major farming accidents often occurred due to subjective experience. There are many factors affecting the water quality of aquaculture. Maintaining an ecological environment with good water quality is the most critical link to ensure the production efficiency and quality of aquaculture. With the continuous development of science and technology, intelligence and informatization in aquaculture has become a new trend. Smart aquaculture cannot only realize real-time monitoring, prediction, warning, and risk control of the physical and chemical factors of the aquaculture environment but can also conduct real-time monitoring of the characteristics and behaviors of the fish, which infers the changes of the aquaculture ecological environment. In this paper, the research achievements over past two decades both are summarized from four aspects: water quality factor acquisition and pre-processing, water quality factor prediction, morphological characteristics, and behavioral characteristic recognition of fish and the mechanism between fish behavior and water quality factors. The advantages and disadvantages of existing research routes, algorithm models, and research methods in smart aquaculture are summarized. The work in this paper can provide a well-organized and summative knowledge reference for further study on the dynamic mechanism between the changes of water quality factors and the fish body characteristics and behavior. Meanwhile, the work can also provide valuable reference for promoting the smart, ecological, and efficient development of aquaculture.

A Water Quality Prediction Method Based on the Deep LSTM Network Considering Correlation in Smart Mariculture.

An accurate prediction of cage-cultured water quality is a hot topic in smart mariculture. Since the mariculturing environment is always open to its surroundings, the changes in water quality parameters are normally nonlinear, dynamic, changeable, and complex. However, traditional forecasting methods have lots of problems, such as low accuracy, poor generalization, and high time complexity. In order to solve these shortcomings, a novel water quality prediction method based on the deep LSTM (long short-term memory) learning network is proposed to predict pH and water temperature. Firstly, linear interpolation, smoothing, and moving average filtering techniques are used to repair, correct, and de-noise water quality data, respectively. Secondly, Pearson's correlation coefficient is used to obtain the correlation priors between pH, water temperature, and other water quality parameters. Finally, a water quality prediction model based on LSTM is constructed using the preprocessed data and its correlation information. Experimental results show that, in the short-term prediction, the prediction accuracy of pH and water temperature can reach 98.56% and 98.97%, and the time cost of the predictions is 0.273 s and 0.257 s, respectively. In the long-term prediction, the prediction accuracy of pH and water temperature can reach 95.76% and 96.88%, respectively.

A Self-Adaptive Progressive Support Selection Scheme for Collaborative Wideband Spectrum Sensing.

The sampling rate of wideband spectrum sensing for sparse signals can be reduced by sub-Nyquist sampling with a Modulated Wideband Converter (MWC). In collaborative spectrum sensing, the fusion center recovers the spectral support from observation and measurement matrices reported by a network of CRs, to improve the precision of spectrum sensing. However, the MWC has a very high hardware complexity due to its parallel structure; it sets a fixed threshold for a decision without considering the impact of noise intensity, and needs a priori information of signal sparsity order for signal support recovery. To address these shortcomings, we propose a progressive support selection based self-adaptive distributed MWC sensing scheme (PSS-SaDMWC). In the proposed scheme, the parallel hardware sensing channels are scattered on secondary users (SUs), and the PSS-SaDMWC scheme takes sparsity order estimation, noise intensity, and transmission loss into account in the fusion center. More importantly, the proposed scheme uses a support selection strategy based on a progressive operation to reduce missed detection probability under low SNR levels. Numerical simulations demonstrate that, compared with the traditional support selection schemes, our proposed scheme can achieve a higher support recovery success rate, lower sampling rate, and stronger time-varying support recovery ability without increasing hardware complexity.

[Effect of calcium cyanamid synthetic drug on Schistosoma japonicum egg morphology].

OBJECTIVE: To study the morphological change of Schistosoma japonicum eggs processed by calcium cyanamide synthetic drug, so as to provide the basis for further study of the mechanism that calcium cyanamide synthetic drug to schistosome eggs. METHODS: The calcium cyanamide synthetic drug was added to the cattle feces containing schistosome eggs and mixed up, and then the cattle feces was stacked as original shape on the marshland. Blank controls were set at the same time. The cattle feces samples were collected and.the schistosome eggs were observed under a microscope on the 1st, 2nd, 3rd, 7th day after the experiment. RESULTS: By the effect of calcium cyanamide synthetic drug, the color of eggs was deepening gradually, the miracidia were atrophied, and the shells of eggs were thickened. The embryonic membrane of miracidia was no longer completed 3 days later, and the miracidia were deformed severely 7 days later. The atrophy of miracidia was not obvious in the blank controls. CONCLUSION: The schistosome miracidia and embryonic membrane can be damaged by the calcium cyanamide synthetic drug, and worse damaged with time extending.

[Effect of schistosomiasis control in towns reached criteria of infection controlled in Nanchang City].

OBJECTIVE: To evaluate the effect of schistosomiasis control in towns that had reached the criteria of infection controlled in Nanchang City. METHODS: The residents and livestock of 14 towns that had reached the criteria of infection controlled in Nanchang, Xinjian and Jinxian counties of Nanchang City were sampled to investigate the schistosomiasis endemic situation, Oncomelania hupensis snail status, and data of schistosomiasis control work. RESULTS: The positive rate of serum tests of the residents was 2.58%, and no positive stool samples were found. No cattle or sheep were positive in stool tests. Totally 1 635 snails were caught, and 1278 were alive with an average density of living snails of 0.051/0.1 M2, while no schistosome infected snails were found. All the surveyed administrative villages had the completed files of schistosomiasis control. Conclusion All the 14 towns that had reached the criteria of infection controlled of schistosomiasis have already reached the criteria of transmission controlled in Nanchang City.

[Epidemic situation of acute schistosomiasis in Nanchang City of Jiangxi Province from 2005 to 2012].

OBJECTIVE: To understand the endemic regulation of acute schistosomiasis in Nanchang City of Jiangxi Province from 2005 to 2012 so as to provide the reference for policy-making of schistosomiasis control. METHODS: The data of acute schistosomiasis were collected and analyzed with the descriptive epidemiology method in Nanchang City from 2005 to 2012. RESULTS: A total of 52 acute schistosomiasis cases were reported in Nanchang City from 2005 to 2012. The morbidity of acute schistosomiasis was 0.003 46% in 2005, and it was 0 in 2012. The morbidity of acute schistosomiasis in different years was significant different (chi2 = 61.077, P < 0.01). The duration of incidence was from May to November, but the peak of the incidence was July. The sex ratio between males and females was 4.78:1 (43:9, chi2 = 22.231, P < 0.01). The ages of cases showed double humps, namely the 6-15 years' group and 30-40 years' group. Most of the acute cases were farmers (65.38%), students (25.00%), and fishermen (3.85%). Fishing and swimming were the main infection ways, with the infection rates of 63.46% and 26.92%, respectively. CONCLUSION: The susceptible populations are peasants and young students; therefore, we should strengthen health education for these high-risk groups.

[Influencing factors of changes of Oncomelania snail densities in Poyang Lake region, Nanchang City, 2011].

OBJECTIVE: To explore the influencing factors of the significant decrease of snail densities in Poyang Lake region, Nanchang City, 2011. METHODS: According to the elevation of the environment, 5 grasslands where there were high snail densities and their elevations were from 14 to 17 m were selected as study areas. The data of snails in the past three years and the hydrological information in the past five years were collected and analyzed. The current snail status was surveyed and the fishermen were interviewed. RESULTS: The snail density of Poyang Lake region in Jinxian County decreased by 91.2% in 2011 compared with that in 2009 (P < 0.01). In 2010, the water levels were 13.90 m in April and 16.07 m in May respectively in Xingzi Station, and the rainfalls were 312 mm in April and 356 mm in May in Poyang Lake region; in 2011, the water levels were 8.73 m in April and 10.31 m in May respectively in Xingzi Station, and the rainfalls were 90 mm in April and 145 mm in May respectively in Poyang Lake region, which were lower than those during the past five years. There was no any other apparently unusual phenomenon. CONCLUSION: The significant decrease of snail densities in Poyang Lake region in 2011 may be related to the long soaking time of marshland in 2010 and low rainfall in the first half of 2011.

[Effect of niclosamide spreading oil on killing schistosome cercariae].

Dechlorinated water (100 ml, 30 degrees C) was put into a plate (diameter 15 cm), and 1% niclosamide spreading oil 5 microl was added, then a ring of Schistosoma japonicum cercariae were picked up to the plate. The time of killing all the cercariae was observed at three time points (immediately, 24, 48 h), and the dechlorinated water was used as control. The results showed that schistosome cercariae were all killed in three minutes by 1% niclosamide spreading oil at the three time points. The cercaria-killing effects of each time point were not significantly different (F = 0.062, P > 0.05). The cercariae were alive in the control in 48 h.