Research on Video Quality Diagnosis Technology Based on Artificial Intelligence and Internet of Things

The remote video diagnosis system based on the Internet of Things is based on the Internet of Things and integrates advanced intelligent technology. To better promote a harmonious society, constructing a video surveillance system is accelerating in our country. Many enterprises and government agencies have invested much money to build video surveillance systems. The quality of video images is an important index to evaluate the video surveillance system. However, as the number of cameras continues to increase, the monitoring time continues to extend. In the face of many cameras, it is not realistic to rely on human eyes to diagnose video-solely quality. Besides, due to human eyes’ subjectivity, there will be some deviation in diagnosis through human eyes, and these factors bring new challenges to system maintenance. Therefore, relying on artificial intelligence technology and digital image processing technology, the intelligent diagnosis system of monitoring video quality is born using the computer’s efficient mathematical operation ability. Based on artificial intelligence, this paper focuses on studying video quality diagnosis technology and establishes a video quality diagnosis system for video definition detection and noise detection. This article takes the artificial intelligence algorithm in the diagnosis of video quality effect. Compared with the improved algorithm, the improved video quality diagnosis algorithm has excellent improvement and can well finish video quality inspection work. The accuracy of the improved definition evaluation function for the definition detection of surveillance video and noise detection is as high as 95.56%.

A novel deep convolution generative adversarial transfer learning model for data-driven assembly quality diagnosis

As the service life of the assembly equipment are short, the tightening data it produces are very limited. Therefore, data-driven assembly quality diagnosis is still a challenge task in industries. Transfer learning can be used to address small data problems. However, transfer learning has strict requirements on the training dataset, which is hard to satisfy. To solve the above problem, an Improved Deep Convolution Generative Adversarial Transfer Learning Model (IDCGAN-TM) is proposed, which integrates three modules: The generative learning module automatically produces source datasets based on small target datasets by using the improved generative-adversarial theory. The feature learning module improves the feature extraction ability by building a lightweight deep learning model (DL). The transfer learning module consists of a pre-trained DL and a one fully connected layer to better perform the intelligent quality diagnosis on the training small sample data. A parallel computing method is adopted to obtain produced source data efficiently. Real assembly quality diagnosis cases are designed and discussed to validate the advance of the proposed model. In addition, the comparison experiments are designed to show that the proposed approach holds the better transfer diagnosis performance compared with the existing three state-of-art approaches.

Deep-Learning-Based Hair Damage Diagnosis Method Applying Scanning Electron Microscopy Images

In recent years, with the gradual development of medicine and deep learning, many technologies have been developed. In the field of beauty services or medicine, it is particularly important to judge the degree of hair damage. Because people in modern society pay more attention to their own dressing and makeup, changes in the shape of their hair have become more frequent, e.g., owing to a perm or dyeing. Thus, the hair is severely damaged through this process. Because hair is relatively thin, a quick determination of the degree of damage has also become a major problem. Currently, there are three specific methods for this purpose. In the first method, professionals engaged in the beauty service industry make a direct judgement with the naked eye. The second way is to observe the damaged cuticle layers of the hair using a microscope, and then make a judgment. The third approach is to conduct experimental tests using physical and chemical methods. However, all of these methods entail certain limitations, inconveniences, and a high complexity and time consumption. Therefore, our proposed method is to use scanning electron microscope to collect various hair sample images, combined with deep learning to identify and judge the degree of hair damage. This method will be used for hair quality diagnosis. Experiment on the data set we made, compared with the experimental results of other lightweight networks, our method showed the highest accuracy rate of 94.8%.

Spatial distribution of lichen communities and air pollution mapping in a tropical city: Medellín, Colombia

Introduction: Enough scientific evidence is available on the harmful effects of air pollution on the health of human beings, fauna, flora, and ecosystems in general. The mechanical and electronical monitoring networks are the first option for the air quality diagnosis, but they do not allow a direct and precise assessment of the impacts in living organisms that may result from the exposure to air pollutants. Objective: To evaluate the changes in the composition of corticulous lichen communities as a response to various stress factors in areas with different levels of air quality to diagnose the state of pollution or intervention in an area with a more complete option. Methods: Air quality contrasts and changes in richness and coverage of corticulous lichens in response to different stress factors, such as land use and distance to roads, in three different biomonitoring areas, were evaluate using GIS, and the data are presented in an easy-to-understand grey scale coded isoline map. Results: Indicators such as lichen coverage (R= -0.4) and richness (R= -0.7) are inverse correlated with PM2.5 concentrations in each area. A total of 110 lichen species were identified, being Phaeophyscia chloantha (Ach.) Moberg and Physcia poncinsii Hue the most frequent species (present in 38 and 33 % of the 86 sampled phorophytes, respectively). The intra-area relationships of lichen richness exhibit significant relationships with regards to the land use and distance to roads (with correlations coefficients greater than 0.5) and the Simpson index was higher than 0.9, in places with better conditions in terms of air quality and microenvironments, likewise the resistance factors calculated suggest that the most sensitive species can be found in environments with a lesser degree of disturbance. Conclusion: These evaluations represent more criteria elements for the diagnosis of the environmental health in the biomonitoring areas.

Access to quality diagnosis and rational treatment for tuberculosis: real-world evidence from China–Gates Tuberculosis Control Project Phase III

Background China has successfully reduced tuberculosis (TB) incidence rate over the past three decades, however, challenges remain in improving the quality of TB diagnosis and treatment. In this paper, we assess the effects of the implementation of “China National Health Commission (NHC) and Gates Foundation TB Prevention and Control Project” on the quality of TB care in the three provinces. Methods We conducted the baseline study in 2016 and the final evaluations in 2019 in the 12 selected project counties. We obtained TB patients’ information from the TB Information Management System and reviewed medical records of TB cases in the TB designated hospitals. We compared TB diagnosis and treatment services with the national practice guideline and used Student’s t-test and Pearson χ2 tests or Fisher’s exact tests to compare the difference before and after the project implementation. Results The percentage of sputum smear-negative (SS–) patients taking culture or rapid molecular test (RMT) doubled between 2015 and 2018 (from 35% to 87%), and the percentage of bacteriologically confirmed pulmonary TB cases increased from 36% to 52%. RMT has been widely used and contributed an additional 20% of bacteriologically confirmed TB cases in 2018. The percentage of TB patients taking drug susceptibility tests (DST) also doubled (from 40% in 2015 to 82% in 2018), and the proportion of TB patients receiving adequate diagnosis services increased from 85% to 96%. Among all SS– TB patients, over 86% received the recommended diagnostic services at the end of the study period, an improvement from 75% prior to the project implementation. However, the proportion of TB patients treated irrationally using second-line anti-TB drugs (SLDs) increased from 12.6% in 2015 to 19.9% in 2018. The regional disparities remained within the project provinces, albeit the gaps between them narrowed down for almost all indicators. Conclusions The quality of TB diagnosis services has been improved substantially, which is attributable to the coverage of new diagnosis technology. However, irrational use of SLDs remains a concern after the project implementation. Graphic abstract

Diagnóstico da qualidade da água do rio Itanhém entre os municípios de Medeiros Neto e Teixeira de Freitas, Bahia

A bacia do rio Itanhém é responsável pelo abastecimento de água dos municípios de Medeiros Neto e Teixeira de Freitas no Extremo Sul baiano, e recebe inúmeras cargas de efluentes domésticos e industriais, que comprometem a qualidade de suas águas. Portanto, objetivou-se neste trabalho avaliar a qualidade da água, identificar os grupos de poluição ou contaminação além de evidenciar possíveis impactos causados pelo uso e ocupação do solo no trecho do rio Itanhém entre Medeiros Neto e Teixeira de Freitas. Foram realizadas 12 coletas mensais entre 08/2018 e 07/2019, em oito pontos do rio para avaliar a qualidade da água em pontos próximos a aglomerações urbanas, com lançamentos de efluentes com carga orgânica, que contribuem para a deterioração da qualidade da água, e em pontos distantes das zonas urbanas, afastados dos despejos de efluentes. Foi utilizando uma sonda multiparamétrica HI9829 HANNA® para leituras realizadas in loco, para valores de potencial de oxirredução, OD (oxigênio dissolvido), pH, salinidade, temperatura, condutividade e STD (sólidos totais dissolvidos). Também foram obtidos em laboratório os parâmetros: Amônia, Nitrito, Nitrato, DBO e CT (coliformes termotolerantes). Com dados de uso e ocupação do solo, cedidos pelo Fórum Florestal do Extremo Sul da Bahia, foi possível verificar as atividades desenvolvidas dentro da bacia hidrográfica e os impactos gerados por estas. Verificou-se que, nos pontos mais próximos aos lançamentos de efluentes, a qualidade da água apresentou-se em desconformidade com a resolução CONAMA 357/2005 para os indicadores CT, OD e a DBO, enquanto, nos pontos mais afastados dos despejos, esses mesmos indicadores se enquadraram na referida resolução ou aproximaram dos valores aceitáveis para corpos de água de classe 2, o indicando a capacidade autodepurativa do rio Itanhém. Water quality diagnosis of the Itanhém river water between municipalities of Medeiros Neto and Teixeira de Freitas, BahiaA B S T R A C TThe Itanhém river basin is responsible for the water supply of the municipalities of Medeiros Neto and Teixeira de Freitas in the far south of Bahia, Brazil and receives numerous loads of domestic and industrial effluents, which compromise the quality of its waters. Therefore, the aim’s work was to evaluate water quality, identify the groups of pollution or contamination and show possible impacts caused by land use and occupation on the Itanhém River stretch between Medeiros Neto and Teixeira de Freitas. Twelve monthly collections were carried out between 2018/08 to 2019/07, in eight points of the river to evaluate the water quality in points near urban agglomerations, with discharges of effluents with organic load, which contribute to the deterioration of water quality, and at points distant from urban areas, away from effluent discharges. A HI9829 HANNA® multiparameter probe was used for on-site readings for oxireduction potential, DO (dissolved oxygen), pH, salinity, temperature, conductivity and TDS (total dissolved solids). The following parameters were also obtained in the laboratory: Ammonia, Nitrite, Nitrate, BOD (Biochemical Oxygen Dynamics) and TC (thermotolerant coliforms). With data on land use and occupation, from the Far South Bahia Forest Forum, it was possible to verify the activities developed within the watershed and the impacts generated by them. It was found that, at the points closest to the discharge of effluents, the water quality was not in compliance with CONAMA resolution 357/2005 for the CT, OD and DBO indicators, with average values for CT (arranged in log) 4.46, 3.35, 3.19 and 3.43 respectively for points P2, p5, P7 and P8, while at the most distant points of the discharges, The same indicators fit the resolution or approached the acceptable values for class 2 water bodies (CONAMA 357/2005), indicating the self-purifying capacity of the Itanhém river.

Integrated Gas Source Analysis for Wells with Sustained Casing Pressure: A Case Study from Sour Gas Fields in Sichuan Basin, China

Sustained casing pressures are observed in many gas-field wells in Sichuan Basin. The presence of corrosive sour gas i.e. H2S and/or CO2 in the annulus, coupling with the none corrosion-resistant alloy (CRA) casing materials, may damage the casing and lead to loss of containment, which could be a disaster to the asset, local communities, and the environment. It is thus of significance to identify the gas source for the wells with sustainable casing pressure. Several wells in the study area were identified as risky wells with an initial risk screening exercise. The further determination of gas source, either sweet gas in the shallow formation or sour gas in the deep formation, would have a big impact on the risk levels and subsequent mitigation plans. An integrated forensic study was conducted to investigate the gas source, including annulus gas composition analysis, isotope fingerprinting, casing pressure profile construction and analysis, casing pressure bleed-off and build-up operations, cement quality evaluation, temperature and noise logging analysis, etc. In this paper, the integration of various tools and data enabled a quality diagnosis of the gas source for two risky wells. It is believed the most likely gas source for the first well is from the shallow sweet gas formation. The risk was then revised down to Low-Medium, and the well was temporarily plugged and abandoned (P&A) for future use. For the second well, the gas source is confirmed from the deep sour gas formation, and thus the risk is relatively high. A permanent P&A program was performed, and both the sour and sweet gas layers were successfully isolated per the standard barrier requirement to protect community and environment. In conclusion, most of the subsurface measurements have limitations and thus result in the imperfect data. The key to solving the subsurface puzzle is to consolidate all the perceptions together after reviewing the problem from different angles. The integration of multiple types of data in this study, including geological and engineering data, static and dynamic measurements, etc., allows a mostly likely interpretation of gas source to support the key operations decision. The results from integrated data analysis have helped improve the risk assessment, guide the development of risk mitigation plans and operations procedures to eliminate and/or reduce the risk of these wells and secure the subsurface integrity.