Establishment of a duplex fluorescent quantitative PCR assay for detection of Porcine circovirus type 2 and type 3

To establish a method for simultaneous detection of porcine circovirus type 2 (PCV2) and porcine circovirus type 3 (PCV3), specific primers and TaqMan probes were designed after sequence alignment according to the specific sequences of PCV2 Cap gene and PCV3 Cap gene on GenBank. By optimizing the reaction conditions, a duplex fluorescence quantitative PCR detection method for simultaneous detection of porcine circovirus type 2 and 3 was established, and the specificity, sensitivity, and reproducibility were tested. Specificity test results showed that in addition to the positive test results for PCV2 and PCV3, tests for PRRSV, CSFV, PPV, PRV, PEDV, and TGEV were all negative with no cross-reaction, indicating its good specificity. Sensitivity test results showed that the minimum detection limit for detection of PCV2 and PCV3 can both reach 10 copies.L-1, indicating its high sensitivity. The coefficient of variation within and between groups of this method was less than 2%, indicating its good stability. A total of 181 pork and whole blood samples collected from Zhejiang Province were tested using the detection method established in this article and the standard common fluorescent PCR detection method. The results showed that the positive rate of PCV2 was 50.83% (92/181), the positive rate of PCV3 was 37.57% (68/181), and the co-infection rate of PCV2 and PCV3 was 12.15% (22/181). The above detection results of ordinary fluorescent PCR were 50.28% (91/181), 36.46% (66/181), and the co-infection rate was 11.60% (21/181). The coincidence rates of the two methods for PCV2 and PCV3 can reach 98.91% and 97.06%, and the coincidence rate for PCV2 and PCV3 mixed infection were 95.45%. In summary, the duplex fluorescence quantitative PCR detection method established in this experiment can distinguish PCV2 and PCV3 rapidly, which can be used for pathogen detection and epidemiological investigation.

Smart Attendance System using Dlib Pre-Trained Neural Network

Recognizing and remembering various people is the most frequent task, which the human brain performs. With regard to this, the process of attendance becomes one of the hectic tasks, which requires subsequent modernization. The spread of COVID- 19 is also drastically increasing and are pushed to the situation of wearing mask the entire time. This brings in a situation of misidentifying the individuals and are also prone to impersonation in many official gatherings such as exams, meetings, etc. This cannot be decreased by unmasking their face in this pandemic situation just for the purpose of verification as it may lead to increase in COVID risk. Here, this research study implements a contactless face recognition system with a simple and smart database, which can take in any form of data as per the convenience. This system solves the above problem by making the face recognition smart using Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) classifier. The main task of the system is to recognize the user's face (live) and automatically mark the time of recognition directly in the Google sheet along with the alphabets of P(Present), A(absent) or L(late) according to the given time range. This system makes effective use of google sheet for easy share ability, accessibility, and error free management. This can be used for number of purposes such as exam centers, schools, colleges, companies, hospitals and various other places in order to verify the people (contact less). © 2023 IEEE.

Vision-based Monitoring of Student Attentiveness in an E-Learning Environment

Due to the global spread of COVID-19, the world's educational institutions had been ordered to close. As a direct result of this, the time-tested method of acquiring knowledge by visiting classes is gradually being replaced by online education. In virtual classrooms, teachers had difficulty detecting student postures and determining whether or not students were comprehending the material. This research suggests using a computationally efficient method based on computer vision and machine learning to determine the attention levels of e-learning students. The method extracts characteristics using HoG and SIFT. Using K-means and PCA, the resulting feature vector is optimized for dimension reduction. The attentiveness is classified using the classifiers Decision Tree, KNN, Random Forest, and SVM. Random Forest yielded the best accuracy at 99.2% with a dataset of 15000 images. © 2022 IEEE.

One-step multiple TaqMan real-time RT-PCR for simultaneous detection of swine diarrhea viruses

Objective: The aim of this study was to establish a one-step multiplex real-time RT-PCR method to simultaneously detect and quantify five swine diarrhea related viruses, PEDV, GARV, PDCoV, SADS-CoV and PTV, so as to provide an efficient and sensitive tool for rapid diagnosis and epidemiological investigation of porcine diarrhea. Method: The ORF3 gene sequences of several genotypes of PEDV were analyzed, and then the primers and probes were designed for detection of PEDV field strains by referring to the ORF3 genes, which contained deletion mutations in attenuated strains. The 5'-end conserved region of NSP5 genes of GARV G3, G4, G5 and G9 strains were analyzed for design of probes and primers. The specific primers and probes targeting to the conserved regions of PDCoV M, PTV 5'UTR and SADS-CoV N genes were designed for detection of the pathogens. The ROC curves were completed by referring to parameters that were set in RStudio. The specificity value, sensitivity value, and areas under the curves (AUC) and Youden value were calculated according to ROC curves to determine the cut-off CT value. The amplified fragments were cloned into pEASY-T1 vector. The standards prepared through in vitro transcription were named as cRNA-PEDV, cRNA-GARV, cRNA-PDCoV, cRNA-PTV and cRNA-SADS-CoV. The sensitivity, specificity and repeatability of one-step multiplex real-time RT-PCR were evaluated. Coincidence rate between this and another similar method were compared in the detection of clinical samples. Result: Both the annealing temperature and optimal concentrations of primers and probes were obtained for detection of the five pathogens. According to the ROC curve, the CT cut off values for detection of PEDV, GARV, PDCoV, PTV, and SADS-CoV were set as 35.78, 34.25, 34.98, 34.60, and 35.70, respectively. The detection sensitivity of this method for the five pathogens could reach 1..102 copies/L. The standard curves had a good linear relationship and the amplification efficiency was between 96.3% and 104%. The established method could not detect the PEDV vaccine strains and other swine infecting viruses and bacteria including TGEV, CSFV, PRV, PRRSV, S.choleraesuis, P.multocida, E.coli, S.suis and S.aureus. The repeatability test showed the range of intra-assay and inter-assay coefficients of variability: 0.22% to 3.08% and 0.89% to 4.0%, respectively. The detection coincidence rates of the established detection method and another similar method for the five pathogens in 242 clinical samples were 97.9%, 98.8%, 100%, 98.3% and 100% for PEDV, GARV, PDCoV, PTV and SADS-CoV, respectively. The Kappa values were all higher than 0.9. The method had advantage over a commercial diagnostic kit for detection of PEDV wild strains in accuracy. Detection results with clinical samples showed that positive rates of PEDV, GARV, PDCoV and PTV was 10.7% (26/242), 13.6% (33/242), 18.2% (44/242) and 14.5% (35/242), respectively, demonstrating the prevalence state of the four pathogens in Sichuan province in the years. SADS-CoV was not detectable in any areas, but the phenomenon of coinfection with different diarrhea causing viruses was common. Therefore, it was necessary to strengthen the surveillance of several porcine diarrhea viruses in Sichuan province for preventive control. Conclusion: In this study, a one-step multiplex real-time RT-PCR was established for simultaneous detection of PEDV wild strains, PDCoV, SADS-COV and GARV, PTV multiple genotypes, which provided an efficient and sensitive tool for the differential diagnosis and epidemiological investigation of swine diarrhea disease.

A Real-Time Crowd Detection and Monitoring System using Machine Learning

The COVID-19 pandemic has unquestionably warned all of us that, the outbreak of an infection can lead to a pandemic-like situation all over the world. In order to prevent outbreaks and provide better healthcare, appropriate crowd detection and monitoring systems must be deployed in public areas. By effectively implementing social distancing measures, the number of new infections can be greatly decreased. This idea served as the inspiration for the creation of a real-time Crowd Detection and Monitoring System (CDMS) for social distancing. This paper proposes a fully autonomous system for Real-Time Crowd Detection and Monitoring to help the educational institutions to monitor the students inside the premises more effectively. This system is developed using an OpenCV based Histogram of Oriented Gradients (HOG) and Support Vector Machine (SVM) detector to detect and count the number of people gathered at an instance. The system raises an alarm to alert the people and adhere to the rules if the gathering is more than the threshold/permitted number of people in the cluster. © 2023 IEEE.

Face Mask Detection Based Entry Control Using XAI and IoT

Today it has become mandatory for all the citizens to wear a face mask to protect them from COVID-19. Also taking two doses of vaccine is a must to visiting public places and currently, the only method to verify whether a person is fully vaccinated is by showing a vaccine certificate. The proposed application is helpful for elderly people who find it difficult to use smart phones. The shop owners, offices, banks, or any public place can check for restrictions of entry if anyone is not wearing a mask. As a result, no need for any guard to keep an eye on people. Machine learning techniques with Explainable AI (XAI) can solve these problems easily and results are made understandable to end-users because of the explaining ability and interpretability of neural network models. The system performs well for prediction and gives more accurate and trustworthy predictions. Hence XAI is more reliable in healthcare systems. The proposed system is implemented completely on Raspberry Pi allowing a complete embedded application. The application is developed using Python and HTML. PyCharm/Visual Studio Code with the help of an open-source library is used for training, defining, etc. Machine learning models used for the system are Tensorflow.js, Keras, OpenCV, etc. The whole application can run on a microcontroller such as Raspberry Pi, which allows one to simply plug and play the system at any time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Face Recognition Attendance System for Online Classes

Due to the increasing need for online lectures due to situations like COVID-19 and various online learning platforms, there is a need for a reliable attendance system for online classes. Our system is developed for deploying an easy and secure way of taking attendance without tedious roll-calls and inaccurate participant lists. The teachers will take screenshots of students in the online meets with their video cameras on. This screenshot will be uploaded to our system which will recognize the students and generate a report of their attendance. Our system will allow students and faculty to view the attendance of each lecture and give feedback if any discrepancy is found. We collected the dataset of face images of 94 students which are then augmented to increase the dataset and then used HOG for face detection. We then applied four algorithms namely VGG-16, MobileNet, InceptionV3, and our own CNN model for face recognition. MobileNet gave us the highest accuracy of 97.14%. We, therefore, deployed this model for our website to recognize faces and generate the attendance report. © 2022 IEEE.

Shocks, cycles and adjustments: The case of China's Hog Market under external shocks

China's hog market has faced the challenge of several external shocks, which arise from the ongoing COVID-19 pandemic, African Swine Fever (ASF) and related global trade uncertainties. This article develops a shocks, cycles and adjustments (SCA) model to evaluate the dynamic impact of different shock scenarios. The SCA model contributes to the existing toolbox for impact evaluation in commodity markets and provides insights into the timing of impact dynamics at refined time intervals. The SCA model is applied to evaluate five sets of shock scenarios, which include a demand shock, a corn price increase, pork import restrictions, a second wave of ASF, and a combination of these shocks. Simulation results demonstrate the reaction of the hog cycle to different shocks with quantitive outcomes. Based on the simulation results, we find that production and economic adjustment lags generate constant and predictable hog cycles, while the external shocks lead hog cycles to be irregular with varying phase and amplitude. [EconLit Citations: Q10, Q11]. © 2022 Wiley Periodicals LLC.

Establishment and preliminary application of a TaqMan real-time quantitative PCR method for PastV3 detection

In order to build a specific, sensitive and rapid detection method for PAstV3 detection, the PAstVB gene sequences in Genbank were used and the conserved region in ORFlb was selected to design specific primers and TaqMan probe. Clinical stool samples were collected and preliminary detected by this newly established real-time RT-PCR method after reaction systems and conditions optimization. This detection method established in this study has a good linear relationship with the standard curve, with R2 value up to 0.9971. The sensitivity is 100 times higher than conventional PCR method, The variation co-efficient of in-batch and inter-batch repeatability test is less than 2.0%, indicating good repeatability. The detection results of Clinical samples showed that the positive rate of this method is higher than conventional PCR method. The establishment of this method provides a rapid detection means for PAstV3 laboratory diagnosis and epidemiological investigation.

Suicide Ideation Detection of Covid Patients Using Machine Learning Algorithm

During Covid pandemic, many individuals are suffering from suicidal ideation in the world. Social distancing and quarantining, affects the patient emotionally. Affective computing is the study of recognizing human feelings and emotions. This technology can be used effectively during pandemic for facial expression recognition which automatically extracts the features from the human face. Monitoring system plays a very important role to detect the patient condition and to recognize the patterns of expression from the safest distance. In this paper, a new method is proposed for emotion recognition and suicide ideation detection in COVID patients. This helps to alert the nurse, when patient emotion is fear, cry or sad. The research presented in this paper has introduced Image Processing technology for emotional analysis of patients using Machine learning algorithm. The proposed Convolution Neural Networks (CNN) architecture with DnCNN preprocessing enhances the performance of recognition. The system can analyze the mood of patients either in real time or in the form of video files from CCTV cameras. The proposed method accuracy is more when compared to other methods. It detects the chances of suicide attempt based on stress level and emotional recognition. © 2023 CRL Publishing. All rights reserved.

Establishment and application of dual TaqMan fluorescent quantitative PCR assay for Senecavirus A and encephalomyocarditis virus

In order to establish a method for rapid differential identification of Senecavirus A (SVA) and en-cephalomyocarditis virus (EMCV), two pairs of corresponding specific primers were designed based on the highly conserved 3D genes of SVA and EMCV. And two different fluorescent labeled TaqMan probes were used to establish a dual TaqMan real-time PCR method for simultaneous detection of these two viruses, and we also optimize the reaction conditions. The results showed that the minimum detection of the method was 760 copies/ micro L and 98 copies/ micro L for SVA and EMCV. respectively, and it can specifically detect SVA and EMCV, and there was no cross reaction with CSFV, PRRSV and PEDV. The established standard curves showed good linear relationship. Repeated experimental group and inter-group coefficient of variation were less than 5%. The results indicated that the dual-quantitative PCR established in this study has the advantages of convenience, rapidity, good specificity. high sensitivity and good repeatability .and can be used for simultaneous detection of SVA and EMCV.

A New approach to Recognize Human Face Under Unconstrained Environment

Human face is considered as one of the most useful traits in biometrics, and it has been widely used in education, security, military and many other applications. However, in most of currently deployed face recognition systems ideal imaging conditions are assumed;to capture a fully featured images with enough quality to perform the recognition process. As the unmasked face will have a considerable impact on the numbers of new infections in the era of COVID-19 pandemic, a new unconstrained partial facial recognition method must be developed. In this research we proposed a mask detection method based on HOG (Histogram of Gradient) features descriptor and SVM (Support Vector Machine) to determine whether the face is masked or not, the proposed method was tested over 10000 randomly selected images from Masked Face-Net database and was able to correctly classify 98.73% of the tested images. Moreover, and to extract enough features from partially occluded face images, a new geometrical features extraction algorithm based on Contourlet transform was proposed. The method achieved 97.86% recognition accuracy when tested over 4784 correctly masked face images from Masked Face-Net database. © Al-Zaytoonah University of Jordan (ZUJ).

COVID-19 Isolation Control Proposal via UAV and UGV for Crowded Indoor Environments: Assistive Robots in the Shopping Malls.

Artificial intelligence researchers conducted different studies to reduce the spread of COVID-19. Unlike other studies, this paper isn't for early infection diagnosis, but for preventing the transmission of COVID-19 in social environments. Among the studies on this is regarding social distancing, as this method is proven to prevent COVID-19 to be transmitted from one to another. In the study, Robot Operating System (ROS) simulates a shopping mall using Gazebo, and customers are monitored by Turtlebot and Unmanned Aerial Vehicle (UAV, DJI Tello). Through frames analysis captured by Turtlebot, a particular person is identified and followed at the shopping mall. Turtlebot is a wheeled robot that follows people without contact and is used as a shopping cart. Therefore, a customer doesn't touch the shopping cart that someone else comes into contact with, and also makes his/her shopping easier. The UAV detects people from above and determines the distance between people. In this way, a warning system can be created by detecting places where social distance is neglected. Histogram of Oriented-Gradients (HOG)-Support Vector Machine (SVM) is applied by Turtlebot to detect humans, and Kalman-Filter is used for human tracking. SegNet is performed for semantically detecting people and measuring distance via UAV. This paper proposes a new robotic study to prevent the infection and proved that this system is feasible.

From Big Ag to Big Finance: a market network approach to power in agriculture

Critics charge that agriculture has reached an unsustainable level of consolidation and expropriation, as exemplified by the supply-chain breakdown of the COVID-19 pandemic. Simultaneously, advocates suggest the current system serves consumers well by keeping prices low and access to choices high. At the center of this debate rests a disagreement over how to compute market power to identify monopolies and oligopolies. We propose a method to study power across different sectors by using Social Network Analysis (SNA) to analyze key players, the presence of core-periphery structures, and agricultural consolidation. We test our market network approach to power through an analysis of the top ten pork powerhouses. We find that Big Finance is closely tied to Big Ag, and that key players limit the capacity for more peripheral actors, like growers, equipment producers, and regional banks, to engage in the network. We identify system level risk of collapse and suggest pathways for reform.

Computer-aided diagnosis of COVID-19 from chest X-ray images using histogram-oriented gradient features and Random Forest classifier.

The decision-making process is very crucial in healthcare, which includes quick diagnostic methods to monitor and prevent the COVID-19 pandemic disease from spreading. Computed tomography (CT) is a diagnostic tool used by radiologists to treat COVID patients. COVID x-ray images have inherent texture variations and similarity to other diseases like pneumonia. Manually diagnosing COVID X-ray images is a tedious and challenging process. Extracting the discriminant features and fine-tuning the classifiers using low-resolution images with a limited COVID x-ray dataset is a major challenge in computer aided diagnosis. The present work addresses this issue by proposing and implementing Histogram Oriented Gradient (HOG) features trained with an optimized Random Forest (RF) classifier. The proposed HOG feature extraction method is evaluated with Gray-Level Co-Occurrence Matrix (GLCM) and Hu moments. Results confirm that HOG is found to reflect the local description of edges effectively and provide excellent structural features to discriminate COVID and non-COVID when compared to the other feature extraction techniques. The performance of the RF is compared with other classifiers such as Linear Regression (LR), Linear Discriminant Analysis (LDA), K-nearest neighbor (kNN), Classification and Regression Trees (CART), Random Forest (RF), Support Vector Machine (SVM), and Multi-layer perceptron neural network (MLP). Experimental results show that the highest classification accuracy (99. 73%) is achieved using HOG trained by using the Random Forest (RF) classifier. The proposed work has provided promising results to assist radiologists/physicians in automatic COVID diagnosis using X-ray images.

A review of pig and poultry diseases in the Eastern Cape province of South Africa, 2000-2020

The informal poultry and pig sector in the Eastern Cape Province (ECP) of South Africa is of significant socio-economic importance as it sustains livelihoods and ensures food security;yet little is known about the distribution and prevalence of infectious and zoonotic diseases in this region. This paper reviews data published for pig and poultry diseases in the province during the last 20 years (2000-2020). The review included relevant published papers identified by a computerised literature search from Web of Science;provincial animal health reports;the national database from the Department of Agriculture, Land Reform and Rural Development (DALRRD);animal health reports submitted by DALRRD to the World Organisation for Animal Health (OIE) via the World Animal Health Information Database (WAHID) interface and laboratory records. A publication was considered eligible if it included qualitative or quantitative information on any disease affecting pigs and poultry including zoonosis. The search retrieved 174 publications, of which 26 were relevant. The review found that Newcastle disease (ND), coccidiosis and fowl pox (FP) were the most reported avian diseases in the national database, whereas avian infectious bronchitis (AIB), ND and highly pathogenic avian influenza (HPAI) were the most reported diseases in the OIE database. Classical swine fever (CSF) was the most reported pig disease in both databases. The retrieved literature on pig and poultry diseases was scarce and no longer up to date, providing decision makers with little information. The review identified important zoonotic diseases that require further studies yet failed to find information on important neglected diseases like leptospirosis.

Detection of Covid-19 from chest X-ray scans using machine learning

Machine Learning (ML) can be used to track the disease and predict the growth of the epidemic. Several detection models for COVID-19 are developed. Due to the uncertainty and lack of essential data, many existing models have shown low accuracy in detection. In several technology domains, ML models have been used to define and prioritize adverse threat variables. This study proposes an improved model to analyses and detect the amount of COVID-19-affected patients. In this study, we propose a classification model that detect the infected condition through the chest X-ray images. A dataset containing chest x-ray images of normal people, people with pneumonia such as SARS and pneumococcus and other patients with COVID-19 were collected. Histogram of oriented gradients (HOG) is used for image features extraction. The images are then classified using Support Vector Machines (SVM), random forests and K-nearest neighbors (KNN). These results may contribute well in detecting COVID-19 disease. © 2022 Author(s).

Covid-19 Classification Using HOG-SVM and Deep Learning Models

COVID-19 is measured as the biggest hazardous and fast infectious grief for the human body which has a severe impact on lives, health, and the community all over the world. It is still spreading throughout the world with different variants which is silently killing many lives globally. Thus, earlier diagnosis and accurate detection of COVID-19 cases are essential to protect global lives. Diagnosis COVID-19 through chest X-ray images is one of the best solutions to detect the virus in the infected person properly and quickly at a low cost. Encouraged by the existing research, in this paper, we proposed a hybrid model to classify the Covid cases and non-Covid cases with chest X-ray images based on feature extraction, machine learning and deep learning techniques. Two feature extractors, Histogram Oriented Gradient (HOG) and CNN (MobileNetV2, Sequential, ResNet152V2) are used to train the model. For the classification, we utilized two approaches: Support Vector Machine (SVM) for machine learning and CNN (MobileNetV2, Sequential, ResNet152V2) classifiers for deep learning. The experimental result analysis shows that the Sequential model and the ResNet152V2 model achieve 100% and 82.6% accuracy respectively which is satisfactory. On the other hand, the HOG-SVM method successfully detects all the test images correctly which provides the best result with 100% accuracy, specificity, and responsiveness over a limited public dataset. © 2022 IEEE.

56th Congress of Veterinary Epidemiology

This proceedings contains 10 papers on risk management policy of the ministry of health, labour and welfare for ensuring safe wild game meat, prospective of application of food safety risk assessment for game meat, coronavirus disease (COVID-19) for animal owners, shelter medicine and COVID-19, the characteristics of bats as natural reservoirs of the novel coronavirus, chalkbrood in honey bees and its control measures, the economic impact of classical swine fever in Japan, benzalkonium chloride resistance in Listeria monocytogenes isolated in Japan, COVID-19 outbreak and epidemiological research in Japan and the amendment of the act on domestic animal infectious diseases control.

Effects of Preprocessing in Person Identification Using Ear Features

Currently, face masking is strongly recommended for people when being outside in order to prevent the COVID-19 spread. However, by doing so, the face area is significantly blocked by the mask, resulting in an ineffective accuracy for face recognition system. To be able to identify a person while wearing a face mask, an alternative system has to be considered. There have been several studies in ear recognition system in which an impressive accuracy is obtained. In this work, ear recognition system with the AMI ear database is studied.The feature in terms of histogram of oriented gradients (HOG) is used, and the support vector machine (SVM) is adopted for classification process. To increase the recognition accuracy, ear images are preprocessed by adjusting the sharpness level. It is found that using the concatenated HOG features from the sharpened RGB and HSV images, a promising average recognition accuracy of 86% and the standard deviation of 2.91% are obtained. © 2021 IEEE.