Non-Contact Spirometry Using a Mobile Thermal Camera and AI Regression.

Infrared imaging theory is an important theoretical basis for the design of infrared imaging systems, but there is no research on infrared imaging theory for designing thermal microscope imaging systems. Therefore, we studied the performance evaluation and optimization theory of thermal microscope imaging systems. In this paper, we analyzed the difference in spectral radiant flux between thermal microscope imaging and telephoto thermal imaging. The expression of signal-to-noise ratio of the output image of the thermal microscope imaging systems was derived, based on the analysis of the characteristics of thermal microscope imaging. We studied the performance evaluation model of thermal microscope imaging systems based on the minimum resolvable temperature difference and the minimum detectable temperature difference. Simulation and analysis of different detectors (ideal photon detector and ideal thermal detector) were also carried out. Finally, based on the conclusion of theoretical research, we carried out a system design and image acquisition experiment. The results show that the theoretical study of thermal microscope imaging systems in this paper can provide reference for the performance evaluation and optimization of thermal microscope imaging systems.

Design and realization of high resolution optical micro-scanning thermal microscope imaging system

<abstract><p>In the realm of machine learning, where data-driven insights guide decision-making, addressing the challenges posed by class imbalance in datasets has emerged as a crucial concern. The effectiveness of classification algorithms hinges not only on their intrinsic capabilities but also on their adaptability to uneven class distributions, a common issue encountered across diverse domains. This study delves into the intricate interplay between varying class imbalance levels and the performance of ten distinct classification models, unravelling the critical impact of this imbalance on the landscape of predictive analytics. Results showed that random forest (RF) and decision tree (DT) models outperformed others, exhibiting robustness to class imbalance. Logistic regression (LR), stochastic gradient descent classifier (SGDC) and naïve Bayes (NB) models struggled with imbalanced datasets. Adaptive boosting (ADA), gradient boosting (GB), extreme gradient boosting (XGB), light gradient boosting machine (LGBM), and k-nearest neighbour (kNN) models improved with balanced data. Adaptive synthetic sampling (ADASYN) yielded more reliable predictions than the under-sampling (UNDER) technique. This study provides insights for practitioners and researchers dealing with imbalanced datasets, guiding model selection and data balancing techniques. RF and DT models demonstrate superior performance, while LR, SGDC and NB models have limitations. By leveraging the strengths of RF and DT models and addressing class imbalance, classification performance in imbalanced datasets can be enhanced. This study enriches credit risk modelling literature by revealing how class imbalance impacts default probability estimation. The research deepens our understanding of class imbalance's critical role in predictive analytics. Serving as a roadmap for practitioners and researchers dealing with imbalanced data, the findings guide model selection and data balancing strategies, enhancing classification performance despite class imbalance.</p></abstract>

With the emergence of the massive educational data, education data mining techniques have extensively drawn considerable interest from scholars to explore the relationship between students’ achievements and other factors. In this study, the data set about the students’ achievements of Portuguese in two secondary education schools in Portugal is selected for education data mining, which involves the personal information, social and school related factors. To analyze the relationship between the students' achievements and other factors, this study proposed an ensemble model based on weighted voting for predicting the students’ achievements of Portuguese in the final period. First, the raw data is preprocessed using some basic methods, including dummy coding, correlation analysis, standardization, and normalization. Second, the isolation forest algorithm-based outlier adaption is applied to deal with the data set to enhance the robustness of the ensemble model. Finally, two base classifiers, i.e. gradient boosting decision tree and extreme gradient boosting, are integrated to form the ensemble model. The experiments are presented for verifying the superiority of the proposed model by comparing with five base classifiers, including gradient boosting decision tree, adaptive boosting, extreme gradient boosting, random forest, and decision tree. The experimental results demonstrate that the ensemble model performs better than other base classifiers in classification, and prove the validity of the outlier adaption based on isolation forest algorithm.

Lung cancer is one of the three deadliest diseases in the world and has rapidly developed. Based on this, researchers conducted research to predict the factors that influence lung cancer. One method to identify this is using data mining methods and classification techniques. Researchers used several popular algorithms in classification to make comparisons of the most accurate algorithms for lung cancer classification. The algorithms used include K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. The researcher used this algorithm because, in the research that the researcher found on the Kaggle platform, he examined the comparison of the algorithm using the breast cancer dataset. In previous studies, their researchers used SVM, which obtained an accuracy of 96.47%, Neural Networks of 97.06%, and Naïve Bayes with an accuracy of 91.18% to study breast cancer. The difference from previous research is that this study uses several existing algorithms in Machine Learning such as K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. In addition, this research was conducted to see whether the results of the accuracy of the algorithm that the researchers carried out using the lung cancer dataset had different results. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood.

Oil and gas pipelines require systematic supervision and control in order to ensure their safe exploitation, even more so during spring/autumn/summer thawing, freezing and flooding seasons when soil deformation is at its highest. In the article, several ways of Earth’s surface space monitoring are considered. It’s pointed out that infrared sounding appears to be the most promising method of space monitoring the condition of main and production pipelines. It’s due to infrared sounding’s unique capability to detect pipeline’s construction flaws and breaches. However, thermal imaging systems are still in need of significant development, due to high noise and low image contrast levels. As of present time, there are no universally applicable filters, capable of detecting and suppressing all types and levels of noise. Further development in this sphere requires broadening of the arsenal of algorithmic processing facilities, which remains insufficient. The quality of thermal imaging depends on temperature distribution on the surface of the examined object as well as characteristics and parameters of thermal imaging systems themselves. The variety of parameters in photosensitive elements of photodetective device’s matrix leads to the appearance of so-called geometric noises in thermal imaging devices. Correction of geometrical noises in thermal imaging systems is one of the key problems. The approach to the solution of this problem is considered in the article.

The thermal camera systems can be used in all kinds of applications that require the detection of heat change, but thermal imaging systems are highly costly systems. In recent years, developments in the field of deep learning have increased the success by obtaining quality results compared to traditional methods. In this paper, thermal images of neonates (healthy - unhealthy) obtained from a high-resolution thermal camera were used and these images were evaluated as high resolution (ground truth) images. Later, these thermal images were downscaled at 1/2, 1/4, 1/8 ratios, and three different datasets consisting of low-resolution images in different sizes were obtained. In this way, super-resolution applications have been carried out on the deep network model developed based on generative adversarial networks (GAN) by using three different datasets. The successful performance of the results was evaluated with PSNR (peak signal to noise ratio) and SSIM (structural similarity index measure). In addition, healthy - unhealthy classification application was carried out by means of a classifier network developed based on convolutional neural networks (CNN) to evaluate the super-resolution images obtained using different datasets. The obtained results show the importance of combining medical thermal imaging with super-resolution methods.

Thermal imaging systems can perform many functions in marine service. They can be used for navigation, surveillance, search and rescue, safety inspection, and communications. The range, sensitivity, resolution, and response time of different thermal imaging systems vary sufficiently to accommodate the operational requirements and pocketbooks of most potential users. The theory of operation, design approaches, materials of construction, and performance levels for different thermal imaging systems are discussed and salient features shown. Typical areas of application in marine service for the thermal imaging systems will be looked at and cost-effective solutions suggested.

Fault detection and classification of an electrical equipment is a significant subject concerning the continuity of efficient working and necessary tasks. The heat concept creates a stimulating effect in case of failure among the electrical equipment. For this reason, thermal camera images can be functional and are used to detect the malfunctions. In this paper, thermal camera images are utilized to detect 11 different conditions of induction motors that are 8 different short-circuit faults of stator windings, rotor failure, cooling fan failure, and no-load. First-order statistics (FOS) are considered to obtain the discriminative information among the thermal images. The classification unit of model is specified examining five efficient algorithms that are neural networks (NN), k-nearest neighbors (k-NN), random forest (RF), logistic regression (LR), and support vector machines (SVM). In the experiments, 10-fold cross validation is chosen as the test method, and four metrics (accuracy, specificity, sensitivity, AUC) are considered to evaluate the performance. Consequently, the best accuracy of 97.29% is observed by k-NN and RF techniques. In a detailed examination, it is revealed that the most qualified technique rises as RF for the proposed model by considering the accuracy and AUC rates.

Streamflow forecasting is crucial for planning, designing, and managing water resources. Accurate streamflow forecasting is essential in developing water resource systems that are both technically and economically efficient. This study tested several machine learning techniques to estimate monthly streamflow data in the Hunza River Basin, Pakistan, using streamflow, precipitation, and air temperature data between 1985 and 2013. The techniques tested included adaptive boosting (AB), gradient boosting (GB), random forest (RF), and K-nearest neighbors (KNN). The models were developed using river discharge as the target variable, while air temperature and precipitation as the input variables. The model's performance was assessed via four statistical performance indicators namely root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R2). The results obtained for RMSE, MSE, MAE, and R2 using AB, GB, RF, and KNN techniques are (16.8, 281, 6.53, and 0.998), (95.1, 9,047, 61.5, and 0.921), (126.8, 16,078, 74.6, and 0.859), and (219.9, 48,356, 146.3, and 0.775), respectively. The results indicate that AB outperforms GB, RF, and KNN in predicting monthly streamflow for the Hunza River Basin. Machine learning, particularly AB, offers a reliable approach for streamflow forecasting, aiding hazard and water management in the area.

Influence of image resolution on the performance of remote breathing rate measurement using thermal imaging technique

With the wide application of unmanned aerial vehicles (UAVs), UAV thermal imaging technology has been brought to the attention of numerous experts and scholars. At present, the application of UAV thermal imaging technology is limited by the problem of low resolution of the images captured by the thermal imaging system itself. In order to solve this problem, this paper proposes a UAV thermal image super-resolution reconstruction method based on bimodal image feature fusion, which improves the UAV thermal image super-resolution characterization capability by making use of the feature information provided by the UAV visible image to compensate for the lack of texture and edge information perception in thermal images. The proposed methodology consists of two tasks: The first task involves a bimodal image feature fusion network that extracts texture and edge information from visible images. This addresses the lack of detailed feature information in thermal images with a differential complementary modal feature fusion module, ultimately producing a fused image with high-quality feature information. The second task entails the integration of a gated multilevel feature fusion module into the UAV thermal image reconstruction network as an attention mechanism, thereby improving the use of fused image feature information for generating high-resolution UAV thermal images. Finally, a joint adaptive training strategy is utilized to further enhance the super-resolution effect of UAV thermal images. The experimental results show that the proposed method can effectively extract the visible image information to compensate for the characterization information in the UAV thermal image super-resolution, and achieves the optimal values of 31.53 dB and 0.9116 in PSNR and SSIM metrics, respectively, providing a new solution for the thermal image super-resolution of UAVs.

Postpartum depression (PPD) presents a significant mental health challenge for mothers following childbirth. While the precise cause of this condition remains unknown, preventive measures and treatments are available. This study aims to employ ensemble learning techniques, utilizing C4.5 decision tree (DT), gradient boosting tree (GBT), and extreme gradient boosting (XGBoost), to predict the occurrences of PPD in the Banjarmasin, South Kalimantan, Indonesia. The predictive model developed encompasses a dataset comprising 317 records gathered from postpartum mothers in hospitals, community health services, and midwifery clinics (referred to as Model 1). Furthermore, resampling techniques (Model 2) were employed to address class imbalance. Additionally, feature selection including forward selection and backward elimination (Model 3) were implemented to enhance model performance. The findings reveal that XGBoost, combined with resampling methods, achieved the highest accuracy rate at 87.57%. Feature selection identified five crucial factors associated with PPD incidence: marital status, number of living children, history of depression, fear of delivery, and family relationships. The utilization of ensemble learning strategies for PPD prediction yields reliable outcomes that can be applied within clinical settings. Exploring alternative ensemble learning strategies such as random forest and adaptive boosting could further optimize model performance and warrant consideration in future research endeavours.

Development of a low-cost thermal imaging system for water stress monitoring in indoor farming

To provide theoretical support for study of locust phototactic vision nature, the locust phototactic physiology and visual spectrum effects were investigated by stimulating the visual system using light from an AvaSpec fiber-optic spectrometer and Flir thermal imaging system. When light stimulated the locust visual system, the biological photoelectric transformation effect of the visual system caused by photon energy, presented with the higher physiological temperature on the forehead, as tested by the Flir thermal system. After stimulation with light, the different absorption degrees of the vision system on the spectral photons, as tested by the AvaSpec spectrometer, showed that the phototactic response to light had the simultaneous requirements of lighting intensity and time. The absorbing differences of spectral photons by the vision system demonstrated the absorption selectivity under light stimulation, as exhibited by the sensitive absorption of spectral energy at 430 nm, 545 nm and 615 nm. Moreover, the higher forehead temperature increment indicated and induced the stronger physiology activity which was the reason that causing the good phototactic response degree of locusts with 30 min light stimulation, and the adaption time was about 60 min. Therefore, only when the visual reaction effect was stimulated to absorb sensitive spectral energy and generate the physiological exciting response could cause the phototactic behavior. Keywords: Phototactic pest control, physiological response, Locusta migratoria, spectral illumination, phototactic vision, spectrum absorption, light simulation DOI: 10.3965/j.ijabe.20160902.1249 Citation: Liu Q H, Zhou Q. Physiological response of locusts to eye stimulation by spectral illumination for phototactic pest control. Int J Agric & Biol Eng, 2016; 9(2): 186－194.