Emotion Analysis Model using Image Processing and Transfer Learning

The rising machine learning (ML) models have become the preferred way for landslide detection based on remote sensing images, but the performance of these models in a sample-free area are rarely concerned in many studies. In this study, we used a cross-validation method (training model in one area and validation in another) to compare the model portability of trained ML models applied in an “off-site” area, as a consideration of the landslide detection ability of these models in sample-free areas. We integrate nighttime light imagery, multi-seasonal optical Landsat time-series and digital elevation data, and we employed support vector machines (SVM), artificial neural networks (ANN) and random forest (RF) models to classify the satellite imagery and identify landslides. Samples of two scenarios generated from two subareas of the Jiuzhaigou disaster-stricken region are used for the cross-application and accuracy evaluation of three ML models. The results revealed that when the trained models are applied in areas outside those in which they were developed, the landslide identification accuracy of these three models has declined. Especially for the SVM and ANN models, the accuracy is greatly reduced and there appears a seriously imbalanced user’s and producer’s accuracy. However, although the performance of the RF model is lower than that of SVM and ANN models in their local area, the RF model exhibits stable portability, and retains the original performance and achieves a satisfactory balance between overestimation and underestimation in “off-site” areas. An additional validation from a new area proved that the landslide detection performance of the RF model with stable portability is higher than that of the SVM and ANN models in “off-site” areas. The results suggest that evaluating the model portability through cross-application can be a useful way to determine the most suitable model for landslide detection in “off-site” areas with a similar geographic environment to model development areas, so as to maximize the accuracy of landslide detection based on limited samples.

This paper analyzes the optimization features of machine learning (ML) model training procedures using multi-GPU systems to enhance cyber security in telecommunication networks. A key aspect of the study is the use of data parallelism, which allows the distribution of the training load across multiple GPUs, significantly reducing training time and improving model accuracy-critical factors for rapid threat detection in cyberspace. A novel approach for optimizing data batch size using Mutual Information (MI) is proposed, which harmonizes the utilization of computational resources with the information content of the training data. MI helps to determine the optimal data batch size that minimizes training errors and improves model accuracy without a significant increase in training time. Experimental results demonstrate the substantial advantages of multi-GPU configurations compared to single-GPU setups, providing faster training and improved model accuracy. It was particularly emphasized that MI-guided batch size tuning significantly outperforms traditional manual tuning methods, ensuring higher validation accuracy and reducing training time. The study showed that the MI-based approach is an effective tool for addressing the problem of optimizing ML model training processes in real-world scenarios where cyber security is critical. The proposed methods allow ML models to train faster and more accurately identify potential threats, making them particularly relevant for telecommunication networks where a rapid response to new threats in real time is required. The implementation of modern computational technologies such as multi-GPU systems and MI-optimized training enhances the efficiency and accuracy of machine learning models. This, in turn, improves cyber security measures and ensures a more reliable defence of telecommunication networks against malicious attacks. It is noted that the proposed approaches can be adapted not only for cyber security but also for other areas where high model accuracy and fast training are important. Future research prospects include the development of new machine learning methods, particularly deep neural networks, the exploration of alternative computational architectures such as quantum computing or distributed systems, and their integration into real-time systems. Special attention should be paid to the ethical aspects of implementing automated cyber security systems, particularly in preventing bias in algorithms and ensuring fairness in their application.

With the establishment of machine learning (ML) techniques in the scientific community, the construction of ML potential energy surfaces (ML-PES) has become a standard process in physics and chemistry. So far, improvements in the construction of ML-PES models have been conducted independently, creating an initial hurdle for new users to overcome and complicating the reproducibility of results. Aiming to reduce the bar for the extensive use of ML-PES, we introduce Asparagus, a software package encompassing the different parts into one coherent implementation that allows an autonomous, user-guided construction of ML-PES models. Asparagus combines capabilities of initial data sampling with interfaces to ab initio calculation programs, ML model training, as well as model evaluation and its application within other codes such as ASE or CHARMM. The functionalities of the code are illustrated in different examples, including the dynamics of small molecules, the representation of reactive potentials in organometallic compounds, and atom diffusion on periodic surface structures. The modular framework of Asparagus is designed to allow simple implementations of further ML-related methods and models to provide constant user-friendly access to state-of-the-art ML techniques. Program summaryProgram Title:AsparagusCPC Library link to program files:https://doi.org/10.17632/9w9xw7mp2h.1Developer's repository link:https://github.com/MMunibas/AsparagusLicensing provisions: MITProgramming language: PythonSupplementary material: Access to Documentation at https://asparagus-bundle.readthedocs.ioNature of problem: Constructing machine-learning (ML) based potential energy surfaces (PESs) for atomistic simulations is a multi-step process that requires a broad knowledge in quantum chemistry, nuclear dynamics and programming. So far, efforts mainly focused on developing and improving ML model architectures. However, there was less effort spent on providing tools for consistent and reproducible workflows that support the construction of ML-PES for a variety of chemical systems for the broader science community.Solution method:Asparagus is a program package written in Python that provides a streamlined and extensible workflow with a user-friendly command structure to support the construction of ML-PESs. This is achieved by bundling and linking data generation and sampling techniques, data management, model training, testing and evaluation tools into one modular, comprehensive workflow including interfaces to other simulation packages for the application of the ML-PESs. By lowering the entrance barriers especially for new users, Asparagus supports the generation and adjustment of ML-PESs that allow an increased focus on the physico-chemical evaluation of the chemical system or application in molecular dynamics simulations.Additional comments including restrictions and unusual features:Asparagus is a modular package written in Python providing an underlying structure for further extensions and maintenance. Currently, methods based on message-passing neural network (NN) models using the PyTorch Python package are available. Additions of new models and interfaces to already implemented modules are possible. The NN architecture and hyperparameters are stored in a global configuration module and as a json file for documentation. Except for essential input information, default input parameters are used if not specifically defined otherwise, which allows a quick setup for the construction of a ML-PES but also the fine-tuning for specific needs.

This study aimed to develop and validate predictive models using electronic health records (EHR) data to determine whether hospitalized COVID-19-positive patients would be admitted to alternative medical care or discharged home. We conducted a retrospective cohort study using deidentified data from the University of Florida Health Integrated Data Repository. The study included 1,578 adult patients (≥18 years) who tested positive for COVID-19 while hospitalized, comprising 960 (60.8%) female patients with a mean (SD) age of 51.86 (18.49) years and 618 (39.2%) male patients with a mean (SD) age of 54.35 (18.48) years. Machine learning (ML) model training involved cross-validation to assess their performance in predicting patient disposition. We developed and validated six supervised ML-based prediction models (logistic regression, Gaussian Naïve Bayes, k-nearest neighbors, decision trees, random forest, and support vector machine classifier) to predict patient discharge status. The models were evaluated based on the area under the receiver operating characteristic curve (ROC-AUC), precision, accuracy, F1 score, and Brier score. The random forest classifier exhibited the highest performance, achieving an accuracy of 0.84 and an AUC of 0.72. Logistic regression (accuracy: 0.85, AUC: 0.71), k-nearest neighbor (accuracy: 0.84, AUC: 0.63), decision tree (accuracy: 0.84, AUC: 0.61), Gaussian Naïve Bayes (accuracy: 0.84, AUC: 0.66), and support vector machine classifier (accuracy: 0.84, AUC: 0.67) also demonstrated valuable predictive capabilities. This study's findings are crucial for efficiently allocating healthcare resources during pandemics like COVID-19. By harnessing ML techniques and EHR data, we can create predictive tools to identify patients at greater risk of severe symptoms based on their medical histories. The models developed here serve as a foundation for expanding the toolkit available to healthcare professionals and organizations. Additionally, explainable ML methods, such as Shapley Additive Explanations, aid in uncovering underlying data features that inform healthcare decision-making processes.

Tomato cultivation is increasingly widespread, yet it faces significant challenges, particularly from plant diseases caused by fungi, bacteria, and insects. Addressing these diseases is crucial for ensuring the quality and yield of tomato crops. To support specialists in accurately identifying and managing these diseases, we propose an advanced automatic system for detecting and identifying tomato leaf diseases using sophisticated image processing techniques. Therefore, we proposed an approach that employs robust feature extraction methods, including the gray level co‐occurrence matrix (GLCM) and scale‐invariant feature transform (SIFT), coupled with a support vector machine (SVM) for adequate classification. We curated an extensive dataset of 2700 tomato leaf images, with a minimum of 300 images for each of the nine distinct disease classes. This comprehensive dataset facilitated the training and testing of various machine learning and deep learning models. The experimental results highlight our proposed approach’s exceptional accuracy and reliability, significantly improving the detection and classification of tomato leaf diseases. A thorough comparative analysis with contemporary state‐of‐the‐art techniques further validates the superiority of our system. Our findings suggest that this framework can significantly benefit tomato cultivation by enabling timely and precise disease management. Future research can explore integrating advanced deep learning algorithms to enhance the system’s accuracy in this multiclass classification challenge.

Oesophagectomy is an operation with a high risk of postoperative complications. The aim of this single-centre retrospective study was to apply machine-learning methods to predict complications (Clavien-Dindo grade IIIa or higher) and specific adverse events. Patients with resectable adenocarcinoma or squamous cell carcinoma of the oesophagus and gastro-oesophageal junction who underwent Ivor Lewis oesophagectomy between 2016 and 2021 were included. The tested algorithms were logistic regression after recursive feature elimination, random forest, k-nearest neighbour, support vector machine, and neural network. The algorithms were also compared with a current risk score (the Cologne risk score). 457 patients had Clavien-Dindo grade IIIa or higher complications (52.9 per cent) versus 407 patients with Clavien-Dindo grade 0, I, or II complications (47.1 per cent). After 3-fold imputation and 3-fold cross-validation, the overall accuracies were: logistic regression after recursive feature elimination, 0.528; random forest, 0.535; k-nearest neighbour, 0.491; support vector machine, 0.511; neural network, 0.688; and Cologne risk score, 0.510. For medical complications, the results were: logistic regression after recursive feature elimination, 0.688; random forest, 0.664; k-nearest neighbour, 0.673; support vector machine, 0.681; neural network, 0.692; and Cologne risk score, 0.650. For surgical complications, the results were: logistic regression after recursive feature elimination, 0.621; random forest, 0.617; k-nearest neighbour, 0.620; support vector machine, 0.634; neural network, 0.667; and Cologne risk score, 0.624. The calculated area under the curve of the neural network was 0.672 for Clavien-Dindo grade IIIa or higher, 0.695 for medical complications, and 0.653 for surgical complications. The neural network scored the highest accuracies compared with all of the other models for the prediction of postoperative complications after oesophagectomy.

The study develops a data-driven based model to predict biological oxygen demand of the treated wastewater from an institutional wastewater treatment plant. First, the data was collected for six parameters (i.e. pH, conductivity, temperature, total suspended solids, total organic carbon and biological oxygen demand) from the selected wastewater treatment plant by collecting and analysing samples over a period of more than two months. The quality parameters were then combined in seven different scenarios for training of machine learning models. These scenarios were tested using four machine learning models, i.e. multiple linear regression, artificial neural network, support vector machine and random forest. Finally, these models were compared to select the best model for prediction of biological oxygen demand using a set of indicators, i.e. coefficient of determination and root mean square error.

The fast and accurate design of terahertz devices for specific applications remains challenging, especially for tailoring metadevices, owing to the complex electromagnetic characteristics of these devices and their large structural parameter space. The unique functionalities achieved by metadevices come at the cost of structural complexity, resulting in a time-consuming parameter sweep for conventional metadevice design. Here, we propose a general solution to achieve efficient inverse design for a terahertz metagrating via machine learning. Metagratings with different structural parameters were selected as illustrations to verify the effectiveness of this method. As proof-of-principle examples, the metagratings predicted via the inverse design model are numerically calculated and experimentally demonstrated. Initially, the physical modeling of a metagrating is performed via the finite element method (FEM). A spectrum dataset obtained from FEM simulation is prepared for the training of machine learning models. Then, trained machine learning models, including the Elman neural network (Elman), support vector machine (SVM), and general regression neutral network (GRNN), are used to predict probable structural parameters. The results of these models are compared and analyzed comprehensively, which verifies the effectiveness of the inverse design method. Compared with conventional methods, the inverse design method is much faster and can encompass a high degree of freedom to generate metadevice structures, which can ensure that the spectra of generated structures resemble the desired ones and can provide accurate data support for metadevice modeling. Furthermore, a metagrating tailored by an inverse design is used as a biological sensor to distinguish different microorganisms. The proposed data-driven inverse design method realizes fast and accurate design of the metagrating, which is expected to have great potential in metadevice design and tailoring for specific applications.

With the advances in machine learning techniques and the potency of cloud computing there is an increasing adoption of third party cloud services for outsourcing training and prediction of machine learning models. Although the usage of cloud hosted machine learning services enables more efficient storage and computation on data, the privacy concerns and issues surrounding data sovereignty remain an important challenge. Privacy preserving machine learning provides a promising solution. In this paper, a privacy preserving neural network generation and utilisation framework is presented, the PPNNBP framework. PPNNBP allows model training and prediction to be securely delegated to a third party with minimal data owner participation once the input data have been encrypted without recourse to secret sharing or multiple party setting. This is achieved using a proposed fully homomorphic encryption scheme, the Modified Liu Scheme (MLS), that permits certain operations over cyphertexts and features order preservation. The PPNNBP framework using MLS addresses the challenge of the computational complexity of model learning using existing schemes; a complexity caused by the increasing size of cyphertexts (cyphertexts inflation) and the quantity of noise introduced into cyphertexts through the application of multiplication operations, as the learning progresses. Both the PPNNBP framework and MLS are fully described and analysed. The reported evaluation demonstrates that the PPNNBP framework achieves an accuracy that is comparable to that obtained using a “standard” framework, whilst at the same time operating in a secure manner with minimal data owner participation.

In this paper, machine learning models for an effective estimation of soil moisture content using a microwave short-range and wideband radar sensor are proposed. The soil moisture is measured as the volumetric water content using a short-range off-the-shelf radar sensor operating at 3–10 GHz. The radar captures the reflected signals that are post processed to determine the soil moisture which is mapped to the input features extracted from the reflected signals for the training of the machine learning models. In addition, the results are compared and analyzed with a contact-based Vernier soil sensor. Different machine learning models trained using neural network, support vector machine, linear regression and k-nearest neighbor are evaluated and presented in this work. The efficiency of the model is computed using root mean square error, co-efficient of determination and mean absolute error. The RMSE and MAE values of KNN, SVM and Linear Regression are 11.51 and 9.27, 15.20 and 12.74, 3.94 and 3.54, respectively. It is observed that the neural network gives the best results with an R2 value of 0.9894. This research work has been carried out with an intention to develop cost-effective solutions for common users such as agriculturists to monitor the soil moisture conditions with improved accuracy.

Machine Learning (ML) techniques are pervasive tools in various emerging commercial applications, but have to be accommodated by powerful computer systems to process very large data. Although general-purpose CPUs and GPUs have provided straightforward solutions, their energy-efficiencies are limited due to their excessive supports for flexibility. Hardware accelerators may achieve better energy-efficiencies, but each accelerator often accommodates only a single ML technique (family). According to the famous No-Free-Lunch theorem in the ML domain, however, an ML technique performs well on a dataset may perform poorly on another dataset, which implies that such accelerator may sometimes lead to poor learning accuracy. Even if regardless of the learning accuracy, such accelerator can still become inapplicable simply because the concrete ML task is altered, or the user chooses another ML technique.In this study, we present an ML accelerator called PuDianNao, which accommodates seven representative ML techniques, including k-means, k-nearest neighbors, naive bayes, support vector machine, linear regression, classification tree, and deep neural network. Benefited from our thorough analysis on computational primitives and locality properties of different ML techniques, PuDianNao can perform up to 1056 GOP/s (e.g., additions and multiplications) in an area of 3.51 mm^2, and consumes 596 mW only. Compared with the NVIDIA K20M GPU (28nm process), PuDianNao (65nm process) is 1.20x faster, and can reduce the energy by 128.41x.

In this age of digital microscopy, image processing, statistical analysis, categorization, and systems for decision-making have become essential tools for medical diagnostics research. By visualizing and analyzing images, clinicians can identify anomalies in intracellular structure. Leukemia is a cancerous condition marked by an unregulated increase in aberrant white blood cells (WBCs). Recognizing acute leukemia tumor cells in blood smear images (BSI) is a challenging assignment. Image segmentation is regarded as the most significant step in the automated identification of this disease. The innovative concavity-based segmentation algorithm is employed in this study to segment WBC in sub-images from the ALLIDB2 database. The concave endpoints and elliptical features are used in the segmentation step of convex-shaped cell images. The procedure involves the extraction of contour evidence, which detects the visible section of each object, and contour estimation, which corresponds to the final object’s contours. Following the identification of the cells and their internal structure by concavity-based segmentation, the cells are categorized based on their morphological and statistical features. The method was evaluated using a public dataset meant to test classification and segmentation approaches. The statistical tool SPSS is used to independently check the significance of derived features. For classification, significant features are passed into machine learning techniques such as support vector machines (SVM), k-nearest neighbor (KNN), neural networks (NN), decision trees (DT), and Nave Bayes (NB). With an AUC of 98.9% and a total accuracy of 95%, the neural network model performed better. We advocate using the neural network model to identify acute leukemia cells based on its accuracy.

Bond rating is regarded as an important event for measuring financial risk of companies and for determining the investment returns of investors. As a result, it has been a popular research topic for researchers to predict companies' credit ratings by applying statistical and machine learning techniques. The statistical techniques, including multiple regression, multiple discriminant analysis (MDA), logistic models (LOGIT), and probit analysis, have been traditionally used in bond rating. However, one major drawback is that it should be based on strict assumptions. Such strict assumptions include linearity, normality, independence among predictor variables and pre-existing functional forms relating the criterion variablesand the predictor variables. Those strict assumptions of traditional statistics have limited their application to the real world. Machine learning techniques also used in bond rating prediction models include decision trees (DT), neural networks (NN), and Support Vector Machine (SVM). Especially, SVM is recognized as a new and promising classification and regression analysis method. SVM learns a separating hyperplane that can maximize the margin between two categories. SVM is simple enough to be analyzed mathematical, and leads to high performance in practical applications. SVM implements the structuralrisk minimization principle and searches to minimize an upper bound of the generalization error. In addition, the solution of SVM may be a global optimum and thus, overfitting is unlikely to occur with SVM. In addition, SVM does not require too many data sample for training since it builds prediction models by only using some representative sample near the boundaries called support vectors. A number of experimental researches have indicated that SVM has been successfully applied in a variety of pattern recognition fields. However, there are three major drawbacks that can be potential causes for degrading SVM's performance. First, SVM is originally proposed for solving binary-class classification problems. Methods for combining SVMs for multi-class classification such as One-Against-One, One-Against-All have been proposed, but they do not improve the performance in multi-class classification problem as much as SVM for binary-class classification. Second, approximation algorithms (e.g. decomposition methods, sequential minimal optimization algorithm) could be used for effective multi-class computation to reduce computation time, but it could deteriorate classification performance. Third, the difficulty in multi-class prediction problems is in data imbalance problem that can occur when the number of instances in one class greatly outnumbers the number of instances in the other class. Such data sets often cause a default classifier to be built due to skewed boundary and thus the reduction in the classification accuracy of such a classifier. SVM ensemble learning is one of machine learning methods to cope with the above drawbacks. Ensemble learning is a method for improving the performance of classification and prediction algorithms. AdaBoost is one of the widely used ensemble learning techniques. It constructs a composite classifier by sequentially training classifiers while increasing weight on the misclassified observations through iterations. The observations that are incorrectly predicted by previous classifiers are chosen more often than examples that are correctly predicted. Thus Boosting attempts to produce new classifiers that are better able to predict examples for which the current ensemble's performance is poor. In this way, it can reinforce the training of the misclassified observations of the minority class. This paper proposes a multiclass Geometric Mean-based Boosting (MGM-Boost) to resolve multiclass prediction problem. Since MGM-Boost introduces the notion of geometric mean into AdaBoost, it can perform learning process considering the geometric mean-based accuracy and errors of multiclass. This study applies MGM-Boost to the real-world bond rating case for Korean companies to examine the feasibility of MGM-Boost. 10-fold cross validations for threetimes with different random seeds are performed in order to ensure that the comparison among three different classifiers does not happen by chance. For each of 10-fold cross validation, the entire data set is first partitioned into tenequal-sized sets, and then each set is in turn used as the test set while the classifier trains on the other nine sets. That is, cross-validated folds have been tested independently of each algorithm. Through these steps, we have obtained the results for classifiers on each of the 30 experiments. In the comparison of arithmetic mean-based prediction accuracy between individual classifiers, MGM-Boost (52.95%) shows higher prediction accuracy than both AdaBoost (51.69%) and SVM (49.47%). MGM-Boost (28.12%) also shows the higher prediction accuracy than AdaBoost (24.65%) and SVM (15.42%)in terms of geometric mean-based prediction accuracy. T-test is used to examine whether the performance of each classifiers for 30 folds is significantly different. The results indicate that performance of MGM-Boost is significantly different from AdaBoost and SVM classifiers at 1% level. These results mean that MGM-Boost can provide robust and stable solutions to multi-classproblems such as bond rating.

Forecasting demand for assets and services can be addressed in various markets, providing a competitive advantage when the predictive models used demonstrate high accuracy. However, the training of machine learning models incurs high computational costs, which may limit the training of prediction models based on available computational capacity. In this context, this paper presents an approach for training demand prediction models using quantum neural networks. For this purpose, a quantum neural network was used to forecast demand for vehicle financing. A classical recurrent neural network was used to compare the results, and they show a similar predictive capacity between the classical and quantum models, with the advantage of using a lower number of training parameters and also converging in fewer steps. Utilizing quantum computing techniques offers a promising solution to overcome the limitations of traditional machine learning approaches in training predictive models for complex market dynamics.

The prediction of autism features in relation to age groups has not been definitively addressed, despite the fact that several studies have been conducted using various methodologies. Research in the field of neuroscience has demonstrated that intracranial brain volume and the corpus callosum provide crucial information for the identification of autism spectrum disorder (ASD). Based on these findings, we present Decision Tree-based Autism Prediction System (DT-APS) and Random Forest-based Autism Prediction System (RF-APS) for automatic ASD identification in this paper. These systems utilize characteristics extracted from the corpus callosum and intracranial brain volume, and are based on machine learning techniques. By prioritizing characteristics with the highest discriminatory power for ASD classification, our proposed approaches, DT-APS and RF-APS, have not only enhanced identification accuracy but also simplified the training of machine learning models. The initial step of this method involves dividing each MRI scan into distinct anatomical areas. These areas are adjacent slices in a single 2D image. Each 2D image is mapped to the curvelet space, and the set of GGD parameters characterizes each of the distinct curvelet sub-bands. The AQ-10 dataset was utilized to evaluate the proposed model. When tested on both types of datasets, the suggested prediction model demonstrated superior performance compared to alternative approaches in all relevant metrics, including accuracy, specificity, sensitivity, precision, and false positive rate (FPR).