Deep Learning Methods and Applications

Enhanced framework embedded with data transformation and multi-objective feature selection algorithm for forecasting wind power

The increasing global interest in utilizing wind turbines for power generation emphasizes the importance of accurate wind power forecasting in managing wind power. This paper proposed a framework that integrates a data transformation mechanism with a multi-objective none-dominated sorting genetic algorithm III (NSGA-III), coupled with a hybrid deep Recurrent Network (DRN) and Long Short-Term Memory (LSTM) architecture for modeling wind power. The feature selection algorithm, multi-objective NSGA-III, identifies the optimal subset features from wind energy datasets. These selected features undergo a data transformation process before being input into the hybrid DRN-LSTM for wind power forecasting. A comparative study demonstrates the proposal's superior effectiveness and robustness compared to existing frameworks with the proposal achieving 2.6593e-10 and 1.630e-05 in terms of MSE and RMSE respectively whereas the classical algorithm recorded 8.8814e-07 and 9.424e-04. The study's contributions lie in its approach integration of data transformation mechanism and the notable enhancements in wind power forecasting accuracy. Furthermore, the study offers valuable insights to guide research efforts in the future.

Machine Learning Model Development for Malignant Prostate Lesion Prediction Using Texture Analysis Features from Ultrasound Shear-Wave Elastography

Introduction: Artificial intelligence (AI) is increasingly utilized for texture analysis and the development of machine learning (ML) techniques to enhance diagnostic accuracy. ML algorithms are trained to differentiate between normal and malignant conditions based on provided data. Texture feature analysis, including first-order and second-order features, is a critical step in ML development. This study aimed to evaluate quantitative texture features of normal and prostate cancer tissues identified through ultrasound B-mode and shear-wave elastography (SWE) imaging and to develop and assess ML models for predicting and classifying normal versus malignant prostate tissues. Methodology: First-order and second-order texture features were extracted from B-mode and SWE imaging, including four reconstructed regions of interest (ROIs) from SWE images for normal and malignant tissues. A total of 94 texture features were derived, including features for intensity, Gray-Level Co-Occurrence Matrix (GLCM), Gray-Level Dependence Length Matrix (GLDLM), Gray-Level Run Length Matrix (GLRLM), and Gray-Level Size Zone Matrix (GLSZM). Five ML models were developed and evaluated using 5-fold cross-validation to predict normal and malignant tissues. Results: Data from 62 patients were analyzed. All ROIs, except those derived from B-mode imaging, exhibited statistically significant differences in features between normal and malignant tissues. Among the developed models, Support Vector Machines (SVM), Random Forest (RF), and Naive Bayes (NB) demonstrated the highest performance across all ROIs. These models consistently achieved strong predictive accuracy for classifying normal versus malignant tissues. Gray Pure SWE and Gray Reconstructed images Provided the highest sensitivity and specificity in PCa prediction by 82%, 90%, and 98%, 96%, respectively. Conclusions: Texture analysis with machine learning on SWE-US and reconstructed images effectively differentiates malignant from benign prostate lesions, with features like contrast, entropy, and correlation playing a key role. Random Forest, SVM, and Naïve Bayes showed the highest classification performance, while grayscale reconstructions (GPSWE and GRRI) enhanced detection accuracy.

An ESG-ConvNeXt network for steel surface defect classification based on hybrid attention mechanism

Defect recognition is crucial in steel production and quality control, but performing this detection task accurately presents significant challenges. ConvNeXt, a model based on self-attention mechanism, has shown excellent performance in image classification tasks. To further enhance ConvNeXt's ability to classify defects on steel surfaces, we propose a network architecture called ESG-ConvNeXt. First, in the image processing stage, we introduce a serial multi-attention mechanism approach. This method fully leverages the extracted information and improves image information retention by combining the strengths of each module. Second, we design a parallel multi-scale residual module to adaptively extract diverse discriminative features from the input image, thereby enhancing the model's feature extraction capability. Finally, in the downsampling stage, we incorporate a PReLU activation function to mitigate the problem of neuron death during downsampling. We conducted extensive experiments using the NEU-CLS-64 steel surface defect dataset, and the results demonstrate that our model outperforms other methods in terms of detection performance, achieving an average recognition accuracy of 97.5%. Through ablation experiments, we validated the effectiveness of each module; through visualization experiments, our model exhibited strong classification capability. Additionally, experiments on the X-SDD dataset confirm that the ESG-ConvNeXt network achieves solid classification results. Therefore, the proposed ESG-ConvNeXt network shows great potential in steel surface defect classification.

Advanced Image Analytics for Mobile Robot-Based Condition Monitoring in Hazardous Environments: A Comprehensive Thermal Defect Processing Framework

In hazardous environments like mining sites, mobile inspection robots play a crucial role in condition monitoring (CM) tasks, particularly by collecting various kinds of data, such as images. However, the sheer volume of collected image samples and existing noise pose challenges in processing and visualizing thermal anomalies. Recognizing these challenges, our study addresses the limitations of industrial big data analytics for mobile robot-generated image data. We present a novel, fully integrated approach involving a dimension reduction procedure. This includes a semantic segmentation technique utilizing the pre-trained VGG16 CNN architecture for feature selection, followed by random forest (RF) and extreme gradient boosting (XGBoost) classifiers for the prediction of the pixel class labels. We also explore unsupervised learning using the PCA-K-means method for dimension reduction and classification of unlabeled thermal defects based on anomaly severity. Our comprehensive methodology aims to efficiently handle image-based CM tasks in hazardous environments. To validate its practicality, we applied our approach in a real-world scenario, and the results confirm its robust performance in processing and visualizing thermal data collected by mobile inspection robots. This affirms the effectiveness of our methodology in enhancing the overall performance of CM processes.

Understanding the cultivation mechanism for mental health education of college students in campus culture construction from the perspective of deep learning

Nowadays, there is an increase in attention to the college student's mental health, and to enhance the awareness related to college students' mental health, colleges and universities have executed an immense range of mental health publicity activities. In order to better combine deep learning with classroom teaching, this paper puts forward a deep learning algorithm formulated on convolutional neural networks. The purpose of this research is to investigate the development and use of a cultivation mechanism for mental health education of college students in campus culture creation from the perspective of deep learning. The study's primary goal is to comprehend college students' mental health training in campus culture creation. The study's objective is to develop experimental outcomes of college students utilizing mental health education courses as an optional or mandatory course. Finally, investigations related to college students' mental health from the current situation in China, the investigation, statistics and analysis related to the college students in China are carried out in this situation. The experimental results of this study show that 62 of the 156 schools and universities assessed provide courses on mental health education for college students that are both obligatory and optional. According to the students questionnaire survey, 86.7% of respondents believe that it is critical to establish mental health related educational courses, 61.9% believe that compulsory courses should be established, and students want to add group guidance or activities to the teaching process to improve their experience and participation.

Identifying Severity Grading of Knee Osteoarthritis from X-ray Images Using an Efficient Mixture of Deep Learning and Machine Learning Models

Recently, many diseases have negatively impacted people's lifestyles. Among these, knee osteoarthritis (OA) has been regarded as the primary cause of activity restriction and impairment, particularly in older people. Therefore, quick, accurate, and low-cost computer-based tools for the early prediction of knee OA patients are urgently needed. In this paper, as part of addressing this issue, we developed a new method to efficiently diagnose and classify knee osteoarthritis severity based on the X-ray images to classify knee OA in (i.e., binary and multiclass) in order to study the impact of different class-based, which has not yet been addressed in previous studies. This will provide physicians with a variety of deployment options in the future. Our proposed models are basically divided into two frameworks based on applying pre-trained convolutional neural networks (CNN) for feature extraction as well as fine-tuning the pre-trained CNN using the transfer learning (TL) method. In addition, a traditional machine learning (ML) classifier is used to exploit the enriched feature space to achieve better knee OA classification performance. In the first one, we developed five classes-based models using a proposed pre-trained CNN for feature extraction, principal component analysis (PCA) for dimensionality reduction, and support vector machine (SVM) for classification. While in the second framework, a few changes were made to the steps in the first framework, the concept of TL was used to fine-tune the proposed pre-trained CNN from the first framework to fit the two classes, three classes, and four classes-based models. The proposed models are evaluated on X-ray data, and their performance is compared with the existing state-of-the-art models. It is observed through conducted experimental analysis to demonstrate the efficacy of the proposed approach in improving the classification accuracy in both multiclass and binary class-based in the OA case study. Nonetheless, the empirical results revealed that the fewer multiclass labels used, the better performance achieved, with the binary class labels outperforming all, which reached a 90.8% accuracy rate. Furthermore, the proposed models demonstrated their contribution to early classification in the first stage of the disease to help reduce its progression and improve people's quality of life.

A Comprehensive Study of Deep Learning-based Covert Communication

Deep learning-based methods have been popular in multimedia analysis tasks, including classification, detection, segmentation, and so on. In addition to conventional applications, this model can be widely used for cover communication, i.e., information hiding. This article presents a review of deep learning-based covert communication scheme for protecting digital contents, devices, and models. In particular, we discuss the background knowledge, current applications, and constraints of existing deep learning-based information hiding schemes, identify recent challenges, and highlight possible research directions. Further, major role of deep learning in the area of information hiding are highlighted. Then, the contribution of surveyed scheme is also summarized and compared in the context of estimation of design objectives, approaches, evaluation metric, and weaknesses. We believe that this survey can pave the way to new research in this crucial field of information hiding in deep-learning environment.

Artificial intelligence (AI) library services innovative conceptual framework for the digital transformation of university education

Purpose

Artificial intelligence (AI) is one of the latest digital transformation (DT) technological trends the university library can use to provide library users with alternative educational services. AI can foster intelligent decisions for retrieving and sharing information for learning and research. However, extant literature confirms a low adoption rate by the university libraries in using AI to provide innovative alternative services, as this is missing in their strategic plan. The research develops (AI-LSICF) an artificial intelligence library services innovative conceptual framework to provide new insight into how AI technology can be used to deliver value-added innovative library services to achieve digital transformation. It will also encourage library and information professionals to adopt AI to complement effective service delivery.

Design/methodology/approach

This study adopts a qualitative content analysis to investigate extant literature on how AI adoption fosters innovative services in various organisations. The study also used content analysis to generate possible solutions to aid AI service innovation and delivery in university libraries.

Findings

This study uses its findings to develop an Artificial Intelligence Library Services Innovative Conceptual Framework (AI-LSICF) by integrating AI applications and functions into the digital transformation framework elements and discussed using a service innovation framework.

Research limitations/implications

In research, AI-LSICF helps increase an understanding of AI by presenting new insights into how the university library can leverage technology to actualise innovation in service provision to foster DT. This trail will be valuable to scholars and academics interested in addressing the application pathways of AI library service innovation, which is still under-explored in digital transformation.

Practical implications

In practice, AI-LSICF could reform the information industry from its traditional brands into a more applied and resolutely customer-driven organisation. This reformation will awaken awareness of how librarians and information professionals can leverage technology to catch up with digital transformation in this age of the fourth industrial revolution.

Social implications

The enlightenment of AI-LSICF will motivate library professionals to take advantage of AI's potential to enhance their current business model and achieve a unique competitive advantage within their community.

Originality/value

AI-LSICF development serves as a revelation, motivating university libraries and information professionals to consider AI in their strategic plan to enable technology to support university education. This act will enable alternative service delivery in the face of unforeseen circumstances like technological disruption and the present global COVID-19 pandemic that requires non-physical interaction.

Streamflow prediction using an integrated methodology based on convolutional neural network and long short-term memory networks

Streamflow (Qflow) prediction is one of the essential steps for the reliable and robust water resources planning and management. It is highly vital for hydropower operation, agricultural planning, and flood control. In this study, the convolution neural network (CNN) and Long-Short-term Memory network (LSTM) are combined to make a new integrated model called CNN-LSTM to predict the hourly Qflow (short-term) at Brisbane River and Teewah Creek, Australia. The CNN layers were used to extract the features of Qflow time-series, while the LSTM networks use these features from CNN for Qflow time series prediction. The proposed CNN-LSTM model is benchmarked against the standalone model CNN, LSTM, and Deep Neural Network models and several conventional artificial intelligence (AI) models. Qflow prediction is conducted for different time intervals with the length of 1-Week, 2-Weeks, 4-Weeks, and 9-Months, respectively. With the help of different performance metrics and graphical analysis visualization, the experimental results reveal that with small residual error between the actual and predicted Qflow, the CNN-LSTM model outperforms all the benchmarked conventional AI models as well as ensemble models for all the time intervals. With 84% of Qflow prediction error below the range of 0.05 m3 s-1, CNN-LSTM demonstrates a better performance compared to 80% and 66% for LSTM and DNN, respectively. In summary, the results reveal that the proposed CNN-LSTM model based on the novel framework yields more accurate predictions. Thus, CNN-LSTM has significant practical value in Qflow prediction.

Classification Framework for Healthy Hairs and Alopecia Areata: A Machine Learning (ML) Approach

Alopecia areata is defined as an autoimmune disorder that results in hair loss. The latest worldwide statistics have exhibited that alopecia areata has a prevalence of 1 in 1000 and has an incidence of 2%. Machine learning techniques have demonstrated potential in different areas of dermatology and may play a significant role in classifying alopecia areata for better prediction and diagnosis. We propose a framework pertaining to the classification of healthy hairs and alopecia areata. We used 200 images of healthy hairs from the Figaro1k dataset and 68 hair images of alopecia areata from the Dermnet dataset to undergo image preprocessing including enhancement and segmentation. This was followed by feature extraction including texture, shape, and color. Two classification techniques, i.e., support vector machine (SVM) and k-nearest neighbor (KNN), are then applied to train a machine learning model with 70% of the images. The remaining image set was used for the testing phase. With a 10-fold cross-validation, the reported accuracies of SVM and KNN are 91.4% and 88.9%, respectively. Paired sample T-test showed significant differences between the two accuracies with a p < 0.001. SVM generated higher accuracy (91.4%) as compared to KNN (88.9%). The findings of our study demonstrate potential for better prediction in the field of dermatology.