Convolutional Neural Networks for Mineral Prospecting Through Alteration Mapping with Remote Sensing Data

Destructive cyber-attacks and cybercriminals are increasing with the increase in IoT (Internet of Things) devices globally. This ha/s led to the need for increase in security in IoT systems. Innovative and novel techniques are used by the intruders to accomplish malicious goals effectively through cyber-attacks. An Intrusion Detection System (IDS) is used for classification of attacks in IoT networks based on anomaly detection and machine learning techniques. Inefficiency is observed in the conventional machine learning models and intrusion detection techniques as the network technologies are unpredictable. Accurate identification of various anomalies is possible with deep learning models in several research segments. The input data along with its prominent characteristics may be categorized automatically for classification and anomaly detection using convolutional neural networks (CNN). Faster computations are enabled due to the performance efficiency of CNN. For IoT networks, an intrusion detection model based on anomaly detection is designed and developed in this paper. A multiclass classification framework is created initially using a CNN model. Further, 3D CNN is used for implementation of the proposed model. Various intrusion detection datasets from IoT networks are used for validation of the proposed CNN model. Pre-trained multiclass CNN model is used for implementation of multiclass and binary classification based on transfer learning. When compared to the conventional deep learning models, the proposed multiclass and binary classification framework has attained improved F1 score, recall, precision and accuracy.

Convolutional Neural Networks (CNNs) have gained significant traction in the field of image categorization, particularly in the domains of health and safety. This study aims to categorize the utilization of face masks, which is a vital determinant of respiratory health. Convolutional neural networks (CNNs) possess a high level of complexity, making it crucial to execute hyperparameter adjustment in order to optimize the performance of the model. The conventional approach of trial-and-error hyperparameter configuration often yields suboptimal outcomes and is time-consuming. Genetic Algorithms (GA), an optimization technique grounded in the principles of natural selection, were employed to identify the optimal hyperparameters for Convolutional Neural Networks (CNNs). The objective was to enhance the performance of the model, namely in the classification of photographs into two categories: those with face masks and those without face masks. The convolutional neural network (CNN) model, which was enhanced by the utilization of hyperparameters adjusted by a genetic algorithm (GA), demonstrated a commendable accuracy rate of 94.82% following rigorous testing and validation procedures. The observed outcome exhibited a 2.04% improvement compared to models that employed a trial and error approach for hyperparameter tuning. Our research exhibits exceptional quality in the domain of investigations utilizing Convolutional Neural Networks (CNNs). Our research integrates the resilience of Genetic Algorithms (GA), in contrast to previous studies that employed Convolutional Neural Networks (CNN) or conventional machine learning models without adjusting hyperparameters. This unique approach enhances the accuracy and methodology of hyperparameter tuning in Convolutional Neural Networks (CNNs).

Speech is a powerful means of expressing thoughts, emotions, and perspectives. However, accurately determining the emotions conveyed through speech remains a challenging task. Existing manual methods for analyzing speech to recognize emotions are prone to errors, limiting our understanding and response to individuals’ emotional states. To address diverse accents, an automated system capable of real-time emotion prediction from human speech is needed. This paper introduces a speech emotion recognition (SER) system that leverages supervised learning techniques to tackle cross-accent diversity. Distinctively, the system extracts a comprehensive set of nine speech features—Zero Crossing Rate, Mel Spectrum, Pitch, Root Mean Square values, Mel Frequency Cepstral Coefficients, chroma-stft, and three spectral features (Centroid, Contrast, and Roll-off) for refined speech signal processing and recognition. Seven machine learning models are employed, encompassing Random Forest, Logistic Regression, Decision Tree, Support Vector Machines, Gaussian Naive Bayes, K-Nearest Neighbors, ensemble learning, and four individual, hybrid deep learning models including Long short-term memory (LSTM) and 1-Dimensional Convolutional Neural Network (1D-CNN) with stratified cross-validation. Audio samples from diverse English regions are combined to train the models. The performance evaluation results of conventional machine learning and deep learning models indicate that the Random Forest-based feature selection model achieves the highest accuracy of up to 76% among the conventional machine learning models. Simultaneously, the 1D-CNN model with stratified cross-validation reaches up to 99% accuracy. The proposed framework enhances the cross-accent emotion recognition accuracy up to 86.3%, 89.87%, 90.27%, and 84.96% by margins of 14.71%, 10.15%, 9.6%, and 16.52% respectively.

Lithological mapping is a critical aspect of geological mapping that can be useful in studying the mineralization potential of a region and has implications for mineral prospectivity mapping. This is a challenging task if performed manually, particularly in highly remote areas that require a large number of participants and resources. The combination of machine learning (ML) methods and remote sensing data can provide a quick, low-cost, and accurate approach for mapping lithological units. This study used deep learning via convolutional neural networks and conventional ML methods involving support vector machines and multilayer perceptron to map lithological units of a mineral-rich area in the southeast of Iran. Moreover, we used and compared the efficiency of three different types of multispectral remote-sensing data, including Landsat 8 operational land imager (OLI), advanced spaceborne thermal emission and reflection radiometer (ASTER), and Sentinel-2. The results show that CNNs and conventional ML methods effectively use the respective remote-sensing data in generating an accurate lithological map of the study area. However, the combination of CNNs and ASTER data provides the best performance and the highest accuracy and adaptability with field observations and laboratory analysis results so that almost all the test data are predicted correctly. The framework proposed in this study can be helpful for exploration geologists to create accurate lithological maps in other regions by using various remote-sensing data at a low cost.

Human activity recognition is an important and difficult topic to study because of the important variability between tasks repeated several times by a subject and between subjects. This work is motivated by providing time-series signal classification and a robust validation and test approaches. This study proposes to classify 60 signs from the American Sign Language based on data provided by the LeapMotion sensor by using different conventional machine learning and deep learning models including a model called DeepConvLSTM that integrates convolutional and recurrent layers with Long-Short Term Memory cells. A kinematic model of the right and left forearm/hand/fingers/thumb is proposed as well as the use of a simple data augmentation technique to improve the generalization of neural networks. DeepConvLSTM and convolutional neural network demonstrated the highest accuracy compared to other models with 91.1 (3.8) and 89.3 (4.0) % respectively compared to the recurrent neural network or multi-layer perceptron. Integrating convolutional layers in a deep learning model seems to be an appropriate solution for sign language recognition with depth sensors data.

The currently deployed prediction models for strawberry fresh produce (FP) are based on either conventional machine learning (ML) or on simple deep learning (DL) models that are mostly applied for yield prediction. In this paper, we propose more comprehensive DL models that are applied for the first time to predict strawberry yield. The strawberry price is predicted as well directly from weather input parameters and yield. The strawberry price prediction is achieved using compound DL models such as Convolutional Long Short-Term Memory Recurrent Neural Network (CNN-LSTM). It is found that by adding attention, the performance of the compound models usually improves. After utilizing an aggregated performance measure to find the best model, the Attention-CNN-LSTM model proved to be the best compared to the rest of the deployed conventional ML models as well as the compound and simple DL models. The aggregated measure shows that this model is capable of precisely predicting strawberry prices five weeks ahead while maintaining the lowest prediction error and the highest model correlation.

In distribution system state estimation (DSSE), the physics-based approach such as the weighted least squares (WLS) technique suffers from convergence issues, whereas the problem with conventional deep learning (DL) models is the lack of generalizability. To address these aspects, this paper proposes a physics-guided deep learning (PGDL) framework, which incorporates the power system physical laws into the deep learning models for DSSE. The proposed approach has two stages. The first stage leverages the DL models to understand the relation between the measurement data and system states, while the second stage involves physics-guided equations to decode the measurement data from the estimated states. Further, a loss function incorporating the estimated states and estimated measurements is derived to guide the learning process of the considered deep learning model. The required database for DL models is generated by carrying out power flow studies on a modified IEEE 37-node unbalanced distribution test system. Various deep learning models such as multi-layer perceptron (MLP), convolutional neural networks (CNN), and hybrid CNN-MLP are implemented in the proposed PGDL framework for DSSE and their performance metrics are evaluated and compared under different scenarios. The results show that the PGDL approaches achieve better performance compared with their conventional DL models and the basic WLS algorithm.

Accurately diagnosing emotional and psychological disorders is essential for prompt mental health interventions, especially in intelligent healthcare systems. This paper proposes a deep learning model that uses convolutional neural networks (CNN) and long short-term memory (LSTM) networks to classify emotional states based on physiological inputs like EEG and ECG. Bayesian optimisation improves the model's learning efficacy and generalisation ability by adjusting hyperparameters. In comparison to conventional machine learning models such as Support Vector Machines (SVM), random forest, and standalone deep learning models (CNN and LSTM), the proposed CNN-LSTM architecture increases classification accuracy by 25%, to 92.1%. Its exceptional performance is demonstrated by its AUC-ROC score of 0.96, accuracy of 0.93, recall of 0.91, and F1-score of 0.92. These results show that the model can distinguish between several emotional states, including neutral, tense, and concerned. A real-time application is used to investigate the potential of wearable EEG-based brain-computer interface (BCI) devices for continuous emotional monitoring. The findings indicate that the proposed framework might be a helpful tool for the early detection and tailored management of mental health conditions in intricate healthcare environments.© The Author(s) 2025. Published by RITHA Publishing. This article is distributed under the terms of the license CC-BY 4.0., which permits any further distribution in any medium, provided the original work is properly cited maintaining attribution to the author(s) and the title of the work, journal citation and URL DOI.

Background and Objectives: Spirometry is the most widely used pulmonary function test for diagnosing respiratory diseases. Its progressive incorporation into non-specialized settings, such as primary care, raises challenges for ensuring the reliability of results. In this context, tools based on artificial intelligence (AI) techniques have emerged as promising solutions to support quality control in spirometry. This systematic review aims to synthesize the available evidence on their application in this field. Methods: A systematic search was conducted in PubMed and IEEE Xplore to identify peer-reviewed original studies, published between 2014 and June 2025, that applied AI to spirometry quality control. The search and data extraction followed the PRISMA guidelines. Results: Six studies met the inclusion criteria. Four analyzed the acceptability and usability of the maneuver, and two focused on detecting errors committed during test performance. The most widely used models were convolutional neural networks, used in four studies, whereas two studies employed other conventional machine learning models. Three models reported area under the ROC curve values higher than 0.88. Conclusions: AI-based tools show great potential to assist in spirometry quality control, both in determining acceptability and in detecting errors. However, current studies remain scarce and highly heterogeneous in both objectives and methods. Broader, multicenter research, including validation in non-specialized settings, is required to confirm their clinical utility and facilitate their implementation in clinical practice.

The challenges of climate change impact greatly on environmental sustainability, where analytical methods are very strong to capture both the spatial variation and temporal changes of the climatic processes. This paper provides a unified framework of the study of the spatiotemporal climatic change based on the use of multi-source remote sensors and machine learning tools. Landsurface temperature land surface, vegetation indices and precipitation satellite measurements in 2000-2024 were joined with the latest machine learning models, such as Rapid Forest, Support Vector machine, Convolutional Neural Network, Long Short-Term Memory network. The models were tested on how well they predicted the climate variables, how they identified the hotspots of climate change as well as making long term predictions. The experiments have shown that deep learning methods perform better than conventional machine learning models, with a lower error of prediction and a greater power of explanation. Using the LSTM model, the lowest RMSE at 1.47 oC, MAE at 1.12 oC, and R2 of 0.93 were obtained when predicting land surface temperatures, which is a reduction of about 30 percent compared to baselines used in the related research. The overall accuracy of CNN-based spatial analysis was 91.8 as it is highly capable of recording the presence of spatial heterogeneity. These findings prove that a combination of remote sensing with machine learning will contribute a lot to monitoring and prediction of climate change. The suggested framework offers a transferable and scalable framework to assist in the assessment of climate impacts, environmental management, and makes policy decisions based on data.

A hybrid machine learning model for sentiment analysis and satisfaction assessment with Turkish universities using Twitter data

Aims: This study aimed to explore the effect of training set diversity on the performance of deep learning models for predicting early gastric cancer (EGC) under endoscopy. Methods: Images of EGC and non-cancerous lesions under narrow-band imaging (ME-NBI) and magnifying blue laser imaging (ME-BLI) were retrospectively collected. Training set 1 was composed of 150 non-cancerous and 309 EGC ME-NBI images, training set 2 was composed of 1505 non-cancerous and 309 EGC ME-BLI images, and training set 3 was the combination of training set 1 and 2. Test set 1 was composed of 376 non-cancerous and 1052 EGC ME-NBI images, test set 2 consisted of 529 non-cancerous and 71 EGC ME-BLI images, and test set 3 was the combination of test set 1 and test set 2. Three deep learning models, convolutional neural network (CNN) 1, CNN 2 and CNN 3 (CNN 1, CNN 2 and CNN 3 were independently trained using training set 1, training set 2 and training set 3, respectively), were constructed, and their performances on each test set were respectively evaluated. One hundred and thirty-eight ME-NBI videos and 17 ME-BLI videos were further collected to evaluate and compare the performance of each model in real time. Results: On the whole, the performance of CNN 3 was the best. The accuracy (Acc), sensitivity (Sn), specificity (Sp) and area under the curve (AUC) of test set 1 in CNN 3 were 87.89% (1255/1428), 90.96% (342/376), 86.79% (913/1052) and 94.60%, respectively. The Acc, Sn, Sp and AUC of test set 2 in CNN 3 were 95% (570/600), 97.92% (518/529), 73.24% (52/71) and 90.93% respectively. The Acc, Sn, Sp and AUC of test set 3 in CNN 3 were 89.99% (1825/2028), 95.03% (860/905), 85.93% (965/1123) and 94.89%, respectively. The performance of CNN 3 was also the best in videos test set. The Acc, Sn and Sp of videos test set in CNN 3 were 91.03% (142/156), 90.58% (125/138) and 94.44% (17/18), respectively. Conclusions: The deep learning model with the most diverse training data has the best diagnostic effect.

Objective pain measurements are essential in clinical settings for determining effective treatment strategies. This study aims to utilize brain-computer interface technology for reliable pain classification and detection. We developed an electroencephalography-based pain detection system comprising two main components: (1) pain/no-pain detection and (2) pain severity classification across three levels: low, moderate, and high. Deep learning models, including convolutional neural networks and recurrent neural networks, were employed to classify the wavelet features extracted through time-frequency domain analysis. Furthermore, we compared the performance of our system against conventional machine learning models, such as support vector machines and random forest classifiers. Our deep learning approach outperformed the baseline models, achieving accuracies of 91.84% for pain/no-pain detection and 87.94% for pain severity classification, respectively.

Hyperspectral Image (HSI) classification is one of the fundamental tasks in the field of remote sensing data analysis. CNN (Convolutional Neural Network) has been proven to be an effective deep learning model, which can extract high-level features directly from the raw data and thereby utilize rich information contained in HSI data. However, labor cost to label enough HIS data for training model is usually expensive, so that it is a strong demand of utilizing limited training data to get a satisfied classification accuracy. In this paper, we put forward a deep cube CNN model – DCNR, which is composed of a cube neighbor HSI pixels strategy, a deep CNN and a random forest classifier. In DCNR model, cubic samples, containing spectral-spatial information, are generated by putting each target pixel and its neighbors together. Then features with high representative ability, extracted by applying a specially designed cube CNN model on each cubic sample, are fed into the random forest classifier for the classification of the target pixel. Results show that DCNR model can achieve classification accuracy of 96.78%, 96.08% and 94.85% on KSC, IP and SA datasets respectively with 20% samples as training set, and 85.03%, 83.45 and 62.17% on KSC, IP and SA datasets respectively with only 1% samples as training set, significantly outperforming random forest and cube CNN models.

Emotion recognition (ER) is crucial for understanding human behaviours, social interactions, and psychological well-being. Electroencephalography (EEG) has emerged as a promising tool for capturing the neural correlates of emotions. This work is a systematic review of articles in ER using EEG signals. A total of 120 articles from 1041 articles were selected based on PRISMA guidelines using defined inclusion and exclusion criteria, published between 2018 and 2024. This article aims to provide an in-depth understanding of the current landscape of ER from EEG signals utilizing deep learning (DL). This review offers valuable guidance for researchers and practitioners seeking more refined and reliable emotion classification systems. To explore the effectiveness of DL models in EEG-based ER, several potential DL models, such as convolutional neural network, long short-term memory (LSTM), gated recurrent unit (GRU), hybrid bidirectional LSTM (BiLSTM), bidirectional GRU, and advanced DL models such as convolutional recurrent neural network and EEG-Conformer models are applied to two popular datasets, SEED and GAMEEMO, respectively, to depict the full process of ER. Additionally, the performance of DL models is also compared with the performance of basic machine learning (ML) models such as SVM, k-nearest neighbors, logistic regression, and boosting algorithms such as AdaBoost, XGBoost and LightGBM. Through extensive experiments and performance evaluations, the performance of different models when applied to the datasets mentioned above is compared. The accuracy, precision, recall, and F1-scores are analysed to determine the most effective model for EEG-based ER. The findings of this study demonstrate that the performance of hybrid DL models is more efficacious than that of ML models. The best-performing model (BiLSTM) classified the emotions, with an accuracy of 90.54% when applied to the GAMEEMO dataset. This research contributes to the growing body of literature on ER and provides insights into the feasibility of using EEG signals to understand emotional states, and presents a structured roadmap for future exploration. The findings can aid in the development of more accurate and reliable ER systems, which can have wide-ranging applications in psychology, social sciences, and human-computer interactions.