Automated Computer-Aided Detection and Classification of Intracranial Hemorrhage Using Ensemble Deep Learning Techniques.

Wearable electroencephalography (EEG) devices for seizure detection accuracy and reliability are deep learning (DL) applications in the field of epilepsy diagnosis. In this study, we sought to increase the accuracy of seizure detection using advanced DL algorithms on the Children’s Hospital Boston - Massachusetts Institute of Technology (CHB-MIT) EEG database. First, a fully convolutional network (FCN) was trained and assessed using accuracy and recall/precision metrics, and the early stopping technique was used to avoid overfitting. To assess the performance, the FCN was evaluated in terms of various metrics, including accuracy, precision, recall, F1-score, and receiver operating characteristic (ROC)-area under the curve (AUC). In addition, two-dimensional (2D) convolutional neural networks (CNNs) and long short-term memory (LSTM) models were used to model the database, and their performance was thoroughly measured using different metrics, graphs, and confusion matrices. Using LSTM variants, such as standard LSTM, bidirectional LSTM, stacked LSTM, and LSTM attention mechanisms, hybrid convolutional LSTM (ConvLSTM) models were trained and compared. The comparison was conducted based on the training and validation accuracy and loss, as well as the graphs resulting from the precision–recall curves. Apart from DL approaches, EEG signal analysis using time–frequency techniques, such as wavelet transform and short-time Fourier transform, has also been investigated. These methods assisted in the analysis of the time–frequency features of EEG signals in combination with DL models. This study demonstrates that the performance of wearable EEG devices can be augmented using a combination of DL and seizure signal processing techniques. The FCN achieved an accuracy of 92%, with a recall for seizures of 33%, an F1-score of 0.03, and strong ROC-AUC results. The 2D CNN achieved 96% accuracy, a seizure recall of 70%, an F1-score of 0.12, and an ROC-AUC score of 78%. The baseline LSTM struggled with effectiveness at 53% accuracy with a seizure recall of 18%. In contrast, the LSTM model, which incorporated synthetic minority oversampling technique (SMOTE) balancing, was able to reach improvements of up to 89% accuracy, with a precision of 91%, a recall of 86%, an F1-score of 0.89, and a strong ROC curve performance. Among the models, the LSTM with SMOTE was the best performer, with 89% accuracy, 91% precision, 86% recall, and an F1-score of 0.89. These results provide evidence that applying techniques for data balancing in combination with certain DL network architectures significantly improves the detection of seizures using wearable EEG devices worn on the body. We believe that real-time monitoring and high-performance systems are feasible using optimized DL frameworks. The analysis of the performance of different models allows for the understanding of the possibilities of optimizing the architectures of DL algorithms for the modern diagnosis of epilepsy in real time. The source code used to carry out the experiments is publicly available at CHB-MIT EEG Dataset Python Scripts (https://www.kaggle.com/code/adnankust/adnaneeg1).

Many countries around the globe, including Tanzania, are investing in renewable energy, partly because of the need to increase electric power generation and meet the ever-increasing electricity demands, and partly because of the need to combat global climate change caused by carbon emissions from fossil fuel-based electricity production. Kishapu Solar Project, located in Kishapu District, Shinyanga Region, Tanzania, is one of the renewable energy projects with a planned generation of 150 MW of electric power once completed, using solar photovoltaic technology. Accurate forecasting of solar radiation is important in managing and maintaining solar energy plants. Inaccurate forecasting of solar radiation can lead to poor harvest of solar energy and poor management of solar energy plants, which directly impacts electricity contribution to the national electricity grid. Long Short-Term Memory (LSTM) and its variant, PeepHole LSTM, are examples of Deep Learning models that can be used to predict solar radiation. The purpose of PeepHole LSTM is to introduce “peephole” connections in the LSTM model, which allow LSTM gates to directly inspect memory cell state and hence have richer information to process. However, there is still a research gap on the impact of “peephole” connections on the prediction performance of the LSTM model, especially in the context of forecasting solar radiation in Kishapu District, where the Kishapu Solar Project is located. The purpose of this study is to fill this research gap by developing both LSTM and PeepHole LSTM models and comparing their performances in forecasting solar radiation in Kishapu District. The 14-year Kishapu District daily solar radiation (Downward Shortwave Radiation) dataset was first pre-processed by scaling (normalizing) it using Standard Scaler and then split into training set (the first 70%), validation set (the next 15%) and test set (the last 15%) before being utilized to train and test the developed LSTM and PeepHole LSTM models. Both LSTM and PeepHole LSTM models used the previous 5 days' solar radiation values as inputs to predict the output (next day (6th day) solar radiation value). The trained and better-performing model between the two was finally saved in .h5 format and integrated with a Gradio based Web Application to provide a user interface for officials in Kishapu District and at Kishapu Solar Project to predict daily solar radiation. The findings from performance evaluation revealed that the LSTM model outperformed the PeepHole LSTM model in predicting solar radiation by achieving test Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) scores of 26.22 W/m2 and 36.65 W/m2, respectively, compared to MAE and RMSE scores of 30.84 W/m2 and 41.88 W/m2, respectively, achieved by the PeepHole LSTM model, concluding that “peephole” connections reduce the performance of the LSTM model rather than increasing it when used to forecast solar radiation in Kishapu District. This study’s recommendation to Artificial Intelligence (AI) software developers and researchers is to use the LSTM rather than the PeepHole LSTM Deep Learning model when forecasting solar radiation in Kishapu District and in locations with similar climatic conditions

Water quality prediction (WQP) plays an essential role in water quality management for aquaculture to make aquaculture production profitable and sustainable. In this work, we propose hybrid deep learning (DL) models, convolutional neural network (CNN) with the long short-term memory (LSTM) and gated recurrent unit (GRU) for aquaculture WQP. CNN can effectively fetch the aquaculture water quality characteristics, whereas GRU and LSTM can learn long-term dependencies in the time series data. We conduct experiments using the two different water quality datasets and present an extensive study on the impact of hyperparameters on the performance of the proposed hybrid DL models. Furthermore, the performance of hybrid CNN-LSTM and CNN-GRU models are compared with different baseline LSTM, GRU and CNN DL models and also with attention-based LSTM and attention-based GRU DL models. The results show that the hybrid CNN-LSTM outperformed all other models in terms of prediction accuracy and computation time.

Purpose To apply conformal prediction to a deep learning (DL) model for intracranial hemorrhage (ICH) detection and evaluate model performance in detection as well as model accuracy in identifying challenging cases. Materials and Methods This was a retrospective (November-December 2017) study of 491 noncontrast head CT volumes from the CQ500 dataset, in which three senior radiologists annotated sections containing ICH. The dataset was split into definite and challenging (uncertain) subsets, in which challenging images were defined as those in which there was disagreement among readers. A DL model was trained on patients from the definite data (training dataset) to perform ICH localization and classification into five classes. To develop an uncertainty-aware DL model, 1546 sections of the definite data (calibration dataset) were used for Mondrian conformal prediction (MCP). The uncertainty-aware DL model was tested on 8401 definite and challenging sections to assess its ability to identify challenging sections. The difference in predictive performance (P value) and ability to identify challenging sections (accuracy) were reported. Results The study included 146 patients (mean age, 45.7 years ± 9.9 [SD]; 76 [52.1%] men, 70 [47.9%] women). After the MCP procedure, the model achieved an F1 score of 0.919 for localization and classification. Additionally, it correctly identified patients with challenging cases with 95.3% (143 of 150) accuracy. It did not incorrectly label any definite sections as challenging. Conclusion The uncertainty-aware MCP-augmented DL model achieved high performance in ICH detection and high accuracy in identifying challenging sections, suggesting its usefulness in automated ICH detection and potential to increase trustworthiness of DL models in radiology. Keywords: CT, Head and Neck, Brain, Brain Stem, Hemorrhage, Feature Detection, Diagnosis, Supervised Learning Supplemental material is available for this article. © RSNA, 2025 See also commentary by Ngum and Filippi in this issue.

This research aims to implement deep learning techniques to determine fact and fake news in Indonesian language. The methods used are Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The stages of the research consisted of collecting data, labeling data, preprocessing data, word embedding, splitting data, forming CNN and LSTM models, evaluating, testing new input data and comparing evaluations of the established CNN and LSTM models. The Data are collected from a fact and fake news provider site that is valid, namely TurnbackHoax.id. There are 1786 news used in this study, with 802 fact and 984 fake news. The results indicate that the CNN and LSTM methods were successfully applied to determine fact and fake news in Indonesian language properly. CNN has an accuracy test, precision and recall value of 0.88, while the LSTM model has an accuracy test and precision value of 0.84 and a recall of 0.83. In testing the new data input, all of the predictions obtained by CNN are correct, while the prediction results obtained by LSTM have 1 wrong prediction. Based on the evaluation results and the results of testing the new data input, the model produced by the CNN method is better than the model produced by the LSTM method.

This paper presents an innovative approach for enhancing power output forecasting of Photovoltaic (PV) power plants in dynamic environmental conditions using a Hybrid Deep Learning Model (DLM). The hybrid DLM employs a synergy of Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) network, and Bidirectional LSTM (Bi-LSTM), effectively capturing spatial and temporal dependencies within weather data crucial for accurate predictions. To optimize the DLM’s performance efficiently, a unique Kepler Optimization Algorithm (KOA) is introduced for hyperparameter tuning, drawing inspiration from Kepler’s laws of planetary motion. By leveraging KOA, the DLM attains optimal hyperparameter configurations, elevating power output prediction precision. Additionally, this study integrates Transductive Transfer Learning (TTL) with the deep learning models to enhance resource efficiency. By leveraging knowledge gained from previously learned tasks, TTL enables the DLM to improve its forecasting capabilities while minimizing resource utilization. Datasets encompassing environmental parameters and PV plant-generated power across diverse sites are employed for DLM training and testing. Three hybrid models, amalgamating KOA, CNN, LSTM, and Bi-LSTM techniques, are introduced and evaluated. Comparative assessment of these models across distinct PV sites yields insightful observations. Performance evaluation, focused on short-term PV power forecasting, underscores the hybrid DLM’s superiority over individual CNN and LSTM models. This hybrid approach achieves remarkable accuracy and resilience in predicting power output under varying weather conditions, showcasing its potential for efficient PV power plant management.

Recently, with the advent of various Internet of Things (IoT) applications, a massive amount of network traffic is being generated. A network operator must provide different quality of service, according to the service provided by each application. Toward this end, many studies have investigated how to classify various types of application network traffic accurately. Especially, since many applications use temporary or dynamic IP or Port numbers in the IoT environment, only payload-based network traffic classification technology is more suitable than the classification using the packet header information as well as payload. Furthermore, to automatically respond to various applications, it is necessary to classify traffic using deep learning without the network operator intervention. In this study, we propose a traffic classification scheme using a deep learning model in software defined networks. We generate flow-based payload datasets through our own network traffic pre-processing, and train two deep learning models: 1) the multi-layer long short-term memory (LSTM) model and 2) the combination of convolutional neural network and single-layer LSTM models, to perform network traffic classification. We also execute a model tuning procedure to find the optimal hyper-parameters of the two deep learning models. Lastly, we analyze the network traffic classification performance on the basis of the F1-score for the two deep learning models, and show the superiority of the multi-layer LSTM model for network packet classification.

Intracranial hemorrhage (ICH) is an acute-stroke type leading to a high mortality rate. ICH diagnoses can keep patients out of life-threatening and longlasting consequences. These diagnoses are typically detected by analyzing images of Computed Tomography (CT) scan and symptoms of the patients. Consequently, the expertise of radiologists is significant in terms of detecting signals of ICH and making in-time decisions to save these patients. Over the past few decades, due to powerful-and-modern machine learning algorithms, several computer-aided detection (CAD) systems have been developed. They are becoming an effective part of routine clinical work to detect a few critical diseases, such as strokes, cancers, and so on. In this paper, we introduce a CAD that combines a deep-learning model and typical image processing techniques to determine whether patients suffer from ICH due to their CT images. The deep-learning model based on MobileNetV2 architecture was trained on RSNA (Radiological Society of North America) Intracranial Hemorrhage dataset. Then it was validated on a dataset of ICH-Vietnamese cases collected from Vinh Long Province Hospital, Vietnam. The experiment indicated that the classifier achieved AUC of 0.991, sensitivity of 0.992, and specificity of 0.807. After the deep-learning model identifies ICH-suspected slices, the Hounsfield Unit (HU) method is employed to highlight specific hemorrhage areas in these slices. DBSCAN is also used to remove noises detected by the HU method.

Tanzania heavily depends on United States Dollar (USD) foreign currency to import various goods and services into the country. Failure to correctly forecast exchange rates between USD and Tanzanian Shillings (TZS) may pose risks such as inability to import intended goods and services, possibility of losing money in stock exchange markets and other investment businesses in case of unexpected currency appreciation or depreciation as well as poor investment decisions in foreign exchange markets. To address this, this study has developed and comparatively evaluated performances of LSTM (Long Short-Term Memory) and BiLSTM (Bidirectional LSTM) deep learning models for forecasting daily USD to TZS exchange rates. The findings reveal that, BiLSTM model outperforms LSTM in forecasting daily USD to TZS exchange rates, achieving a MAPE (Mean Absolute Percentage Error) score of 0.363 on test set (unseen data) compared to a MAPE score of 1.471 achieved by LSTM model. This study recommends to the prospective Artificial Intelligence (AI) researchers and software developers to use BiLSTM instead of LSTM model to forecast (predict) USD to TZS exchange rates. Also, this study has developed USD to TZS exchange rates dataset which can be used by AI researchers, saving them time and costs involved with creating datasets from scratch. This study has also developed ready to use BiLSTM and LSTM models which can be used by Tanzanian business men and women involved in stock exchange markets, foreign exchange markets and other businesses, to predict daily USD to TZS exchange rates and make appropriate business and investment decisions.

Background and Purpose:Accurate automated infarct segmentation is needed for acute ischemic stroke studies relying on infarct volumes as an imaging phenotype or biomarker that require large numbers of subjects. This study investigates whether an ensemble of convolutional neural networks (CNN) trained on multiparametric DWI maps outperforms single networks trained on solo DWI parametric maps.Materials and Methods:CNNs were trained on combinations of DWI, ADC, and low b-value-weighted images from 116 subjects. The performances of the networks (measured by Dice score, sensitivity and precision) were compared to one another and to ensembles of 5 networks. To assess the generalizability of the approach, the best performing model was applied to an independent evaluation cohort of 151 subjects. Agreement between manual and automated segmentations for identifying patients with large lesions volumes was calculated across multiple thresholds (21 cm3, 31 cm3, 51 cm3, and 70 cm3).ResultsAn ensemble of CNNs trained on DWI, ADC and low b-value-weighted images produced the most accurate acute infarct segmentation over individual networks (p<0.0001). Automated volumes correlated with manually measured volumes (Spearman’s ρ=0.91, p<0.0001) for the independent cohort. For the task of identifying patients with large lesion volumes, agreement between manual outlines and automated outlines was high (Cohen’s κ 0.86 to 0.90, p<0.0001).ConclusionAcute infarcts are more accurately segmented using ensembles of CNNs trained with multi-parametric maps than using a single model trained with a solo map. Automated lesion segmentation can perform with high agreement with manual techniques for identifying patients with large lesion volumes.

Diabetes is a persistent health condition led by insufficient use or inappropriate use of insulin in the body. If left undetected, it can lead to further complications involving organ damage such as heart, lungs, and eyes. Timely detection of diabetes helps obtain the right medication, diet, and exercise plan to lead a healthy life. ML approach has been utilized to obtain rapid and reliable diabetes detection, however, existing approaches suffer from the use of limited datasets, lack of generalizability, and lower accuracy. This study proposes a novel feature extraction approach to overcome these limitations by using an ensemble of convolutional neural network (CNN) and long short-term memory (LSTM) models. Multiple datasets are combined to make a larger dataset for experiments and multiple features are utilized for investigating the efficacy of the proposed approach. Features from the extra tree classifier, CNN, and LSTM are also considered for comparison. Experimental results reveal the superb performance of CNN-LSTM-based features with random forest model obtaining a 0.99 accuracy score. This performance is further validated by comparison with existing approaches and k-fold cross-validation which shows the proposed approach provides robust results.

BackgroundPredicting hypoglycemia while maintaining a low false alarm rate is a challenge for the wide adoption of continuous glucose monitoring (CGM) devices in diabetes management. One small study suggested that a deep learning model based on the long short-term memory (LSTM) network had better performance in hypoglycemia prediction than traditional machine learning algorithms in European patients with type 1 diabetes. However, given that many well-recognized deep learning models perform poorly outside the training setting, it remains unclear whether the LSTM model could be generalized to different populations or patients with other diabetes subtypes.ObjectiveThe aim of this study was to validate LSTM hypoglycemia prediction models in more diverse populations and across a wide spectrum of patients with different subtypes of diabetes.MethodsWe assembled two large data sets of patients with type 1 and type 2 diabetes. The primary data set including CGM data from 192 Chinese patients with diabetes was used to develop the LSTM, support vector machine (SVM), and random forest (RF) models for hypoglycemia prediction with a prediction horizon of 30 minutes. Hypoglycemia was categorized into mild (glucose=54-70 mg/dL) and severe (glucose<54 mg/dL) levels. The validation data set of 427 patients of European-American ancestry in the United States was used to validate the models and examine their generalizations. The predictive performance of the models was evaluated according to the sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).ResultsFor the difficult-to-predict mild hypoglycemia events, the LSTM model consistently achieved AUC values greater than 97% in the primary data set, with a less than 3% AUC reduction in the validation data set, indicating that the model was robust and generalizable across populations. AUC values above 93% were also achieved when the LSTM model was applied to both type 1 and type 2 diabetes in the validation data set, further strengthening the generalizability of the model. Under different satisfactory levels of sensitivity for mild and severe hypoglycemia prediction, the LSTM model achieved higher specificity than the SVM and RF models, thereby reducing false alarms.ConclusionsOur results demonstrate that the LSTM model is robust for hypoglycemia prediction and is generalizable across populations or diabetes subtypes. Given its additional advantage of false-alarm reduction, the LSTM model is a strong candidate to be widely implemented in future CGM devices for hypoglycemia prediction.

Wave runup prediction is necessary for offshore structure designs and early warnings. Data-driven methods based on machine learning have inspired reduced-order solutions for wave–structure interaction problems. This study provides the quantification of deep learning algorithms’ potential for wave runup prediction. Two prominent deep learning models were utilized to predict the wave runups along the fore column of semisubmersible under head seas. The long short-term memory (LSTM) and the temporal convolutional networks (TCNs) were comprehensively compared based on the datasets from a model test carried out in the deep ocean basin. The LSTM and TCN model structures were optimized to compare prediction accuracy and computational complexity reasonably. The results reveal that (1) both developed TCN and LSTM models had a satisfied prediction accuracy of over 90%. Their predictions were extended to 10 s into the future with accuracies over 80% and 45%, respectively. (2) With the noise-extended datasets, the LSTM model was robust to noises, while the TCN model showed better prediction performance on the extreme wave runup events. (3) The incident wave and dominant rotation provided the major information for wave runup prediction. TCN and LSTM models’ prediction accuracies were 91.5% and 89.3% based on the simplified input tensors composed of incident wave and pitch. The comparison showed the great potential of the TCN model to predict the nonlinear wave runup with less time and memory costs. The input tensors’ design and optimization based on physical understanding also play a significant role in the prediction performance.

Ensemble-based systems are well known to have the capacity to outperform individual approaches if the ensemble members are sufficiently accurate and diverse. This paper investigates how an efficient ensemble of deep convolutional neural networks (CNNs) can be created by forcing them to adjust their parameters during the training process to increase diversity in their decisions. As a new theoretical approach to reach this aim, we join the member neural architectures via a fully connected layer and insert a new correlation penalty term in the loss function to obstruct their similar operation. With this complementary term, we implement the standard guideline of ensemble creation to increase the members’ diversity for CNNs in a more detailed and flexible way than similar existing techniques. As for applicability, we show that our approach can be efficiently used in various classification tasks. More specifically, we demonstrate its performance in challenging medical image analysis and natural image classification problems. Besides the theoretical considerations and foundations, our experimental findings suggest that the proposed technique is competitive. Namely, on the one hand, the classification rate of the ensemble trained in this way outperformed all the individual accuracies of the state-of-the-art member CNNs according to the standard error functions of these application domains. On the other hand, it is also validated that the ensemble members get more diverse and their accuracies are raised by adding the penalization term. Moreover, we performed a full comparative analysis, including other state-of-the-art ensemble-based approaches recommended for the same classification tasks. This comparative study also confirmed the superiority of our method, as it overcame the current solutions.

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.