The accurate prediction of cryptocurrency prices is crucial due to the volatility and complexity of digital asset markets, which pose significant challenges to traders, investors, and researchers. This research addresses these challenges by leveraging machine learning and deep learning techniques to forecast closing prices for cryptocurrencies, focusing on Bitcoin, Ethereum, Binance Coin, and Litecoin cryptocurrency datasets. A Random Forest ensemble learning algorithm, a Gradient Boosting model, and a feedforward neural network were implemented to handle the complexities in cryptocurrency data. A Z-Score-based anomaly detection framework was integrated to classify closing prices as normal or abnormal, aiding in identifying significant market events. Evaluation metrics, such as the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²), demonstrate the superior precision and reliability of the Random Forest and Gradient Boosting models. The deep learning model indicates strong generalization capabilities, suggesting potential advantages on more complex datasets. These findings highlight the importance of combining advanced machine learning techniques and cryptocurrencies to develop a robust framework for cryptocurrency forecasting and anomaly detection.

Cardiac arrhythmias are irregular heart rhythms that, if undetected, can lead to severe cardiovascular conditions. Detecting these anomalies early through electrocardiogram (ECG) signal analysis is critical for preventive healthcare and effective treatment. However, the automatic classification of arrhythmias poses significant challenges, including class imbalance and noise interference in ECG signals. This paper introduces the Multi-Scale Convolutional LSTM Dense Network (MS-CLDNet) model, an advanced deep-learning model specifically designed to address these issues and improve arrhythmia classification accuracy and other relevant metrics. This paper aims to develop an efficient deep-learning model, MS-CLDNet, for accurately classifying cardiac arrhythmias from electrocardiogram (ECG) signals. Addressing challenges like class imbalance and noise interference, the model integrates bidirectional long short-term memory (LSTM) networks for temporal pattern recognition, Dense Blocks for feature refinement, and Multi-Scale Convolutional Neural Networks (CNNs) for robust feature extraction. To achieve accurate classification of different types of arrhythmias, the Classification Head refines these extracted features even further. Utilizing the MIT-BIH arrhythmia dataset, key pre-processing techniques such as wavelet-based denoising were employed to enhance signal clarity. Results indicate that the MS-CLDNet model achieves a classification accuracy of 98.22 %, outperforming baseline models with low average loss values (0.084). This research highlights how crucial it is to combine sophisticated neural network architectures with efficient pre-processing techniques to improve the precision and accuracy of automated cardiovascular diagnostic systems, which could have important healthcare applications for early and accurate arrhythmia detection.

Background: Alzheimer’s is a disease in the human brain characterized by gradual memory loss, confusion, and alterations in behavior. It is a complex and continuously degenerative disorder of the nervous system, which still has early detection and diagnosis as challenges to overcome. The disease causes significant damage in individuals suffering from the disorder as they progressively lose cognitive ability. Its diagnosis and management depend primarily on the ability to diagnose early to initiate proper intervention. Unfortunately, this remains a difficult feat, given the resemblance of early signs of the disease with symptoms associated with normal aging and other disorders involving cognition. While clinical tests have their limitations, brain imaging such as MRI can provide detailed insights into changes in the brain. Deep learning techniques, mainly when applied to MRI data, have proven helpful in the early detection of Alzheimer’s Disease.Methods: In the proposed study, a lightweight, self-attention-based vision transformer (ViT) is employed to predict Alzheimer’s disease using MRI images from the OASIS-3 dataset. Data pre-processing and augmentation techniques have been added to strengthen the model’s generalization ability and enhance model performance, which is visualized using Grad-Cam.Results: The proposed model achieves exceptional results with an accuracy of 98.57%, approximate precision of 98.7%, Recall of about 98.47%, and specificity of 98.67%. It also achieves a Kappa Score of 97.2% and an AUC ROC Score of 99%.Conclusion: This paper, along with comprehensive data pre-processing and augmentation, represents one of the major steps toward achieving more robust and clinically applicable models for Alzheimer’s disease prediction. The proposed study indicates that deep learning models have the potential to enhance the diagnosis of Alzheimer’s disease. By integrating Deep learning techniques with careful data processing, more reliable early detection models can be developed, which in turn leads to better treatment outcomes.

Road safety is a critical concern, as accidents happen globally. Despite efforts to enhance roads and enforce stricter driving rules, the number of accidents remains high. These issues arise from distracted driving, speeding, and driving under the influence. In the United States, fatal accidents increased by 16% from 2018 to 2022. The number of deaths rose from 36,835 in 2018 to 42,795 in 2022. This trend reveals a critical need for new solutions to reduce traffic incidents and improve road safety. Machine learning (ML) can help make roads safer and reduce traffic-related deaths. This paper presents an ML-based real-time highway traffic incident forecasting system named “VehiCast”. VehiCast utilizes vehicular ad hoc networks (VANETs) and federated learning (FL) to collect real-time traffic data, such as average delay, average speed, and the total number of vehicles across several highway zones, to enhance traffic incident prediction accuracy in real-time. Our extensive experimental results showcase that VehiCast reaches an impressive prediction accuracy of 91%, highlighting the power of innovation and determination.

The demand for contactless biometric authentication has significantly increased during the COVID-19 pandemic and beyond to prevent the spread of Coronavirus. The global pandemic unexpectedly affords a greater opportunity for contactless authentication, but iris and facial recognition biometrics have many usability, security, and privacy challenges, including mask-wearing and presentation attacks (PAs). Mainly, liveness detection against spoofing is notably a challenging task as various biometric authentication methods cannot efficiently assess the real user’s physical presence in unsupervised environments. Although several face anti-spoofing methods have been proposed using add-on sensors, dynamic facial texture features, and 3-D mapping, most of them require expensive sensors and substantial computational resources, or fail to detect sophisticated 3-D face spoofing. This article presents a software-based facial liveness detection method named Apple in My Eyes (AIME). AIME is intended to detect the liveness against spoofing for mobile device security using challenge-response testing. AIME generates various screen patterns as authentication challenges, then passively detects corneal-specular reflection responses from human eyes using a frontal camera and analyzes the detected reflections using lightweight machine learning techniques. AIME system components include challenge and pattern detection, feature extraction and classification, and data augmentation and training. We have implemented AIME as a cross-platform application compatible with Android, iOS, and the Web. Our comprehensive experimental results reveal that AIME detects liveness with high accuracy at around 200-ms against different types of sophisticated PAs. AIME can also efficiently detect liveness in multiple contactless biometric authentications without any costly extra sensors nor involving users’ active responses.