Artificial intelligence (AI) techniques for intelligent mobile computing in healthcare has opened up new opportunities in healthcare systems. Combining AI techniques with the existing Internet of Medical Things (IoMT) will enhance the quality of care that patients receive at home remotely and the successful establishment of smart living environments. Building a real AI for mobile AI in an integrated smart hospital environment is a challenging problem due to the complexities of receiving IoT medical sensors data, data analysis, and deep learning algorithm complexity programming for mobile AI engine implementation AI-based cloud computing complexities, especially when we tackle real-time environments of AI technologies. In this paper, we propose a new mobile AI smart hospital platform architecture for stroke prediction and emergencies. In addition, this research is focused on developing and testing different modules of integrated AI software based on XAI architecture, this is for the mobile health app as an independent expert system or as connected with a simulated environment of an AI-cloud-based solution. The novelty is in the integrated architecture and results obtained in our previous works and this extended research on hybrid GMDH and LSTM deep learning models for the proposed artificial intelligence and IoMT engine for mobile health edge computing technology. Its main goal is to predict heart–stroke disease. Current research is still missing a mobile AI system for heart/brain stroke prediction during patient emergency cases. This research work implements AI algorithms for stroke prediction and diagnosis. The hybrid AI in connected health is based on a stacked CNN and group handling method (GMDH) predictive analytics model, enhanced with an LSTM deep learning module for biomedical signals prediction. The techniques developed depend on the dataset of electromyography (EMG) signals, which provides a significant source of information for the identification of normal and abnormal motions in a stroke scenario. The resulting artificial intelligence mHealth app is an innovation beyond the state of the art and the proposed techniques achieve high accuracy as stacked CNN reaches almost 98% for stroke diagnosis. The GMDH neural network proves to be a good technique for monitoring the EMG signal of the same patient case with an average accuracy of 98.60% to an average of 96.68% of the signal prediction. Moreover, extending the GMDH model and a hybrid LSTM with dense layers deep learning model has improved significantly the prediction results that reach an average of 99%.

Post-translational glycosylation and glycation are common types of protein post-translational modifications (PTMs) in which glycan binds to protein enzymatically or nonenzymatically, respectively. They are associated with various diseases such as coronavirus, Alzheimer’s, cancer, and diabetes diseases. Identifying glycosylation and glycation sites is significant to understanding their biological mechanisms. However, utilizing experimental laboratory tools to identify PTM sites is time-consuming and costly. In contrast, computational methods based on machine learning are becoming increasingly essential for PTM site prediction due to their higher performance and lower cost. In recent years, advances in Transformer-based Language Models based on deep learning have been transferred from Natural Language Processing (NLP) into the proteomics field by developing language models for protein sequence representation known as Protein Language Models (PLMs). In this work, we proposed a novel method, PTG-PLM, for improving the performance of PTM glycosylation and glycation site prediction. PTG-PLM is based on convolutional neural networks (CNNs) and embedding extracted from six recent PLMs including ProtBert-BFD, ProtBert, ProtAlbert, ProtXlnet, ESM-1b, and TAPE. The model is trained and evaluated on two public datasets for glycosylation and glycation site prediction. The results show that PTG-PLM based on ESM-1b and ProtBert-BFD has better performance than PTG-PLM based on the other PLMs. Comparison results with the existing tools and representative supervised learning methods show that PTG-PLM surpasses the other models for glycosylation and glycation site prediction. The outstanding performance results of PTG-PLM indicate that it can be used to predict the sites of the other types of PTMs.

One of the significant aspects of our digital world is that data are literally everywhere, and it is increasing. On the other hand, the number of cyberattacks aiming to seize this data and use it illegally is increasing at an exponential rate, and this is the challenge. Therefore, intrusion detection systems (IDS) have attracted considerable interest from researchers and industries. In this regard, machine learning (ML) techniques are playing a pivotal role as they put the responsibility of analyzing enormous amounts of data, finding patterns, classifying intrusions, and solving issues on computers instead of humans. This paper implements two separate classification layers of ML-based algorithms with the recently published NF-UQ-NIDS-v2 dataset, preprocessing two volumes of sample records (100 k and 10 million), utilizing MinMaxScaler, LabelEncoder, selecting superlative features by recursive feature elimination, normalizing the data, and optimizing hyper-parameters for classical algorithms and neural networks. With a small dataset volume, the results of the classical algorithms layer show high detection accuracy rates for support vector (98.26%), decision tree (98.78%), random forest (99.07%), K-nearest neighbors (98.16%), CatBoost (99.04%), and gradient boosting (98.80%). In addition, the layer of neural network algorithms has proven to be a very powerful technology when using deep learning, particularly due to its unique ability to effectively handle enormous amounts of data and detect hidden correlations and patterns; it showed high detection results, which were (98.87%) for long short-term memory and (98.56%) for convolutional neural networks.

The proliferation of Internet of Things (IoT) devices has become inevitable in contemporary life, significantly affecting myriad applications. Nevertheless, the pervasive use of heterogeneous IoT gadgets introduces vulnerabilities to malicious cyber-attacks, resulting in data breaches that jeopardize the network’s integrity and resilience. This study proposes an Intrusion Detection System (IDS) for IoT environments that leverages Transfer Learning (TL) and the Convolutional Block Attention Module (CBAM). We extensively evaluate four prominent pre-trained models, each integrated with an independent CBAM at the uppermost layer. Our methodology is validated using the BoT-IoT dataset, which undergoes preprocessing to rectify the imbalanced data distribution, eliminate redundancy, and reduce dimensionality. Subsequently, the tabular dataset is transformed into RGB images to enhance the interpretation of complex patterns. Our evaluation results demonstrate that integrating TL models with the CBAM significantly improves classification accuracy and reduces false-positive rates. Additionally, to further enhance the system performance, we employ an Ensemble Learning (EL) technique to aggregate predictions from the two best-performing models. The final findings prove that our TL-CBAM-EL model achieves superior performance, attaining an accuracy of 99.93% as well as high recall, precision, and F1-score. Henceforth, the proposed IDS is a robust and efficient solution for securing IoT networks.

Humans are distinguished by their walking patterns; many approaches, including using various types of sensors, have been used to establish walking patterns as biometrics. By studying the distinguishing features of a person's footsteps, footstep recognition may be utilized in numerous security applications, such as managing access in protected locations or giving an additional layer of biometric verification for secure admittance into restricted regions. We proposed biometric systems for verifying and identifying a person by acquiring spatial foot pressure images from the values obtained from the piezoelectric sensors using the Swansea Foot Biometric Database, which contains 19,980 footstep signals from 127 users and is the most prominent open-source gait database available for footstep recognition. The images acquired are fed into the ConvNeXt model, which was trained using the transfer learning technique, using 16 stride footstep signals in each batch with an Adam optimizer and a learning rate of 0.0001, and using sparse categorical cross-entropy as the loss function. The proposed ConvNeXt model has been adjusted to acquire 512 feature vectors per image, and these feature vectors are used to train the logistic regression models. We propose two biometric systems. The first biometric system is based on training one logistic regression model as a classifier to identify 40 different users using 1600 signals for training, 6697 signals for validation, and 200 signals for evaluation. The second biometric system is based on training 40 logistic regression models, one for each user, to validate the user's authenticity, with a total number of 2363 training signals, 7077 validation signals, and 500 evaluation signals. Each of the 40 models has a 40-training signal per client and a different number of signals per imposter, a different number of signals for the validation that ranges between 8 and 650 signals, a 5-signal for an authenticated client, and a different number of signals per imposter for evaluation. Independent validation and evaluation sets are used to evaluate our systems. In the biometric identification system, we obtained an equal error rate of 15.30% and 21.72% for the validation and evaluation sets, while in the biometric verification system, we obtained an equal error rate of 6.97% and 10.25% for the validation and evaluation sets.