IMPROVING THE EXPLAINABILITY AND TRANSPARENCY OF DEEP LEARNING MODELS IN INTRUSION DETECTION SYSTEMS

Electrocardiogram signal analysis can be time-consuming, tedious, and error-prone. Therefore, automated analysis is need of time that will assist clinicians in detecting cardiac abnormalities accurately and efficiently. Recently, deep learning models have shown unprecedented progress and strong arrhythmia classification capabilities, but their deployment in the medical sector is constrained due to their “black-box” nature. This paper proposes a robust explainability method to assist in explaining the underlying decision-making process in deep neural networks (DNN) and help provide feedback on biases that would benefit in improving DNN models. To achieve these objectives, initially, a deep learning model is trained on the MIT-BIH Arrhythmia Database and their classification performance is evaluated. The classification findings are then interpreted using the post-hoc explanation methods such as the SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME) and Gradient-weighted Class Activation Mapping (Grad-CAM) that interpret the decision rationale. As these methods are initially proposed for image applications therefore a new masking approach is proposed to cater these post-hoc explainability methods for ECG time-series data. After evaluating these methods for ECG arrhythmia classification, several drawbacks are drawn such as they fail to locate a feature’s importance if there are multiple occurrences of the same feature in a signal and also, SHAP and LIME perform random perturbations that sometimes produce unreliable explanations. Therefore, to overcome the drawbacks associated with these post-hoc explainability methods on time-series data, a novel K-GradCam method is proposed. The proposed K-GradCam method ensemble the benefits of these gradient based and perturbation based approaches and has demonstrated advantages over SHAP, Grad-CAM and LIME in terms of interpreting the models’ decisions. To compare the the proposed technique with post-hoc explainability methods quantitatively, the confidence index of the proposed method is evaluated using dice loss. The proposed method shares 71% similarity with SHAP and 81% similarity with Grad-CAM methods; however, it shares the benefits of both methods and is computationally faster than SHAP and LIME.

ObjectiveAsthma, a chronic respiratory condition characterized by airway inflammation and constriction, affects millions of individuals worldwide, resulting in high healthcare expenses and a lower quality of life. Early prediction and control of asthma risk are critical for avoiding exacerbations and improving outcomes.MethodsIn this study, we describe a comprehensive asthma prediction model that uses machine learning and deep learning techniques to estimate asthma risk based on a variety of health and environmental parameters. Recursive feature elimination and Extra Trees Classifier were used to choose features, and the synthetic minority over-sampling approach was used to balance the dataset to overcome class imbalance. Hyperparameter tuning was used to optimize performance for 12 machine learning models such as extreme gradient boosting, Random Forest, and support vector machine as well as deep learning models, including multilayer perceptrons, convolutional neural networks, recurrent neural network, and artificial neural network.ResultsAfter hyperparameter adjustment, ensemble approaches that used both hard and soft voting were evaluated. When hyperparameter adjustment was used, the soft voting ensemble that combined XGBoost and CatBoost achieved the highest accuracy (93.61%). Shapley additive explanations and local interpretable model-agnostic explanations were employed to make predictions interpretable, providing information on feature contributions and boosting clinician confidence. A Flask server and web interface were also deployed, enabling real-time user interaction where patients and medical professionals could enter data and obtain asthma risk estimations immediately.ConclusionsThis study presents an accurate and explainable asthma risk prediction framework using ensemble machine and deep learning models, achieving 93.61% accuracy with real-time clinical applicability.

The adoption of wind energy has grown significantly in recent years. New, cost-effective technologies have been developed, led by customer awareness of green technologies and a legal framework proposed at the European Union level. The stochastic nature of wind speed is transferred to wind turbine output, making wind energy difficult to predict. The main scope of predicting wind energy production is to be proactive in balancing and reserving energy to meet demand. When the prediction identifies a potential gap between supply and demand, additional energy from other sources must be generated and supplied. Creating a synergy of physical devices through advanced sensing capabilities, software, storage and analytics capabilities, the Industrial Internet of Things is enabling the effective transition to wind energy through automation by removing many of the disadvantages in a way that has recently become accessible. This research focuses on the data analytics, proposing a fast univariate network-based approach for wind energy prediction, using Feed Forward Neural Networks, Recurrent Neural Networks, Long-Short Term Memory, Gated Recurrent Unit, and Convolutional Neural Networks. Moreover, by introducing the theoretical fundamentals, the implementation method and the hyperparameters of the final models, this article becomes unique in the context of wind energy. At the time of this study, no prior research studies have presented a direct comparison between feedforward, recurrent, and convolutional neural networks ? these being the most important in the field of supervised learning.

This study presents the development of a realistic and comprehensive SDN-ATK dataset designed to evaluate the effectiveness of machine learning (ML) and deep learning (DL) approaches for attack detection in Software-Defined Networking (SDN) environments. Unlike existing datasets, SDN-ATK explicitly includes attacks targeting key SDN components such as SDN controllers and OpenFlow switches, addressing a critical gap in current research. We evaluated three ML (XGBoost, Random Forest, and Decision Tree) and three DL (Convolutional Neural Network (CNN), Feed-forward Neural Network (FNN), and Long Short-Term Memory (LSTM)) algorithms across binary and multiclass classification tasks to assess detection performance. Our results demonstrate that DL models, particularly FNN and CNN outperform ML counterparts, achieving 98–99% accuracy, precision, and recall in binary classification. Explainability analyses were conducted using SHAP (SHapley Additive explanations) on the XGBoost model, offering valuable insights into the importance of feature and improving transparency in ML-based attack detection. The study’s findings provide critical guidance for both academia and industry, highlighting that within our Ryu-based SDN testbed, DL models demonstrated more reliable and balanced performance for large-scale attack detection. This work lays a solid foundation for future research, including developing real-time, intelligent, and explainable intrusion detection systems for SDN environments.

Internet of Things (IoT) technology has been incorporated into the majority of people’s everyday lives and places of employment due to the quick development in information technology. Modern agricultural techniques increasingly use the well-known and superior approach of managing a farm known as “smart farming”. Utilizing a variety of information and agricultural technologies, crops are observed for their general health and productivity. This requires monitoring the condition of field crops and looking at many other indicators. The goal of smart agriculture is to reduce the amount of money spent on agricultural inputs while keeping the quality of the final product constant. The Internet of Things (IoT) has made smart agriculture possible through data collection and storage techniques. For example, modern irrigation systems use effective sensor networks to collect field data for the best plant irrigation. Smart agriculture will become more susceptible to cyber-attacks as its reliance on the IoT ecosystem grows, because IoT networks have a large number of nodes but limited resources, which makes security a difficult issue. Hence, it is crucial to have an intrusion detection system (IDS) that can address such challenges. In this manuscript, an IoT-based privacy-preserving anomaly detection model for smart agriculture has been proposed. The motivation behind this work is twofold. Firstly, ensuring data privacy in IoT-based agriculture is of the utmost importance due to the large volumes of sensitive information collected by IoT devices, including on environmental conditions, crop health, and resource utilization data. Secondly, the timely detection of anomalies in smart agriculture systems is critical to enable proactive interventions, such as preventing crop damage, optimizing resource allocation, and ensuring sustainable farming practices. In this paper, we propose a privacy-encoding-based enhanced deep learning framework for the difficulty of data encryption and intrusion detection. In terms of data encoding, a novel method of a sparse capsule-auto encoder (SCAE) is proposed along with feature selection, feature mapping, and feature normalization. An SCAE is used to convert information into a new encrypted format in order to prevent deduction attacks. An attention-based gated recurrent unit neural network model is proposed to detect the intrusion. An AGRU is an advanced version of a GRU which is enhanced by an attention mechanism. In the results section, the proposed model is compared with existing deep learning models using two public datasets. Parameters such as recall, precision, accuracy, and F1-score are considered. The proposed model has accuracy, recall, precision, and F1-score of 99.9%, 99.7%, 99.9%, and 99.8%, respectively. The proposed method is compared using a variety of machine learning techniques such as the deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), and long short-term memory (LSTM).

As 5G and beyond networks grow in heterogeneity, complexity, and scale, traditional Intrusion Detection Systems (IDS) struggle to maintain accurate and precise detection mechanisms. A promising alternative approach to this problem has involved the use of Deep Learning (DL) techniques; however, DL-based IDS suffer from issues relating to interpretation, performance variability, and high computational overheads. These issues limit their practical deployment in real-world applications. In this study, CiNeT is introduced as a novel DL-based IDS employing Convolutional Neural Networks (CNN) within a bijective encoding–decoding framework between network traffic features (such as IPv6, IPv4, Timestamp, MAC addresses, and network data) and their RGB representations. This transformation facilitates our DL IDS in detecting spatial patterns without sacrificing fidelity. The bijective pipeline enables complete traceability from detection decisions to their corresponding network traffic features, enabling a significant initiative towards solving the ‘black-box’ problem inherent in Deep Learning models, thus facilitating digital forensics. Finally, the DL IDS has been evaluated on three datasets, UNSW NB-15, InSDN, and ToN_IoT, with analysis conducted on accuracy, GPU usage, memory utilisation, training, testing, and validation time. To summarise, this study presents a new CNN-based IDS with an end-to-end pipeline between network traffic data and their RGB representation, which offers high performance and enhanced interpretability through revisable transformation.

This study investigates the use of deep learning algorithms to predict the discharge coefficient (Cd) of contaminated multi-hole orifice flow meters with circular opening. Datasets (MHO1 and MHO2) were obtained from computational fluid dynamic simulations for two circular multi-hole orifice flow meters of different geometries. To evaluate the performance and generalization capabilities of different models, three distinct scenarios, each involving different dataset configurations and normalization techniques were designed. For each scenario, three deep learning models (feedforward neural networks, convolutional neural network, and recurrent neural network) were implemented and evaluated based on their performance metrics, including mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2). For all three scenarios eight models for each neural network model were developed (FFNN – four models, CNN – two models, RNN – two models). The same structure of models was used across all scenarios to ensure consistency in the evaluation process. Key input parameters include geometrical and flow variables such as β – parameter, contamination thickness, radial distance, Reynolds number, and orifice diameters. Results demonstrate the effectiveness of deep learning in accurately predicting discharge coefficient for different contamination conditions and different geometries. This study showed that deep learning models can be used for prediction of discharge coefficients for multi-hole orifice flow meters of similar geometry, based on data obtained from one orifice flow meter for different contamination parameters.

1 - Congruence of deep learning in biomedical engineering: future prospects and challenges

Deep learning (also known as deep structured learning, hierarchical learning, or deep machine learning) is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Deep learning has been characterized as a class of machine learning algorithms with the following characteristics [257]: • They use a cascade of many layers of nonlinear processing units for feature extraction and transformation. Each successive layer uses the output from the previous layer as input. The algorithms may be supervised or unsupervised and applications include pattern analysis (unsupervised) and classification (supervised). • They are based on the (unsupervised) learning of multiple levels of features or representations of the data. Higher-level features are derived from lower-level features to form a hierarchical representation. • They are part of the broader machine learning field of learning representations of data. • They learn multiple levels of representations that correspond to different levels of abstraction; the levels form a hierarchy of concepts. These definitions have in common: multiple layers of nonlinear processing units and the supervised or unsupervised learning of feature representations in each layer, with the layers forming a hierarchy from low-level to high-level features. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks (DBN), and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition, and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. In this chapter we start in Section 7.1 with an introduction, giving a brief history of this field, the relevant literature, and its applications. Then we study some basic concepts of deep learning such as convolutional neural networks, recurrent neural networks, backpropagation algorithm, restricted Boltzmann machines, and deep learning networks in Section 7.2. Then we illustrate three examples for Apache Spark implementation for mobile big data (MBD), user moving pattern extraction, and combination with nonparametric Bayesian learning, respectively, in Sections 7.3 through 7.5. Finally, we have summary in Section 7.6.

Attacks on networks are currently the most pressing issue confronting modern society. Network risks affect all networks, from small to large. An intrusion detection system must be present for detecting and mitigating hostile attacks inside networks. Machine Learning and Deep Learning are currently used in several sectors, particularly the security of information, to design efficient intrusion detection systems. These systems can quickly and accurately identify threats. However, because malicious threats emerge and evolve regularly, networks need an advanced security solution. Hence, building an intrusion detection system that is both effective and intelligent is one of the most cognizant research issues. There are several public datasets available for research on intrusion detection. Because of the complexity of attacks and the continually evolving detection of an attack method, publicly available intrusion databases must be updated frequently. A convolutional recurrent neural network is employed in this study to construct a deep-learning-based hybrid intrusion detection system that detects attacks over a network. To boost the efficiency of the intrusion detection system and predictability, the convolutional neural network performs the convolution to collect local features, while a deep-layered recurrent neural network extracts the features in the proposed Hybrid Deep-Learning-Based Network Intrusion Detection System (HDLNIDS). Experiments are conducted using publicly accessible benchmark CICIDS-2018 data, to determine the effectiveness of the proposed system. The findings of the research demonstrate that the proposed HDLNIDS outperforms current intrusion detection approaches with an average accuracy of 98.90% in detecting malicious attacks.

Intrusion Detection Systems (IDS) are crucial for maintaining the security and integrity of network infrastructures. This review paper comprehensively examines the evolution and advancements in IDS technologies, focusing on both traditional methods and contemporary machine learning and deep learning approaches. Traditional IDS methods, including signature-based and anomaly-based detection, laid the groundwork for current systems but faced challenges such as high false-positive rates and limited adaptability. Recent advancements in machine learning, specifically supervised and unsupervised learning algorithms, have significantly enhanced the accuracy and efficiency of IDS. Deep learning techniques, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), offer promising solutions for complex and high-volume network traffic analysis. This review also explores federated learning for IDS, emphasizing its potential for data privacy preservation and reduced computational load. Furthermore, hybrid models combining various algorithms are discussed for their capability to leverage the strengths of multiple techniques. The paper synthesizes current research, highlighting key methodologies, datasets, evaluation metrics, and the future direction of IDS research. By providing a thorough analysis of existing literature and identifying gaps, this review aims to guide future research efforts and practical implementations in the field of network security.

Personalized medicine represents a paradigm shift in healthcare, aiming to tailor treatment strategies to the unique genetic, environmental, and lifestyle characteristics of individual patients. This approach holds immense potential for improving therapeutic efficacy and minimizing adverse drug reactions. With the rapid advancement of artificial intelligence, deep learning has emerged as a transformative tool in pharmacology, enabling precise modeling of complex biological data and uncovering hidden patterns in patient-specific information. This study investigates the application of deep learning techniques - such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Transformer architectures, and Generative Adversarial Networks (GANs) - in optimizing personalized treatment strategies. Using a diverse dataset comprising electronic health records (EHRs), genomic sequences, and clinical indicators, we developed and trained deep learning models for tasks including drug response prediction, biomarker identification, and adverse drug reaction (ADR) forecasting. Among the models evaluated, Transformer-based architectures demonstrated superior performance, achieving an accuracy of 91.2% and an AUC-ROC of 0.92 in drug response prediction tasks. Moreover, the integration of deep learning models into the treatment pipeline resulted in a 20-30% improvement in drug-patient matching efficiency compared to traditional statistical methods. The findings underscore the potential of AI-powered systems to enhance clinical decision-making and enable precision pharmacotherapy. However, challenges such as data privacy, model interpretability, and regulatory compliance remain critical barriers to widespread adoption. The study also explores future directions, including the implementation of explainable AI (XAI) and federated learning, to address these limitations and facilitate the integration of deep learning into routine clinical practice.

Analysis of electrocardiograms (ECG) is vital to identify cardiological problems; however, traditional interpretation requires a lot of clinical knowledge and is influenced by inter-observer variability. In order to solve these problems, this research presents an interpretable deep learning framework that fuses Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an Attention mechanism for multi-label ECG classification. In addition to employing the PTB-XL dataset, the system commits to clinical trust by integrating explainability methods SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations) to enhance transparency.The model reaches a macro F1-score of 0.369 and an ROC-AUC of 0.919, reflecting its high capability of simultaneous multi-class identification of different cardiac diseases. The SHAP Attention superposition helps in providing easy-to-understand explanations, which enable the doctor to see the time-related and shape-related factors of the ECG waveform.This paper focuses on the importance of combining accuracy with explanation in AI healthcare systems and provides a robust, transparent method for computer-assisted cardiac diagnosis.

Deep learning (DL) has shown explosive growth in its application to bioinformatics and has demonstrated thrillingly promising power to mine the complex relationship hidden in large-scale biological and biomedical data. A number of comprehensive reviews have been published on such applications, ranging from high-level reviews with future perspectives to those mainly serving as tutorials. These reviews have provided an excellent introduction to and guideline for applications of DL in bioinformatics, covering multiple types of machine learning (ML) problems, different DL architectures, and ranges of biological/biomedical problems. However, most of these reviews have focused on previous research, whereas current trends in the principled DL field and perspectives on their future developments and potential new applications to biology and biomedicine are still scarce. We will focus on modern DL, the ongoing trends and future directions of the principled DL field, and postulate new and major applications in bioinformatics.

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.