Deep Learning Architecture Research Articles

Role of Machine and Deep Learning Algorithms in Secure Intrusion Detection Systems (IDS) for IOT & Smart Cities

In this study the authors have examines various machine learning algorithms that could be used in IDS for making secure IoT and Smart Cities. The study examines various deep learning architectures of supervised, unsupervised, and semi-supervised learning methods to improve security and resource usage. Federated learning, edge computing, explainable AI, adversarial machine learning defense, and transfer learning are also explored for smart farming and IoT challenges. Machine learning has the potential to improve security and agricultural sustainability, but it must be researched and developed.

Multimodal Biometric Authentication System for Military Weapon Access: Face and ECG Authentication

Unimodal or Single factor biometric systems refer to biometric systems that employ only one form of biometric data to authenticate an individual’s identity. These kinds of biometrics are susceptible to higher error rates and security vulnerabilities because it relays on a single trait for authentication. To overcome this, multimodal biometrics method is proposed. Multi-modal biometric system can authenticate more than once and some advantages include; highaccuracy, low error rate, and large population coverage. These biometrics systems increase integrity and privacy since it will contain several biometric features of every customer. So, here designed a multimodal biometrics project utilizing deep learning to enhance authentication security by combining face and Electrocardiogram(ECG) signals. VGG-16 model, a deep learning architecture used to capture complex patterns in accurate individual identification with both ECG and Facial data. The high-resolution convolutional filters capture the intricate details of the face and ECG waveform, ensuring high accuracy in distinguishing different individuals.

Tutorial on Molecular Latent Space Simulators (LSSs): Spatially and Temporally Continuous Data-Driven Surrogate Dynamical Models of Molecular Systems.

The inherently serial nature and requirement for short integration time steps in the numerical integration of molecular dynamics (MD) calculations place strong limitations on the accessible simulation time scales and statistical uncertainties in sampling slowly relaxing dynamical modes and rare events. Molecular latent space simulators (LSSs) are a data-driven approach to learning a surrogate dynamical model of the molecular system from modest MD training trajectories that can generate synthetic trajectories at a fraction of the computational cost. The training data may comprise single long trajectories or multiple short, discontinuous trajectories collected over, for example, distributed computing resources. Provided the training data provide sufficient sampling of the relevant thermodynamic states and dynamical transitions to robustly learn the underlying microscopic propagator, an LSS furnishes a global model of the dynamics capable of producing temporally and spatially continuous molecular trajectories. Trained LSS models have produced simulation trajectories at up to 6 orders of magnitude lower cost than standard MD to enable dense sampling of molecular phase space and large reduction of the statistical errors in structural, thermodynamic, and kinetic observables. The LSS employs three deep learning architectures to solve three independent learning problems over the training data: (i) an encoding of the high-dimensional MD into a low-dimensional slow latent space using state-free reversible VAMPnets (SRVs), (ii) a propagator of the microscopic dynamics within the low-dimensional latent space using mixture density networks (MDNs), and (iii) a generative decoding of the low-dimensional latent coordinates back to the original high-dimensional molecular configuration space using conditional Wasserstein generative adversarial networks (cWGANs) or denoising diffusion probability models (DDPMs). In this software tutorial, we introduce the mathematical and numerical background and theory of LSS and present example applications of a user-friendly Python package software implementation to alanine dipeptide and a 28-residue beta-beta-alpha (BBA) protein within simple Google Colab notebooks.

Burned Area Detection with Sentinel-2A Data: Using Deep Learning Techniques with eXplainable Artificial Intelligence

Abstract. Annually, a considerable quantity of forest is burned on a global scale. Therefore, it is essential to obtain precise and fast information regarding the size of burned regions in order to effectively monitor the adverse consequences of wildfires. The objective of this investigation is to indicate the effectiveness and usefulness of a deep learning (DL) architecture, such as Convolutional Neural Networks (CNNs), in the mapping of areas affected by fire, employing an eXplainable artificial intelligence (XAI) algorithm known as SHapley Additive exPlanations (SHAP) with accuracy evaluation criteria. Furthermore, this paper presents the evaluation of the Çanakkale-Kizilkeçili village wildfire. The research investigated the impacts of a variety of spectral indices, including the normalized burn index (NBR), differentiated normalized burn index (dNBR), Green-Red Vegetation Index (GRVI), simple ratio vegetation index (RVI), and normalized difference vegetation index (NDVI). At the end of the training process, the model achieved a training accuracy of approximately 0.99, with model loss values converging to approximately 0.1. The findings of the burned area identification analysis indicate that by incorporating spectral indices as supplementary information, the CNN model achieved a high level of accuracy, with an overall accuracy of 98.88% and a Kappa Coefficient of 0.98. Additionally, the SHAP technique was employed to gain insights into the output of the models. The feature importances of the spectral bands were determined through the SHAP analysis of the CNN model. Hence, the significance of the auxiliary data generated by the NBR, dNBR, and NDVI indices was identified as being the highest among the original bands and auxiliary data employed in this investigation.

Abstract A010: Biofluid-Ensemble Analysis through Multi-modal Spectroscopy (BEAMS): A deep learning architecture for rapid early-stage liquid biopsy cancer diagnostics

Abstract Introduction: Head and neck cancer (HNC) is one of the most common cancer types globally without an accessible rapid screening method. Conventional screening occurs at the clinician’s office, where grading and staging of the tumors are physically performed, and the clinician’s preliminary diagnosis is usually confirmed through laborious procedures of histology and CT/PET/MR scans. Patient’s quality of life and expected outcomes can be improved through early-stage screening, yet there is no existing technology on the market that tackles this dire need. As such, we propose a rapid liquid biopsy diagnostic platform empowered by deep learning algorithms that makes early-stage non-invasive screening possible. The platform utilizes the complementary vibrational spectral biomarkers information from Fourier Transform Infrared Spectroscopy (FTIR) and Raman spectroscopy. We coupled the techniques with two biofluids: saliva and plasma, which offered information on circulating and localized metabolites. Materials and Methods: The patient’s biofluid is first drop-casted on top of a substrate and air-dried at room temperature. Using an FTIR microscope or a Raman microscope, 25 spot measurements are made in a 5 by 5 grid pattern to produce a comprehensive scan of the sample. The measured spectra are subsequently fed into the deep learning framework to perform classification. The deep machine learning framework is composed of spectrum and subject-level models. Specifically, the spectrum-level model employs cascading convolutional layers to identify the prominent features within the spectrum. This is followed by a sequence of linear layers that further extract features from the convolutional layers and carry out binary classification. For each patient, preliminary classification results of the spectral level model are then evaluated on a per- modality basis across our four modalities (FTIR/Raman measurements made on saliva/plasma) where the patient is classified as positive if any of the modality models deem it so. This framework is applied to a cohort of 96 patients, with 36 non-cancerous patients, 28 early-stage patients, and 32 late-stage patients. Results and Discussion: Our model optimized for general cancer detection has a sensitivity of 91.7%, specificity of 77.8%, and accuracy of 86.5%. Late- stage cancer has proven to be less challenging to detect since our model optimized for late-stage cancer diagnosis has a sensitivity of 93.8%, a specificity of 83.3%, and an accuracy of 88.2%. Our best early-stage model has a sensitivity of 89.3%, a specificity of 69.4%, and an accuracy of 78.1%. Conclusions: Our proposed framework has demonstrated promising capability as the preliminary screening method for high-risk patients (e.g. tobacco users) while providing further interpretability of the deep learning model that is often characterized as a “black box”. The modular nature of our model structure offers substantial flexibility, enabling effective performance even when specific biofluids or spectroscopy modalities are unavailable. Citation Format: Kwan Lun Chiu, Antonio Guillen-Perez, Rebecca Mayer, Wesley Viner, Hanna Koster, Matthew Benson, Jeremy Rowe, Maria Navas-Moreno, Andrew Birkeland, Maria-Dolores Cano, J. Sebastián Gomez-Diaz, Randy Carney. Biofluid-Ensemble Analysis through Multi-modal Spectroscopy (BEAMS): A deep learning architecture for rapid early-stage liquid biopsy cancer diagnostics [abstract]. In: Proceedings of the AACR Special Conference: Liquid Biopsy: From Discovery to Clinical Implementation; 2024 Nov 13-16; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(21_Suppl):Abstract nr A010.

Dual-encoder architecture for metal artifact reduction for kV-cone-beam CT images in head and neck cancer radiotherapy.

During a radiotherapy(RT) course, geometrical variations of target volumes, organs at risk, weight changes (loss/gain), tumor regression and/or progression can significantly affect the treatment outcome. Adaptive RT has become the effective methods along with technical advancements in imaging modalities including cone-beam computed tomography (CBCT). Planning CT (pCT) can be modified via deformable image registration (DIR), which is applied to the pair of pCT and CBCT. However, the artifact existed in both pCT and CBCT is a vulnerable factor in DIR. The dose calculation on CBCT is also suggested. Missing information due to the artifacts hinders the accurate dose calculation on CBCT. In this study, we aim to develop a deep learning-based metal artifact reduction(MAR) model to reduce the metal artifacts in CBCT for head and neck cancer RT. To train the proposed MAR model, we synthesized the kV-CBCT images including metallic implants, with and without metal artifacts (simulated image data pairs) through sinogram image handling process. We propose the deep learning architecture which focuses on both artifact removal and reconstruction of anatomic structure using a dual-encoder architecture. We designed four single-encoder models and three dual-encoder models based on UNet (for an artifact removal) and FusionNet (for a tissue restoration). Each single-encoder model contains either UNet or FusionNet, while the dual-encoder models have both UNet and FusionNet architectures. In the dual-encoder models, we implemented different feature fusion methods, including simple addition, spatial attention, and spatial/channel wise attention. Among the models, a dual-encoder model with spatial/channel wise attention showed the highest scores in terms of peak signal-to-noise ratio, mean squared error, structural similarity index, and Pearson correlation coefficient. CBCT images from 34 head and neck cancer patients were used to test the developed models. The dual-encoder model with spatial/channel wise attention showed the best results in terms of artifact index. By using the proposed model to CBCT, one can achieve more accurate synthetic pCT for head and neck patients as well as better tissue recognition and structure delineation for CBCT image itself.

Analysis of Quantum-Classical Hybrid Deep Learning for 6G Image Processing with Copyright Detection

This study investigates the integration of quantum computing, classical methods, and deep learning techniques for enhanced image processing in dynamic 6G networks, while also addressing essential aspects of copyright technology and detection. Our findings indicate that quantum methods excel in rapid edge detection and feature extraction but encounter difficulties in maintaining image quality compared to classical approaches. In contrast, classical methods preserve higher image fidelity but struggle to satisfy the real-time processing requirements of 6G applications. Deep learning techniques, particularly CNNs, demonstrate potential in complex image analysis tasks but demand substantial computational resources. To promote the ethical use of AI-generated images, we introduce copyright detection mechanisms that employ advanced algorithms to identify potential infringements in generated content. This integration improves adherence to intellectual property rights and legal standards, supporting the responsible implementation of image processing technologies. We suggest that the future of image processing in 6G networks resides in hybrid systems that effectively utilize the strengths of each approach while incorporating robust copyright detection capabilities. These insights contribute to the development of efficient, high-performance image processing systems in next-generation networks, highlighting the promise of integrated quantum-classical–classical deep learning architectures within 6G environments.

An End-to-End Brain Computer Interface System for Mental Workload Estimation through Hybrid Deep Learning Model

AbstractIn this paper, a new cascade one-dimensional convolutional neural network (1DCNN) and bidirectional long short-term memory (BLSTM) model has been developed for binary and ternary classification of mental workload (MWL). MWL assessment is important to increase the safety and efficiency in brain–computer interface (BCI) systems and professions, where multi-tasking is required. Keeping in mind the necessity of MWL assessment, a two-fold study is presented, firstly binary classification is done to classify MWL into low and high classes. Secondly, ternary classification is applied to classify MWL into low, moderate, and high classes. The cascaded1DCNN-BLSTM deep learning architecture has been developed and tested over the Simultaneous task EEG workload (STEW) dataset. Unlike recent research in MWL, handcrafted feature extraction and engineering are not done, rather end-to-end deep learning is used over 14 channel EEG signals for classification. Accuracies exceeding the previous state-of-the-art studies have been obtained. In binary and ternary classification accuracies of 96.77% and 95.36%have been achieved with sevenfold cross-validation, respectively.

Optimal Feature Selection and Classification for Parkinson’s Disease Using Deep Learning and Dynamic Bag of Features Optimization

Parkinson’s Disease (PD) is a neurological condition that worsens with time and is characterized bysymptoms such as cognitive impairment andbradykinesia, stiffness, and tremors. Parkinson’s is attributed to the interference of brain cells responsible for dopamine production, a substance regulating communication between brain cells. The brain cells involved in dopamine generation handle adaptation and control, and smooth movement. Convolutional Neural Networks are used to extract distinctive visual characteristics from numerous graphomotor sample representations generated by both PD and control participants. The proposed method presents an optimal feature selection technique based on Deep Learning (DL) and the Dynamic Bag of Features Optimization Technique (DBOFOT). Our method combines neural network-based feature extraction with a strong optimization technique to dynamically choose the most relevant characteristics from biological data. Advanced DL architectures are then used to classify the chosen features, guaranteeing excellent computational efficiency and accuracy. The framework’s adaptability to different datasets further highlights its versatility and potential for further medical applications. With a high accuracy of 0.93, the model accurately identifies 93% of the cases that are categorized as Parkinson’s. Additionally, it has a recall of 0.89, which means that 89% of real Parkinson’s patients are accurately identified. While the recall for Class 0 (Healthy) is 0.75, meaning that 75% of the real healthy cases are properly categorized, the precision decreases to 0.64 for this class, indicating a larger false positive rate.

Deep Learning Methods in Soft Robotics: Architectures and Applications

The area of soft robotics has been subject to intense research efforts in the past two decades and constitutes a paradigm for advanced machine design in future robotic applications. However, standard methods for industrial robotics may be difficult to apply when analyzing soft robots. Deep learning, which has undergone rapid and transformative advancements in recent years, offers a set of powerful tools for analyzing and designing complex soft machines capable of operating in unstructured environments and interacting with humans and objects in a delicate manner. This review summarizes the most important state‐of‐the‐art deep learning architectures classified under supervised, unsupervised, semisupervised, and reinforcement learning scenarios and discusses their main features and benefits for different soft robotic applications, including soft robot manipulators, soft grippers, soft sensors, and e‐skins, as well as bioinspired soft robots. Specific properties of recent deep learning architectures and the usefulness of their features in addressing various types of issues found in soft robotics are analyzed. The existing challenges and future prospects are identified and discussed in view of the enhanced integration of both areas, which improves the performance of next‐generation soft machines operating in real‐world conditions.

Deep Learning-Driven Virtual Furniture Replacement Using GANs and Spatial Transformer Networks

This study proposes a Generative Adversarial Network (GAN)-based method for virtual furniture replacement within indoor scenes. The proposed method addresses the challenge of accurately positioning new furniture in an indoor space by combining image reconstruction with geometric matching through combining spatial transformer networks and GANs. The system leverages deep learning architectures like Mask R-CNN for executing image segmentation and generating masks, and it employs DeepLabv3+, EdgeConnect algorithms, and ST-GAN networks for carrying out virtual furniture replacement. With the proposed system, furniture shoppers can obtain a virtual shopping experience, providing an easier way to understand the aesthetic effects of furniture rearrangement without putting in effort to physically move furniture. The proposed system has practical applications in the furnishing industry and interior design practices, providing a cost-effective and efficient alternative to physical furniture replacement. The results indicate that the proposed method achieves accurate positioning of new furniture in indoor scenes with minimal distortion or displacement. The proposed system is limited to 2D front-view images of furniture and indoor scenes. Future work would involve synthesizing 3D scenes and expanding the system to replace furniture images photographed from different angles. This would enhance the efficiency and practicality of the proposed system for virtual furniture replacement in indoor scenes.

From Data to Diagnosis: Leveraging Deep Learning Architectures in Healthcare IoT

From Data to Diagnosis: Leveraging Deep Learning Architectures in Healthcare IoT

Clinical application of machine-based deep learning in patients with radiologically presumed adult-type diffuse glioma grades 2 or 3

Abstract BACKGROUND Radiologically presumed diffuse lower-grade glioma (dLGG) are typically non or minimal enhancing tumors, with hyperintensity in T2w-images. The aim of this study was to test the clinical usefulness of deep learning (DL) in IDH mutation prediction in patients with radiologically presumed dLGG. METHODS 314 patients were retrospectively recruited from six neurosurgical departments in Sweden, Norway, France, Austria, and the United States. Collected data included patients’ age, sex, tumor molecular characteristics (IDH, and 1p19q), and routine preoperative radiological images. A clinical model was built using multivariable logistic regression with the variables age and tumor location. DL models were built using MRI data only, and four DL architectures used in glioma research. In the final validation test, the clinical model and the best DL model were scored on an external validation cohort with 155 patients from the Erasmus Glioma Dataset. RESULTS The mean age in the recruited and external cohorts was 45.0 (SD 14.3) and 44.3 years (SD 14.6). The cohorts were rather similar, except for sex distribution (53.5% vs 64.5% males, p-value 0.03) and IDH status (30.9% vs 12.9% IDH wild-type, p-value <0.01). Overall, the area under the curve for the prediction of IDH mutations in the external validation cohort was 0.86, 0.82, and 0.87 for the clinical model, the DL model, and the model combining both models’ probabilities. CONCLUSIONS In their current state, when these complex models were applied to our clinical scenario, they did not seem to provide a net gain compared to our baseline clinical model.

SentinelGuard Pro: Deploying Cutting‐Edge FusionNet for Unerring Detection and Enforcement of Wrong Parking Incidents

ABSTRACTWrong parking incidents pose a pervasive challenge in urban environments, disrupting the smooth flow of traffic, compromising safety and contributing to various logistical issues. Unauthorized parking occurs when vehicles are parked in locations not designated for such purposes, leading to a myriad of problems for both authorities and the general public. This research introduces a pioneering approach to confront the persistent challenge of unauthorized parking incidents in urban environments. The study focuses on harnessing the advanced capabilities of the FusionNet model to enhance the accuracy of license plate detection. This paper introduces the YOLO v8 Model, a deep learning architecture designed to enhance urban parking management by accurately detecting vehicles parked in unauthorized slots. The objective is to enhance parking management efficiency by accurately detecting vehicles and their occupancy status in designated parking areas. The methodology begins with data collection and preprocessing of images of parking spaces, followed by the training of YOLO v8 to identify vehicles and parking spaces in real time. Leveraging a diverse dataset encompassing various parking scenarios, including instances of unauthorized parking, the model achieves an accuracy of 98.50% in identifying vehicles outside designated areas. This model segments characters from detected license plates, enabling the accurate extraction of alphanumeric information associated with each vehicle. The integrated system provides timely identification of parking violations and facilitates effective enforcement actions through captured license plate data. Results demonstrate the model's effectiveness in real‐world scenarios, showcasing its potential for improving urban safety and efficiency. The implementation of FusionNet in the Python programming language, the proposed solution aims to streamline parking management, improve compliance with parking regulations and enhance overall urban mobility., with robust precision 96.17%, specificity 97.42% and sensitivity 96.19%, surpassing other MobileNet, CNN, ANN, DNN and EfficientNet models.

DGNMDA: Dual Heterogeneous Graph Neural Network Encoder for miRNA-Disease Association Prediction

In recent years, numerous studies have highlighted the pivotal importance of miRNAs in personalized healthcare, showcasing broad application prospects. miRNAs hold significant potential in disease diagnosis, prognosis assessment, and therapeutic target discovery, making them an integral part of precision medicine. They are expected to enable precise disease subtyping and risk prediction, thereby advancing the development of precision medicine. GNNs, a class of deep learning architectures tailored for graph data analysis, have greatly facilitated the advancement of miRNA-disease association prediction algorithms. However, current methods often fall short in leveraging network node information, particularly in utilizing global information while neglecting the importance of local information. Effectively harnessing both local and global information remains a pressing challenge. To tackle this challenge, we propose an innovative model named DGNMDA. Initially, we constructed various miRNA and disease similarity networks based on authoritative databases. Subsequently, we creatively design a dual heterogeneous graph neural network encoder capable of efficiently learning feature information between adjacent nodes and similarity information across the entire graph. Additionally, we develop a specialized fine-grained multi-layer feature interaction gating mechanism to integrate outputs from the neural network encoders to identify novel associations connecting miRNAs with diseases. We evaluate our model using 5-fold cross-validation and real-world disease case studies, based on the HMDD V3.2 dataset. Our method demonstrates superior performance compared to existing approaches in various tasks, confirming the effectiveness and potential of DGNMDA as a robust method for predicting miRNA-disease associations.

LGSur‐Net: A Local Gaussian Surface Representation Network for Upsampling Highly Sparse Point Cloud

AbstractWe introduce LGSur‐Net, an end‐to‐end deep learning architecture, engineered for the upsampling of sparse point clouds. LGSur‐Net harnesses a trainable Gaussian local representation by positioning a series of Gaussian functions on an oriented plane, complemented by the optimization of individual covariance matrices. The integration of parametric factors allows for the encoding of the plane's rotational dynamics and Gaussian weightings into a linear transformation matrix. Then we extract the feature maps from the point cloud and its adjoining edges and learn the local Gaussian depictions to accurately model the shape's local geometry through an attention‐based network. The Gaussian representation's inherent high‐order continuity endows LGSur‐Net with the natural ability to predict surface normals and support upsampling to any specified resolution. Comprehensive experiments validate that LGSur‐Net efficiently learns from sparse data inputs, surpassing the performance of existing state‐of‐the‐art upsampling methods. Our code is publicly available at https://github.com/Rangiant5b72/LGSur-Net.

Comparison of Efficient Deep Learning Architectures for Lactobacillus Species Identification

Comparison of Efficient Deep Learning Architectures for Lactobacillus Species Identification

A new fuzzy-based ensemble framework based on attention-based deep learning architectures for automated detection of abnormal EEG

A new fuzzy-based ensemble framework based on attention-based deep learning architectures for automated detection of abnormal EEG

Edge Computing for Smart-City Human Habitat: A Pandemic-Resilient, AI-Powered Framework

The COVID-19 pandemic has highlighted the need for a robust medical infrastructure and crisis management strategy as part of smart-city applications, with technology playing a crucial role. The Internet of Things (IoT) has emerged as a promising solution, leveraging sensor arrays, wireless communication networks, and artificial intelligence (AI)-driven decision-making. Advancements in edge computing (EC), deep learning (DL), and deep transfer learning (DTL) have made IoT more effective in healthcare and pandemic-resilient infrastructures. DL architectures are particularly suitable for integration into a pandemic-compliant medical infrastructures when combined with medically oriented IoT setups. The development of an intelligent pandemic-compliant infrastructure requires combining IoT, edge and cloud computing, image processing, and AI tools to monitor adherence to social distancing norms, mask-wearing protocols, and contact tracing. The proliferation of 4G and beyond systems including 5G wireless communication has enabled ultra-wide broadband data-transfer and efficient information processing, with high reliability and low latency, thereby enabling seamless medical support as part of smart-city applications. Such setups are designed to be ever-ready to deal with virus-triggered pandemic-like medical emergencies. This study presents a pandemic-compliant mechanism leveraging IoT optimized for healthcare applications, edge and cloud computing frameworks, and a suite of DL tools. The framework uses a composite attention-driven framework incorporating various DL pre-trained models (DPTMs) for protocol adherence and contact tracing, and can detect certain cyber-attacks when interfaced with public networks. The results confirm the effectiveness of the proposed methodologies.

Vision transformers for glioma classification using T1 magnetic resonance imaging

Automated image analysis and classification have increasingly advanced in recent decades owing to machine learning and computer vision. In particular, deep learning (DL) architectures have become popular in resource-limited and labor-restricted environments such as the health-care sector. Transformer architecture, a DL method with self-attention mechanism, excels in natural language processing; however, its application in image-based diagnosis in health-care sector remains limited. Herein, the feasibility, bottlenecks, and performance of transformers in magnetic resonance imaging (MRI)-based brain tumor classification were investigated. To this end, a vision transformer (ViT) model was trained and tested using the popular Brain Tumor Segmentation (BraTS) 2015 dataset for glioma classification. Owing to limited data availability, domain adaptation techniques were used to pretrain the ViT model and the BraTS 2015 dataset was used for its fine-tuning. With the model only trained for 100 epochs, the confusion matrix for the two-class problem of tumor and nontumor classification showed an overall classification accuracy of 81.8%. In conclusion, although convolutional neural networks are traditionally used for DL-based medical image classification owing to their attention mechanism and long-range dependency-capturing capability, ViTs can outperform them in MRI-based brain tumor classification.