Deep Learning Architecture Research Articles

NEURO DEEP FUZZY GENETIC ALGORITHM APPROACH FOR CLASSIFICATION AND DETECTION OF BRAIN TUMOR FROM LARGE DATASETS

Brain tumors represent one of the most critical and life-threatening diseases. Early detection and accurate classification are essential for effective treatment planning and survival rate improvement. With the exponential growth of medical data, particularly in imaging and diagnostic datasets, traditional algorithms face limitations in handling large-scale, high-dimensional data efficiently. Conventional machine learning and diagnostic methods often struggle with classification accuracy, computational complexity, and overfitting in large, noisy datasets. Addressing these issues is crucial for the development of robust diagnostic tools capable of handling real-world clinical data. This paper presents a novel hybrid approach combining Neural Networks, Deep Learning, Fuzzy Logic, and Genetic Algorithms, termed Neuro Deep Fuzzy Genetic Algorithm (NDFGA), for the classification and detection of brain tumors from large datasets. Neural Networks and Deep Learning architectures are leveraged for feature extraction and hierarchical learning. Fuzzy Logic improves interpretability and manages uncertainty in medical data, while Genetic Algorithms optimize feature selection and model parameters. This hybrid method is designed to maximize classification accuracy while minimizing false positives and computational overhead. The proposed approach was tested on a large brain tumor dataset comprising over 10,000 MRI scans. The NDFGA approach demonstrated superior performance compared to standalone methods. It achieved a classification accuracy of 97.8%, a sensitivity of 96.5%, and a specificity of 98.1%. The model also showed improved robustness in handling large datasets, reducing false positives by 12% and computational time by 15% compared to traditional methods. This hybrid model presents a scalable and efficient solution for brain tumor detection, especially in clinical environments.

Transfer learning for molecular property predictions from small datasets

Machine learning has emerged as a new tool in chemistry to bypass expensive experiments or quantum-chemical calculations, for example, in high-throughput screening applications. However, many machine learning studies rely on small datasets, making it difficult to efficiently implement powerful deep learning architectures such as message passing neural networks. In this study, we benchmark common machine learning models for the prediction of molecular properties on two small datasets, for which the best results are obtained with the message passing neural network PaiNN as well as SOAP molecular descriptors concatenated to a set of simple molecular descriptors tailored to gradient boosting with regression trees. To further improve the predictive capabilities of PaiNN, we present a transfer learning strategy that uses large datasets to pre-train the respective models and allows us to obtain more accurate models after fine-tuning on the original datasets. The pre-training labels are obtained from computationally cheap ab initio or semi-empirical models, and both datasets are normalized to mean zero and standard deviation one to align the labels’ distributions. This study covers two small chemistry datasets, the Harvard Organic Photovoltaics dataset (HOPV, HOMO–LUMO-gaps), for which excellent results are obtained, and the FreeSolv dataset (solvation energies), where this method is less successful, probably due to a complex underlying learning task and the dissimilar methods used to obtain pre-training and fine-tuning labels. Finally, we find that for the HOPV dataset, the final training results do not improve monotonically with the size of the pre-training dataset, but pre-training with fewer data points can lead to more biased pre-trained models and higher accuracy after fine-tuning.

Intelligent Handwritten Identification Using Novel Hybrid Convolutional Neural Networks – Long-short-term Memory Architecture

Handwritten character identification finds broad applications in document analysis, digital forensics, and human-computer interaction. Conventional methods encounter challenges in accurately deciphering a range of handwriting styles and variations. Consequently, investigating intelligent system for handwriting identification becomes crucial to enhance accuracy and efficiency. This paper introduces an innovative hybrid deep learning architecture, seamlessly integrating the strengths of convolutional neural networks (CNN) and long-short term memory (LSTM) within a one single framework. The combination of these structures enables the model to effectively capture both spatial features and temporal dependencies inherent in handwritten strokes, resulting in improved recognition performance. The proposed 2DCNN-LSTM algorithm has been tested on MNIST dataset. The proposed hybrid CNN-LSTM structure has been compared to conventional intelligent machine learning methods, and the results demonstrate the superior performance of the hybrid CNN-LSTM, showcasing heightened accuracy, sensitivity, specificity, and other evaluation metrics.

Deep learning approaches for assessing pediatric sleep apnea severity through SpO2 signals

Pediatric Sleep Apnea–Hypopnea (SAH) presents a significant health challenge, particularly in diagnostic contexts, where conventional Polysomnography (PSG) testing, although effective, can be distressing for children. Addressing this, our research proposes a less invasive method to assess pediatric SAH severity by analyzing blood oxygen saturation (SpO2) signals. We adopted two advanced deep learning architectures, namely ResNet-based and attention-augmented hybrid CNN-BiGRU models, to process SpO2 signals in a one-dimensional (1D) format for Apnea–Hypopnea Index (AHI) estimation in pediatric subjects. Employing the CHAT dataset, which includes 844 SpO2 signals, the data was partitioned into training (60%), testing (30%), and validation (10%) sets. A predefined validation subset was randomly selected to ensure the models' robustness via a threefold cross-validation approach. Comparative analysis revealed that while the ResNet model attained an average accuracy of 72.9% across four SAH severity categories with a kappa score of 0.57, the CNN-BiGRU-Attention model demonstrated superior performance, achieving an average accuracy of 75.95% and a kappa score of 0.63. This distinction underscores our method's efficacy in both estimating AHI and categorizing SAH severity levels with notable precision. Further, to evaluate diagnostic capabilities, the models were benchmarked against common AHI thresholds (1, 5, and 10 events/hour) in each test fold, affirming their effectiveness in identifying pediatric SAH. This study marks a significant advance in the field, offering a non-invasive, child-friendly alternative for pediatric SAH diagnosis. Although challenges persist in accurately estimating AHI, particularly in severe cases, our findings represent a critical stride towards improving diagnostic processes in pediatric SAH.

Artificial Intelligence-based Deep Learning Architecture for Tuberculosis Detection

Artificial Intelligence-based Deep Learning Architecture for Tuberculosis Detection

Improved deep learning architecture for skin cancer classification

Improved deep learning architecture for skin cancer classification

Enhancing the analysis of murine neonatal ultrasonic vocalizations: Development, evaluation, and application of different mathematical models.

Rodents employ a broad spectrum of ultrasonic vocalizations (USVs) for social communication. As these vocalizations offer valuable insights into affective states, social interactions, and developmental stages of animals, various deep learning approaches have aimed at automating both the quantitative (detection) and qualitative (classification) analysis of USVs. So far, no notable efforts have been made to determine the most suitable architecture. We present the first systematic evaluation of different types of neural networks for USV classification. We assessed various feedforward networks, including a custom-built, fully-connected network, a custom-built convolutional neural network, several residual neural networks, an EfficientNet, and a Vision Transformer. Our analysis concluded that convolutional networks with residual connections specifically adapted to USV data, are the most suitable architecture for analyzing USVs. Paired with a refined, entropy-based detection algorithm (achieving recall of 94.9 % and precision of 99.3 %), the best architecture (achieving 86.79 % accuracy) was integrated into a fully automated pipeline capable of analyzing extensive USV datasets with high reliability. In ongoing projects, our pipeline has proven to be a valuable tool in studying neonatal USVs. By comparing these distinct deep learning architectures side by side, we have established a solid foundation for future research.

Deep learning of 3D point clouds for detecting geometric defects in gears

Geometric integrity directly impacts the functionality, reliability, and safety of final manufactured products, making the qualification of parts based on measurements of their geometry a fundamental quality control activity in modern manufacturing. Recent advancements in three-dimensional (3D) metrology technologies have enabled fine-scale inspection of geometric integrity characterized by dimensional accuracy, surface quality, and shape conformity. However, the widespread adoption of high-resolution 3D metrology in manufacturing faces some significant challenges posed by the inherent data structures of 3D point clouds such as high dimensionality, unstructured nature, and sparsity in defective regions. To address these challenges, this paper first creates a “MFGNet-gear” dataset, which is a scalable and comprehensive benchmark dataset comprising 12 part designs with four quality classes for each design. Subsequently, we develop a deep learning model adapted from the PointNet++ architecture to enable automated, end-to-end analysis of 3D point clouds. The model can be configured for different decision-making tasks including part design classification and multi-class geometric defect detection. Implementations of the proposed model on the “MFGNet-gear” dataset achieve accuracies up to 100% in classifying gear designs and up to 85% in four-class quality inspection. Additionally, we systematically investigate the impacts of measurement resolution and precision on the classification performance through a series of case studies. The obtained results highlight the potential of using deep learning methods for automated analysis of 3D point clouds for a variety of quality control tasks beyond gear manufacturing. This study also proposes future research directions, including the development of new deep learning architectures specifically designed for manufacturing 3D point clouds and strategies for adaptive measurement planning.

The Integration of Radiomics and Artificial Intelligence in Modern Medicine.

With profound effects on patient care, the role of artificial intelligence (AI) in radiomics has become a disruptive force in contemporary medicine. Radiomics, the quantitative feature extraction and analysis from medical images, offers useful imaging biomarkers that can reveal important information about the nature of diseases, how well patients respond to treatment and patient outcomes. The use of AI techniques in radiomics, such as machine learning and deep learning, has made it possible to create sophisticated computer-aided diagnostic systems, predictive models, and decision support tools. The many uses of AI in radiomics are examined in this review, encompassing its involvement of quantitative feature extraction from medical images, the machine learning, deep learning and computer-aided diagnostic (CAD) systems approaches in radiomics, and the effect of radiomics and AI on improving workflow automation and efficiency, optimize clinical trials and patient stratification. This review also covers the predictive modeling improvement by machine learning in radiomics, the multimodal integration and enhanced deep learning architectures, and the regulatory and clinical adoption considerations for radiomics-based CAD. Particular emphasis is given to the enormous potential for enhancing diagnosis precision, treatment personalization, and overall patient outcomes.

An omics-driven computational model for angiogenic protein prediction: Advancing therapeutic strategies with Ens-deep-AGP

Angiogenic proteins (AGPs) play a critical role in both pathological and physiological activities, making them key therapeutic targets in diseases like cancer, heart disease, and stroke. Traditional methods for identifying AGPs are labor-intensive and time-consuming, creating a need for more efficient approaches. This study addresses this challenge by developing a novel computational model, Ens-Deep-AGP, designed to enhance AGP prediction. The model introduces innovative feature engineering techniques, including Position Specific Scoring Matrix-Decomposition-Discrete Cosine Transform (PSSM-DC-DCT) and Position Specific Scoring Matrix-Auto-Cross-Discrete Wavelet Transform (PSSM-ACC-DWT), which capture comprehensive protein sequence information. The ensemble feature set of these approaches are then fed into Multi-headed Ensemble Residual Convolutional Neural Network (MERCNN), a robust deep learning architecture. Ens-Deep-AGP achieved remarkable accuracy rates of 99.79 % on training dataset and 92.97 % on testing dataset, surpassing Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Bidirectional Long Short-Term Memory Networks (BiLSTM). The successful prediction of AGPs is crucial for accelerating drug development, discovering novel therapeutic targets and deepen our understanding of AGPs' complex roles in healthcare.

Computer Vision Promising Innovations

Computer vision, an interdisciplinary field bridging artificial intelligence and image processing, seeks to bestow machines with the capability to interpret and make decisions based on visual data. As the digital age propels forward, the ubiquity of visual content underscores the importance of efficient and effective automated interpretation. This paper delves deeply into the modern advancements and methodologies of computer vision, emphasizing its transformative role in various applications ranging from medical imaging to autonomous driving. With the increasing complexity of visual data, challenges arise pertaining to real-time processing, scalability, and the ethical implications of automated decision-making. Through an exhaustive literature review and novel experimentation, this research demystifies the multifaceted domain of computer vision, elucidating its potential and constraints. The study culminates in a visionary outlook, highlighting future avenues for research, including the fusion of augmented reality with computer vision, novel deep learning architectures, and ensuring ethical AI practices in visual interpretation.

A Novel Hybrid Framework for Enhanced Early Detection and Classification of Ocular Diseases: Integrating Deep Learning with Traditional Machine Learning Approaches

Ocular diseases pose a significant global health challenge, with early detection and accurate classification being crucial for effective treatment and prevention of vision loss. This study introduces an innovative hybrid framework that synergistically combines state-of-the-art deep learning architectures with traditional machine learning algorithms to advance the field of ocular disease detection and classification. The proposed approach achieves remarkable performance with an average accuracy of 96.8% across eight common ocular diseases, demonstrating a sensitivity of 95.6% and a specificity of 96.7%. These results highlight the potential of this hybrid model to improve significantly the diagnostic capabilities in ophthalmology. This research study offers a comprehensive and insightful narrative that integrates the key findings from the data analysis, making significant contributions to the field of ophthalmology and providing valuable guidance for future research endeavors.

SSResNeXt: A Novel Deep Learning Architecture for Multi-class Breast Cancer Pathological Image Classification

Multi-class classification of breast cancer pathological images remains challenging due to complex image features and limited datasets. This study proposes SSResNeXt, a novel deep learning architecture incorporating a new Small-SE-ResNeXt Block with asymmetric convolutions and channel attention mechanisms. Evaluated on the BreaKHis dataset, SSResNeXt achieves state-of-the-art performance with accuracies of 95.2%, 94.0%, 92.7%, and 93.5% for 40X, 100X, 200X, and 400X magnification scales, respectively. Comparative experiments demonstrate SSResNeXt's superior performance over existing models, including ResNet and Swin Transformer variants. The proposed architecture offers improved feature extraction capabilities for breast cancer pathological images without significantly increasing model complexity, providing a promising tool for computer-aided diagnosis systems.

A Comprehensive Comparative Analysis of Deep Learning Architectures for Suspicious Activity Detection in Video Surveillance

Abstract: In the landscape of modern security infrastructure, video surveillance has evolved into a ubiquitous and indispensable tool for ensuring public safety and safeguarding critical assets. This research paper delves into an extensive examination of various deep learning architectures for the purpose of detecting suspicious activities in video surveillance. The investigation encompasses Convolutional Long Short-Term Memory (ConvLSTM), Convolutional Neural Network (CNN) combined with Long Short-Term Memory (LSTM), ConvLSTM, Bidirectional Long Short-Term Memory (BiLSTM), and diverse combinations thereof. Each model is rigorously trained and tested on a carefully curated dataset designed to encapsulate a spectrum of normal and suspicious activities like shooting and fighting. The study aspires to identify the most efficacious model for enhancing the accuracy of suspicious activity detection in complex and dynamic environments. Metrics such as accuracy, precision, recall, and F1 score will be rigorously assessed to ascertain the model’s comparative performances

Indonesian Fake News Classification Using Transfer Learning in CNN and LSTM

Fake news spreads quickly and is challenging to stop due to the ease of accessing and sharing information online. Deep learning techniques are a method that can be used to identify fake news quickly and accurately. The types of neural networks commonly utilized in deep learning architectures include Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), which can perform well when managing the task of classifying fake news, according to several pertinent studies. Regarding handling instances of Indonesian fake news classification, this study compares how well the CNN and LSTM models perform. However, given that Indonesian is a low-resource language with scant documentation, it is challenging to build an adequate data set. At the same time, the CNN and LSTM classification models require significant training data. We proposed a transfer learning method by combining two classification models with a pre-trained IndoBERT language model. 1340 news text data were used, including 643 actual news texts from CNN Indonesia, Liputan6, and Detik and 697 fake news texts from TurnBackHoax. As a result, the performance of the combination of the LSTM classification model with IndoBERT outperformed that of the CNN classification model with IndoBERT, which only produced an accuracy of 92.91%, down by 6%, and was able to produce an accuracy of up to 97.76%, an increase of 4.8% from before. Furthermore, the results show that the LSTM classification model outperforms the CNN classification model in capturing the representation created by IndoBERT. Additionally, these insights may serve as a basis for future research on identifying fake news in Indonesia, helping to improve methods for combatting misinformation in Indonesia.

A systematic review of deep learning techniques for plant diseases

Agriculture is one of the most crucial sectors, meeting the fundamental food needs of humanity. Plant diseases increase food economic and food security concerns for countries and disrupt their agricultural planning. Traditional methods for detecting plant diseases require a lot of labor and time. Consequently, many researchers and institutions strive to address these issues using advanced technological methods. Deep learning-based plant disease detection offers considerable progress and hope compared to classical methods. When trained with large and high-quality datasets, these technologies robustly detect diseases on plant leaves in early stages. This study systematically reviews the application of deep learning techniques in plant disease detection by analyzing 160 research articles from 2020 to 2024. The studies are examined in three different areas: classification, detection, and segmentation of diseases on plant leaves, while also thoroughly reviewing publicly available datasets. This systematic review offers a comprehensive assessment of the current literature, detailing the most popular deep learning architectures, the most frequently studied plant diseases, datasets, encountered challenges, and various perspectives. It provides new insights for researchers working in the agricultural sector. Moreover, it addresses the major challenges in the field of disease detection in agriculture. Thus, this study offers valuable information and a suitable solution based on deep learning applications for agricultural sustainability.

Machine Learning Driven Options Pricing Model for Changing Market Conditions

This paper presents the design and implementation of an Adaptive Options Pricing Model utilizing deep learning techniques to enhance the accuracy of options pricing in volatile financial markets. Traditional models such as the Black-Scholes and Binomial frameworks have served as foundational tools in options pricing; however, they are constrained by assumptions of constant volatility and market efficiency, which often fail to reflect real-world dynamics. To address these limitations, the proposed model incorporates historical pricing data alongside real-time market sentiment derived from news articles and social media. By leveraging advanced deep learning architectures, particularly Long Short-Term Memory (LSTM) networks, the model dynamically adapts to changing market conditions, capturing complex, nonlinear relationships in the data. The performance of the model is evaluated against traditional pricing methods, demonstrating significant improvements in pricing accuracy and responsiveness to market fluctuations. This research contributes valuable insights for traders and risk managers seeking to optimize their strategies in the derivatives market.

Enhancing Gene Expression Predictions Using Deep Learning and Functional Annotations.

Transcriptome-wide association studies (TWAS) aim to uncover genotype-phenotype relationships through a two-stage procedure: predicting gene expression from genotypes using an expression quantitative trait locus (eQTL) data set, then testing the predicted expression for trait associations. Accurate gene expression prediction in stage 1 is crucial, as it directly impacts the power to identify associations in stage 2. Currently, the first stage of such studies is primarily conducted using linear models like elastic net regression, which fail to capture the nonlinear relationships inherent in biological systems. Deep learning methods have the potential to model such nonlinear effects, but have yet to demonstrably outperform linear methods at this task. To address this gap, we propose a new deep learning architecture to predict gene expression from genotypic variation across individuals. Our method utilizes a learnable input scaling layer in conjunction with a convolutional encoder to capture nonlinear effects and higher-order interactions without compromising on interpretability. We further augment this approach to allow for parameter sharing across multiple networks, enabling us to utilize prior information for individual variants in the form of functional annotations. Evaluations on real-world genomic data show that our method consistently outperforms elastic net regression across a large set of heritable genes. Furthermore, our model statistically significantly improved predictive performance by leveraging functional annotations, whereas elastic net regression failed to show equivalent gains when using the same information, suggesting that our method can capture nonlinear functional information beyond the capability of linear models.

Epileptic EEG classification via deep learning-based strange attractor

Electroencephalography is commonly exploited in recording brains’ electrical activities for revealing the symptoms of various neurological diseases, e.g., epileptic seizures. We hypothesize that its capability primarily comes from the information it captures from the brain, which is supposed to be a chaotic dynamical system. Therefore, seizure detection in clinical practice could benefit from strange attractor reconstruction from time series in classifying non-ictal and ictal epileptic seizures. We propose a deep learning architecture and the loss function in a latent space to implement the reconstruction. By leveraging the proposed deep model, the hidden coordinates can be derived from a low-dimensional time series or univariate time series (e.g., Electroencephalography). Furthermore, added variables can extract more features from the reconstructed dynamical system. The proposed pipeline is evaluated by using a publicly available epileptic seizure database. Experimental results demonstrated the promising outcome of the proposed approach.

E-Commerce Fake Reviews Detection Using LSTM with Word2Vec Embedding

Customer reviews inform potential buyers' decisions, but fake reviews in e-commerce can skew perceptions as customers may feel pressured to leave positive feedback. Detecting fake reviews in e-commerce platforms is a critical challenge, impacting online shopping and deceiving customers. Effective detection strategies, employing deep learning architectures and word embeddings, are essential to combat this issue. Specifically, the study presented in this paper employed a 1-layer Simple LSTM model, a 1D Convolutional model, and a combined CNN+LSTM model. These models were trained using different pre-trained word embeddings including Word2Vec, GloVe, FastText, and Keras embeddings, to convert the text data into vector form. The models were evaluated based on accuracy and F1-score to provide a comprehensive measure of their performance. The results indicated that the Simple LSTM model with Word2Vec embeddings achieved an accuracy of nearly 91% and an F1-score of 0.9024, outperforming all other model-embedding combinations. The 1D convolutional model performed best without any embeddings, suggesting its ability to extract meaningful features from the raw text. The transformer-based models, BERT and DistilBERT, showed progressive learning but struggled with generalization, indicating the need for strategies such as early stopping, dropout, or regularization to prevent overfitting. Notably, the DistilBERT model consistently outperformed the LSTM model, achieving optimal performance with an accuracy of 96% and an F1-score of 0.9639 using a batch size of 32 and a learning rate of 4.00E-05.