Network Architecture Research Articles

Prediction of paroxysmal atrial fibrillation using a convolutional neural network and electrocardiogram signals

Atrial fibrillation (AF) is the most clinically diagnosed arrhythmia in cardiac pathology. The incidence of AF begins at a very early age and its initial state is paroxysmal atrial fibrillation (PAF). This type of heart disease can be detected and predicted by analyzing the spectrogram of a surface electrocardiogram (ECG) signal. In many studies, different ECG signal formats and convolutional neural network (CNN) architectures have been used. However, the lack of good signal preprocessing or signal adequacy may have affected the accuracy, especially on short-term ECG signals. In this study, we analyzed a preprocessed ECG signal, determined the optimal set to predict PAF, and evaluated the accuracy using ECG signals of different durations. The PAF Prediction Challenge–PhysioNet database was used to extract spectrograms in 30-sec and 5-sec windows for two classes (Normal, PAF) and 3 classes (Normal, Close-AF, Distant-AF). Then, the AlexNet architecture was used. The proposed method achieved a two-class accuracy of 99.92% with a 30-sec window and 99.42% with a 5-sec window, improving the PAF prediction performance compared with similar works. In addition, the three-class accuracies were 96.92% and 97.43% with windows of 30-sec, and 5-sec, respectively. These results prove the efficacy of the method for the early diagnosis of PAF, even based on short-term ECG signals.

A deep learning-based system for accurate diagnosis of pelvic bone tumors

Bone image analysis and categorizing bone cancers have both seen advancements thanks to deep learning (DL), more notably convolution neural networks (CNN). This study suggests a brand-new CNN-based methodology for categorizing pelvic bone tumors specifically. This work aims to create a pelvic bone computed tomography (CT) image categorization system based on deep learning. The proposed technique uses a convolutional neural network (CNN) architecture to automatically extract information from the CT images and classify them into distinct categories of tumors. A total of 178 3D CT pictures was discovered and added retroactively. DenseNet created the image-based model with Adam optimizer and cross entropy loss. The suggested system's accuracy is assessed using a variety of performance indicators, including sensitivity, specificity, and F1-score. As demonstrated by the experiment findings, the suggested deep learning based classification system has a high degree of accuracy (94%), making it useful for the diagnosis and treatment of pelvic bone tumors. Our promising results might hasten the use of DL-assisted CT diagnosis for pelvic bone tumors in the future.

A robust neural network for privacy-preserving heart rate estimation in remote healthcare systems

In this study, we propose a computationally-light and robust neural network for estimating heart rate in remote healthcare systems. We develop a model that can be trained on consumer-grade graphics processing units (GPUs), and can be deployed on edge devices for swift inference. We propose a hybrid model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) architectures for estimating heart rate from Electrocardiogram (ECG) and Photoplethysmography (PPG) signals. Considering the sensitive nature of the ECG signals, we ensure a formal privacy guarantee, differential privacy, for the model training. We perform a tight accounting of the overall privacy budget of our training algorithm using the Rényi Differential Privacy technique. We demonstrate that our model outperforms state-of-the-art networks on a benchmark dataset for both ECG and PPG signals despite having a much smaller number of trainable parameters and, consequently, much smaller training and inference times. Our CNN-BiLSTM architecture can also provide excellent heart rate estimation performance even under strict privacy constraints. We develop a prototype Arduino-based data collection system that is low-cost, efficient, and useful for providing access to modern healthcare services to people living in remote areas.

Eye Strain Expression Classification using Attention Capsule Network for Adapting Screen Vision

Beside the conventional facial expression recognition methods, the research focuses on developing a system for recognizing various eye expressions under different screen conditions. This research deals with the use of Capsule Network (a recent Deep Learning algorithm) to enhance facial expression recognition capabilities and to develop adaptive screen technologies aimed at mitigating digital eye strain. The main objective of this research is to engineer a sophisticated system that employs the capabilities of Capsule Nets to recognize the various expressions that user makes and based on the recognized expression, dynamically modify screen settings, ensuring optimal user visual comfort. The research primarily concentrates on the exploration and application of various Capsule Net architectures designed for the recognition of expressions related to eye strain. The baseline model utilized elementary convolutional layers which feed into subsequent fully connected layers for the task of classification. The model has since been refined by incorporating advanced techniques such as attention mechanisms and more sophisticated network architectures where the classification is done by Capsule Network. Results have demonstrated a modest enhancement in the Capsule Net’s predictive performance, attributed to its superior spatial and hierarchical processing of facial features, in comparison to conventional deep learning approaches. The final model has an accuracy of 82.27%. As a final system the model has been deployed to an application to process frames from video camera in the device and make prediction to prompt the notifications or recommendations.

Automated 3D convolutional neural network architecture design using genetic algorithm for pulmonary nodule classification

Cancer of the lungs is considered one of the primary causes of death among patients globally. Early detection contributes significantly to the success of pulmonary cancer treatment. To aid the pulmonary nodule classification, many models for the analysis of medical image utilizing deep learning have been developed. Convolutional neural network (CNN) recently, has attained remarkable results in various image classification tasks. Nevertheless, the CNNs performance is heavily dependent on their architectures which still heavily reliant on human domain knowledge. This study introduces a cutting-edge approach that leverages genetic algorithms (GAs) to automatically design 3D CNN architectures for differentiation between benign and malignant pulmonary nodules. The suggested algorithm utilizes the dataset of lung nodule analysis 2016 (LUNA16) for evaluation. Notably, our approach achieved exceptional model accuracy, with evaluations on the testing dataset yielding up to 95.977%. Furthermore, the algorithm exhibited high sensitivity, showcasing its robust performance in distinguishing between benign and malignant nodules. Our findings demonstrate the outstanding capabilities of the proposed algorithm and show an outstanding performance and attain a state of art solution in lung nodule classification.

A good result of brain tumor classification based on simple convolutional neural network architecture

A good result of brain tumor classification based on simple convolutional neural network architecture

An Effective Classification of Brain Tumor using Deep Learning Techniques

Abstract: Brain tumor classification is a critical task in medical imaging, aiding in timely diagnosis and treatment planning. In this paper, we propose a comprehensive approach utilizing deep learning models for the classification of brain tumors into four categories: glioma, meningioma, pituitary tumors, and no tumors. We employ state-of-the-art convolutional neural network (CNN) architectures including ResNet50, DenseNet201, EfficientNetB3, and InceptionV3 for the classification task. To enhance the performance of the model, we employ resizing and augmentation techniques such as flips and rotation, thereby increasing the diversity of the training dataset. This is particularly crucial due to the limitations posed by small-sized datasets in previous methodologies. Our findings underscore the efficacy of deep learning approaches in brain tumor classification, with EfficientNetB3 emerging as a promising model for accurate diagnosis. Furthermore, our utilization of resizing and augmentation techniques demonstrates their significance in mitigating the challenges associated with limited training data.

Brain Tumor Segmentation Using U-Net Model

Abstract: Cancer of the brain presents a significant challenge due to its lethality, necessitating precise surgical segmentation. This study explores the application of U-Net, a Convolutional Neural Network (CNN) architecture, to segment brain tumors. Specifically, the segmentation involves distinguishing necrotic, edematous, growing, and healthy tissues within the brain. Analyzing overlaps between these diverse tissue types can be intricate, making the extraction of relevant information from images challenging. The study enhances the 2D U-Net network, leveraging the BraTS datasets for training. U-Net's flexibility in setting up various encoder and decoder routes proves invaluable for extracting pertinent information from images, adaptable for diverse applications

Comparative Analysis of VGG16, RESNET50, AND CNN Models for Lung Disease Prediction: A Deep Learning Approach

Abstract: Utilizing deep learning methods in medical image analysis has shown promise in enhancing disease detection and diagnosis. In this study, we conducted a detailed comparative analysis of threewidely recognized convolutional neural network (CNN) architectures: VGG16, ResNet50, and a custom CNN model tailored for pneumonia and COVID-19 detection from chest X-ray images. Leveraging transfer learning techniques and meticulously curated datasets, we evaluated the models' performance in accurately identifying respiratory diseases. Our investigation utilized two publicly available datasets, the ChestX-ray14 dataset and the NIH Chest X-ray Dataset, both annotated for pneumonia and COVID-19. Prior to model training, we conducted thorough preprocessing to ensure optimal data quality and consistency. Through rigorous experimentation, we assessed the models' accuracy, sensitivity, and specificity in disease detection. The results revealed nuanced differences in model performance across disease categories. While VGG16 demonstrated robust accuracy in pneumonia detection, ResNet50 exhibited enhanced sensitivity and specificity in identifying COVID-19 cases. Our custom CNN model, leveraging insights from both architectures, showcased competitive performance, emphasizing the importance of tailored model design for optimal diagnostic outcomes. Through comprehensive analysis and discussion, we elucidated the strengths and limitations of each model, considering factors such as computational efficiency, interpretability, and generalizability. Our findings underscore the potential of deep learningbased diagnostic tools in supporting healthcare professionals in timely and accurate disease diagnosis

Driver Distraction Detection and Alert System Using Convolutional Neural Networks

Abstract: The Driver Distraction and Alert System Using Convolutional Neural Networks provide a real-time machine learning and webcam-based monitoring system for driver distraction detection. The system uses a sophisticated Convolutional Neural Network (CNN) architecture trained on the State Form of Distracted Driver Detection dataset, which is made possible by utilizing the OpenCV, TensorFlow, and Pandas packages. With improvements like dropout layers and Xavier weight initialization, the model efficiently classifies ten driver attention states through preprocessing stages like image scaling and normalization. The results of the experiment show how well the suggested method works to identify distracted driving behaviors; a revised model on the Kaggle competition platform achieved a competitive public score of 2.67118

Summarization and Translation Using NLP

Abstract: Text summarization and translation are two critical tasks in natural language processing with significant applications in various domains such as news aggregation, document summarization, machine translation, and information retrieval. In recent years, there has been remarkable progress in the development of techniques and models for both tasks, leveraging advancements in deep learning and neural network architectures. This paper presents a comprehensive review and comparative analysis of state-of-the-art methods in text summarization and translation. First, we provide an overview of the different approaches to text summarization, including extractive, abstractive, and hybrid methods, highlighting their strengths and weaknesses. We discuss various evaluation metrics and datasets commonly used for benchmarking summarization systems, shedding light on the challenges and opportunities in this field.

Deep Learning based Credit Card Fraudulency Detection System

Abstract: Huge increase in the internet usage has been observed since last decade. It led to the emergence of services like ecommerce, tap and pay systems, online bill payment systems, etc. have proliferated and become more widely used. Due to various online payment options introduced by e- commerce and other numerous websites, the possibility of online fraud has risen drastically. Thus, due to an increase in fraud rates, research on analyzing and detecting fraud in online transactions has begun utilizing various machine learning techniques. The Deep Learning techniques viz., Convolutional Neural Network Architecture is used to detect credit card frauds in the proposed model. The Principal Component Analysis transformation gives a set of numerical input variables as output which are taken as the features to be considered. Due to confidentiality concerns, some of the original characteristics and background information about the data are not entirely disclosed. Features of credit card frauds must be chosen carefully as they play important role when deep learning techniques are used for credit card fraud detection. The TensorFlow and Keras are used for the development of the current proposed model. The proposed model aims to predict credit card frauds with 91.9% accuracy

AI Assisted Deceptive Content Analysis System Using Bi-LSTM

Abstract: In an age of widespread misinformation, creating accurate machine learning algorithms is vital for ensuring the integrity of information sharing. This project aims to develop a machine learning model capable of distinguishing between fake and true news articles. [1]The model utilizes a Bidirectional Long Short-Term Memory (Bi-LSTM) neural network architecture. Exploratory data analysis techniques are employed to gain in-sights into the characteristics and distributions within the dataset. Data visualization techniques aid in understanding patterns and relationships within the dataset. Additionally, unigram analysis is conducted to extract meaningful features from the text data. The datasets are then prepared for model training, involving preprocessing steps such as tokenization and vectorization. Fi-nally, the Bi-LSTM model is constructed, leveraging its ability to capture long-range dependencies in sequential data. The model is trained on the prepared datasets, optimized using appropri-ate techniques, and evaluated using metrics such as accuracy, precision, recall, and F1-score. The Bi-LSTM architecture offers the advantage of capturing long-range dependencies in sequential data, thereby enhancing the model’s ability to discern nuanced patterns in news articles. The primary objective of this project is to develop a robust and accurate system for automatically detecting fake news, thus playing a pivotal role in enhancing the dissemination of reliable information in the digital age.

Prediction of Abnormal Growth of Breast Cancer Cell Using Support Vector Machine

Abstract: Breast cancer is a serious health concern that affects millions of women worldwide. Early detection of breast cancer is crucial for effective treatment and improved survival rates. Artificial intelligence (AI) has shown great promise in the field of medical imaging and has been increasingly used for breast cancer detection. Cancer is one of the most dangerous diseases to humans, and yet no permanent cure has been developed for it. Breast cancer is one of the most common cancer types. According to the National Breast Cancer foundation, in 2020 alone, more than 276,000 new cases of invasive breast cancer and more than 48,000 non-invasive cases were diagnosed in the US. To put these figures in perspective, 64% of these cases are diagnosed early in the disease’s cycle, giving patients a 99% chance of survival. In this paper we develop a system for diagnosis, prognosis and prediction of breast cancer using AI. This will assist the doctors in diagnosis of the disease. In this research work, we systematically reviewed previous work done on detection and treatment of breast cancer using genetic sequencing or histopathological imaging with the help of deep learning and machine learning We use of AI for breast cancer detection, including studies that have used mammography, ultrasound, and magnetic resonance imaging (MRI) as imaging modalities. AI can also improve the accuracy and efficiency of breast cancer screening and diagnosis, as well as the challenges that must be addressed to ensure the successful integration of AI into clinical practice. However, further research and development are needed to optimize AI algorithms and ensure their safety and effectiveness in clinical practice. Breast cancer detection has emerged as a critical area of research, leveraging the power of Artificial Intelligence (AI) to enhance diagnostic accuracy and efficiency. Utilizing AI technologies, particularly deep learning, enables the development of robust and precise models for early breast cancer detection. These models analyze mammographic images, identifying subtle patterns indicative of malignancies that may escape human eye detection. Transfer learning, employing pre-trained neural network architectures, has demonstrated significant success in leveraging existing knowledge for improved performance. The integration of convolutional neural networks (CNNs) and image processing techniques empowers AI models to discern subtle abnormalities, aiding in the timely identification of potential breast tumors. Additionally, AI-driven diagnostic tools can streamline radiologists' workflow, providing rapid and reliable assessments, ultimately contributing to early intervention and improved patient outcomes. As these technologies continue to evolve, the synergy between AI and breast cancer detection promises to revolutionize screening methods, fostering a paradigm shift towards more accurate, efficient, and accessible diagnostic practices in the realm of breast health.

Intrusion Detection System Using Probabilistic Adaptive Learning

Abstract: Machine learning and deep learning techniques are widely used to evaluate intrusion detection systems (IDS) capable of rapidly and automatically recognizing and classifying cyber-attacks on networks and hosts. However, when destructive attacks are becoming more extensive, more challenges develop, needing a comprehensive response. Numerous intrusion detection datasets are publicly accessible for further analysis by the cybersecurity research community. The Intrusion Detection System (IDS) is an effective tool utilized in cybersecurity systems to detect and identify intrusion attacks. With the increasing volume of data generation, the possibility of various forms of intrusion attacks also increases. Feature selection is crucial and often necessary enhance performance. The structure of the dataset can impact the efficiency of the machine learning model. Furthermore, data imbalance can pose a problem, but sampling approaches can help mitigate it. With technological advancements, machine learning-based methods have emerged as the cornerstone of modern intrusion detection, enabling more precise identification of abnormal behaviors and potential intrusions by learning the patterns of normal network traffic. In response to these challenges, this paper introduces an innovative intrusion detection model that amalgamates the Probabilistic Adaptiv eLearning Network architecture.

Parkinson Disease Detection Using CNN Algorithm

Abstract: Parkinson's disease, a progressive neurological disorder, results from the depletion of dopamine-producing neurons in the brain, leading to diminished motor function. Common symptoms include tremors, rigidity, bradykinesia, shivering, and impaired balance. This study introduces two neural network architectures: the Voice Impairment Classifier, designed for early disease detection. The research conducted a thorough assessment of convolutional neural networks (CNNs) for classifying gait signals transformed into spectrogram images, and deep dense networks for analyzing voice recordings. Results demonstrated superior performance of the proposed models, with the VGFR Spectrogram Detector achieving 88.1% accuracy and the Voice Impairment Classifier achieving 89.15% accuracy, surpassing current state-of-the-art techniques.

Neural Style Transfer

Abstract: The Basically [NST] means a Neural Style Transfer is one Model for changing the whole behaviour of the images. Through the NST we can create a multiple new images using a multiple content image and multiple style images, through this model we can change the all internal structure & Environment of the images, and also in some images the model can transform the style or change a style. Neural style transfer is a machine learning, deep learning and artificial intelligence related one technique thatcombines the features of a content images and style images.Under the content images the all content are present and under the style images all style related images are present are over here. This technique combines the contents imageswith the style of another image creating visually captivatingart works that bridge the gap between human creativity andcomputational process. Introducing the neural network architecture that enables the extraction of content and style features from images.

Estimation of the mean effective pressure of a spark ignition internal combustion engine using a neural network, considering the wall-wetting dynamics

The management and development of internal combustion engines stand as critical pursuits within the automotive and related industries. Utilizing cylinder pressure as feedback, engine controllers rely on intricate systems to regulate performance. However, due to the inherent complexity and nonlinearity of engines, direct measurement of cylinder pressure through pressure sensors is costly and computationally demanding. Consequently, the need for accurate and detailed engine models becomes paramount. Neural networks offer a promising avenue for simulating internal combustion engines, combining speed and precision. By treating the engine as an enigmatic entity, neural networks can construct detailed models. This study aims to employ two types of neural networks—multilayer perceptron and radial basis functions—to train and build a model of an internal combustion engine. These networks will simulate and estimate the engine's mean suitable pressure, allowing for a comparison of their effectiveness. Prior to implementing the neural network architecture, an engine model was constructed in MATLAB to gather necessary training data. This preliminary step ensured a robust foundation for subsequent network design and implementation. In summary, this research focuses on leveraging neural networks to model internal combustion engines, utilizing both multilayer perceptron and radial basis functions to simulate engine behavior and estimate mean suitable pressure.

A three-dimensional, discrete-continuum model of blood pressure in microvascular networks.

We present a 3D discrete-continuum model to simulate blood pressure in large microvascular tissues in the absence of known capillary network architecture. Our hybrid approach combines a 1D Poiseuille flow description for large, discrete arteriolar and venular networks coupled to a continuum-based Darcy model, point sources of flux, for transport in the capillary bed. We evaluate our hybrid approach using a vascular network imaged from the mouse brain medulla/pons using multi-fluorescence high-resolution episcopic microscopy (MF-HREM). We use the fully-resolved vascular network to predict the hydraulic conductivity of the capillary network and generate a fully-discrete pressure solution to benchmark against. Our results demonstrate that the discrete-continuum methodology is a computationally feasible and effective tool for predicting blood pressure in real-world microvascular tissues when capillary microvessels are poorly defined.

Network architecture for single image super‐resolution: A comprehensive review and comparison

AbstractSingle image super‐resolution (SISR) is a promising research direction in computer vision and image processing for improving the visual perception of low‐quality images. In recent years, deep learning algorithms have driven tremendous development in SR, and SR methods based on various network architectures have significantly improved the quality of reconstructed images. Although there has been a large amount of reviews focusing on SISR, few studies have focused specifically on network architectures for SISR. This paper aims to provide a systematic overview of the design ideas of SISR using multiple architectures, including Convolutional Neural Networks (CNN), Generative Adversarial Networks (GAN), Transformer, and Diffusion model. In addition, an experimental analysis and comparison of state‐of‐the‐art SR algorithms have been performed on publicly available quantitative and qualitative datasets. Finally, some future directions are discussed that may help other community researchers.