Concept Of Deep Learning Research Articles

Deep Learning for Reliable Communication Optimization on Autonomous Vehicles

Recent breakthroughs in the autonomous vehicle industry have brought this technology closer to consumers. However, the cost of self-driving solutions still constitutes an entry barrier to many potential users due to its reliance on powerful onboard computers. As an alternative, autonomous driving algorithm processing may be offloaded to remote machines, which requires a reliable connection to the cloud servers. However, despite significant 5G coverage in many countries, mobile network reliability and latency are still inadequate for this purpose. This work explores deep learning concepts to forecast signal quality as a vehicle moves, predicting when periods of degraded network quality will occur. We develop a Long Short-Term Memory (LSTM)-based neural network, trained on multivariate time series containing historical data on several mobile network parameters, and evaluate the results of multi-step Reference Signal Received Power (RSRP) prediction. Results show that our model achieves a rapidly increasing Root-Mean-Square Error (RMSE), reaching over 8 dBm after 25-time steps. This error does not allow for the accurate prediction of future signal quality.

The development system of local music teaching materials based on deep learning

In the education industry, the transformation of educational concepts, the reform of teaching courses and the reorganization of teaching materials are the only way to strengthen quality education. Local music(LM) education is no exception. The development of LM teaching materials (TMs) suitable for various regions and schools is of great significance to deepen students' understanding of TMC and improve their interest in LM courses. Deep learning is a new artificial intelligence method that has been widely concerned and widely used in recent years. It is the hottest development content in artificial intelligence and is used in many fields. Deep neural network models have strong expressiveness, and model training is closer to the way the brain works. Therefore, based on the concept of deep learning, this paper builds a development system for local music teaching materials. Each school can refer to this system to develop textbooks, and in the process of TD, intelligent development software can be used to write textbooks. This paper analyzes the current situation of the development of TM teaching materials in 15 schools in a province through the methods of investigation, interview and data statistics, and expounds the attitudes and factors affecting the development of TMs from the perspectives of schools, teachers and students(TAS). The results show that there are 9 schools. Support the development of TMs. A total of 58.65 % of teachers and students are in favor of the development of TMs, but 39.29 % of teachers believe that their ability to develop traditional music TMs is average, and students do not have a deep understanding of LM. Therefore, the development of traditional music teaching It is necessary to conduct an in-depth discussion on the two teaching subjects of TAS.

SCNN Based Classification Technique for the Face Spoof Detection Using Deep Learning Concept

SCNN Based Classification Technique for the Face Spoof Detection Using Deep Learning Concept

An IoT-Based Framework and Ensemble Optimized Deep Maxout Network Model for Breast Cancer Classification

Internet of Things (IoT) plays an essential role in the area of the healthcare system. IoT devices provide information about patients in the healthcare monitoring framework. Moreover, patients can examine their health with smart devices and hence IoT is a major factor in all aspects of the health care management system. Breast cancer is a deadly cancer in women and the detection of this disease at the primary stage increases the survival rate. Due to the computational complexity associated with acquiring features, classification results generated from the existing methods are unsatisfactory and hence it is important to design a method using deep learning concepts for classifying cancer disease. An efficient and robust classification model named Student Psychology Whale Optimization-based Deep maxout network with optimization (SPWO-based Deep maxout network) classifies breast cancer disease. The advantage of using a Deep maxout network is that it effectively learns intrinsic features from the data. The weight factor of the deep learning model is updated with respect to iteration based on the fitness measure that in turn results in higher results by acquiring a minimal error value. However, the proposed model obtains outstanding accuracy, sensitivity, and specificity in terms of testing with the values of 0.931, 0.953, and 0.915 with 100 nodes.

An Educational Graphical User Interface to Construct Convolutional Neural Networks for Teaching Artificial Intelligence in Radiology.

Deep learning techniques using convolutional neural networks (CNNs) have been successfully developed for various medical image analysis tasks. However, the skills to understand and develop deep learning models are not usually taught during radiology training, which constitutes a barrier for radiologists looking to integrate machine learning (ML) into their research or clinical practice. In this work, we developed and evaluated an educational graphical user interface (GUI) to construct CNNs for teaching deep learning concepts to radiology trainees. The GUI was developed in Python using the PyQt and PyTorch frameworks. The functionality of the GUI was demonstrated through a binary classification task on a dataset of MR images of the brain. The usability of the GUI was assessed through 45-min user testing sessions with 5 neuroradiologists and neuroradiology fellows, assessing mean task completion times, the System Usability Scale (SUS), and a qualitative questionnaire as metrics. Task completion times were compared against a ML expert who performed the same tasks. After a 20-min introduction to CNNs and a walkthrough of the GUI, users were able to perform all assigned tasks successfully. There was no significant difference in task completion time compared to a ML expert. The educational GUI achieved a score of 82.5 on the SUS, suggesting that the system is highly usable. Users indicated that the GUI seems useful as an educational tool to teach ML topics to radiology trainees. An educational GUI allows interactive teaching in ML that can be incorporated into radiology training.

Literature Review on Image Restoration

Image restoration is an essential part in the field of computer vision, which aims at predicting and filling the pixels of the missing images to achieve satisfactory visual effects, it has extensive application value in the fields of film and television special effects production, image editing, digital cultural heritage protection and virtual reality. With the introduction and application of the concept of deep learning in recent years, it has been widely studied in the academic and industrial fields, the performance of image restoration has been significantly improved, so that this long-standing research topic has once again aroused widespread concern and heated discussion on the social level. In order to enable more researchers to explore the theory of image restoration and its development, this paper reviews the related technologies in this field: firstly, the traditional image restoration methods are described, secondly, the background of deep learning is introduced, then the image restoration methods based on deep learning are described, subsequently, the several deep-learning based methods are compared and analyzed, finally, the future research direction and emphasis of image restoration are analyzed and prospected.

Overview of Deep Learning-Based CSI Feedback in Massive MIMO Systems

Many performance gains achieved by massive multiple-input and multiple-output depend on the accuracy of the downlink channel state information (CSI) at the transmitter (base station), which is usually obtained by estimating at the receiver (user equipment) and feeding back to the transmitter. The overhead of CSI feedback occupies substantial uplink bandwidth resources, especially when the number of transmit antennas is large. Deep learning (DL)-based CSI feedback refers to CSI compression and reconstruction by a DL-based autoencoder and can greatly reduce feedback overhead. In this paper, a comprehensive overview of state-of-the-art research on this topic is provided, beginning with basic DL concepts widely used in CSI feedback and then categorizing and describing some existing DL-based feedback works. The focus is on novel neural network architectures and utilization of communication expert knowledge to improve CSI feedback accuracy. Works on joint design of CSI feedback with other communication modules are also introduced, and some practical issues, including bitstream generation, multirate feedback, imperfect feedback, NN complexity, training dataset collection, online training, and standardization effect, are discussed. At the end of the paper, some challenges and potential research directions associated with DL-based CSI feedback in future wireless communication systems are identified.

Myoelectric Control With Fixed Convolution-Based Time-Domain Feature Extraction: Exploring the Spatio–Temporal Interaction

The role of feature extraction in electromyogram (EMG) based pattern recognition has recently been emphasized with several publications promoting deep learning (DL) solutions that outperform traditional methods. It has been shown that the ability of DL models to extract temporal, spatial, and spatio–temporal information provides significant enhancements to the performance and generalizability of myoelectric control. Despite these advancements, it can be argued that DL models are computationally very expensive, requiring long training times, increased training data, and high computational resources, yielding solutions that may not yet be feasible for clinical translation given the available technology. The aim of this paper is, therefore, to leverage the benefits of spatio–temporal DL concepts into a computationally feasible and accurate traditional feature extraction method. Specifically, the proposed novel method extracts a set of well-known time-domain features into a matrix representation, convolves them with predetermined fixed filters, and temporally evolves the resulting features over a short and long-term basis to extract the EMG temporal dynamics. The proposed method, based on Fixed Spatio–Temporal Convolutions, offers significant reductions in the computational costs, while demonstrating a solution that can compete with, and even outperform, recent DL models. Experimental tests were performed on sparse-and high-density EMG (HD-EMG) signals databases, across a total of 44 subjects performing a maximum of 53 movements. Despite the simplification compared to deep approaches, our results show that the proposed solution significantly reduces the classification error rates by 3% to 10% in comparison to recent DL models, while being efficient for real-time implementations.

Explainability and controllability of patient-specific deep learning with attention-based augmentation for markerless image-guided radiotherapy.

We reported the concept of patient-specific deep learning (DL) for real-time markerless tumor segmentation in image-guided radiotherapy (IGRT). The method was aimed to control the attention of convolutional neural networks (CNNs) by artificial differences in co-occurrence probability (CoOCP) in training datasets, that is, focusing CNN attention on soft tissues while ignoring bones. However, the effectiveness of this attention-based data augmentation has not been confirmed by explainable techniques. Furthermore, compared to reasonable ground truths, the feasibility of tumor segmentation in clinical kilovolt (kV) X-ray fluoroscopic (XF) images has not been confirmed. The first aim of this paper was to present evidence that the proposed method provides an explanation and control of DL behavior. The second purpose was to validate the real-time lung tumor segmentation in clinical kV XF images for IGRT. This retrospective study included 10 patients with lung cancer. Patient-specific and XF angle-specific image pairs comprising digitally reconstructed radiographs (DRRs) and projected-clinical-target-volume (pCTV) images were calculated from four-dimensional computer tomographic data and treatment planning information. The training datasets were primarily augmented by random overlay (RO) and noise injection (NI): RO aims to differentiate positional CoOCP in soft tissues and bones, and NI aims to make a difference in the frequency of occurrence of local and global image features. The CNNs for each patient-and-angle were automatically optimized in the DL training stage to transform the training DRRs into pCTV images. In the inference stage, the trained CNNs transformed the test XF images into pCTV images, thus identifying target positions and shapes. The visual analysis of DL attention heatmaps for a test image demonstrated that our method focused CNN attention on soft tissue and global image features rather than bones and local features. The processing time for each patient-and-angle-specific dataset in the training stage was ∼30min, whereas that in the inference stage was 8ms/frame. The estimated three-dimensional 95 percentile tracking error, Jaccard index, and Hausdorff distance for 10 patients were 1.3-3.9mm, 0.85-0.94, and 0.6-4.9mm, respectively. The proposed attention-based data augmentation with both RO and NI made the CNN behavior more explainable and more controllable. The results obtained demonstrated the feasibility of real-time markerless lung tumor segmentation in kV XF images for IGRT.

Application of Deep learning in computer vision

The application of artificial intelligence is deep learning which is one of the current topics in the computer field as well as for the application of computer vision. With the continuous enhancement of deep learning, the algorithm performance is constantly updated. This review paper provides a brief overview of the basic concepts of computer vision and deep learning. Image classification, semantic segmentation and object detection are introduced in this paper followed by a description of their real world applications in various computer vision tasks, such as smart transportation and face recognition. Afterwards, the main applications of deep learning in the research field are demonstrated in this paper.

A survey on deep learning applied to medical images: from simple artificial neural networks to generative models.

Deep learning techniques, in particular generative models, have taken on great importance in medical image analysis. This paper surveys fundamental deep learning concepts related to medical image generation. It provides concise overviews of studies which use some of the latest state-of-the-art models from last years applied to medical images of different injured body areas or organs that have a disease associated with (e.g., brain tumor and COVID-19 lungs pneumonia). The motivation for this study is to offer a comprehensive overview of artificial neural networks (NNs) and deep generative models in medical imaging, so more groups and authors that are not familiar with deep learning take into consideration its use in medicine works. We review the use of generative models, such as generative adversarial networks and variational autoencoders, as techniques to achieve semantic segmentation, data augmentation, and better classification algorithms, among other purposes. In addition, a collection of widely used public medical datasets containing magnetic resonance (MR) images, computed tomography (CT) scans, and common pictures is presented. Finally, we feature a summary of the current state of generative models in medical image including key features, current challenges, and future research paths.

Determining Optimal Zone Radius of Zone Routing Protocol Based on Deep Recurrent Neural Networks in the Next Generation Wireless Backhaul Networks

Next-generation wireless networks are becoming more popular and rely on reliable backhaul networks to work properly. Wireless backhaul networks also adopt various innovative technologies to improve capacity and provide more flexible deployments to meet networks' high-quality requirements. One of the essential innovations to maintain the wireless backhaul performance is combining the existing routing protocol technology and the deep learning concept. The concept of deep learning is gaining traction as a powerful way to add intelligence to wireless networks with complex topologies and radio environments. This is because conventional routing protocols do not learn from their previous experiences with various network anomalies. This paper proposed a predictive model of zone radius value using the deep recurrent neural network variant, namely the long short-term memory recurrent neural network (LSTM-RNN) algorithm. Determination of zone radius value conducted by measuring the whole of nodes routing zone using various network performance as input parameters such as Routing Overhead, Energy Consumption, Throughput, and User Usage. Performance measurements such as mean square error (MSE), error distribution histogram, training state, regression, correlation, and time series response are gauged and compared for static and mobile node environments. Results showed that the proposed algorithm can accurately predict zone radius for both environments. However, the accuracy of the proposed algorithm is higher when implemented in a static node environment.

Deep learning in neuroimaging data analysis: Applications, challenges, and solutions.

Methods for the analysis of neuroimaging data have advanced significantly since the beginning of neuroscience as a scientific discipline. Today, sophisticated statistical procedures allow us to examine complex multivariate patterns, however most of them are still constrained by assuming inherent linearity of neural processes. Here, we discuss a group of machine learning methods, called deep learning, which have drawn much attention in and outside the field of neuroscience in recent years and hold the potential to surpass the mentioned limitations. Firstly, we describe and explain the essential concepts in deep learning: the structure and the computational operations that allow deep models to learn. After that, we move to the most common applications of deep learning in neuroimaging data analysis: prediction of outcome, interpretation of internal representations, generation of synthetic data and segmentation. In the next section we present issues that deep learning poses, which concerns multidimensionality and multimodality of data, overfitting and computational cost, and propose possible solutions. Lastly, we discuss the current reach of DL usage in all the common applications in neuroimaging data analysis, where we consider the promise of multimodality, capability of processing raw data, and advanced visualization strategies. We identify research gaps, such as focusing on a limited number of criterion variables and the lack of a well-defined strategy for choosing architecture and hyperparameters. Furthermore, we talk about the possibility of conducting research with constructs that have been ignored so far or/and moving toward frameworks, such as RDoC, the potential of transfer learning and generation of synthetic data.

An intelligent driven deep residual learning framework for brain tumor classification using MRI images

Brain tumor classification is an expensive complicated challenge in the sector of clinical image analysis. Machine learning algorithms enabled radiologists to accurately diagnose tumors without requiring major surgery. However, several challenges rise; first, the major challenge in designing the most accurate deep learning architecture for classifying brain tumors; and secondly, difficulty of finding an expert who is experienced in the field of classifying brain tumors using images by deep learning models. These difficulties made us motivated to propose an advanced and high accurate framework based on the concepts of deep learning and evolutionary algorithms to automatically design the ResNet architecture efficiently for classifying three types of brain tumors on a large database of MRI images. Thus, we propose an optimization-based deep convolutional ResNet model combined with a novel evolutionary algorithm to optimize the architecture and hyperparameters of deep ResNet model automatically without need of human experts as well manual architecture design which is complicated task to classify different types of brain tumor. Also, we propose an improved version of ant colony optimization (IACO) based on the concepts of differential evolution strategy and multi-population operators. These two concepts make an effective balance for solution diversity and convergence speed as well as enhancing the optimization performance and avoiding falling into the local optima for designing the deep learning-based ResNet architectures. The experimental finding revealed that our proposed framework obtained an average accuracy of 0.98694 which efficiently shows that our IACO-ResNet algorithm can help excellently with the automatic classification of brain tumors.

Deep learning in bladder cancer imaging: A review.

Deep learning (DL) is a rapidly developing field in machine learning (ML). The concept of deep learning originates from research on artificial neural networks and is an upgrade of traditional neural networks. It has achieved great success in various domains and has shown potential in solving medical problems, particularly when using medical images. Bladder cancer (BCa) is the tenth most common cancer in the world. Imaging, as a safe, noninvasive, and relatively inexpensive technique, is a powerful tool to aid in the diagnosis and treatment of bladder cancer. In this review, we provide an overview of the latest progress in the application of deep learning to the imaging assessment of bladder cancer. First, we review the current deep learning approaches used for bladder segmentation. We then provide examples of how deep learning helps in the diagnosis, staging, and treatment management of bladder cancer using medical images. Finally, we summarize the current limitations of deep learning and provide suggestions for future improvements.

A Survey on Medical Image Segmentation Based on Deep Learning Techniques

Deep learning techniques have rapidly become important as a preferred method for evaluating medical image segmentation. This survey analyses different contributions in the deep learning medical field, including the major common issues published in recent years, and also discusses the fundamentals of deep learning concepts applicable to medical image segmentation. The study of deep learning can be applied to image categorization, object recognition, segmentation, registration, and other tasks. First, the basic ideas of deep learning techniques, applications, and frameworks are introduced. Deep learning techniques that operate the ideal applications are briefly explained. This paper indicates that there is a previous experience with different techniques in the class of medical image segmentation. Deep learning has been designed to describe and respond to various challenges in the field of medical image analysis such as low accuracy of image classification, low segmentation resolution, and poor image enhancement. Aiming to solve these present issues and improve the evolution of medical image segmentation challenges, we provide suggestions for future research.

A transfer learning‐based system for grading breast invasive ductal carcinoma

AbstractBreast carcinoma is a sort of malignancy that begins in the breast. Breast malignancy cells generally structure a tumour that can routinely be seen on an x‐ray or felt like a lump. Despite advances in screening, treatment, and observation that have improved patient endurance rates, breast carcinoma is the most regularly analyzed malignant growth and the subsequent driving reason for malignancy mortality among ladies. Invasive ductal carcinoma is the most boundless breast malignant growth with about 80% of all analyzed cases. It has been found from numerous types of research that artificial intelligence has tremendous capabilities, which is why it is used in various sectors, especially in the healthcare domain. In the initial phase of the medical field, mammography is used for diagnosis, and finding cancer in the case of a dense breast is challenging. The evolution of deep learning and applying the same in the findings are helpful for earlier tracking and medication. The authors have tried to utilize the deep learning concepts for grading breast invasive ductal carcinoma using Transfer Learning in the present work. The authors have used five transfer learning approaches here, namely VGG16, VGG19, InceptionReNetV2, DenseNet121, and DenseNet201 with 50 epochs in the Google Colab platform which has a single 12GB NVIDIA Tesla K80 graphical processing unit (GPU) support that can be used up to 12 h continuously. The dataset used for this work can be openly accessed from http://databiox.com. The experimental results that the authors have received regarding the algorithm's accuracy are as follows: VGG16 with 92.5%, VGG19 with 89.77%, InceptionReNetV2 with 84.46%, DenseNet121 with 92.64%, DenseNet201 with 85.22%. From the experimental results, it is clear that the DenseNet121 gives the maximum accuracy in terms of cancer grading, whereas the InceptionReNetV2 has minimal accuracy.

A Pattern-Recognizer Artificial Neural Network for the Prediction of New Crescent Visibility in Iraq

Various theories have been proposed since in last century to predict the first sighting of a new crescent moon. None of them uses the concept of machine and deep learning to process, interpret and simulate patterns hidden in databases. Many of these theories use interpolation and extrapolation techniques to identify sighting regions through such data. In this study, a pattern recognizer artificial neural network was trained to distinguish between visibility regions. Essential parameters of crescent moon sighting were collected from moon sight datasets and used to build an intelligent system of pattern recognition to predict the crescent sight conditions. The proposed ANN learned the datasets with an accuracy of more than 72% in comparison to the actual observational results. ANN simulation gives a clear insight into three crescent moon visibility regions: invisible (I), probably visible (P), and certainly visible (V). The proposed ANN is suitable for building lunar calendars, so it was used to build a four-year calendar on the horizon of Baghdad. The built calendar was compared with the official Hijri calendar in Iraq.

The Generation of Piano Music Using Deep Learning Aided by Robotic Technology.

In order to improve the accuracy and precision of music generation assisted by robotics, this study analyzes the application of deep learning in piano music generation. Firstly, based on the basic concepts of robotics and deep learning, the advantages of long short-term memory (LSTM) networks are introduced and applied to the piano music generation. Meanwhile, based on LSTM, dropout coefficients are used for optimization. Secondly, various parameters of the algorithm are determined, including the effects of the number of iterations and neurons in the hidden layer on the effect of piano music generation. Finally, the generated music sequence spectrograms are analyzed to illustrate the accuracy and rationality of the algorithm. The spectrograms are compared with the music sequence spectrograms generated by the traditional restricted Boltzmann machine (RBM) music generation algorithm. The results show that (1) when the dropout coefficient value is 0.7, the function converges faster, and the experimental results are better; (2) when the number of iterations is 6000, the error between the generated music sequence and the original music is the smallest; (3) the number of hidden layers of the network is set to 4. When the number of neurons in each hidden layer is set to 1024, the training result of the network is optimal; (4) compared with the traditional RBM piano music generation algorithm, the LSTM-based algorithm and the sampling frequency distribution tend to be consistent with the original sample. The results show that the network has good performance in music generation and can provide a certain reference for automatic music generation.

Deep Learning-Based ECG Abnormality Identification Prediction and Analysis

In recent years, China’s economy has been developing rapidly, and people’s life and quality of life have been improving; more importantly, people’s habits and living habits have also developed from the previous “unhygienic” and “not very careful” to the current “Healthier, more hygienic, greener and more sophisticated” direction. In the process of this development, due to the rapid development of the economy and the industrialization of cities, the incidence of heart disease is also increasing year by year. According to relevant studies, China’s urbanization process has been unprecedented, the number of urbanized people in China has exploded in recent years, and the ratio of urban to rural population has increased from about 20 percent to about 75 percent today. The effects of the population and the urbanization of urban architecture are affecting people’s physical and mental health, both consciously and unconsciously, causing both positive and negative physical and mental effects on the psychological and physical levels. In this paper, the concept of deep learning is fully utilized to train the CNN neural network model and apply it to the ECG abnormality recognition and prediction examination. In order to fully validate the application and significance of deep learning in ECG abnormality identification and prediction, the whole project was completed through subjective and objective experiments. The experimental results show that, from the subjective aspect, the ECG examination has been accepted by most people for different age groups, and the analysis results of the ECG examination with the deep learning model in this paper are more satisfactory; from the objective aspect, the CNN-ECG abnormality recognition prediction network model trained in this paper has high. The accuracy of the model for ECG abnormality recognition prediction can reach 86% when the learning rate is set to 0.0001 and the batch size is set to 120, and the model can reduce the burden of medical personnel to a certain extent.