CNN-based Deep Learning Research Articles

Detecting the presence of supernumerary teeth during the early mixed dentition stage using deep learning algorithms: A pilot study.

Supernumerary teeth are a common anomaly and are frequently observed in paediatric patients. To prevent or minimize complications, early diagnosis and treatment is ideal in children with supernumerary teeth. This study aimed to apply convolutional neural network (CNN)-based deep learning to detect the presence of supernumerary teeth in children during the early mixed dentition stage. Three CNN models, AlexNet, VGG16-TL, and InceptionV3-TL, were employed in this study. A total of 220 panoramic radiographs (from children aged 6years 0months to 9years 6months) including supernumerary teeth (cases, n=120) or no anomalies (controls, n=100) were retrospectively analyzed. The CNN performances were assessed according to accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curves, and area under the ROC curves for a cross-validation test dataset. The VGG16-TL model had the highest performance according to accuracy, sensitivity, specificity, and area under the ROC curve, but the other models had similar performance. CNN-based deep learning is a promising approach for detecting the presence of supernumerary teeth during the early mixed dentition stage.

Voxel-based morphometry and a deep learning model for the diagnosis of early Alzheimer's disease based on cerebral gray matter changes.

This study aimed to analyse cerebral grey matter changes in mild cognitive impairment (MCI) using voxel-based morphometry and to diagnose early Alzheimer's disease using deep learning methods based on convolutional neural networks (CNNs) evaluating these changes. Participants (111 MCI, 73 normal cognition) underwent 3-T structural magnetic resonance imaging. The obtained images were assessed using voxel-based morphometry, including extraction of cerebral grey matter, analyses of statistical differences, and correlation analyses between cerebral grey matter and clinical cognitive scores in MCI. The CNN-based deep learning method was used to extract features of cerebral grey matter images. Compared to subjects with normal cognition, participants with MCI had grey matter atrophy mainly in the entorhinal cortex, frontal cortex, and bilateral frontotemporal lobes (p < 0.0001). This atrophy was significantly correlated with the decline in cognitive scores (p < 0.01). The accuracy, sensitivity, and specificity of the CNN model for identifying participants with MCI were 80.9%, 88.9%, and 75%, respectively. The area under the curve of the model was 0.891. These findings demonstrate that research based on brain morphology can provide an effective way for the clinical, non-invasive, objective evaluation and identification of early Alzheimer's disease.

Blockchain and deep learning technologies for construction equipment security information management

Construction equipment security information management (CESIM) is a critical component of equipment security management. However, equipment-related information's authenticity and integrity cannot be guaranteed in centralized systems currently, which limits the effectiveness of CESIM. In addressing this issue, a framework that combines blockchain and deep learning technologies is proposed by providing decentralized data storage, keeping data authentic, and protecting data from tampering. In accordance with the proposed framework, a prototype system is developed and further evaluated. Results show that the prototype system can improve the efficiency of equipment supervision, decision making, and accident tracking in equipment security management. In conclusion, this study aims to place emphasis on: (1) applying blockchain technology to ensure equipment-related information authentic and secure; (2) developing word2vec + CNN-based deep learning to automatically identify keywords and categories of equipment inspection reports; and (3) verifying the feasibility of the proposed framework and developing a prototype system for further application

Automated Diagnosis of Cervical Intraepithelial Neoplasia in Histology Images via Deep Learning.

Artificial intelligence has enabled the automated diagnosis of several cancer types. We aimed to develop and validate deep learning models that automatically classify cervical intraepithelial neoplasia (CIN) based on histological images. Microscopic images of CIN3, CIN2, CIN1, and non-neoplasm were obtained. The performances of two pre-trained convolutional neural network (CNN) models adopting DenseNet-161 and EfficientNet-B7 architectures were evaluated and compared with those of pathologists. The dataset comprised 1106 images from 588 patients; images of 10% of patients were included in the test dataset. The mean accuracies for the four-class classification were 88.5% (95% confidence interval [CI], 86.3–90.6%) by DenseNet-161 and 89.5% (95% CI, 83.3–95.7%) by EfficientNet-B7, which were similar to human performance (93.2% and 89.7%). The mean per-class area under the receiver operating characteristic curve values by EfficientNet-B7 were 0.996, 0.990, 0.971, and 0.956 in the non-neoplasm, CIN3, CIN1, and CIN2 groups, respectively. The class activation map detected the diagnostic area for CIN lesions. In the three-class classification of CIN2 and CIN3 as one group, the mean accuracies of DenseNet-161 and EfficientNet-B7 increased to 91.4% (95% CI, 88.8–94.0%), and 92.6% (95% CI, 90.4–94.9%), respectively. CNN-based deep learning is a promising tool for diagnosing CIN lesions on digital histological images.

Recognition of mRNA N4 Acetylcytidine (ac4C) by Using Non-Deep vs. Deep Learning

Deep learning models have been successfully applied in a wide range of fields. The creation of a deep learning framework for analyzing high-performance sequence data have piqued the research community’s interest. N4 acetylcytidine (ac4C) is a post-transcriptional modification in mRNA, is an mRNA component that plays an important role in mRNA stability control and translation. The ac4C method of mRNA changes is still not simple, time consuming, or cost effective for conventional laboratory experiments. As a result, we developed DL-ac4C, a CNN-based deep learning model for ac4C recognition. In the alternative scenario, the model families are well-suited to working in large datasets with a large number of available samples, especially in biological domains. In this study, the DL-ac4C method (deep learning) is compared to non-deep learning (machine learning) methods, regression, and support vector machine. The results show that DL-ac4C is more advanced than previously used approaches. The proposed model improves the accuracy recall area by 9.6 percent and 9.8 percent, respectively, for cross-validation and independent tests. More nuanced methods of incorporating prior bio-logical knowledge into the estimation procedure of deep learning models are required to achieve better results in terms of predictive efficiency and cost-effectiveness. Based on an experiment’s acetylated dataset, the DL-ac4C sequence-based predictor for acetylation sites in mRNA can predict whether query sequences have potential acetylation motifs.

An Improved Anti-Jamming Method Based on Deep Reinforcement Learning and Feature Engineering

To improve the performance of anti-jamming communication in dynamic and adversarial jamming environment, an improved anti-jamming method is proposed based on deep reinforcement learning and feature engineering. Different from the existing studies that use computer vision of deep learning based on the infinite state of spectrum waterfall, the proposed method relays on analyzing spectrum differences between adjacent time slots which contains information and features of jamming patterns. First, anti-jamming strategy is trained by countering the jammer which carries out a random jamming patterns switching strategy. Second, an improved state space is introduced by containing historical spectrum of communication and jamming signal between adjacent time slots, which can help an anti-jamming agent effectively extract the features of jamming patterns to reduce computational complexity. In addition, an improved reward function based on channel switch cost is improved for considering propagation characteristics which may cause communication performance lost. Taking advantage of both feature engineering and deep reinforcement learning, an improved anti-jamming method is proposed to improve reliable anti-jamming performance. Compared with the traditional CNN-based deep reinforcement learning anti-jamming method, simulation results show that the improved method can obtain better performance and lower computational complexity.

Multi-Objective Genetic Algorithm and CNN-Based Deep Learning Architectural Scheme for effective spam detection

E-mail has traditionally been regarded as the most powerful medium in online social networks, where users can discuss, connect, and share links with other online social media users. In particular, Twitter, in particular, has been determined to be the most popular social network that serves as the best communication channel for its users to share current news, ideas, thoughts, comments, and beliefs with other online social media users. Despite the efforts put in to combat spam operations on the online social network, Twitter spam has a new type of functionality that is limited to 140 characters. It is not only the major cause of annoyance for day-to-day users, but also responsible for the majority of computer security issues that cost billions of dollars in terms of productivity losses. In this paper, we propose a Multi-Objective Genetic Algorithm and a CNN-based Deep Learning Architectural Scheme (MOGA–CNN–DLAS) for the predominant Twitter spam detection process. The experimental details and results discussions of the proposed MOGA-CNN-DLAS are evaluated in terms of accuracy, precision, recall, F-Score, RMSE, and MAE by varying the ratio of training data under the utilization of three real datasets, such as the Twitter 100k dataset and the ASU dataset.

Fabric Hairiness Analysis for Quality Inspection of Pile Fabric Products Using Computer Vision Technology

The textile industry is one of the important industries which can enhance their productivity using Artificial Intelligence technology. Most of the textile industries inspect the product manually, however, the development of AI-driven technology pushes manufacturing industries into a new era. In this paper, a computer vision-based approach for hairiness analysis in pile textile is proposed. The proposed system detects and highlights the hairy area of the fabric where the images were acquired by using an RGB camera. The experimental images were collected in our laboratory using a stereo ZED camera, but only the RGB images were processed to detect the hairiness of the fabric. The proposed hardware architecture consists mainly of camera, processing device, robotics, camera control system, while the software prototype consists of image processing techniques. In software architecture, image acquisition systems, image pre-processing, image classification, and image visualization are the major steps. A CNN-based deep learning architecture was used to classify the hairier textile and the test was carried out in big images using sliding window techniques. The classification accuracy was 99% during the training and test accuracy was 92%.

Detection and Weak Segmentation of Masses in Gray-Scale Breast Mammogram Images Using Deep Learning.

PurposeIn this paper, we propose deep-learning methodology with which to enhance the mass differentiation performance of convolutional neural network (CNN)-based architecture.Materials and MethodsWe differentiated breast mass lesions from gray-scale X-ray mammography images based on regions of interest (ROIs). Our dataset comprised breast mammogram images for 150 cases of malignant masses from which we extracted the mass ROI, and we composed a CNN-based deep learning model trained on this dataset to identify ROI mass lesions. The test dataset was created by shifting some of the training data images. Thus, although both datasets were different, they retained a deep structural similarity. We then applied our trained deep-learning model to detect masses on 8-bit mammogram images containing malignant masses. The input images were preprocessed by applying a scaling parameter of intensity before being used to train the CNN model for mass differentiation.ResultsThe highest area under the receiver operating characteristic curve was 0.897 (Î 20).ConclusionOur results indicated that the proposed patch-wise detection method can be utilized as a mass detection and segmentation tool.

Methods of Generating Time Series Image for detecting Anomalies in Time Series data

To detect anomalies in time series data, statistical techniques such as PCA and autoencoder are used, or anomalies are detected based on deep learning models such as RNN. It is difficult to expect good performance only with simple statistical techniques or RNN-based deep learning models because the environment and causes in which anomalies are recorded are not simple and various variables affect them. In this paper, we proposed a method of detecting anomalies using CNN-based deep learning model, a binary classification model of representative images, by imaging time series data. RP, GASF, GADF, and MAF algorithms were used as methods for imaging. All of time series image-based models showed equal or higher accuracy than conventional LSTM-based models, and among imaging-based CNN models, the method of imaging with MTF algorithm derived the highest accuracy.

Fusion-Based Semantic Segmentation Using Deep Learning Architecture in Case of Very Small Training Dataset

Semantic segmentation is a pre-processing step in computer vision-based applications. It is the task of assigning a predefined class label to every pixel of an image. Several supervised and unsupervised algorithms are available to classify pixels of an image into predefined object classes. The algorithms, such as random forest and SVM are used to obtain the semantic segmentation. Recently, convolutional neural network (CNN)-based architectures have become popular for the tasks of object detection, object recognition, and segmentation. These deep architectures perform semantic segmentation with far better accuracy than the algorithms that were used earlier. CNN-based deep learning architectures require a large dataset for training. In real life, some of the applications may not have sufficient good quality samples for training of deep learning architectures e.g. medical applications. Such a requirement initiated a need to have a technique of effective training of deep learning architecture in case of a very small dataset. Class imbalance is another challenge in the process of training deep learning architecture. Due to class imbalance, the classifier overclassifies classes with large samples. In this paper, the challenge of training a deep learning architecture with a small dataset and class imbalance is addressed by novel fusion-based semantic segmentation technique which improves segmentation of minor and major classes.

Reconstructed phase space portraits for detecting brain diseases using deep learning

Background and objectiveAbnormalities in the brain affect its functions, and is observed among people of all background. Automatic identification of these abnormalities will assist treatment. These abnormalities are observable in the electroencephalogram (EEG) signal which measures the electrical activity of the brain. The EEG signal is nonlinear and chaotic in nature. Automatic detection of certain diseases affecting the brain has been attempted using the spatial and temporal characteristics of the EEG employing signal processing, image processing and machine learning techniques. We propose the automatic identification of the abnormalities in the brain based on the depiction of its nonlinear chaotic nature.MethodsAccurate detection across multiple brain diseases is a far more challenging problem given the dynamic nature of the EEG signal. We employ Reconstructed Phase Space (RPS) portraits to model these nonlinear dynamics. The EEG signal analysis of short segments results in RPS portraits that implicitly capture the dynamics. In this study, we examine the performance of CNN-based deep learning models as feature extractors from RPS portraits of EEG signals in achieving an improved screening of brain diseases, by classifying them as normal or diseased.ResultsThe use of CNN architectures like Inception-v4 results in high accuracy (97.30%) in the identification of brain diseases (Epilepsy, Schizophrenia, and Sleep Disorder). A further improvement (98.44±1.5%) in the disease identification is achieved using a voting classifier.ConclusionsThe non-linear dynamics and CNNs for learning salient features suitable for accurately identifying the brain disease in an end-to-end system is a novel contribution of this study. The high performance of the system makes it feasible to study its utility as a diagnostic support tool.

Prediction of Beck Depression Inventory Score in EEG: Application of Deep-Asymmetry Method

There is ongoing research on using electroencephalography (EEG) to predict depression. In particular, the deep learning method in which brain waves are used as inputs of a convolutional neural network (CNN) is being widely researched and has shown remarkable performance. We built a regression model to predict the severity score (Beck Depression Inventory [BDI]) of depressed patients as an extension of the deep-asymmetry method, which has shown promising performance in depression classification. Predicting the severity of depression is very important because the treatment and coping methods are different for each severity level. We imaged brain waves using the deep-asymmetry method, used them to train a two-dimensional CNN-based deep learning model, and achieved satisfactory performance. The EEG image-based CNN approach will make an important contribution to creating a highly interpretable model for predicting depression in the future.

MDCHD: A novel malware detection method in cloud using hardware trace and deep learning

With the development of cloud computing, more and more enterprises and institutes have deployed important computing tasks and data into virtualization environments. Virtualization security has become very important for cloud computing. When an attacker controls a victim’s virtual machine, he (or she) may launch malware for malicious purpose in that virtual machine. To defend against malware attacks in the cloud, many virtualization-based approaches are proposed. However, the existing methods suffer from limitations in terms of transparency and performance cost. To address these issues, we propose MDCHD, a novel malware detection solution for virtualization environments. This method first utilizes the Intel Processor Trace (IPT) mechanism to collect the run-time control flow information of the target program. Then, it converts the control flow information into color images. By doing so, we can utilize a CNN-based deep learning method to identify malware from the images. To improve the performance of our detection mechanism, we leverage Lamport’s ring buffer algorithm. In this way, the control flow information collector and security checker can work concurrently. The evaluation shows that our approach can achieve acceptable detection accuracy with a minimal performance cost.

Mask Detection and Tracing System

Covid19 has given a new identity for wearing a mask. It is meaningful when these masked faces are detected accurately and efficiently. As a unique face detection task, face mask detection is much more difficult because of extreme occlusions which leads to the loss of face details. Besides, there is almost no existing large-scale accurately labelled masked face dataset, which increase the difficulty of face mask detection. The system encourages to use CNN-based deep learning algorithms which has done vast progress towards researches in face detection In this paper, we propose novel CNN-based method which is formed of three convolutional neural networks to detect face mask. Besides, because of the shortage of face masked training samples, we propose a new dataset called” face mask dataset” to finetune our CNN models. We evaluate our proposed face mask detection algorithm on the face mask testing set, and it achieves satisfactory performance

Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies—Part 2: Recommendations and Best Practices

Convolutional neural network (CNN)-based deep learning (DL) has a wide variety of applications in the geospatial and remote sensing (RS) sciences, and consequently has been a focus of many recent studies. However, a review of accuracy assessment methods used in recently published RS DL studies, focusing on scene classification, object detection, semantic segmentation, and instance segmentation, indicates that RS DL papers appear to follow an accuracy assessment approach that diverges from that of traditional RS studies. Papers reporting on RS DL studies have largely abandoned traditional RS accuracy assessment terminology; they rarely reported a complete confusion matrix; and sampling designs and analysis protocols generally did not provide a population-based confusion matrix, in which the table entries are estimates of the probabilities of occurrence of the mapped landscape. These issues indicate the need for the RS community to develop guidance on best practices for accuracy assessment for CNN-based DL thematic mapping and object detection. As a first step in that process, we explore key issues, including the observation that accuracy assessments should not be biased by the CNN-based training and inference processes that rely on image chips. Furthermore, accuracy assessments should be consistent with prior recommendations and standards in the field, should support the estimation of a population confusion matrix, and should allow for assessment of model generalization. This paper draws from our review of the RS DL literature and the rich record of traditional remote sensing accuracy assessment research while considering the unique nature of CNN-based deep learning to propose accuracy assessment best practices that use appropriate sampling methods, training and validation data partitioning, assessment metrics, and reporting standards.

LSTMCNNsucc: A Bidirectional LSTM and CNN-Based Deep Learning Method for Predicting Lysine Succinylation Sites.

Lysine succinylation is a typical protein post-translational modification and plays a crucial role of regulation in the cellular process. Identifying succinylation sites is fundamental to explore its functions. Although many computational methods were developed to deal with this challenge, few considered semantic relationship between residues. We combined long short-term memory (LSTM) and convolutional neural network (CNN) into a deep learning method for predicting succinylation site. The proposed method obtained a Matthews correlation coefficient of 0.2508 on the independent test, outperforming state of the art methods. We also performed the enrichment analysis of succinylation proteins. The results showed that functions of succinylation were conserved across species but differed to a certain extent with species. On basis of the proposed method, we developed a user-friendly web server for predicting succinylation sites.

The Study of Noise Effect on CNN-Based Deep Learning from Medical Images

Currently, computational modeling methods based on machine learning techniques in medical imaging are gaining more and more interests from health science researchers and practitioners. The high interest is due to efficiency of modern algorithms such as convolutional neural networks (CNN) and other types of deep learning. CNN is the most popular deep learning algorithm because of its prominent capability on learning key features from images that help capturing the correct class of images. Moreover, several sophisticated CNN architectures with many learning layers are available in the cloud computing environment. In this study, we are interested in performing empirical research work to compare performance of CNNs when they are dealing with noisy medical images. We design a comparative study to observe performance of the AlexNet CNN model on classifying diseases from medical images of two types: images with noise and images without noise. For the case of noisy images, the data had been further separated into two groups: a group of images that noises harmoniously cover the area of the disease symptoms (NIH) and a group of images that noises do not harmoniously cover the area of the disease symptoms (NNIH). The experimental results reveal that NNIH has insignificant effect toward the performance of CNN. For the group of NIH, we notice some effect of noise on CNN learning performance. In NIH group of images, the data preparation process before learning can improve the efficiency of CNN.

STDNet: A CNN-based approach to single-/mixed-script detection

Script identification serves as a guide to the detection of the text of the scene through optical character recognition (OCR). But this is not a principal concern for the OCR engine. Until script identification, it is important to identify the script-type because today the text of the scene in natural images does not consist only of a single script, rather mixed-script words at character level are very often encountered. These words are also used in various ways, such as signboards, t-shirt graffiti, hoardings, and banners and often written in artistic way. In this work, a CNN-based deep learning framework, named as STDNet: Script-Type detection Network, was developed to detect single-/mixed-script images. To determine the feasibility of the system presented, tests were also undertaken with an outlier which is composed of a wide range of single scripts. Experiments were performed with over 20K images and 99.53% highest accuracy was reached. This approach was compared to a state-of-the-art deep learning techniques and handcrafted feature-based methodologies where the proposed approach obtained a better performance.

Convolutional Neural Networks(CNN) based Eye-Gaze Tracking System using Machine Learning Algorithm

To avoid the rising number of car crash deaths, which are mostly caused by drivers' inattentiveness, a paradigm shift is expected. The knowledge of a driver's look area may provide useful details about his or her point of attention. Cars with accurate and low-cost gaze classification systems can increase driver safety. When drivers shift their eyes without turning their heads to look at objects, the margin of error in gaze detection increases. For new consumer electronic applications such as driver tracking systems and novel user interfaces, accurate and effective eye gaze prediction is critical. Such systems must be able to run efficiently in difficult, unconstrained conditions while using reduced power and expense. A deep learning-based gaze estimation technique has been considered to solve this issue, with an emphasis on WSN based Convolutional Neural Networks (CNN) based system. The proposed study proposes the following architecture, which is focused on data science: The first is a novel neural network model that is programmed to manipulate any possible visual feature, such as the states of both eyes and head location, as well as many augmentations; the second is a data fusion approach that incorporates several gaze datasets. However, due to different factors such as environment light shifts, reflections on glasses surface, and motion and optical blurring of the captured eye signal, the accuracy of detecting and classifying the pupil centre and corneal reflection centre depends on a car environment. This work also includes pre-trained models, network structures, and datasets for designing and developing CNN-based deep learning models for Eye-Gaze Tracking and Classification.