Deep Learning-based Convolutional Neural Network Research Articles

Efficient Intelligent Intrusion Detection System for Heterogeneous Internet of Things (HetIoT)

Moving towards a more digital and intelligent world equipped with internet-of-thing (IoT) devices creates many security issues. A distributed denial of service (DDoS) attack is one of the most formidable and challenging security threats that has taken hold with the emergence of the heterogeneous IoT (HetIoT). The massive DDoS attacks have exhibited their impact by continuously destroying a variety of infrastructures, resulting in huge losses, and endangering the overall availability of the digital world. The emphasis of this research is to identify and mitigate various DDoS attacks for HetIoT. The research proposes an intelligent intrusion detection system (IDS) using a convolutional neural network (CNN), i.e., HetIoT-CNN IDS, a novel deep learning-based convolutional neural network for the HetIoT environment. The proposed intelligent IDS successfully identifies and mitigates various DDoS attacks in the HetIoT infrastructure. The feasibility of the new proposed HetIoT-CNN IDS is assessed by considering binary and multi-class (8- and 13-classes) classification. The performance of the proposed intelligent IDS is compared with two state-of-the-art deep learning approaches for HetIoT, and the results reveal that the proposed HetIoT-CNN IDS outperforms it. The proposed HetIoT-CNN IDS successfully identifies various DDoS attacks with an accuracy rate of 99.75% for binary classes, 99.95% for 8-classes, and 99.99% for 13-classes. The work also compares the individual accuracy of binary classes, 8-classes, and 13-classes with state-of-the-art work.

Convolutional neural network-based respiration analysis of electrical activities of the diaphragm

The electrical activity of the diaphragm (Edi) is considered a new respiratory vital sign for monitoring breathing patterns and efforts during ventilator care. However, the Edi signal contains irregular noise from complex causes, which makes reliable breathing analysis difficult. Deep learning was implemented to accurately detect the Edi signal peaks and analyze actual neural breathing in premature infants. Edi signals were collected from 17 premature infants born before gestational age less than 32 weeks, who received ventilatory support with a non-invasive neurally adjusted ventilatory assist. First, a local maximal detection method that over-detects candidate Edi peaks was used. Subsequently, a convolutional neural network-based deep learning was implemented to classify candidates into final Edi peaks. Our approach showed superior performance in all aspects of respiratory Edi peak detection and neural breathing analysis compared with the currently used recording technique in the ventilator. The method obtained a f1-score of 0.956 for the Edi peak detection performance and {R}^{2} value of 0.823 for respiratory rates based on the number of Edi peaks. The proposed technique can achieve a more reliable analysis of Edi signals, including evaluation of the respiration rate in premature infants.

Computer vision-based approach to detect fatigue driving and face mask for edge computing device

The fatality of road accidents in this era is alarming. According to WHO, approximately 1.30 million people die each year in road accidents. Road accidents result in significant socioeconomic losses for people, their families, and the country. The integration of modern technologies into automobiles can help to reduce the number of people killed or injured in road accidents. Most of the study and police reports claim that fatigued driving is one of the deadliest factors behind many road accidents. This paper presents a complete embedded system to detect fatigue driving using deep learning, computer vision, and heart rate monitoring with Nvidia Jetson Nano developer kit, Arduino Uno, and AD8232 heart rate module. The proposed system can monitor the driver's real-time situations, then analyze the situation to detect any fatigue conditions and act accordingly. The onboard camera module constantly monitors the driver. The frames are retrieved and analyzed by the core system that uses deep learning and computer vision techniques to verify the situation with Nvidia Jetson Nano. The driver's states are identified using eye and mouth localization approaches from 68 distinct facial landmarks. Experimentally driven threshold data is employed to classify the states. The onboard heart rate module constantly measures the heart rates and detects any fluctuation in BPM related to the drowsiness. This system uses a convolutional neural network-based deep learning framework to include additional face mask detection to cope with the current pandemic situation. The heart rate module works parallelly where the other modules work in a conditional sequential manner to ensure uninterrupted detection. It will detect any sign of drowsiness in real-time and generate the alarm. The system successfully passed the initial lab tests and some actual situation experiments with 97.44% accuracy in fatigue detection and 97.90% accuracy in face mask identification. The automatic device was able to analyze different situations of drivers (different distances of driver from the camera, various lighting conditions, wearing eyeglasses, oblique projection) more precisely and generate an alarm before the accident happened.

A hybrid approach for Bangla sign language recognition using deep transfer learning model with random forest classifier

Sign language is the comprehensive medium of mass communication for hearing and speaking impaired individuals. As they cannot speak or hear, they are not able to use sound or vocal signals as an information medium for their communication. Rather, they are bound to exchange visual signals to express their feeling in their day-to-day life. For this, they use various body language mainly hand gestures as sign language. Sign language fundamentals can be largely divided into two parts namely digits (numerals) and characters (alphabetical). In this paper, we proposed a hybrid model consisting of a deep transfer learning-based convolutional neural network with a random forest classifier for the automatic recognition of Bangla Sign Language (numerals and alphabets). The overall performance of the presented system is verified on ‘Ishara-Bochon’ and ‘Ishara-Lipi’ datasets. ‘Ishara-Bochon’ and ‘Ishara-Lipi’ are datasets of isolated numerals and alphabets respectively which are the first complete multipurpose open-access dataset for Bangla Sign Language (BSL). Besides, we also proposed a background elimination algorithm that removes unnecessary features from the sign images. Along with the proposed background elimination technique, the system is able to achieve accuracy, precision, recall, f1-score values of 91.67%, 93.64%, 91.67%, 91.47% for character recognition and 97.33%, 97.89%, 97.33%, 97.37% for digit recognition respectively. The detailed experimental analysis assures the feasibility and effectiveness of the proposed system for BSL recognition.

Osteoporosis diagnosis in knee X-rays by transfer learning based on convolution neural network.

Osteoporosis degrades the quality of bones and is the primary cause of fractures in the elderly and women after menopause. The high diagnostic and treatment costs urge the researchers to find a cost-effective diagnostic system to diagnose osteoporosis in the early stages. X-ray imaging is the cheapest and most common imaging technique to detect bone pathologies butmanual interpretation of x-rays for osteoporosis is difficult and extraction of required features and selection of high-performance classifiers is a very challenging task. Deep learning systems have gained the popularity in image analysis field over the last few decades. This paper proposes a convolution neural network (CNN) based approach to detect osteoporosis from x-rays. In our study, we have used the transfer learning of deep learning-based CNNs namely AlexNet, VggNet-16, ResNet, and VggNet −19 to classify the x-ray images of knee joints into normal, osteopenia, and osteoporosis disease groups. The main objectives of the current study are: (i) to present a dataset of 381 knee x-rays medically validated by the T-scores obtained from the Quantitative Ultrasound System, and (ii) to propose a deep learning approach using transfer learning to classify different stages of the disease. The performance of these classifiers is compared and the best accuracy of 91.1% is achieved by pretrained Alexnet architecture on the presented dataset with an error rate of 0.09 and validation loss of 0.54 as compared to the accuracy of 79%, an error rate of 0.21, and validation loss of 0.544 when pretrained network was not used.. The results of the study suggest that a deep learning system with transfer learning can help clinicians to detect osteoporosis in its early stages hence reducing the risk of fractures.

Paralyzed Patients-Oriented Electroencephalogram Signals Processing using Convolutional Neural Network Through Python

Aim: Some of the systems that use brain–computer interfaces (BCIs) that translate brain activity patterns into commands for an interactive application make use of samples produced by motor imagery. This study focuses on processing electroencephalogram (EEG) signals using convolutional neural network (CNN). It is aimed to analyze EEG signals using Python, convert data to spectrogram, and classify them with CNN in this article. Materials and Methods: EEG data used were sampled at a sampling frequency of 128 Hz, in the range of 0.5–50 Hz. The EEG file is processed using Python programming language. Spectrogram images of the channels were obtained with the Python YASA library. Results: The success of the CNN model applied to dataset was found to be 89.58%. Conclusion: EEG signals make it possible to detect diseases using various machine learning methods. Deep learning-based CNN algorithms can also be used for this purpose.

Diagnosis of Early Glottic Cancer Using Laryngeal Image and Voice Based on Ensemble Learning of Convolutional Neural Network Classifiers

The purpose of study is to improve the classification accuracy by comparing the results obtained by applying decision tree ensemble learning, which is one of the methods to increase the classification accuracy for a relatively small dataset, with the results obtained by the convolutional neural network (CNN) algorithm for the diagnosis of glottal cancer. Pusan National University Hospital (PNUH) dataset were used to establish classifiers and Pusan National University Yangsan Hospital (PNUYH) dataset were used to verify the classifier's performance in the generated model. For the diagnosis of glottic cancer, deep learning-based CNN models were established and classified using laryngeal image and voice data. Classification accuracy was obtained by performing decision tree ensemble learning using probability through CNN classification algorithm. In this process, the classification and regression tree (CART) method was used. Then, we compared the classification accuracy of decision tree ensemble learning with CNN individual classifiers by fusing the laryngeal image with the voice decision tree classifier. We obtained classification accuracy of 81.03 % and 99.18 % in the established laryngeal image and voice classification models using PNUH training dataset, respectively. However, the classification accuracy of CNN classifiers decreased to 73.88 % in voice and 68.92 % in laryngeal image when using an external dataset of PNUYH. To solve this problem, decision tree ensemble learning of laryngeal image and voice was used, and the classification accuracy was improved by integrating data of laryngeal image and voice of the same person. The classification accuracy was 87.88 % and 89.06 % for the individualized laryngeal image and voice decision tree model respectively, and the fusion of the laryngeal image and voice decision tree results represented a classification accuracy of 95.31 %. The results of our study suggest that decision tree ensemble learning aimed at training multiple classifiers is useful to obtain an increased classification accuracy despite a small dataset. Although a large data amount is essential for AI analysis, when an integrated approach is taken by combining various input data high diagnostic classification accuracy can be expected.

Crop type discrimination using Geo-Stat Endmember extraction and machine learning algorithms

The identification of crop diversity in today's world is very crucial to ensure adaptation of the crop with changing climate for better productivity as well as food security. Towards this, Hyperspectral Remote Sensing (HRS) is an efficient technique that offers the opportunity to discriminate crop types based on morphological as well as physiological features due to availability of contiguous spectral bands. The current work utilized the benefits of Airborne Visible Infrared Imaging Spectrometer- New Generation (AVIRIS-NG) data and explored the techniques for classification and identification of crop types. The endmembers were identified using the Geo-Stat Endmember Extraction (GSEE) algorithm for pure pixels identification and to generate the spectral library of the different crop types. Spectral feature comparison was done among AVIRIS-NG, Analytical Spectral Device (ASD)-Spectroradiometer and Continuum Removed (CR) spectra. The best-fit spectra obtained with the Reference ASD-Spectroradiometer and Pure Pixel spectral library were then used for crop discrimination using the ten supervised classifiers namely Spectral Angle Mapper (SAM), Spectral Information Divergence (SID), Support Vector Machine (SVM), Minimum Distance Classifier (MDC), Binary Encoding, deep learning-based Convolution Neural Network (CNN) and different algorithms of Ensemble learning such as Tree Bag, AdaBoost (Adaptive Boosting), Discriminant and RUSBoost (Random Under Sampling). In total, nine crop types were identified, namely, wheat, maize, tobacco, sorghum, linseed, castor, pigeon pea, fennel and chickpea. The performance evaluation of the classifiers was made using various metrics like Overall Accuracy, Kappa Coefficient, Precision, Recall and F1 score. The classifier 2D-CNN was found to be the best with Overall Accuracy, Kappa Coefficient, Precision, Recall and F1 score values of 89.065 %, 0.871, 87.565%, 89.541% and 88.678% respectively. The output of this work can be utilized for large scale mapping of crop types at the species level in a short interval of time with high accuracy.

A One-Dimensional Convolutional Neural Network (1D-CNN) Based Deep Learning System for Network Intrusion Detection

The connectivity of devices through the internet plays a remarkable role in our daily lives. Many network-based applications are utilized in different domains, e.g., health care, smart environments, and businesses. These applications offer a wide range of services and provide services to large groups. Therefore, the safety of network-based applications has always been an area of research interest for academia and industry alike. The evolution of deep learning has enabled us to explore new areas of research. Hackers make use of the vulnerabilities in networks and attempt to gain access to confidential systems and information. This information and access to systems can be very harmful and portray losses beyond comprehension. Therefore, detection of these network intrusions is of the utmost importance. Deep learning based techniques require minimal inputs while exploring every possible feature set in the network. Thus, in this paper, we present a one-dimensional convolutional neural network-based deep learning architecture for the detection of network intrusions. In this research, we detect four different types of network intrusions, i.e., DoS Hulk, DDoS, and DoS Goldeneye which belong to the active attack category, and PortScan, which falls in the passive attack category. For this purpose, we used the benchmark CICIDS2017 dataset for conducting the experiments and achieved an accuracy of 98.96% as demonstrated in the experimental results.

Detection of Fungal Infections in Gloriosa Superba Plant Using the Convolution Neural Network Model

Herbal treatments’ efficacy, safety, and mild side effects are also high priorities in primary care. Furthermore, as the world’s population expands, food production becomes more difficult. We need to use innovative biotechnology-based fertilization technologies to boost food production output. Gloriosa superba is one of the most well-known plants for its antibacterial and medicinal capabilities. The money plant is also known as the Gloriosa superba. We used a deep learning-based convolution neural network (CNN) classifier model to optimize the CNN algorithm parameter for better prediction. The enhanced particle swarm optimization (PSO) technique was used for optimization. Scale-invariant feature transform (SIFT) was used to extract the fungal spotted area. Digital camera with a high resolution acquires 300 dataset photographs from different villages in India for this investigation. Using a real-time fungal-affected image to train and test the model, different parametric measures are used to assess the model’s performance. The categorization accuracy obtained in this experiment was 99.32 percent.

Detection of features from the internet of things customer attitudes in the hotel industry using a deep neural network model

Tourism and the hotel business have benefited greatly from the use of digital social networking. Using social big data research, the application of deep learning seems to have been beneficial in a marketing strategies and customer preference estimate. Recognizing human psychology, which is critical to industrial success, has benefited greatly from digital technology and social media. The Internet of Things (IoT) provides a chance for a hotel sector to improve the customer experience although lowering operational expenses. The ratings are determined by the following factors: Value, Apartment, Location, Hygiene, Front Office, Facilities, Professional Service, Internet, and Parking. Traditional techniques which anticipate hotel evaluations through minimal precision add difficulty to the rating assessment. As a result, efficient deep learning algorithms are employed to evaluate reviews designed to help consumers in selecting better hotels. To predict qualities, multiple classification techniques, including convolutional neural network-based deep learning (CNN-DL) and support vector machine (SVM) network-based deep learning, were used in this research. The system examines system efficiency by using the TripAdvisor website, this is a well American database. The research results reveal that the CNN-DL method outperforms another method in terms of classification efficiency and failure rate.The graphical results could also be utilized to enhance the effectiveness of the suggested model and offer insights into response tactics, demonstrating the study's academic and conceptual achievements. Although it is feasible to conclude from such research that the possibility of IoT within the hotel industry has not yet been fully investigated, as researchers commonly speculate on using IoT for implementations that might quickly be of involvement to a hotel sector, but refuse to recognize that possibility as a massive market.

Efficient self-attention mechanism and structural distilling model for Alzheimer’s disease diagnosis

Structural magnetic resonance imaging (sMRI) is commonly used for the identification of Alzheimer’s disease because of its keen insight into atrophy-induced changes in brain structure. Current mainstream convolutional neural network-based deep learning methods ignore the long-term dependencies between voxels; thus, it is challenging to learn the global features of sMRI data. In this study, an advanced deep learning architecture called Brain Informer (BraInf) was developed based on an efficient self-attention mechanism. The proposed model integrates representation learning, feature distilling, and classifier modeling into a unified framework. First, the proposed model uses a multihead ProbSparse self-attention block for representation learning. This self-attention mechanism selects the first ⌊lnN⌋ elements that can represent the overall features from the perspective of probability sparsity, which significantly reduces computational cost. Subsequently, a structural distilling block is proposed that applies the concept of patch merging to the distilling operation. The block reduces the size of the three-dimensional tensor and further lowers the memory cost while preserving the original data as much as possible. Thus, there was a significant improvement in the space complexity. Finally, the feature vector was projected into the classification target space for disease prediction. The effectiveness of the proposed model was validated using the Alzheimer’s Disease Neuroimaging Initiative dataset. The model achieved 97.97% and 91.89% accuracy on Alzheimer’s disease and mild cognitive impairment classification tasks, respectively. The experimental results also demonstrate that the proposed framework outperforms several state-of-the-art methods.

Deep Learning-Based Automated Detection of Arterial Vessel Wall and Plaque on Magnetic Resonance Vessel Wall Images.

PurposeTo develop and evaluate an automatic segmentation method of arterial vessel walls and plaques, which is beneficial for facilitating the arterial morphological quantification in magnetic resonance vessel wall imaging (MRVWI).MethodsMRVWI images acquired from 124 patients with atherosclerotic plaques were included. A convolutional neural network-based deep learning model, namely VWISegNet, was used to extract the features from MRVWI images and calculate the category of each pixel to facilitate the segmentation of vessel wall. Two-dimensional (2D) cross-sectional slices reconstructed from all plaques and 7 main arterial segments of 115 patients were used to build and optimize the deep learning model. The model performance was evaluated on the remaining nine-patient test set using the Dice similarity coefficient (DSC) and average surface distance (ASD).ResultsThe proposed automatic segmentation method demonstrated satisfactory agreement with the manual method, with DSCs of 93.8% for lumen contours and 86.0% for outer wall contours, which were higher than those obtained from the traditional U-Net, Attention U-Net, and Inception U-Net on the same nine-subject test set. And all the ASD values were less than 0.198 mm. The Bland–Altman plots and scatter plots also showed that there was a good agreement between the methods. All intraclass correlation coefficient values between the automatic method and manual method were greater than 0.780, and greater than that between two manual reads.ConclusionThe proposed deep learning-based automatic segmentation method achieved good consistency with the manual methods in the segmentation of arterial vessel wall and plaque and is even more accurate than manual results, hence improved the convenience of arterial morphological quantification.

A Novel Method to Inspect 3D Ball Joint Socket Products Using 2D Convolutional Neural Network with Spatial and Channel Attention.

Product defect inspections are extremely important for industrial manufacturing processes. It is necessary to develop a special inspection system for each industrial product due to their complexity and diversity. Even though high-precision 3D cameras are usually used to acquire data to inspect 3D objects, it is hard to use them in real-time defect inspection systems due to their high price and long processing time. To address these problems, we propose a product inspection system that uses five 2D cameras to capture all inspection parts of the product and a deep learning-based 2D convolutional neural network (CNN) with spatial and channel attention (SCA) mechanisms to efficiently inspect 3D ball joint socket products. Channel attention (CA) in our model detects the most relevant feature maps while spatial attention (SA) finds the most important regions in the extracted feature map of the target. To build the final SCA feature vector, we concatenated the learned feature vectors of CA and SA because they complement each other. Thus, our proposed CNN with SCA provides high inspection accuracy as well as it having the potential to detect small defects of the product. Our proposed model achieved 98% classification accuracy in the experiments and proved its efficiency on product inspection in real-time.

Cyberbullying detection using deep transfer learning

Social networking platforms like Facebook, Twitter, and others have numerous advantages, but they have many dark sides also. One of the issues on these social platforms is cyberbullying. The impact of cyberbullying is immeasurable on the life of victims as it’s very subjective to how the person would tackle this. The message may be a bully for victims, but it may be normal for others. The ambiguities in cyberbullying messages create a big challenge to find the bully content. Some research has been reported to address this issue with textual posts. However, image-based cyberbullying detection is received less attention. This research aims to develop a model that helps to prevent image-based cyberbullying issues on social platforms. The deep learning-based convolutional neural network is initially used for model development. Later, transfer learning models are utilized in this research. The experimental outcomes of various settings of the hyper-parameters confirmed that the transfer learning-based model is the better choice for this problem. The proposed model achieved a satisfactory accuracy of 89% for the best case, indicating that the system detects most cyberbullying posts.

Detecting the presence of taurodont teeth on panoramic radiographs using a deep learning-based convolutional neural network algorithm.

Artificial intelligence (AI) techniques like convolutional neural network (CNN) are a promising breakthrough that can help clinicians analyze medical imaging, diagnose taurodontism, and make therapeutic decisions. The purpose of the study is to develop and evaluate the function of CNN-based AI model to diagnose teeth with taurodontism in panoramic radiography. 434 anonymized, mixed-sized panoramic radiography images over the age of 13years were used to develop automatic taurodont tooth segmentation models using a Pytorch implemented U-Net model. Datasets were split into train, validation, and test groups of both normal and masked images. The data augmentation method was applied to images of trainings and validation groups with vertical flip images, horizontal flip images, and both flip images. The Confusion Matrix was used to determine the model performance. Among the 43 test group images with 126 labels, there were 109 true positives, 29 false positives, and 17 false negatives. The sensitivity, precision, and F1-score values of taurodont tooth segmentation were 0.8650, 0.7898, and 0.8257, respectively. CNN's ability to identify taurodontism produced almost identical results to the labeled training data, and the CNN system achieved close to the expert level results in its ability to detect the taurodontism of teeth.

A Deep Learning Approach for Gait Event Detection from a Single Shank-Worn IMU: Validation in Healthy and Neurological Cohorts.

Many algorithms use 3D accelerometer and/or gyroscope data from inertial measurement unit (IMU) sensors to detect gait events (i.e., initial and final foot contact). However, these algorithms often require knowledge about sensor orientation and use empirically derived thresholds. As alignment cannot always be controlled for in ambulatory assessments, methods are needed that require little knowledge on sensor location and orientation, e.g., a convolutional neural network-based deep learning model. Therefore, 157 participants from healthy and neurologically diseased cohorts walked 5 m distances at slow, preferred, and fast walking speed, while data were collected from IMUs on the left and right ankle and shank. Gait events were detected and stride parameters were extracted using a deep learning model and an optoelectronic motion capture (OMC) system for reference. The deep learning model consisted of convolutional layers using dilated convolutions, followed by two independent fully connected layers to predict whether a time step corresponded to the event of initial contact (IC) or final contact (FC), respectively. Results showed a high detection rate for both initial and final contacts across sensor locations (recall , precision ). Time agreement was excellent as witnessed from the median time error (0.005 s) and corresponding inter-quartile range (0.020 s). The extracted stride-specific parameters were in good agreement with parameters derived from the OMC system (maximum mean difference 0.003 s and corresponding maximum limits of agreement (−0.049 s, 0.051 s) for a confidence level). Thus, the deep learning approach was considered a valid approach for detecting gait events and extracting stride-specific parameters with little knowledge on exact IMU location and orientation in conditions with and without walking pathologies due to neurological diseases.

Traffic Sign Detection and Recognition Based on Convolutional Neural Network

As autonomous vehicles are developing and maturing the technology to implement the domestic autonomous vehicles. The critical technological problem for self-driving vehicles is traffic sign detection and recognition. A traffic sign recognition system is essential for an intelligent transportation system. The digital image processing techniques for object recognition and extraction of features from visual objects is a huge process and include many conversions and pre-processing steps. A deep learning-based convolutional neural network (CNN) model is one of the suitable approach for traffic sign detection and recognition. This model has overcome significant shortcomings of traditional visual object detection approaches. This paper proposed a traffic sign identification and detection system. The proposed design and strategy are implemented using the Tensorflow framework in google colab environment. The experiment is applied on the publicly available traffic sign data sets. The defined deep convolution neural network based model experimental results achieved 94.52% and 80.85% precision and recall respectively. Improving the seep of recognition and identifying appropriate features of traffic sign objects are addressed using deep learning-based encoders and transformers.

Automated detection of posterior restorations in permanent teeth using artificial intelligence on intraoral photographs

ObjectivesIntraoral photographs might be considered the machine-readable equivalent of a clinical-based visual examination and can potentially be used to detect and categorize dental restorations. The first objective of this study was to develop a deep learning-based convolutional neural network (CNN) for automated detection and categorization of posterior composite, cement, amalgam, gold and ceramic restorations on clinical photographs. Second, this study aimed to determine the diagnostic accuracy for the developed CNN (test method) compared to that of an expert evaluation (reference standard). MethodsThe whole image set of 1761 images (483 of unrestored teeth, 570 of composite restorations, 213 of cements, 278 of amalgam restorations, 125 of gold restorations and 92 of ceramic restorations) was divided into a training set (N = 1407, 401, 447, 66, 231, 93, and 169, respectively) and a test set (N = 354, 82, 123, 26, 47, 32, and 44). The expert diagnoses served as a reference standard for cyclic training and repeated evaluation of the CNN (ResNeXt-101–32 × 8d), which was trained by using image augmentation and transfer learning. Statistical analysis included the calculation of contingency tables, areas under the receiver operating characteristic curve and saliency maps. ResultsAfter training was complete, the CNN was able to categorize restorations correctly with the following diagnostic accuracy values: 94.9% for unrestored teeth, 92.9% for composites, 98.3% for cements, 99.2% for amalgam restorations, 99.4% for gold restorations and 97.8% for ceramic restorations. ConclusionsIt was possible to categorize different types of posterior restorations on intraoral photographs automatically with a good diagnostic accuracy. Clinical significanceDental diagnostics might be supported by artificial intelligence-based algorithms in the future. However, further improvements are needed to increase accuracy and practicability.

Deep Learning-Based Electrocardiograph in Evaluating Radiofrequency Ablation for Rapid Arrhythmia.

This study is aimed at analyzing the important role of deep learning-based electrocardiograph (ECG) in the efficacy evaluation of radiofrequency ablation in the treatment of tachyarrhythmia. In this study, 158 patients with rapid arrhythmia treated by radiofrequency ablation were divided into effective treatment group (142 cases) and ineffective treatment group (16 cases). ECG examination was performed on all patients, and the indicators of ECG examination were quantified by the deep learning-based convolutional neural network model. The indicators of ECG examination of the effective treatment group and the ineffective treatment group were compared. The results showed that compared with the ineffective treatment group, the end-systolic volume (ESV), end-diastolic volume (EDV), end-systolic volume index (ESVI), and end-diastolic volume index (EDVI) of the effective treatment group were significantly decreased, and the left ventricular ejection fraction (LVEF) was significantly increased (P < 0.05). After radiofrequency ablation, the ventricular rate of patients in the effective treatment group was significantly lower than that of the ineffective treatment group at 12 h and 24 h after treatment (P < 0.05). In addition, compared with patients in the ineffective treatment group, the QT dispersion of the ECG in the effective treatment group was significantly higher (P < 0.05). The accuracy, specificity, and sensitivity of ECG in evaluating the therapeutic effect of patients with tachyarrhythmia were 86.81%, 84.29%, and 77.27%, respectively. The area under the curve was determined as 0.798 according to the receiver operating characteristic (ROC) curve of the subjects. In summary, indicators of ECG examination based on deep learning can provide auxiliary reference information for the efficacy evaluation of radiofrequency ablation in the treatment of tachyarrhythmia.