Neural Network-based System Research Articles

A deep learning model for early risk prediction of heart failure with preserved ejection fraction by DNA methylation profiles combined with clinical features

BackgroundHeart failure with preserved ejection fraction (HFpEF), affected collectively by genetic and environmental factors, is the common subtype of chronic heart failure. Although the available risk assessment methods for HFpEF have achieved some progress, they were based on clinical or genetic features alone. Here, we have developed a deep learning framework, HFmeRisk, using both 5 clinical features and 25 DNA methylation loci to predict the early risk of HFpEF in the Framingham Heart Study Cohort.ResultsThe framework incorporates Least Absolute Shrinkage and Selection Operator and Extreme Gradient Boosting-based feature selection, as well as a Factorization-Machine based neural network-based recommender system. Model discrimination and calibration were assessed using the AUC and Hosmer–Lemeshow test. HFmeRisk, including 25 CpGs and 5 clinical features, have achieved the AUC of 0.90 (95% confidence interval 0.88–0.92) and Hosmer–Lemeshow statistic was 6.17 (P = 0.632), which outperformed models with clinical characteristics or DNA methylation levels alone, published chronic heart failure risk prediction models and other benchmark machine learning models. Out of them, the DNA methylation levels of two CpGs were significantly correlated with the paired transcriptome levels (R < −0.3, P < 0.05). Besides, DNA methylation locus in HFmeRisk were associated with intercellular signaling and interaction, amino acid metabolism, transport and activation and the clinical variables were all related with the mechanism of occurrence of HFpEF. Together, these findings give new evidence into the HFmeRisk model.ConclusionOur study proposes an early risk assessment framework for HFpEF integrating both clinical and epigenetic features, providing a promising path for clinical decision making.

New Trends in Melanoma Detection Using Neural Networks: A Systematic Review.

Due to its increasing incidence, skin cancer, and especially melanoma, is a serious health disease today. The high mortality rate associated with melanoma makes it necessary to detect the early stages to be treated urgently and properly. This is the reason why many researchers in this domain wanted to obtain accurate computer-aided diagnosis systems to assist in the early detection and diagnosis of such diseases. The paper presents a systematic review of recent advances in an area of increased interest for cancer prediction, with a focus on a comparative perspective of melanoma detection using artificial intelligence, especially neural network-based systems. Such structures can be considered intelligent support systems for dermatologists. Theoretical and applied contributions were investigated in the new development trends of multiple neural network architecture, based on decision fusion. The most representative articles covering the area of melanoma detection based on neural networks, published in journals and impact conferences, were investigated between 2015 and 2021, focusing on the interval 2018–2021 as new trends. Additionally presented are the main databases and trends in their use in teaching neural networks to detect melanomas. Finally, a research agenda was highlighted to advance the field towards the new trends.

Real-Time Prediction of Car Driver’s Emotions using Facial Expression with a Convolutional Neural Network-based Intelligent System

Real-Time Prediction of Car Driver’s Emotions using Facial Expression with a Convolutional Neural Network-based Intelligent System

DeepASLR: A CNN based human computer interface for American Sign Language recognition for hearing-impaired individuals

BackgroundSign language is an essential means of communication for hearing-impaired individuals. ObjectiveWe aimed to develop an American sign language recognition dataset and use it in the deep learning model which depends on neural networks to interpret gestures of sign language and hand poses to natural language. MethodsIn this study, we developed a dataset and a Convolutional Neural Network-based sign language interface system to interpret gestures of sign language and hand poses to natural language. The neural network developed in this study is a Convolutional Neural Network (CNN) which enhances the predictability of the American Sign Language alphabet (ASLA). This research establishes a new dataset of the American Sign Language alphabet which takes into consideration various conditions such as lighting and distance. ResultsThe dataset created in this study is a new addition in the field of sign language recognition (SLR). This dataset may be used to develop SLR systems. Furthermore, our research compares the results of our dataset with two different datasets from other studies. The other datasets have invariant scene conditions, but our suggested CNN model demonstrated high accuracy for all the tested datasets. Despite the different conditions and volume of the new dataset, it achieved 99.38% accuracy with excellent prediction and small loss (0.0250). ConclusionsThe proposed system may be considered a promising solution in medical applications that use deep learning with superior accuracy. Moreover, our dataset was created under variable conditions which increases the number of contributions, comparisons, results and conclusions in the field of SLR and may enhance such systems.

Influence of different types of real-time feedback on hand washing quality assessed with neural networks/simulated neural networks

Background: Thousands of people die every day around the world from infections acquired in a hospital. Hands are the main pathways of germ transmission during healthcare. Hand hygiene monitoring can be performed using various methods. One of the latest techniques that can combine all is a neural network-based hand hygiene monitoring system. Methods/Design: Each participant performed 3 hand-washing trials, each time receiving different type of feedback. The order in which each participant of the study used the developed applications was strictly defined, thus each hand-washing study session started with performing hand washing using application A, B and C accordingly. All captured videos of hand-wash episodes were saved and later analysed with neural networks. In the end, both evaluation results were compared and evaluated. Results show that when the participants use Application Type A, they perform hand washing much faster, as well as in comparison of Application Type A versus application type C. However, the longest time spent for the hand washing was detected while using the application type B. Conclusion: Study shows that structured guidance provided during the real time hand washing could be associated with better overall performance. The Application C has confirmed its effectiveness. Proving its advantage among other applications, the Application C can be integrated into the clinical environment

Expert system-supported optimization of laser welding of additively manufactured thermoplastic components

Laser transmission welding (LTW) is a known technique to join conventionally produced thermoplastic parts, e.g. injected molded parts. When using LTW for additively manufactured parts (usually prototypes, small series), this technique has to be evolved to overcome the difficulties in the part composition resulted in the additive manufacturing process itself.In this paper, a method is presented to enhance the weld seam quality of laser welded additively manufactured parts assisted by a neural network-based expert system. To validate the expert system, specimens are additively manufactured from polylactide. The parameters of the additive manufacturing process, the transmissivity, and the LTW process parameters are used to predict the shear tensile force with the neural network. The transparent samples are welded to black absorbent samples in overlap configuration and shear tensile tests are performed. In this work, the prediction of the shear tensile force with an accuracy of 88.1% of the neuronal network based expert system is demonstrated.

Decision-Based Attack to Speaker Recognition System via Local Low-Frequency Perturbation

Despite neural network-based speaker recognition systems (SRS) have enjoyed significant success, they are proved to be quite vulnerable to adversarial examples. In practice, the SRS model parameters are not always available. Attackers have to probe the model only via querying, and such decision-based attacking merely relies on the output label is quite challenging. This letter proposes a two-step query-efficient decision-based attack based on local low-frequency perturbation. Specifically, instead of imposing perturbation on the entire audio sample, a local attacking region is firstly sought, confining the perturbed distortion to a local region. Second, considering that the majority of energy concentrates on the low-frequency bands, the proposed method suggests performing perturbation generation in the low-frequency domain. Experimental results demonstrate that, compared with the recent methods, our method could implement target attacking to SRS with a higher attacking success rate, at the cost of much lower queries and adversarial perturbation.

Bearing Fault Detection based on Internet of Things using Convolutional Neural Network

In the age of the industrial revolution, industry and machinery are elements of the utmost importance to the development of human civilization. As industries are dependent on their machines, regular maintenance of these machines is required. However, if the machine is too big for humans to look after, we need a system that will observe these giants. This paper proposes a convolutional neural network-based system that detects faults in industrial machines by diagnosing motor sounds using accelerometers sensors. The sensors collect data from the machines and augment the data into 261756 samples to train (70%) and test (30%) the models for better accuracy. The sensor data are sent to the server through the wireless sensor network and decomposed using discrete wavelet transformation (DWT). This big data is processed to detect faults. The study shows that custom CNN architectures surpass the performance of the transfer learning-based MobileNetV2 fault diagnosis model. The system could successfully detect faults with up to 99.64% accuracy and 99.83% precision with the MobileNetV2 pre-trained on the ImageNet Dataset. However, the Convolutional 1D and 2D architectures perform excellently with 100% accuracy and 100 % precision.

Recurrent Neural Network-Based Temperature Control System Weight Pruning Based on Nonlinear Reconstruction Error

Recurrent Neural Networks (RNNs) have been widely applied in various fields. However, in real-world application, because most devices like mobile phones are limited to the storage capacity when processing real-time information, an over-parameterized model always slows down the system speed and is not suitable to be employed. In our proposed temperature control system, the RNN-based control model processes the real-time temperature signals. It is necessary to compress the trained model with acceptable loss of control performance for further implementation in the actual controller when the system resource is limited. Inspired by the layer-wise neuron pruning method, in this paper, we apply the nonlinear reconstruction error (NRE) guided layer-wise weight pruning method on the RNN-based temperature control system. The control system is established based on MATLAB/Simulink. In order to compress the model size to save the memory capacity of temperature controller devices, we first prove the validity of the proposed reference-model (ref-model) guided RNN model for real-time online data processing on an actual temperature object; relative experiments are implemented based on a digital signal processor. On this basis, we then verified the NRE guided layer-wise weight pruning method on the well-trained temperature control model. Compared with the classical pruning method, experiment results indicate that the pruned control model based on NRE guided layer-wise weight pruning can effectively achieve the high accuracy at targeted sparsity of the network.

The Identification of Non-Driving Activities with Associated Implication on the Take-Over Process.

In conditionally automated driving, the engagement of non-driving activities (NDAs) can be regarded as the main factor that affects the driver’s take-over performance, the investigation of which is of great importance to the design of an intelligent human–machine interface for a safe and smooth control transition. This paper introduces a 3D convolutional neural network-based system to recognize six types of driver behaviour (four types of NDAs and two types of driving activities) through two video feeds based on head and hand movement. Based on the interaction of driver and object, the selected NDAs are divided into active mode and passive mode. The proposed recognition system achieves 85.87% accuracy for the classification of six activities. The impact of NDAs on the perspective of the driver’s situation awareness and take-over quality in terms of both activity type and interaction mode is further investigated. The results show that at a similar level of achieved maximum lateral error, the engagement of NDAs demands more time for drivers to accomplish the control transition, especially for the active mode NDAs engagement, which is more mentally demanding and reduces drivers’ sensitiveness to the driving situation change. Moreover, the haptic feedback torque from the steering wheel could help to reduce the time of the transition process, which can be regarded as a productive assistance system for the take-over process.

Hybrid Convolutional Neural Network-Based Diagnosis System for Intracranial Hemorrhage

Early diagnosis of intracranial hemorrhage significantly reduces mortality. Hemorrhage is diagnosed by using various imaging methods and the most time-efficient one among them is computed tomography (CT). However, it is clear that accurate CT scans requires time, diligence, and experience. Computer-aided design methods are vital for the treatment because they facilitate early diagnosis of intracranial hemorrhage. At this point, deep learning can provide effective outcomes through an automated diagnosis way. However, as different from the known solutions, diagnosis of five different hemorrhage subtypes is a critical problem to be solved.This study focused on deep learning methods and employed cranial computed tomography scans in order to detect intracranial hemorrhage. The diagnosis approach in the study aimed to detect five subtypes of hemorrhage. In detail, EfficientNet-B3 and ResNet-Inception-V2 architectures were used for diagnosis purposes. Eventually, the study also proposed a two-architecture hybrid method for the diagnosis purpose. The obtained findings by the hybrid method were evaluated in terms of a comparative perspective.Results showed that the newly designed hybrid method was quite effective in terms of increasing classification rates of detecting intracranial hemorrhage according to the subtypes. Briefly, an accuracy of 98.5%, which is higher than those of the EfficientNet-B3 and the Inception-ResNet-V2, were obtained thanks to the developed hybrid method.

Adding Interpretability to Neural Knowledge DNA

This paper proposes a novel approach that adds the interpretability to Neural Knowledge DNA (NK-DNA) via generating a decision tree. The NK-DNA is a promising knowledge representation approach for acquiring, storing, sharing, and reusing knowledge among machines and computing systems. We introduce the decision tree-based generative method for knowledge extraction and representation to make the NK-DNA more explainable. We examine our approach through an initial case study. The experiment results show that the proposed method can transform the implicit knowledge stored in the NK-DNA into explicitly represented decision trees bringing fair interpretability to neural network-based intelligent systems.

Modeling Uncertainty in Fracture Age Estimation from Pediatric Wrist Radiographs

In clinical practice, fracture age estimation is commonly required, particularly in children with suspected non-accidental injuries. It is usually done by radiologically examining the injured body part and analyzing several indicators of fracture healing such as osteopenia, periosteal reaction, and fracture gap width. However, age-related changes in healing timeframes, inter-individual variabilities in bone density, and significant intra- and inter-operator subjectivity all limit the validity of these radiological clues. To address these issues, for the first time, we suggest an automated neural network-based system for determining the age of a pediatric wrist fracture. In this study, we propose and evaluate a deep learning approach for automatically estimating fracture age. Our dataset included 3570 medical cases with a skewed distribution toward initial consultations. Each medical case includes a lateral and anteroposterior projection of a wrist fracture, as well as patients’ age, and gender. We propose a neural network-based system with Monte-Carlo dropout-based uncertainty estimation to address dataset skewness. Furthermore, this research examines how each component of the system contributes to the final forecast and provides an interpretation of different scenarios in system predictions in terms of their uncertainty. The examination of the proposed systems’ components showed that the feature-fusion of all available data is necessary to obtain good results. Also, proposing uncertainty estimation in the system increased accuracy and F1-score to a final 0.906±0.011 on a given task.

A Convolutional Neural Network-Based Intelligent Medical System with Sensors for Assistive Diagnosis and Decision-Making in Non-Small Cell Lung Cancer.

In many regions of the world, early diagnosis of non-small cell lung cancer (NSCLC) is a major challenge due to the large population and lack of medical resources, which is difficult toeffectively address via limited physician manpower alone. Therefore, we developed a convolutional neural network (CNN)-based assisted diagnosis and decision-making intelligent medical system with sensors. This system analyzes NSCLC patients’ medical records using sensors to assist staging a diagnosis and provides recommended treatment plans to physicians. To address the problem of unbalanced case samples across pathological stages, we used transfer learning and dynamic sampling techniques to reconstruct and iteratively train the model to improve the accuracy of the prediction system. In this paper, all data for training and testing the system were obtained from the medical records of 2,789,675 patients with NSCLC, which were recorded in three hospitals in China over a five-year period. When the number of case samples reached 8000, the system achieved an accuracy rate of 0.84, which is already close to that of the doctors (accuracy: 0.86). The experimental results proved that the system can quickly and accurately analyze patient data and provide decision information support for physicians.

Analysis of Curative Effect and Prognostic Factors of Radiotherapy for Esophageal Cancer Based on the CNN.

An esophageal cancer intelligent diagnosis system is developed to improve the recognition rate of esophageal cancer image diagnosis and the efficiency of physicians, as well as to improve the level of esophageal cancer image diagnosis in primary care institutions. In this paper, by collecting medical images related to esophageal cancer over the years, we establish an intelligent diagnosis system based on the convolutional neural network for esophageal cancer images through the steps of data annotation, image preprocessing, data enhancement, and deep learning to assist doctors in intelligent diagnosis. The convolutional neural network-based esophageal cancer image intelligent diagnosis system has been successfully applied in hospitals and widely praised by frontline doctors. This system is beneficial for primary care physicians to improve the overall accuracy of esophageal cancer diagnosis and reduce the risk of death of esophageal cancer patients. We also analyze that the efficacy of radiation therapy for esophageal cancer can be influenced by many factors, and clinical attention should be paid to grasp the relevant factors in order to improve the final treatment effect and prognosis of patients.

Data Augmentation for Inertial Sensor Data in CNNs for Cattle Behavior Classification

Cattle behavior monitoring is critical for understanding cattle welfare and health status. One of the most powerful and cost-effective monitoring methods is a neural network-based monitoring system that analyzes time series data from inertial sensors attached to cows. However, while deep learning has achieved many successes in pattern recognition, large-scale datasets are often required. When given a limited number of data, data augmentation is an extremely useful and low-cost preprocessing step for neural network-based systems. Data augmentation for inertial sensor data, however, has yet to be thoroughly investigated. This letter proposes several inertial sensor data augmentation methods in a manner that fits the characteristics of cattle behavioral data. The proposed approaches are applied to the task of cattle behavior classification with convolutional neural networks, which is challenging given limited data. The classification performance increases from 83.07 to 94.43% with appropriate augmentation steps. In conclusion, the data augmentation approaches presented here can help to improve deep learning performance regarding cattle behavior classification and decrease the overall system cost stemming from data acquisition and labeling.

A Novel deep neural network-based emotion analysis system for automatic detection of mild cognitive impairment in the elderly

A significant number of people are suffering from cognitive impairment all over the world. Early detection of cognitive impairment is of great importance to both patients and caregivers. However, existing approaches have their shortages, such as time consumption and financial expenses involved in clinics and the neuroimaging stage. It has been found that patients with cognitive impairment show abnormal emotion patterns. In this paper, we present a novel deep neural network-based system to detect the cognitive impairment through the analysis of the evolution of facial emotions while participants are watching designed video stimuli. In our proposed system, a novel facial expression recognition algorithm is developed using layers from MobileNet and Support Vector Machine (SVM), which showed satisfactory performance in 3 datasets. To verify the proposed system in detecting cognitive impairment, 61 elderly people including patients with cognitive impairment and healthy people as a control group have been invited to participate in the experiments and a dataset was built accordingly. With this dataset, the proposed system has successfully achieved the detection accuracy of 73.3%.

CNN-SSDI: Convolution neural network inspired surveillance system for UAVs detection and identification

In recent years, the availability of commercial unmanned air vehicles (UAVs) has increased enormously because of device miniaturization and low cost. However, the abuse of UAVs needs to be investigated to prevent serious security threats for civilians. Therefore, this paper presents a convolutional neural network-based surveillance system for drone detection and its type identification, namely CNN-SSDI. The network architecture is cleverly designed based on deep convolution layers to successfully learn all intrinsic feature maps of radio-frequency signals that are collected from three different types of drones. Further, a detailed comparative analysis of various kernel impairments of the convolution layer structure was investigated under various performance metrics evaluation and higher accuracy in drone surveillance systems. According to the empirical results, CNN-SSDI can detect a UAV with 99.8% accuracy and recognize drone types with an accuracy of 94.5%, which outperforms other existing drone detection and identification techniques.

Backdoor Attacks to Deep Neural Network-Based System for COVID-19 Detection from Chest X-ray Images

Open-source deep neural networks (DNNs) for medical imaging are significant in emergent situations, such as during the pandemic of the 2019 novel coronavirus disease (COVID-19), since they accelerate the development of high-performance DNN-based systems. However, adversarial attacks are not negligible during open-source development. Since DNNs are used as computer-aided systems for COVID-19 screening from radiography images, we investigated the vulnerability of the COVID-Net model, a representative open-source DNN for COVID-19 detection from chest X-ray images to backdoor attacks that modify DNN models and cause their misclassification when a specific trigger input is added. The results showed that backdoors for both non-targeted attacks, for which DNNs classify inputs into incorrect labels, and targeted attacks, for which DNNs classify inputs into a specific target class, could be established in the COVID-Net model using a small trigger and small fraction of training data. Moreover, the backdoors were effective for models fine-tuned from the backdoored COVID-Net models, although the performance of non-targeted attacks was limited. This indicated that backdoored models could be spread via fine-tuning (thereby becoming a significant security threat). The findings showed that emphasis is required on open-source development and practical applications of DNNs for COVID-19 detection.

Detection of obstructive sleep apnea using Belun Sleep Platform wearable with neural network-based algorithm and its combined use with STOP-Bang questionnaire.

Many wearables allow physiological data acquisition in sleep and enable clinicians to assess sleep outside of sleep labs. Belun Sleep Platform (BSP) is a novel neural network-based home sleep apnea testing system utilizing a wearable ring device to detect obstructive sleep apnea (OSA). The objective of the study is to assess the performance of BSP for the evaluation of OSA. Subjects who take heart rate-affecting medications and those with non-arrhythmic comorbidities were included in this cohort. Polysomnography (PSG) studies were performed simultaneously with the Belun Ring in individuals who were referred to the sleep lab for an overnight sleep study. The sleep studies were manually scored using the American Academy of Sleep Medicine Scoring Manual (version 2.4) with 4% desaturation hypopnea criteria. A total of 78 subjects were recruited. Of these, 45% had AHI < 5; 18% had AHI 5–15; 19% had AHI 15–30; 18% had AHI ≥ 30. The Belun apnea-hypopnea index (bAHI) correlated well with the PSG-AHI (r = 0.888, P < 0.001). The Belun total sleep time (bTST) and PSG-TST had a high correlation coefficient (r = 0.967, P < 0.001). The accuracy, sensitivity, specificity in categorizing AHI ≥ 15 were 0.808 [95% CI, 0.703–0.888], 0.931 [95% CI, 0.772–0.992], and 0.735 [95% CI, 0.589–0.850], respectively. The use of beta-blocker/calcium-receptor antagonist and the presence of comorbidities did not negatively affect the sensitivity and specificity of BSP in predicting OSA. A diagnostic algorithm combining STOP-Bang cutoff of 5 and bAHI cutoff of 15 events/h demonstrated an accuracy, sensitivity, specificity of 0.938 [95% CI, 0.828–0.987], 0.944 [95% CI, 0.727–0.999], and 0.933 [95% CI, 0.779–0.992], respectively, for the diagnosis of moderate to severe OSA. BSP is a promising testing tool for OSA assessment and can potentially be incorporated into clinical practices for the identification of OSA.Trial registration: ClinicalTrial.org NCT03997916 https://clinicaltrials.gov/ct2/show/NCT03997916?term=belun+ring&draw=2&rank=1