Deep Residual Neural Network Research Articles

A deep residual neural network model for synchronous motor fault diagnostics

Synchronous motors play a significant role in a wide range of industrial applications. Their reliable operation is paramount. Any faults in synchronous motors can lead to costly downtime, decreased productivity, and potential safety hazards. By accurately diagnosing and classifying faults, we can proactively address issues before they escalate, ensuring the smooth operation of synchronous motors and minimizing the risk of equipment failure. The accurate diagnosis and fault detection in synchronous motors pose a significant challenge in their operation and maintenance. In the existing models, the feature data at various depths are not thoroughly extracted to maximize their feature extraction capability. Additionally, they employ a single support vector machine to make the final decision on the output. The single support vector machine may not consistently produce more accurate outcomes. Therefore, this paper proposes a novel fault diagnosis model based on a deep residual neural network and multiple support vector machines to diagnose mechanical and electrical faults of synchronous motors. The proposed model improves upon existing fault diagnosis models in two key aspects. Firstly, by employing a deep neural network, the model is able to effectively process and extract fault features from the motor fault dataset, capturing more nuanced information that may be missed by existing models. Secondly, the use of multiple support vector machines enhances the decision-making capability of the model, allowing for more accurate fault diagnosis. By combining these two aspects, the proposed model achieves superior diagnostic performance compared to single support vector machine-based models. Our proposed model has been rigorously evaluated using mechanical and electrical fault datasets, and the results of experimental tests clearly demonstrate its superior diagnostic performance when compared to existing fault diagnosis models. The synergy of deep neural networks and multiple support vector machines not only improves fault detection accuracy but also enhances the robustness and generalizability of the model, making it a valuable tool for real-world industrial applications.

Analysis of Bladder Cancer Staging Prediction Using Deep Residual Neural Network, Radiomics, and RNA-Seq from High-Definition CT Images.

Bladder cancer has recently seen an alarming increase in global diagnoses, ascending as a predominant cause of cancer-related mortalities. Given this pressing scenario, there is a burgeoning need to identify effective biomarkers for both the diagnosis and therapeutic guidance of bladder cancer. This study focuses on evaluating the potential of high-definition computed tomography (CT) imagery coupled with RNA-sequencing analysis to accurately predict bladder tumor stages, utilizing deep residual networks. Data for this study, including CT images and RNA-Seq datasets for 82 high-grade bladder cancer patients, were sourced from the TCIA and TCGA databases. We employed Cox and lasso regression analyses to determine radiomics and gene signatures, leading to the identification of a three-factor radiomics signature and a four-gene signature in our bladder cancer cohort. ROC curve analyses underscored the strong predictive capacities of both these signatures. Furthermore, we formulated a nomogram integrating clinical features, radiomics, and gene signatures. This nomogram's AUC scores stood at 0.870, 0.873, and 0.971 for 1-year, 3-year, and 5-year predictions, respectively. Our model, leveraging radiomics and gene signatures, presents significant promise for enhancing diagnostic precision in bladder cancer prognosis, advocating for its clinical adoption.

Least-squares reverse time migration of simultaneous sources with deep-learning-based denoising

Least-squares reverse time migration (LSRTM) is currently one of the most advanced migration imaging techniques in the field of geophysics. It uses least-squares inversion to fit the observed data, resulting in high-resolution imaging results with more accurate amplitudes and better illumination compensation than conventional reverse time migration (RTM). However, noise in the observed data and the Born approximation forward operator can result in high-wavenumber artifacts in the final imaging results. Moreover, iteratively solving LSRTM leads to one or two orders of computational cost higher than conventional RTM, making it challenging to apply extensively in industrial applications. Simultaneous source acquisition technology can reduce the computational cost of LSRTM by reducing the number of wavefield simulations. However, this technique also can cause high-wavenumber crosstalk artifacts in the migration results. To effectively remove the high-wavenumber artifacts caused by these issues, simultaneous source and deep learning are combined to speed up LSRTM as well as suppress high-wavenumber artifacts. A deep residual neural network (DR-Unet) is trained with synthetic samples, which are generated by adding field noise to synthesized noise-free migration images. Then, the trained DR-Unet is applied on the gradient of LSRTM to remove high-wavenumber artifacts in each iteration. Compared to directly applying DR-Unet denoising to LSRTM results, embedding DR-Unet denoising into the inversion process can better preserve weak reflectors and improve denoising effects. Finally, the proposed LSRTM method is tested on two synthetic data sets and a land data set. The tests demonstrate that the proposed method can effectively remove high-wavenumber artifacts, improve imaging results, and accelerate convergence speed.

Surface hardness determination of laser cladding using laser-induced breakdown spectroscopy and machine learning (PLSR, CNN, ResNet, and DRSN).

In this study, we employed laser-induced breakdown spectroscopy (LIBS) along with machine learning algorithms, which encompass partial least squares regression (PLSR), the deep convolutional neural network (CNN), the deep residual neural network (ResNet), and the deep residual shrinkage neural network (DRSN), to estimate the surface hardness of laser cladding layers. (The layers were produced using Fe316L, FeCrNiCu, Ni25, FeCrNiB, and Fe313 powders, with 45 steel and Q235 serving as substrates.) The research findings indicate that both linear and nonlinear models can effectively fit the relationship between LIBS spectra and surface hardness. Particularly, the model derived from the ResNet exhibits superior performance with an R 2 value as high as 0.9967. We hypothesize that the inclusion of numerous noises in the LIBS spectra contributes to the enhanced predictive capability for surface hardness, thereby leading to the superior performance of the ResNet compared to the DRSN.

Research on the perception of the terrain image of the tourism destination based on multimodal user-generated content data.

Destination image is a powerful means by which destinations compete in the tourism industry, and the accurate identification of a destination image better serves destination marketing and management. This study uses multimodal data, such as text, images, and videos uploaded by tourists, to construct a comprehensive and systematic destination image process. The "cognitive-emotional-overall image" model, latent Dirichlet allocation (LDA) model, and deep residual neural networks are implemented to build a framework to examine the perception of a destination image, travelogues, and short videos from the sources called Ctrip, Qunar, and TikTok. The results show that tourists' overall perception of Sanya is based mainly on the cognitive image of natural scenery, human resources, and food. In addition, there are differences between textual and visual cognitive images among the perceptual images when multimodal data is under consideration. Furthermore, tourists have an overall positive affective image of Sanya as a destination.

A fault diagnosis method for nuclear power plants rotating machinery based on deep learning under imbalanced samples

Rotating machinery is a critical equipment widely used in nuclear power plants (NPPs). Effective fault diagnosis technology can provide reliable operation and maintenance support for rotating machinery. Data-driven intelligent fault diagnosis technology has attracted much attention in recent years. However, in practical situations, the available fault data is limited, and the imbalanced samples will make the intelligent fault diagnosis model prone to problems such as poor generalization performance and low diagnostic accuracy. Therefore, a fault diagnosis method based on deep learning is proposed to alleviate the impact of imbalanced samples on fault diagnosis of rotating machinery. First, the adaptive synthetic sampling (ADASYN) approach is used to synthesize the multi-channel vibration data to expand the unbalanced samples. Subsequently, ensemble empirical mode decomposition (EEMD) and continuous wavelet transform (CWT) are used to convert the vibration data into time–frequency images to highlight the fault features of the samples. Then, the deep residual neural network is constructed to extract the features of mixed samples and implement fault diagnosis. Fault simulation experiments are carried out based on motors and bearings, and various imbalance degree datasets are formed to provide data support for verifying the effectiveness of the proposed method. The proposed method can achieve good diagnostic performance under various degrees of imbalanced samples. In addition, the comparison results with other methods show that the proposed method has the best comprehensive performance, demonstrating the potential application value in the fault diagnosis of NPPs rotating machinery.

Prioritizing rear-end crash explanatory factors for injury severity level using deep learning and global sensitivity analysis

Traffic accidents are usually unique events with unpredictable geographical and temporal dimensions; thus, accident injury severity level (INJ-SL) analysis presents formidable categorization and data stability problems. Classical statistical models are limited in their ability to correctly model INJ-SL, whilst sophisticated machine learning approaches do not appear to have any equations to prioritize/analyze multiple contributing factors to forecast accidents accompanying INJ-SLs. In addition, the intercorrelations between the input variables may render the conclusions of a formal sensitivity analysis incorrectly. Rear-end collisions are the most common form of traffic accidents; consequently, their linked INJ-SL requires more research. This paper provides a complex technique based on a deep learning paradigm paired with different indicators of Global Sensitivity Analysis to address all of these concerns. Unlike existing neural network designs, this technique presents a deep residual neural network structure that employs residual shortcuts (i.e., connections). The connections enable the DRNNs to sidestep a few levels of the deep network architecture, evading the regular training with high accuracy issues. Using the trained DRNNs model, a Latin Hypercube sampling simulation was undertaken to determine each explanatory component's influence on the resulting INJ-SL. The latest available data from 2011 to 2018 is used to assess all rear-end collisions in North Carolina. A comparison was made between the performance of two different schemes of data categorization using a set of global sensitivity metrics. It was determined that the devised technique overcame the data heterogeneity problems to achieve an accuracy of 87%. In addition, the proposed sensitivity analysis identified the most relevant factors associated with INJ-SL rear-end collisions.

Sustainable Drone Detection using Deep Learning Paradigms

Drones are becoming more and more common, which has advantages but also concerns. They can be used to support illegal operations like drug trafficking and endanger places that are important to security. While advances in sensor technology haven't produced reliable answers in the literature, current drone detection and neutralization methods frequently require previous detection and categorization. Using radio frequency (RF) signals and a frequency signature-based deep learning model, this work promotes an environmentally friendly and multidisciplinary method of drone identification and categorization. Using commercial drones, we generated a novel drone RF dataset and thoroughly evaluated two-stage and combined detection-classification frameworks, assessing their efficacy in simultaneous multi-signal and single-signal scenarios. According to our investigation, the Deep Residual Neural Network (DRNN) framework achieves classification performance that is equivalent to that of the YOLOV5 framework, but it offers improved detection performance in multi-signal settings when compared to traditional Goodness-of-Fit (GoF) spectrum sensing. This study opens the door for multidisciplinary efforts to address new security concerns by showcasing the possibility of long-term, data-driven drone detection methods.

Global sensitivity analysis for studying hot-mix asphalt dynamic modulus parameters

The dynamic modulus (E*) of hot-mix asphalt mixtures is one of the most laborious and time-consuming material parameters to measure in the laboratory. It involves expensive, specialized equipment and expertize that are not readily available in most laboratories. Consequently, several efforts have been devoted to E* prediction models. Unfortunately, developing these prediction models is complex because of the numerous contributory factors and their non-linear influence on E* values. Moreover, such models are not able to prioritize or screen the major factors influencing the E* values. This study presents a new framework for analyzing the dynamic modulus influencing factors by adopting two modeling approaches. First, deep residual neural networks (DRNNs) for non-parametric approaches are used to improve the E* prediction capabilities and derive deep insight into the contributory parameters' effect on the E* value. Second, the well-known Witczak 1–40D prediction equation is used as a representative of the classical statistical modeling approach. In the validation of the models, a comprehensive laboratory database is utilized to account for all significant contributory parameters, such as binder characteristics, volumetric properties, mixture gradation, and testing circumstances parameters. Then, the performance is assessed using typical performance metrics. Lastly, intensive global sensitivity analysis (GSA) is undertaken with the assistance of Latin Hypercube Simulation. Three distinct GSA methods are used to emphasize the influence of each contributory factor on the value of E* in actual practice while reducing the possibility for result distortion owing to correlations between contributory variables. Performance metrics of the DRNNs and the Witczak 1–40D prediction models give the GSA conclusions high credibility. The GSA reveals that, among all possible inputs, the binder content, shear modulus, voids in the mineral aggregates, and temperature are the most significant factors in determining the E* value.

Employing Deep Learning Techniques for the Identification and Assessment of Skin Cancer

These days, skin cancer is a prominent cause of death for people. Skin cancer is the name given to the abnormal development of skin cells that are exposed to the sun. These skin cells can develop anywhere on the human body. The majority of malignancies are treatable in the early stages. Thus, early detection of skin cancer is anticipated in order to preserve patient life. With cutting edge innovation, it is possible to detect skin cancer early on. Here, we provide a novel framework for the recognition of dermo duplication pictures that makes use of a neighbouring descriptor encoding method and deep learning technique. Specifically, the deep representations of a rescaled dermo duplication image that were initially removed through training an extraordinarily deep residual neural network on a big dataset of normal images. Subsequently, the neighbourhood deep descriptors are obtained by request-less visual measurement highlights, which rely on fisher vector encoding to create an international image representation. Lastly, a convolution neural network (CNN) was utilised to orchestrate melanoma images employing the Fisher vector encoded depictions. This proposed technique can give more discriminative parts to oversee huge contrasts inside melanoma classes and little varieties among melanoma and non-melanoma classes with least readiness information.

Hyperdimensional Brain-Inspired Learning for Phoneme Recognition With Large-Scale Inferior Colliculus Neural Activities.

Develop a novel and highly efficient framework that decodes Inferior Colliculus (IC) neural activities for phoneme recognition. We propose using Hyperdimensional Computing (HDC) to support an efficient phoneme recognition algorithm, in contrast to widely applied Deep Neural Networks (DNN). The high-dimensional representation and operations in HDC are rooted in human brain functionalities and naturally parallelizable, showing the potential for efficient neural activity analysis. Our proposed method includes a spatial and temporal-aware HDC encoder that effectively captures global and local patterns. As part of our framework, we deploy the lightweight HDC-based algorithm on a highly customizable and flexible hardware platform, i.e., Field Programmable Gate Arrays (FPGA), for optimal algorithm speedup. To evaluate our method, we record IC neural activities on gerbils while playing the sound of different phonemes. We compare our proposed method with multiple baseline machine learning algorithms in recognition quality and learning efficiency, across different hardware platforms. The results show that our method generally achieves better classification quality than the best-performing baseline. Compared to the Deep Residual Neural Network (i.e., ResNet), our method shows a speedup up to 74×, 67×, 210× on CPU, GPU, and FPGA respectively. We achieve up to 15% (10%) higher accuracy in consonant (vowel) classification than ResNet. By leveraging brain-inspired HDC for IC neural activity encoding and phoneme classification, we achieve orders of magnitude runtime speedup while improving accuracy in various challenging task settings. Decoding IC neural activities is an important step to enhance understanding about human auditory system. However, these responses from the central auditory system are noisy and contain high variance, demanding large-scale datasets and iterative model fine-tuning. The proposed HDC-based framework is more scalable and viable for future real-world deployment thanks to its fast training and overall better quality.

Global sensitivity analysis for seismic performance of shear wall with high-strength steel bars and recycled aggregate concrete

In terms of bearing lateral loads, a reinforced concrete shear wall (SW) is one of the most crucial structural elements in structures. Despite their significance, recent experimental research and post-earthquake surveys have exposed the inadequate safety margins of the SWs. Significant SW components cannot be accurately identified due to the absence of empirical and mechanistic models. This study introduces a novel paradigm for assessing the SW's crucial elements by using two consecutive modeling strategies. Initially, a finite element model is calibrated to mimic one of the laboratory-experimented SW structures. Then, deep residual neural networks (DRNNs) for non-parametric techniques are used to enhance the Abaqus software prediction skills and comprehensively understand the input parameters' influence on the selected SW structure's displacement value. The suggested DRNNs' design uses residual shortcuts (i.e., connections) that skip several levels in the deep network structure in order to address the issue of training with high accuracy. A thorough global sensitivity analysis (GSA) is done using the Latin Hypercube Simulation. Three distinct GSA techniques are used to emphasize the influence of each input variable on the amount of displacement in real-world applications while limiting the risk of result misinterpretation owing to interactions between input variables. In each GSA approach, an effort would be made to rank, filter, or map the input variables. The performance metrics of the DRNNs prediction models lend confidence to the GSA's results. The diameter of steel stirrups is reported to be the most significant component in the SW structure, while SW's displacement is more sensitive to higher and lower values of the lateral load domain.

Ordinal-ResLogit: Interpretable deep residual neural networks for ordered choices

This study presents an Ordinal version of Residual Logit (Ordinal-ResLogit) model to investigate the ordinal responses. We integrate the standard ResLogit model into COnsistent RAnk Logits (CORAL) framework, classified as a binary classification algorithm, to develop a fully interpretable deep learning-based ordinal regression model. As the formulation of the Ordinal-ResLogit model enjoys the Residual Neural Networks concept, our proposed model addresses the main constraint of machine learning algorithms, known as black-box. Moreover, the Ordinal-ResLogit model, as a binary classification framework for ordinal data, guarantees consistency among binary classifiers. We showed that the resulting formulation is able to capture underlying unobserved heterogeneity from the data as well as being an interpretable deep learning-based model. Formulations for market share, substitution patterns, and elasticities are derived. We compare the performance of the Ordinal-ResLogit model with an Ordered Logit Model using a stated preference (SP) dataset on pedestrian wait time and a revealed preference (RP) dataset on travel distance. Our results show that Ordinal-ResLogit outperforms the traditional ordinal regression model. Furthermore, the results obtained from the Ordinal-ResLogit RP model show that travel attributes such as driving and transit cost have significant effects on choosing the location of non-mandatory trips. In terms of the Ordinal-ResLogit SP model, our results highlight that the road-related variables and traffic condition are contributing factors in the prediction of pedestrian waiting time such that the mixed traffic condition significantly increases the probability of choosing longer waiting times.

Which cortical regions affect the prediction of cerebrospinal fluid amyloid beta from PET images by novel residual neural network (ArcheD)

AbstractBackgroundAmyloid‐β (Aβ) aggregation, as a biological hallmark of Alzheimer’s disease (AD), is a key component of biological classification of AD in the AT(N) framework. This research aimed to develop a new deep learning model for predicting Aβ cerebrospinal fluid (CSF) measures from amyloid PET scans and explore which cortical regions are most important contributors in the model’s prediction.MethodWe developed a Residual Network model (ArcheD) to predict Aβ CSF from amyloid PET images, and trained it on 1,870 PET scans from the Alzheimer’s Disease Neuroimaging Initiative. We registered PET scans to MNI152 template and used the Neuromorphometrics atlas to derive cortical gray matter (GM) regions. We extracted brain regions’ contributions to model decision‐making by guided backpropagation, and visualized these contributions as relevance heatmaps. We used bootstrapping, Welch’s t‐test and FDR correction in testing significance of brain regions’ relevance to predictions in the whole cohort, and separately in clinical diagnostic classes of AD, mild cognitive impairment (MCI), and cognitively normal (CN) cases.ResultArcheD showed high accuracy in predicting Aβ CSF (r = 0.81; p<0.00001). According to the relevance analysis for all samples (n = 1,390) temporal (mean 0.106; 95%CI [0.105, 0.108]) and parietal (0.105; 95%CI [0.104, 0.107]) lobes were the most important GM regions for the model decision‐making. Occipital (0.098; 95%CI [0.098, 0.100]) and frontal lobes (0.091; 95%CI [0.089, 0.92]) showed noticeably fewer relevance values. Based on between‐classes comparison, these regions contribute significantly more to CSF prediction in AD and MCI individuals compared to CN (p<0.05). Analysis of 49 smaller regions showed an almost 7‐fold difference between the most and least contributing regions.ConclusionWe developed a deep residual neural network model that predicted Aβ CSF from amyloid PET scans with high accuracy, and found that temporal and parietal lobes have the highest influence on Aβ CSF predictions. In the next step, we will validate the model in independent data and aim to develop the model further for clinical use.

Which cortical regions affect the prediction of cerebrospinal fluid amyloid beta from PET images by novel residual neural network (ArcheD)

AbstractBackgroundAmyloid‐ß (Aß) aggregation, as a biological hallmark of Alzheimer’s disease (AD), is a key component of biological classification of AD in the AT(N) framework. This research aimed to develop a new deep learning model for predicting Aß cerebrospinal fluid (CSF) measures from amyloid PET scans and explore which cortical regions are most important contributors in the model’s prediction.MethodWe developed a Residual Network model (ArcheD) to predict Aß CSF from amyloid PET images, and trained it on 1,870 PET scans from the Alzheimer’s Disease Neuroimaging Initiative. We registered PET scans to MNI152 template and used the Neuromorphometrics atlas to derive cortical gray matter (GM) regions. We extracted brain regions’ contributions to model decision‐making by guided backpropagation, and visualized these contributions as relevance heatmaps. We used bootstrapping, Welch’s t‐test and FDR correction in testing significance of brain regions’ relevance to predictions in the whole cohort, and separately in clinical diagnostic classes of AD, mild cognitive impairment (MCI), and cognitively normal (CN) cases.ResultArcheD showed high accuracy in predicting Aß CSF (r = 0.81; p<0.00001). According to the relevance analysis for all samples (n = 1,390) temporal (mean 0.106; 95%CI [0.105, 0.108]) and parietal (0.105; 95%CI [0.104, 0.107]) lobes were the most important GM regions for the model decision‐making. Occipital (0.098; 95%CI [0.098, 0.100]) and frontal lobes (0.091; 95%CI [0.089, 0.92]) showed noticeably fewer relevance values. Based on between‐classes comparison, these regions contribute significantly more to CSF prediction in AD and MCI individuals compared to CN (p<0.05). Analysis of 49 smaller regions showed an almost 7‐fold difference between the most and least contributing regions.ConclusionWe developed a deep residual neural network model that predicted Aß CSF from amyloid PET scans with high accuracy, and found that temporal and parietal lobes have the highest influence on Aß CSF predictions. In the next step, we will validate the model in independent data and aim to develop the model further for clinical use.

Biologically inspired deep residual networks

<p>Many difficult computer vision issues have been effectively tackled by deep neural networks. Not only that but it was discovered that traditional residual neural networks (ResNet) captures features with high generalizability, rendering it a cutting-edge convolutional neural network (CNN). The images classified by the authors of this research introduce a deep residual neural network that is biologically inspired introduces hexagonal convolutions along the skip connection. With the competitive training techniques, the effectiveness of several ResNet variations using square and hexagonal convolution is assessed. Using the hex-convolution on skip connection, we designed a family of ResNet architecture,hexagonal residual neural network (HexResNet), which achieves the highest testing accuracy of 94.02%, and 55.71% on Canadian Institute For Advanced Research (CIFAR)-10 and TinyImageNet, respectively. We demonstrate that the suggested method improves vanilla ResNet architectures’ baseline image classification accuracy on the CIFAR-10 dataset, and a similar effect was seen on the TinyImageNet dataset. For Tiny- ImageNet and CIFAR-10, we saw an average increase in accuracy of 1.46% and 0.48% in the baseline Top-1 accuracy, respectively. The generalized performance of advancements was reported for the suggested bioinspired deep residual networks. This represents an area that might be explored more extensively in the future to enhance all the discriminative power of image classification systems.</p>

A comparative analysis of super-resolution techniques for enhancing micro-CT images of carbonate rocks

High-resolution digital rock micro-CT images captured from a wide field of view are essential for various geosystem engineering and geoscience applications. However, the resolution of these images is often constrained by the capabilities of scanners. To overcome this limitation and achieve superior image quality, advanced deep learning techniques have been used. This study compares four different super-resolution techniques, including super-resolution convolutional neural network (SRCNN), efficient sub-pixel convolutional neural networks (ESPCN), enhanced deep residual neural networks (EDRN), and super-resolution generative adversarial networks (SRGAN) to enhance the resolution of micro-CT images obtained from heterogeneous porous media. Our investigation employs a dataset consisting of 5000 micro-CT images acquired from a highly heterogeneous carbonate rock. The performance of each algorithm is evaluated based on its accuracy to reconstruct the pore geometry and connectivity, grain-pore edge sharpness, and preservation of petrophysical properties, such as porosity. Our findings indicate that EDRN outperforms other techniques in terms of the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) index, increased by nearly 4 dB and 17%, respectively, compared to bicubic interpolation. Furthermore, SRGAN exhibits superior performance compared to other techniques in terms of the learned perceptual image patch similarity (LPIPS) index and porosity preservation error. SRGAN shows a nearly 30% reduction in LPIPS compared to bicubic interpolation. Our results provide deeper insights into the practical applications of these techniques in the domain of porous media characterizations, facilitating the selection of optimal super-resolution CNN-based methodologies.

Lungs X-Ray Image Segmentation and Classification of Lung Disease using Convolutional Neural Network Architectures

Lung disease is one of the biggest causes of death in the world. The SARS-CoV-2 virus causes diseases like COVID-19, and the bacteria Streptococcus sp., which causes pneumonia, are two sample causes of lung disease. X-ray images are used to detect the lung disease. This study aimed to combine the stages of segmentation and classification of lung disease. This study in segmentation aims to separate the features contained in the lung images. The classification aimed to provide holistic information on lung disease. This research method used the Deep Residual U-Net (DrU-Net) segmentation architecture and the Deep Residual Neural Network (DResNet) classification architecture. DrU-Net is a modified U-Net architecture with dropout added in its convolutional layers. DResNet is a modified Residual Network (ResNet) architecture with dropout added in its convolutional block layers. The result of this study was segmentation using the DrU-Net architecture obtained 99% for accuracy, 98% for precision, 98% for recalls, 98% for F1-Score, and 96.1% for IoU. The classification results of the segmented images using the DResNet architecture obtained 91% for accuracy, 86% for precision, 85% for recalls, and 84% for F1-Score. The performance results of DrU-Net architecture were excellent and robust in image segmentation. Unfortunately, the average performance of DResNet in classification was still below 90%. These results indicate that Dres-Net performs well in classifying lung disorders in 3 labels, namely Covid, Normal, and Pneumonia, but still needs improvement.

Prediction and classification of minerals using deep residual neural network

Prediction and classification of minerals using deep residual neural network

Combined RF-Based Drone Detection and Classification

Abstract: Despite various positive uses, drones are also utilised for illegal purposes like as drug trafficking, weapon smuggling, and posing dangers to security-sensitive locations such as airports and nuclear power plants. Existing drone localisation and neutralisation solutions are predicated on the drone having previously been discovered and categorised. Despite significant progress in the sensor sector over the last decade, no viable drone detection and classification approach has been suggested in the literature. The frequency signature of the sent signal is used in this research to identify and classify drones using radio frequency (RF). Using commercial drones, we built an unique drone RF dataset and provided a comprehensive comparison of a two-stage and integrated detection and classification framework. Both frameworks' detection and classification results are demonstrated for a single-signal and simultaneous multi-signal situation. We demonstrate that the You Only Look Once (YOLO) framework outperforms the Goodness-of-Fit (GoF) spectrum sensing framework in a simultaneous multi-signal situation, and that it outperforms the Deep Residual Neural Network (DRNN) framework in classification