Deep Network Research Articles

Topology-adaptive Bayesian optimization for deep ring echo state networks in speech emotion recognition

Topology-adaptive Bayesian optimization for deep ring echo state networks in speech emotion recognition

Safeguarding User-Centric Privacy in Smart Homes

Internet of Things (IoT) devices have been increasingly deployed in smart homes to automatically monitor and control their environments. Unfortunately, extensive recent research has shown that on-path external adversaries can infer and further fingerprint people’s sensitive private information by analyzing IoT network traffic traces. In addition, most recent approaches that aim to defend against these malicious IoT traffic analytics cannot adequately protect user privacy with reasonable traffic overhead. In particular, these approaches often did not consider practical traffic reshaping limitations, user daily routine permitting, and user privacy protection preference in their design. To address these issues, we design a new low-cost, open source user-centric defense system—PrivacyGuard—that enables people to regain the privacy leakage control of their IoT devices while still permitting sophisticated IoT data analytics that is necessary for smart home automation. In essence, our approach employs intelligent deep convolutional generative adversarial network assisted IoT device traffic signature learning, long short-term memory based artificial traffic signature injection, and partial traffic reshaping to obfuscate private information that can be observed in IoT device traffic traces. We evaluate PrivacyGuard using IoT network traffic traces of 31 IoT devices from five smart homes and buildings. We find that PrivacyGuard can effectively prevent a wide range of state-of-the-art adversarial machine learning and deep learning based user in-home activity inference and fingerprinting attacks and help users achieve the balance between their IoT data utility and privacy preserving.

The Identification, Separation, and Clamp Function of an Intelligent Flexible Blueberry Picking Robot

Identifying fruit maturity accurately and achieving damage-free harvesting are challenges in designing blueberry-picking robots. This paper presents an intelligent flexible picking system. First, we trained a deep learning-based YOLOv8n network to locate the position of the fruit and determine fruit ripeness. We used a neural network to establish the relationship between fruit hardness and shape parameters, achieving an adaptive gripping force for different fruits. To address the issue of dense clusters in some blueberry varieties, we designed a fruit separation subsystem using a combination of flow field analysis and pressure-sensitive experiments. The results show that the mean average precision can reach 84.62%, the precision is 94.49%, the recall is 83.85%, the F1 score is 88.85%, and the test time is 0.12 s, which can meet the requirements for blueberry fruit recognition accuracy and speed. The spacing between closely packed fruits can increase by 4 mm, and the damage-free picking rate exceeds 92%, achieving stable, damage-free harvesting.

An efficient deep learning method for amino acid substitution model selection.

Amino acid substitution models play an important role in studying the evolutionary relationships among species from protein sequences. The amino acid substitution model consists of a large number of parameters; therefore, it is estimated from hundreds or thousands of alignments. Both general models and clade-specific models have been estimated and widely used in phylogenetic analyses. The maximum likelihood method is normally used to select the best fit model for a specific protein alignment under the study. A number of studies have discussed theoretical concerns as well as computational burden of the maximum likelihood methods in model selection. Recently, machine learning methods have been proposed for selecting nucleotide models. In this paper, we propose a method to measure substitution rates among amino acids (called summary statistics) from protein alignments to efficiently train a deep learning network of so-called ModelDetector for detecting amino acid substitution models. The ModelDetector network was trained from 2,246,400 alignments on a computer with 8 cores (without GPU) in about 3.3 hours. Experiments on simulation data showed that the accuracy of the ModelDetector was comparable with that of the maximum likelihood method ModelFinder. It was orders of magnitude faster than the maximum likelihood method in inferring amino acid substitution models and able to analyze genome alignments with millions of sites in minutes. The results indicate that the deep learning network can play as a promising tool for amino acid substitution model selection.

Power Load Prediction Algorithm Based on Wavelet Transform

To address the environmental impact, low efficiency, and poor accuracy of existing power load prediction methods, this study innovatively proposes a power load prediction system that combines wavelet transform with digital twin technology. Compared with similar power load prediction methods, the proposed method achieved the highest power load prediction accuracy rate of 97.26%, with the lowest MAPE and RMSE being only 3.96% each. Our proposed method has good noise resistance and overcomes the disadvantage of traditional power load prediction methods that are easily affected by the environment. Moreover, the false detection rate of the load information data obtained from the power system in the Fuxin area from 2022 to 2023 was less than 5%, further verifying the reliability of the proposed method. This achievement is attributed to the powerful signal processing capabilities of the discrete wavelet transform, advanced pattern recognition and prediction capabilities of these three deep learning network algorithms, and the intelligence of digital twin technology. The combination of these three elements has brought new technological breakthroughs to the field of power load prediction.

A Study of Radar Anti-Jamming Based on Deep Convolutional Mix Separation Network

A Study of Radar Anti-Jamming Based on Deep Convolutional Mix Separation Network

Software Refactoring Network: An Improved Software Refactoring Prediction Framework Using Hybrid Networking‐Based Deep Learning Approach

ABSTRACTSoftware refactoring plays a vital role in maintaining and improving the quality of software systems. The software refactoring network aims to connect developers, researchers, and practitioners to share knowledge, best practices, and tools related to refactoring. However, the network faces various challenges, such as the complexity of software systems, the diversity of refactoring techniques, and the need for automated and intelligent solutions to assist developers in making refactoring decisions. By leveraging deep learning techniques, the software refactoring network can enhance the speed, accuracy, and relevance of refactoring suggestions, ultimately improving the overall quality and maintainability of software systems. So, in this paper, an advanced deep learning–based software refactoring framework is proposed. The suggested model performs three phases as (a) data collection, (b) feature extraction, and (c) prediction of software refactoring. Initially, the data is collected from ordinary datasets. Then, the collected data is fed to the feature extraction stage, where the source code, process, and ownership metrics of all refactored and non‐refactored data are retrieved for further processing. After that, the extracted features are predicted using Adaptive and Attentive Dilation Adopted Hybrid Network (AADHN) techniques, in which it is performed using Deep Temporal Context Networks (DTCN) with a Bidirectional Long‐Short Term Memory (Bi‐LSTM) model. Here, the parameters in the hybrid networking model are optimized with the help of Constant Integer Updated Golden Tortoise Beetle Optimizer (CIU‐GTBO) for improving the prediction process. Therefore, the accuracy of the developed algorithm has achieved for different datasets, whereas it shows the value of 96.41, 96.38, 96.38, 96.38, 96.41, 96.38, and 96.39 for antlr4, junit, mapdb, mcMMO, mct, oryx, and titan. Also, the precision of the developed model has shown the better performance of 96.38, 96.32, 96.37, 96.33, 96.35, 96.37, and 96.31 for the datasets like antlr4, junit, mapdb, mcMMO, mct, oryx, and titan.

Efficient labeling for fine-tuning chest X-ray bone-suppression networks for pediatric patients.

Pneumonia, a major infectious cause of morbidity and mortality among children worldwide, is typically diagnosed using low-dose pediatric chest X-ray [CXR (chest radiography)]. In pediatric CXR images, bone occlusion leads to a risk of missed diagnosis. Deep learning-based bone-suppression networks relying on training data have enabled considerable progress to be achieved in bone suppression in adult CXR images; however, these networks have poor generalizability to pediatric CXR images because of the lack of labeled pediatric CXR images (i.e., bone images vs. soft-tissue images). Dual-energy subtraction imaging approaches are capable of producing labeled adult CXR images; however, their application is limited because they require specialized equipment, and they are infrequently employed in pediatric settings. Traditional image processing-based models can be used to label pediatric CXR images, but they are semiautomatic and have suboptimal performance. We developed an efficient labeling approach for fine-tuning pediatric CXR bone-suppression networks capable of automatically suppressing bone structures in CXR images for pediatric patients without the need for specialized equipment and technologist training. Three steps were employed to label pediatric CXR images and fine-tune pediatric bone-suppression networks: distance transform-based bone-edge detection, traditional image processing-based bone suppression, and fully automated pediatric bone suppression. In distance transform-based bone-edge detection, bone edges were automatically detected by predicting bone-edge distance-transform images, which were then used as inputs in traditional image processing. In this processing, pediatric CXR images were labeled by obtaining bone images through a series of traditional image processing techniques. Finally, the pediatric bone-suppression network was fine-tuned using the labeled pediatric CXR images. This network was initially pretrained on a public adult dataset comprising 240 adult CXR images (A240) and then fine-tuned and validated on 40 pediatric CXR images (P260_40labeled) from our customized dataset (named P260) through five-fold cross-validation; finally, the network was tested on 220 pediatric CXR images (P260_220unlabeled dataset). The distance transform-based bone-edge detection network achieved a mean boundary distance of 1.029. Moreover, the traditional image processing-based bone-suppression model obtained bone images exhibiting a relative Weber contrast of 93.0%. Finally, the fully automated pediatric bone-suppression network achieved a relative mean absolute error of 3.38%, a peak signal-to-noise ratio of 35.5dB, a structural similarity index measure of 98.1%, and a bone-suppression ratio of 90.1% on P260_40labeled. The proposed fully automated pediatric bone-suppression network, together with the proposed distance transform-based bone-edge detection network, can automatically acquire bone and soft-tissue images solely from CXR images for pediatric patients and has the potential to help diagnose pneumonia in children.

A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning

Epilepsy is a chronic neurological disorder that poses significant challenges to patients and their families. Effective detection and prediction of epilepsy can facilitate patient recovery, reduce family burden, and streamline healthcare processes. Therefore, it is essential to propose a deep learning method for efficient detection and prediction of epileptic electroencephalography (EEG) signals. This paper reviews several key aspects of epileptic EEG signal processing, focusing on epilepsy detection and prediction. It covers publicly available epileptic EEG datasets, preprocessing techniques, feature extraction methods, and deep learning-based networks used in these tasks. The literature is categorized based on patient independence, distinguishing between patient-independent and non-patient-independent studies. Additionally, the evaluation methods are classified into general classification indicators and specific epilepsy prediction criteria, with findings organized according to the prediction cycles reported in various studies. The review reveals several important insights. Despite the availability of public datasets, they often lack diversity in epilepsy types and are collected under controlled conditions that may not reflect real-world scenarios. As a result, signal preprocessing methods tend to be limited and may not fully represent practical conditions. Feature extraction and network designs frequently emphasize fusion mechanisms, with recent advances in Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) showing promising results, suggesting that new network models warrant further exploration. Studies using patient-independent data generally produce better results than those relying on non-patient-independent data. Metrics based on general classification methods typically perform better than those using specific epilepsy prediction criteria, though future research should focus on the latter for more accurate evaluation. Epilepsy prediction cycles are typically kept under 1 h, with most studies concentrating on intervals of 30 min or less.

The deep convolution network in immersive design of digital media art in smart city.

The goal of the paper is to examine how convolutional neural network (CNN) is used in the immersive world of digital media art. In order to do this, this paper first explains digital media art in the context of smart cities and the use of immersive scenarios. Next, a brief analysis of the Unet network model and deep aggregation structure is provided. Then, a projector, camera, and computer-based immersive projector-camera display system is constructed. Based on the mathematical reflection model of the system, this paper discusses the method of using CNN to solve the photometric compensation of the projection picture. Meanwhile, a Projection Compensation Network (PCN) is designed, and a multi-scale perceptual loss is added to this compensation network, and the content information of the compensated image is improved by calculating the loss of feature maps of different scales. The final network is named Perceptual Loss-Projection Compensation Network (PL-PCN). Experiments are used to confirm the PL-PCN model's efficacy. The outcomes demonstrate that the SSIM and PSNR of the projected picture compensated by PL-PCN are boosted by 35.8% and 31.6%, respectively. While the RMSE is reduced by 40.9%, demonstrating an improvement in the compensated image's quality. Additionally, utilizing a CNN makes it possible to do cross-reflection compensation. Additionally, compared to the network without deep polymerization, the PL-PCN with deep polymerization structure boosts the projected image's SSIM and PSNR by 6% and 7.57%, respectively, and lowers the RMSE by 13.3% This demonstrates that the addition of deep polymerization structure can have a stronger compensatory effect. This paper can offer a theoretical framework for improving the immersive scene quality of digital media art.

Physics-informed two-tier neural network for non-linear model order reduction

AbstractIn recent years, machine learning (ML) has had a great impact in the area of non-intrusive, non-linear model order reduction (MOR). However, the offline training phase often still entails high computational costs since it requires numerous, expensive, full-order solutions as the training data. Furthermore, in state-of-the-art methods, neural networks trained by a small amount of training data cannot be expected to generalize sufficiently well, and the training phase often ignores the underlying physical information when it is applied with MOR. Moreover, state-of-the-art MOR techniques that ensure an efficient online stage, such as hyper reduction techniques, are either intrusive or entail high offline computational costs. To resolve these challenges, inspired by recent developments in physics-informed and physics-reinforced neural networks, we propose a non-intrusive, physics-informed, two-tier deep network (TTDN) method. The proposed network, in which the first tier achieves the regression of the unknown quantity of interest and the second tier rebuilds the physical constitutive law between the unknown quantities of interest and derived quantities, is trained using pretraining and semi-supervised learning strategies. To illustrate the efficiency of the proposed approach, we perform numerical experiments on challenging non-linear and non-affine problems, including multi-scale mechanics problems.

Automatic face detection based on bidirectional recurrent neural network optimized by improved Ebola optimization search algorithm.

Face detection is a multidisciplinary research subject that employs fundamental computer algorithms, image processing, and patterning. Neural networks, on the other hand, have been widely developed to solve challenges in the domains of feature extraction, pattern detection, and the like in general. The presented study investigates the DNN (deep neural networks) use in the creation of facial detection operating systems. In this study, a novel optimized deep network has been presented to face detection. In this paper, after using some preprocessing stages for contrast enhancement and increasing the data number for the next deep tool, they fed to a bidirectional recurrent neural network (BRNN). The network is optimized via a novel enhanced version of Ebola optimization algorithm to provide far greater accuracy. The suggested procedure is examined on GTFD (Georgia Tech Face Database) and the results indicate that the proposed technique significantly outperforms other comparative methods, attaining an accuracy of 94.3%, a precision of 93.51%, a recall of 94.53%, and an F1-score of 92.47%. Furthermore, the method exhibits resilience against various challenges, achieving an accuracy of 95.6% under occlusions, 96.3% under lighting variations, 94.8% under pose variations, and 92.4% under low resolution conditions. Simulation results depict that the suggested technique gives far greater accuracy in comparison with the other comparative approaches.

Estimation of Cation Exchange Capacity for Low-Activity Clay Soil Fractions Using Experimental Data from South China

The cation exchange capacity (CEC) of the clay fraction (<2 μm), denoted as CECclay, serves as a crucial indicator for identifying low-activity clay (LAC) soils and is an essential criterion in soil classification. Traditional methods of estimating CECclay, such as dividing the whole-soil CEC (CECsoil) by the clay content, can be problematic due to biases introduced by soil organic matter and different types of clay minerals. To address this issue, we introduced a soil pedotransfer functions (PTFs) approach to predict CECclay from CECsoil using experimental soil data. We conducted a study on 122 pedons in South China, focusing on highly weathered and strongly leached soils. Samples from the B horizon were used, and eight models and PTFs (four machine learning methods, multiple linear regression (MLR) and three PTFs from publication) were evaluated for their predictive performance. Four covariate datasets were combined based on available soil data and environmental variables and various parameters for machine learning techniques including an artificial neural network, a deep belief network, support vector regression and random forest were optimized. The results, based on 10-fold cross-validation, showed that the simple division of CECsoil by clay content led to significant overestimation of CECclay, with a mean error of 14.42 cmol(+) kg−1. MLR produced the most accurate predictions, with an R2 of 0.63–0.71 and root mean squared errors (RMSE) of 3.21–3.64 cmol(+) kg−1. The incorporation of environmental variables improved the accuracy by 2–10%. A linear model was fitted to enhance the current calculation method, resulting in the equation: CECclay = 15.31 + 15.90 × (CECsoil/Clay), with an R2 of 0.41 and RMSE of 4.48 cmol(+) kg−1. Therefore, given limited soil data, the MLR PTFs with explicit equations were recommended for predicting the CECclay of B horizons in humid subtropical regions.

Automated Lymph Node Classification and Gastric Cancer Segmentation in CT Images Using Advanced Segmentation Techniques

The growing number of cases of stomach cancer makes it even more important to have accurate and quick diagnosis tools. This study uses cutting edge image processing techniques to try to solve this problem. The proposed method study uses a wide range of CT pictures that show different types of patients and imaging conditions. The method used to make sure the reliability of later studies includes pre-processing steps like noise reduction and intensity adjustment. For lymph node classification, the method created a complex program with advanced features that made it easier for lymph nodes to be automatically found and put into groups in the pictures. Similarly, the method used cutting-edge segmentation tools to correctly separate cancerous areas in the stomach cancer segmentation. The suggested method has been thoroughly tested using standard criteria, showing that it can accurately classify lymph nodes and divide stomach cancer into segments. Comparing the deep learning method to existing ones showed that it was better, showing that it has the ability to make a big difference in how medical picture analysis is done now. As part of the conversation, the proposed method strengths and weaknesses were emphasized, along with how the results were interpreted. The results show that the deep learning model could have a positive effect on patients by making diagnoses more accurately, making examination easier for the doctors, and eventually better patient outcomes. The proposed method for automatic lymph node labelling and the stomach cancer segmentation system are both exciting steps forward in the field of medical image analysis. The paper study's strong points and high levels of accuracy using deep learning network show that this approach has the ability to completely change how stomach cancer is diagnosed, leading to better patient care and results.

Weld Seam Recognition and Tracking With Omnidirectional Wall-Climbing Robot for Spherical Tank Inspection

Abstract Weld seams of in-service pressure storage equipment, such as spherical tanks, require regular inspection to ensure safe operation. Wall-climbing robots can replace manual operations, increasing inspection efficiency and reducing maintenance costs. High precision and fast weld seam identification and tracking are beneficial for improving the automated navigation and spatial positioning of wall-climbing robots. This study proposes a weld seam recognition and tracking method with the omnidirectional wall-climbing robot for spherical tank inspection. Based on deep learning networks, the robot has a front-mounted camera to recognize weld seams and extract weld paths. Weld seam deviation data (drift angle and offset distance) were used in real time to provide feedback on the robot's relative position. For the robot to quickly correct deviations and track weld seams, a seam path-tracking controller based on sliding mode control was designed and simulated. Weld recognition experiments revealed that the robot can accurately recognize and extract weld paths, and the recognition time for each image was approximately 0.25 s. In the weld seam tracking experiments, the robot could successfully track longitudinal and transverse weld seams at different speeds (from 0.05 to 0.2 m/s). During the process of weld seam tracking, the robot angle error was kept within ±3 deg, and the maximum offset distance was less than ±35 mm. Field tests on a 3000-m3 spherical tank were conducted to verify the practicability and effectiveness of the weld seam tracking system. This robotic system can autonomously complete weld seam identification and tracking, which promotes the automation of spherical tank inspection and maintenance.

Evaluating Deep Learning Networks Versus Hybrid Network for Smart Monitoring of Hydropower Plants

One of the main goals of the International Energy Agency (IEA) is to manage and utilize clean energy to achieve net zero emissions by 2050. Hydropower plants can significantly contribute to this goal as they are vital components of the global energy infrastructure, providing a clean, safe, and sustainable power source. Accordingly, there is great interest in developing methods to prevent errors and anomalies and ensure full operational availability. With modern hydropower plants equipped with sensors that capture extensive data, machine learning algorithms utilizing these data to detect and predict anomalies have gained research attention. This paper demonstrates that deep learning algorithms are particularly powerful in predicting time series. Three well-known deep learning networks are examined and compared to previous approaches, followed by the introduction of a new, innovative hybrid network. Using real-world data from two hydropower plants, the hybrid model outperforms individual deep learning models by achieving more accurate fault detection, reducing false positives, offering early fault prediction, and identifying faults several weeks before occurrence. These results showcase the hybrid network’s potential to enhance maintenance planning, reduce downtime, and improve operational efficiency in energy systems.

Quotient Network-A Network Similar to ResNet but Learning Quotients

The emergence of ResNet provides a powerful tool for training extremely deep networks. The core idea behind it is to change the learning goals of the network. It no longer learns new features from scratch but learns the difference between the target and existing features. However, the difference between the two kinds of features does not have an independent and clear meaning, and the amount of learning is based on the absolute rather than the relative difference, which is sensitive to the size of existing features. We propose a new network that perfectly solves these two problems while still having the advantages of ResNet. Specifically, it chooses to learn the quotient of the target features with the existing features, so we call it the quotient network. In order to enable this network to learn successfully and achieve higher performance, we propose some design rules for this network so that it can be trained efficiently and achieve better performance than ResNet. Experiments on the CIFAR10, CIFAR100, and SVHN datasets prove that this network can stably achieve considerable improvements over ResNet by simply making tiny corresponding changes to the original ResNet network without adding new parameters.

Adversarial imitation learning with deep attention network for swarm systems

AbstractSwarm systems consist of a large number of interacting individuals, which exhibit complex behavior despite having simple interaction rules. However, crafting individual motion policies that can manifest desired collective behaviors poses a significant challenge due to the intricate relationship between individual policies and swarm dynamics. This paper addresses this issue by proposing an imitation learning method, which derives individual policies from collective behavior data. The approach leverages an adversarial imitation learning framework, with a deep attention network serving as the individual policy network. Our method successfully imitates three distinct collective behaviors. Utilizing the ease of analysis provided by the deep attention network, we have verified that the individual policies underlying a certain collective behavior are not unique. Additionally, we have analyzed the different individual policies discovered. Lastly, we validate the applicability of the proposed method in designing policies for swarm robots through practical implementation on swarm robots.

Research on deep unfolding network reconstruction method based on scalable sampling of transient signals.

In order to solve the problems of long reconstruction time and low reconstruction accuracy of compressed sensing reconstruction algorithm in the measurement of transient signals, a deep unfolding network reconstruction method based on scalable sampling is proposed to achieve fast and high-quality reconstruction of transient signal under low number of measurements. Firstly, the measurement process of compressed sensing is embedded into the neural network to realize automatic design and optimization of the observation matrix, which can reduce the number of measurements. Secondly, scalable sampling is introduced into the measurement process of compressed sensing, which can realize the training of data with different sampling ratios in the same model. Finally, a deep unfolding network model is designed to reconstruct the transient signal, which not only realizes the interpretability of the reconstructed network, but also achieves fast and high-quality reconstruction of the transient signal under the low number of measurements. Experimental results show that compared with the traditional compressed sensing reconstruction algorithms, the proposed method can obtain high-quality reconstruction accuracy with lower measurement times, and the reconstruction time is greatly reduced. The algorithm in this paper also obtains good reconstruction results under different sampling ratios, which shows that the method in this paper has good adaptability and effectiveness.

Drug Sensitivity Prediction Based on Multi-stage Multi-modal Drug Representation Learning.

Accurate prediction of anticancer drug responses is essential for developing personalized treatment plans in order to improve cancer patient survival rates and reduce healthcare costs. To this end, we propose a drug sensitivity prediction model based on multi-stage multi-modal drug representations (ModDRDSP) to reflect the properties of drugs more comprehensively, and to better model the complex interactions between cells and drugs. Specifically, we adopt the SMILES representation learning method based on the deep hierarchical bi-directional GRU network (DSBiGRU) and the molecular graph representation learning method based on the deep message-crossing network (DMCN) for the multi-modal information of drugs. Additionally, we integrate the multi-omics information of cell lines based on a convolutional neural network (CNN). Finally, we use an ensemble deep forest algorithm for the prediction of drug sensitivity. After validation, the ModDRDSP shows impressive performance which outperforms the four current industry-leading models. More importantly, ablation experiments demonstrate the validity of each module of the proposed model, and case studies show the good results of ModDRDSP for predicting drug sensitivity, further establishing the superiority of ModDRDSP in terms of performance.