Data Dropouts Research Articles

Advanced Image Classification Using Convolutional Neural Networks

Deep learning is essential for computer vision and object detection. This project explores the use of Convolutional Neural Networks (CNNs) for image classification using the CIFAR-10 dataset, which is widely used and provides a robust benchmark for evaluating image classification models. The CNN model, comprising various convolutional, pooling, and fully connected layers, is trained on a portion of the dataset and tested on another portion to evaluate its performance. Techniques such as data augmentation, dropout, and specific activation functions are employed to enhance the model’s efficacy. The study details the CNN architecture and reports the results, including accuracy metrics, to demonstrate the model’s effectiveness.

A Quantitative Computational Framework for Allopolyploid Single-Cell Data Integration and Core Gene Ranking in Development.

Polyploidization drives regulatory and phenotypic innovation. How the merger of different genomes contributes to polyploid development is a fundamental issue in evolutionary developmental biology and breeding research. Clarifying this issue is challenging because of genome complexity and the difficulty in tracking stochastic subgenome divergence during development. Recent single-cell sequencing techniques enabled probing subgenome-divergent regulation in the context of cellular differentiation. However, analyzing single-cell data suffers from high error rates due to high dimensionality, noise, and sparsity, and the errors stack up in polyploid analysis due to the increased dimensionality of comparisons between subgenomes of each cell, hindering deeper mechanistic understandings. In this study, we develop a quantitative computational framework, called "pseudo-genome divergence quantification" (pgDQ), for quantifying and tracking subgenome divergence directly at the cellular level. Further comparing with cellular differentiation trajectories derived from single-cell RNA sequencing data allows for an examination of the relationship between subgenome divergence and the progression of development. pgDQ produces robust results and is insensitive to data dropout and noise, avoiding high error rates due to multiple comparisons of genes, cells, and subgenomes. A statistical diagnostic approach is proposed to identify genes that are central to subgenome divergence during development, which facilitates the integration of different data modalities, enabling the identification of factors and pathways that mediate subgenome-divergent activity during development. Case studies have demonstrated that applying pgDQ to single-cell and bulk tissue transcriptomic data promotes a systematic and deeper understanding of how dynamic subgenome divergence contributes to developmental trajectories in polyploid evolution.

Diseño de una aplicación para detectar covid-19 mediante redes neuronales convolucionales e imágenes de rayos X

This research presents the design of an application to detect covid-19 using convolutional neural networks and X-ray images in two scenarios (covid/Non-covid and covid/Normal/Pneumonia). To avoid overfitting online data augmentation, dropout, batch normalization, and Adam optimizer was used. The three-class network was used as a pre-trained model, tuning only the dense and output layers to obtain the binary model. Additionally, hyper-parameter optimization was used to get dropout probabilities, activation functions, and neurons. The learning rate was adjusted using callbacks to avoid local optimums. Networks were converted to TensorFlow.js format and embedded locally in a hybrid application using Ionic and Capacitor and were deployed through Firebase to help provide diagnostics. The application obtained an accuracy of 98.61% and 96.48% for two and three classes, respectively, achieving higher performance when compared to other proposals (offline models) in the literature and using fewer training parameters.

Almost sure and mean square convergence of iterative learning control system with state feedback under random packet dropouts

This paper investigates the almost sure and mean square convergence of a state feedback-based iterative learning control scheme for a class of discrete-time multi-input–multi-output linear systems with a direct feedback term in the presence of random data dropouts. Firstly, the realisability of the control system is considered. It is shown that the realisability of the control system is only determined by the direct feedback matrix, which has nothing to do with the input–output coupling matrix, and the direct feedback matrix to be full-row rank is enough to guarantee the system realisable. Secondly, the convergence of output tracking errors is analysed in both the almost sure and mean square senses, respectively. By the contraction mapping method combined with matrix decomposition and transformation techniques, it is strictly proved that the output sequence can converge to any given desired trajectory in the sense of almost sure and mean square, respectively, if and only if the general spectral radius condition is satisfied. Finally, an example is given to show the correctness of the theoretical analysis.

Prediction-Based Power Consumption Monitoring of Industrial Equipment Using Interpretable Data-Driven Models

Efficient energy optimization and scheduling in industrial factories depend on accurate, reasonable, and real-time monitoring of equipment power consumption. However, the power prediction of industrial equipment requires a large number of process data, which could be inevitably contaminated by some imperfect data, due to the harsh environments. Monitoring or predicting equipment power consumption is usually not feasible using data-driven black-box models with imperfect data. This paper proposes a prediction-based approach for power consumption monitoring using an interpretable data-driven model. First, a data preprocessing method is used to remove outliers and fill in missing values. Then, a Volterra polynomial basis function (VPBF) model is built to predict equipment power consumption. This model decomposes power values into a series of basis functions consisting of input parameters. Moreover, to compensate for data dropouts during the power consumption monitoring process, a networked predictive monitoring system is also proposed. Finally, this paper presents two case studies based on actual production equipment in an industrial manufacturing factory. The results demonstrate that the proposed approach can achieve satisfactory monitoring accuracy and adaptation ability. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —This paper is motivated by the problem of power consumption monitoring of industrial equipment in harsh production environments. A conventional solution is to predict the power consumption using data-driven black-box models, with limited feasibility and interpretability. This paper proposes a new power consumption monitoring approach, utilizing an interpretable data-driven model and a networked predictive method. This approach accurately reveals the transparent relationships between the output and input parameters. The power prediction result is consequently interpretable and more reasonable. Meanwhile, this approach actively compensates for data dropouts in the network, which can help operators real-time grasp the power consumption of equipment. Furthermore, this approach can be integrated into energy optimization systems as a basis of optimization and decision-making. Practical applications in an aluminum manufacturing company located in Guangdong Province demonstrate that this approach is feasible and applicable. Future research is to expand this approach further for energy optimization and scheduling.

Quantized iterative learning control of communication-constrained systems with encoding and decoding mechanism

In practical applications, due to the limited communication bandwidth, the network control systems (NCSs) are prone to data dropouts when the load is high. In this paper, the problem of quantized iterative learning control (ILC) based on encoding and decoding mechanism for such communication-constrained systems is studied. By combining the encoding and decoding mechanism with the uniform quantizer, the network burden and the impact of quantization error on the tracking performance of the systems are significantly mitigated. Meanwhile, data dropouts are represented as the Bernoulli random variable model, and an ILC law based on gradient is designed. When data dropouts occur, the signals maintain the value of the previous trial, otherwise the signals are updated. For this kind of learning framework, the asymptotic zero-error tracking performance has been rigorously proven for the uniform quantizer. To validate the proposed design, a joint motion of an industrial robot in the horizontal plane is simulated as an example.

Feedforward-feedback-enhanced model-free adaptive iterative learning control with measurement disturbance and data dropout for an autonomous bus trajectory tracking system.

This article presents an innovative enhanced model-free adaptive iterative learning control approach suited for autonomous bus trajectory tracking systems that may experience measurement disruptions and random data dropouts. Data loss can occur independently and randomly at different times and in different iterations with varying probabilities, leading to successive data dropouts on both the time and iteration axes. The proposed enhanced model-free adaptive iterative learning control controller incorporates a data compensation mechanism to compensate for missing data, ensuring excellent control performance. This data-driven control strategy requires only input/output data for controller design. The convergence and effectiveness of the proposed approach are verified through rigorous mathematical analysis and simulation outcomes.

Asymptotic Stability of Delayed Boolean Networks With Random Data Dropouts.

In real networks, communication constraints often prevent the full exchange of information between nodes, which is inevitable. This brief investigates the problem of time delay and randomly missing data in Boolean networks (BNs). A Bernoulli random variable is assigned to each node to characterize the probability of data packet dropout. Time delay and missing data are modeled by independent random variables. A novel data-sending rule that incorporates both communication constraints is proposed. An augmented system, comprising current states, delayed information, and successfully transmitted data, is established for theoretical analysis. Using the semitensor product (STP), the necessary and sufficient condition for asymptotic stability of delayed BNs with random data dropouts is derived. The convergence rate is also obtained.

Optimization and Stabilization of Distributed Secondary Voltage Control with Time Delays and Packet Losses Using LMIs

The proposed hierarchical secondary voltage control is a spatially distributed control system using communication networks which are disturbed by both a time delays and packet data dropouts. A state feedback integral control is adopted to eliminate the effect of non-zero disturbance and provide exact tracking of the references of the pilot points and alignment of the reactive powers of the generators that participate in the control. The system is modeled as a discrete-time switched system, and the control gains are synthesized by solving LMIs for a stability condition based on a state-dependent Lyapunov function. For that, the cone complementarity linearization (CCL) algorithm is used. The effectiveness of the proposed control strategy in preventing time delays and packet losses is simulated, considering the model of a realistic electric power grid under typical operational conditions using MATLAB.

Quantized iterative learning control for impulsive differential inclusion systems with data dropouts

This paper studies the quantized iterative learning control with encoding–decoding mechanism of a class of impulsive differential inclusion systems with random data dropouts. First, the set-valued mappings in the differential inclusion systems are transformed into single-valued mappings by using the Steiner-type selector. Then, a learning algorithm based on the intermittent update principle is designed to address the data asynchronism problem caused by two-sided data dropouts. If the data are successfully transmitted at the actuator and measurement sides, then the control input is effectively updated. Furthermore, a suitable scaling sequence is introduced to ensure the system output to achieve zero-error tracking performance for a desired trajectory. An upper bound of the quantization level is determined such that the quantization error is always bounded. The results show that the quantization method reduces the burden of network communication at the cost of increasing the amount of computation, and the learning algorithm does not require the data dropouts to satisfy a certain probability distribution. Finally, the effectiveness of the learning algorithm is verified by numerical simulations of the switched reluctance motor system.

A light-weighted convolutional neural network for image classification in autopilot system

Autopilot has been a heated technology in recent days, and it is used in plenty of car brands. People are becoming dependent on autopilot technology. However, before this technology becomes mature, there are still a lot of insufficiencies that need to improve. The focus of this essay is on the object detection shortage that exists in the autopilot system. This essay is first going to introduce a lite CNN-based method to improve the object detection and identification module. In the result part of the essay, the essay is going to show the result of the training and some new prediction function will be implemented. Also, some accuracy improving methods including data augmentation and Dropout will be introduced, and the effect of the improving methods will be shown in the essay. After training, the autopilot system is going to distinguish pedestrians from vehicles. Although the road condition is far more complex than just vehicles and pedestrians, for convenience this essay is only going to implement the two datasets. Also, some further improvement intension will be introduced.

Collecting Paediatric Health-Related Quality of Life Data: Assessing the Feasibility and Acceptability of the Australian Paediatric Multi-Instrument Comparison (P-MIC) Study.

Collecting data using paediatric health-related quality of life (HRQoL) instruments is complex, and there is a paucity of evidence regarding the comparative performance of paediatric HRQoL instruments. The Australian Paediatric Multi-Instrument Comparison (P-MIC) study was conducted to address this paucity of evidence. This study aims to understand the (1) feasibility of collecting data using paediatric HRQoL instruments in a research setting and (2) acceptability and feasibility for children and their caregivers to complete common paediatric HRQoL instruments using data from the Australian P-MIC study. Data were from children aged 5-18 years from the Australian P-MIC study. Demographics, cost and time for data collection, dropout rates, and inconsistent responses were used to assess Aim 1. Participant-reported difficulty and completion time were used to assess Aim 2. Subgroup analyses included child age, report type (self/proxy), sample recruitment pathway (hospital/online), and online panel sample type (general population/condition groups). Overall, 5945 P-MIC participants aged 5-18 years completed an initial survey, of these, 2346 also completed the follow-up survey (39.5% response rate). Compared with online panel recruitment, hospital recruitment was more costly and time-consuming and had higher follow-up completion (33.5% versus 80.4%) (Aim 1). Data were of similar good quality (based on inconsistent responses) for both recruitment pathways (Aim 1). Participants completed each instrument in <3 min, on average, and >70% reported each instrument as easy to complete (Aim 2). The Australian P-MIC study was able to collect good-quality data using both online panel and hospital recruitment pathways. All instruments were acceptable and feasible to children and their caregivers.

System for quantitative diagnosis of COVID-19 associated Pneumonia based on Superpixels with deep learning and chest CT

COVID-19 is a disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that can lead to complications such as acute respiratory distress syndrome, acute heart injury and secondary infections in a relatively high proportion of patients and, consequently, lead to significant mortality. The definitive diagnosis of COVID-19 is performed by real-time Polymerase Chain Reaction (RT-PCR). However, as RT-PCR results usually take longer to be completed than computed tomography (CT), the latter has had an important role in the detection of patients infected with COVID-19. A rough estimate of the extent of lung involvement by the disease is also important and considered an additional criterion for deciding on discharge or hospitalization. Recent research has adopted deep neural networks and other machine learning approaches to detect the presence of lung infection caused by COVID-19. However, the extent of lung involvement (volume) caused by the disease has been only superficially investigated. In this work, we created an end-to-end computer vision system to automatically quantify the Percentage of Infection (POI) in chest CT images of COVID-19 cases confirmed by laboratorial analysis. We evaluated the performance of three well-known deep neural networks, trained using three different strategies: (1) no transfer learning with randomly initialized weights; (2) transfer learning using with ImageNet weights without fine-tuning; and (3) transfer learning with weight fine-tuning. Data augmentation and dropout were used during training to reduce overfitting and increase the generalization capacity of the models. Our approach consists of segmenting a chest CT with the SLIC Superpixels method and classifying each segment (superpixel) into a specific class (COVID or non-COVID). We used the weights of the best deep neural network to classify the superpixels and quantify the COVID-19 infection by calculating the POI on chest CT. The results indicate that deep learning models can be successfully used to support radiologists in the quantitative diagnosis of lung infection caused by COVID-19, reaching an accuracy of up to 98.4% with Inception-Resnet-v2 architecture.

Heart sounds classification: Application of a new CyTex inspired method and deep convolutional neural network with transfer learning

Analysis of heart sounds is an effective means for the early diagnosis of cardiac pathologies. Heart sound classification is a challenging multi-disciplinary field that attracts many machine learning researchers. This paper proposes a new CyTex-inspired transform to convert heart sound signals to textured images. In our proposed method, the neighboring pixels have meaningful relationships that result in semi-periodic patterns in the output image. This method has two significant benefits. Firstly, this makes it possible to apply deep convolutional neural networks (DCNN) to heart sound classification. Consequently, correlative moving masks of the convolutional layers can extract short-term and long-term information from these images in vertical and horizontal directions. Secondly, by converting the heart sound signal to images as a compatible input for DCNNs, we can employ a transfer learning scheme to reduce the risk of overfitting. The performance of four popular pre-trained DCNNs – AlexNet, VGG16, InceptionV3, and ResNet50 – has been tested. Furthermore, data augmentation, hyper-parameter optimization, and drop-out techniques are employed. The performance of the proposed system is verified on the heart sounds dataset PhysioNet. Results were obtained using cross-validation techniques. Our experiments demonstrate the potential of our proposed method for achieving excellent performance compared to previous methods on the same dataset with a score of over 0.9200 at a sensitivity of 0.8775 and specificity of 0.9637 using the ResNet with data augmentation, hyperparameter optimization, and dropout techniques.

MozzieNet: A deep learning approach to efficiently detect malaria parasites in blood smear images

AbstractOur study presents MozzieNet, a customized CNN model aimed at improving the identification of malaria parasites in blood smear microscopic images. By optimizing hyperparameters and incorporating techniques like data augmentation, batch normalization, and dropout, our model enhances robustness and generalization, addressing overfitting issues. Using the open‐source NIH malaria dataset with 27,558 images, we achieve a classification accuracy of 96.73%, recall rate of 97.90%, precision of 95.67%, area under the curve (AUC) of 99.35%, and F1 score of 96.77%. We performed feature maps and Grad‐CAM analysis on our proposed MozzieNet model to visualize and examine the targeted regions that are crucial for accurate predictions. Statistical analysis shows that the proposed architecture achieves promising performance and is superior to pre‐trained models and existing methods for malaria detection. MozzieNet is designed for cloud and low‐end smartphones, enabling malaria diagnosis in remote areas, thereby assisting physicians in informed malaria diagnosis and decision‐making.

Input predictors for networked iterative learning control systems with data dropouts and time delays

Hold-up compensation decelerates the convergence of iterative learning control (ILC) systems with data dropouts and time delays. Only depending on the prior knowledge of both ILC controllers and transmission channels, this paper develops a predictor to calculate the input not received on time due to data dropouts and time delays. First, a controller adopting the proportional learning strategy is considered directly, which is appropriate for objects in ideal communication conditions. After that, two data-receiving equations are given to describe the effect of data dropouts and one-step time delays. Finally, a predictor is designed according to the innovation analysis approach. Since the prediction uses all historical input at the identical time index in previous iterations, the predicted input is more approximate to the one not received on time than the input held up for compensation. Simulation results show the object with prediction compensation tracks the expected trajectory faster than that with input-hold compensation.

Mask recognition in computer vision technology

In order to lessen the strain on employees and the potential for carelessness, intelligent identification is required in China where there is a scarcity of staff to monitor the wearing of masks in public areas. In this work, we use a mask recognition technique to determine which members of the population weren't wearing masks by using the CNN and the VGG16 model. The ideas of data augmentation, dropout, non malicious, and transfer learning are used in the proposed study. This method may be used at hospitals, retail centers, transit hubs, dining establishments, and other community gatherings that require monitoring.

Autonomous face mask detection using single shot multibox detector, and ResNet-50 with identity retrieval through face matching using deep siamese neural network.

The COVID-19 pandemic poses a global health challenge. The World Health Organization states that face masks are proven to be effective, especially in public areas. Real-time monitoring of face masks is challenging and exhaustive for humans. To reduce human effort and to provide an enforcement mechanism, an autonomous system has been proposed to detect non-masked people and retrieve their identity using computer vision. The proposed method introduces a novel and efficient method that involves fine-tuning the pre-trained ResNet-50 model with a new head layer for classification between masked and non-masked people. The classifier is trained using adaptive momentum optimization algorithm with decaying learning rate and binary cross-entropy loss. Data augmentation and dropout regularization are employed to achieve best convergence. During real-time application of our classifier on videos, a Caffe face detector model based on Single Shot MultiBox Detector is used to extract the face regions of interest from each frame, on which the trained classifier is applied for detecting the non-masked people. The faces of these people are then captured, which is passed on to a deep siamese neural network, based on VGG-Face model for face matching. The captured faces are compared with the reference images from the database, by extracting the features and calculating cosine distance. If the faces match, the details of that person are retrieved from the database and displayed on the web application. The proposed method has secured best results where the trained classifier has achieved 99.74% accuracy, and the identity retrieval model achieved 98.24% accuracy.

Learning-Based Robust Bipartite Consensus Control for a Class of Multiagent Systems

This article studies the robust bipartite consensus problems for heterogeneous nonlinear nonaffine discrete-time multiagent systems (MASs) with fixed and switching topologies against data dropout and unknown disturbances. The controlled system’s virtual linear data model is first developed by employing the pseudopartial derivative technique, and a distributed combined measurement error function is established utilizing a signed graph theory. Then, an input gain compensation scheme is formulated to mitigate the effects of data dropout in both feedback and forward channels. Moreover, a data-driven learning-based robust bipartite consensus control (LRBCC) scheme based on a radial basis function neural network observer is proposed to estimate the unknown disturbance, using the online input/output data without requiring any information on the mathematical dynamics. The stability analysis of the proposed LRBCC approach is given. Finally, simulation and hardware testing results further demonstrate the designed method’s correctness and effectiveness.

A Kalman-Based Compensation Strategy for Platoons Subject to Data Loss: Numerical and Empirical Study

This article considers a homogeneous platoon with vehicles that communicate through channels prone to data loss. The vehicles use a predecessor-following topology, where each vehicle sends relevant data to the next, and data loss is modeled through a Bernoulli process. To address the lossy communication, we propose a strategy to estimate the missing data based on the Kalman filter with intermittent observations combined with a linear extrapolation stage. This strategy enables the followers to better deal with data dropouts. We compare this approach to one purely based on the linear extrapolation of previous data. The performance of both strategies is analyzed through Monte Carlo simulations and experiments in an ad hoc testbed, considering various data loss and transmission loss probabilities depending on the inter-vehicle distance. The results show that for the considered cases, the proposed strategy outperforms the linear extrapolation approach in terms of tracking and estimation error variances. Our results also show that the proposed strategy can achieve string stability for the mean and variance for both the tracking and estimation errors in scenarios where the basic extrapolation strategy cannot.