Search

Development of paper-based microfluidic devices that perform colorimetric measurements requires quantitative image analysis. Because the design geometries of paper-based microfluidic devices are not standardized, conventional methods for performing batch measurements of regularly spaced areas of signal intensity, such as those for well plates, cannot be used to quantify signal from most of these devices. To streamline the device development process, we have developed an open-source program called ColorScan that can automatically recognize and measure signal-containing zones from images of devices, regardless of output zone geometry or spatial arrangement. This program, which measures color intensity with the same accuracy as standard manual approaches, can rapidly process scanned device images, simultaneously measure identified output zones, and effectively manage measurement results to eliminate requirements for time-consuming and user-dependent image processing procedures.

Longwall top coal caving technology is one of the main methods of thick coal seam mining in China, and the classification evaluation of top coal cavability in longwall top coal caving working face is of great significance for improving coal recovery. However, the empirical or numerical simulation method currently used to evaluate the top coal cavability has high cost and low-efficiency problems. Therefore, in order to improve the evaluation efficiency and reduce evaluation the cost of top coal cavability, according to the characteristics of classification evaluation of top coal cavability, this paper improved and optimized the fuzzy neural network developed by Nauck and Kruse and establishes the fuzzy neural network prediction model for classification evaluation of top coal cavability. At the same time, in order to ensure that the optimized and improved fuzzy neural network has the ability of global approximation that a neural network should have, its global approximation is verified. Then use the data in the database of published papers from CNKI as sample data to train, verify and test the established fuzzy neural network model. After that, the tested model is applied to the classification evaluation of the top coal cavability in 61,107 longwall top coal caving working face in Liuwan Coal Mine. The final evaluation result is that the top coal cavability grade of the 61,107 longwall top coal caving working face in Liuwan Coal Mine is grade II, consistent with the engineering practice.

Emergency responders require accurate and comprehensive data to make informed decisions. Moreover, the data should be acquired and analyzed swiftly to ensure an efficient response. One of the tasks at hand post-disaster is damage assessment within the impacted areas. In particular, building damage should be assessed to account for possible casualties, and displaced populations, to estimate long-term shelter capacities, and to assess the damage to services that depend on essential infrastructure (e.g. hospitals, schools, etc.). Remote sensing techniques, including satellite imagery, can be used to gathering such information so that the overall damage can be assessed. However, specific points of interest among the damaged buildings need higher resolution images and detailed information to assess the damage situation. These areas can be further assessed through unmanned aerial vehicles and 3D model reconstruction. This paper presents a multi-UAV coverage path planning method for the 3D reconstruction of postdisaster damaged buildings. The methodology has been implemented in NetLogo3D, a multi-agent model environment, and tested in a virtual built environment in Unity3D. The proposed method generates camera location points surrounding targeted damaged buildings. These camera location points are filtered to avoid collision and then sorted using the K-means or the Fuzzy C-means methods. After clustering camera location points and allocating these to each UAV unit, a route optimization process is conducted as a multiple traveling salesman problem. Final corrections are made to paths to avoid obstacles and give a resulting path for each UAV that balances the flight distance and time. The paper presents the details of the model and methodologies, and an examination of the texture resolution obtained from the proposed method and the conventional overhead flight with the nadir-looking method used in 3D mappings. The algorithm outperforms the conventional method in terms of the quality of the generated 3D model. © 2021, The Author(s). This study was partly funded by the Japan Society for the Promotion of Science (JSPS) Kakenhi Program (17H06108 and 21H05001); the Core Research Cluster of Disaster Science; the Tough Cyberphysical AI Research Center at Tohoku University, and the National Program for Scientic Research and Advanced Studies (PROCIEN-CIA/CONCYTEC - PERU) [contract number 038-2019 FONDECYT-BM-INC-INV].

Australia faces a dryness disaster whose impact may be mitigated by rainfall prediction. Being an incredibly challenging task, yet accurate prediction of rainfall plays an enormous role in policy making, decision making and organizing sustainable water resource systems. The ability to accurately predict rainfall patterns empowers civilizations. Though short-term rainfall predictions are provided by meteorological systems, long-term prediction of rainfall is challenging and has a lot of factors that lead to uncertainty. Historically, various researchers have experimented with several machine learning techniques in rainfall prediction with given weather conditions. However, in places like Australia where the climate is variable, finding the best method to model the complex rainfall process is a major challenge. The aim of this paper is to: (a) predict rainfall using machine learning algorithms and comparing the performance of different models. (b) Develop an optimized neural network and develop a prediction model using the neural network (c) to do a comparative study of new and existing prediction techniques using Australian rainfall data. In this paper, rainfall data collected over a span of ten years from 2007 to 2017, with the input from 26 geographically diverse locations have been used to develop the predictive models. The data was divided into training and testing sets for validation purposes. The results show that both traditional and neural network-based machine learning models can predict rainfall with more precision.

Clinical studies from WHO have demonstrated that only 50–70% of patients adhere properly to prescribed drug therapy. Such adherence failure can impact therapeutic efficacy for the patients in question and compromises data quality around the population-level efficacy of the drug for the indications targeted. In this study, we applied various ensemble learning and deep learning models to predict medication adherence among patients. Our contribution to this endeavour involves targeting the problem of adherence prediction for a particularly challenging class of patients who self-administer injectable medication at home. Our prediction pipeline, based on event history, comprises a connected sharps bin which aims to help patients better manage their condition and improve outcomes. In other words, the efficiency of interventions can be significantly improved by prioritizing the patients who are most likely to be non-adherent. The collected data comprising a rich event feature set may be exploited for the purposes of predicting the status of the next adherence state for individual patients. This paper reports on how this concept can be realized through an investigation using a wide range of ensemble learning and deep learning models on a real-world dataset collected from such a system. The dataset investigated comprises 342,174 historic injection disposal records collected over the course of more than 5 years. A comprehensive comparison of different models is given in this paper. Moreover, we demonstrate that the selected best performer, long short-term memory (LSTM), generalizes well by deploying it in a true future testing dataset. The proposed end-to-end pipeline is capable of predicting patient failure in adhering to their therapeutic regimen with 77.35 % accuracy (Specificity: 78.28 %, Sensitivity: 76.42%, Precision: 77.87%,F1 score: 0.7714, ROC AUC: 0.8390).

To solve the problem that the traditional hyperspectral image classification method cannot effectively distinguish the boundary of objects with a single scale feature, which leads to low classification accuracy, this paper introduces the idea of guided filtering into hyperspectral image classification, and then proposes a multi-scale guided feature extraction and classification (MGFEC) algorithm for hyperspectral images. Firstly, the principal component analysis theory is used to reduce the dimension of hyperspectral image data. Then, guided filtering algorithm is used to achieve multi-scale spatial structure extraction of hyperspectral image by setting different sizes of filtering windows, so as to retain more edge details. Finally, the extracted multi-scale features are input into the support vector machine classifier for classification. Several practical hyperspectral image datasets were used to verify the experiment, and compared with other spectral feature extraction algorithms. The experimental results show that the multi-scale features extracted by the MGFEC algorithm proposed in this paper are more accurate than those extracted by only using spectral information, which leads to the improvement of the final classification accuracy. This fully shows that the proposed method is not only effective, but also suitable for processing different hyperspectral image data.

This paper presents a comprehensive review of advanced technologies with various control approaches in terms of their respective merits and outcomes for power grids. Distributed energy storage control is classified into automatic voltage regulator and load frequency control according to corresponding functionalities. These control strategies maintain a power balance between generation and demand. Besides, three basic electric vehicle charging technologies can be distinguished, i.e. stationary, quasi-dynamic and dynamic control. For realizing charge-sustaining operation at minimum cost quasi-dynamic and dynamic strategies are adopted for in-route charging, while stationary control can only be utilized when the electric vehicle is in stationary mode. Moreover, power system frequency stability and stabilization techniques in non-synchronous generator systems are reviewed in the paper. Specifically, a synchronverter can damp power system oscillations and ensure stability by providing virtual inertia. Furthermore, it is crucial to manage the massive information and ensure its security in the smart grid. Therefore, several attack detection and mitigation schemes against cyber-attacks are further presented to achieve reliable, resilient, and stable operation of the cyber-physical power system. Thus, bidirectional electrical power flows with two-way digital control and communication capabilities have poised the energy producers and utilities to restructure the conventional power system into a robust smart distribution grid. These new functionalities and applications provide a pathway for clean energy technology. Finally, future research trends on smart grids such as IoT-based communication infrastructure, distributed demand-response with artificial intelligence and machine learning solutions, and synchrophasor-based wide-area monitoring protection and control (WAMPC) are examined in the present study.

The use of Augmented Reality (AR) in anatomical education has been promoted by numerous authors. Next to financial and ethical advantages, AR has been described to decrease cognitive load while increasing student motivation and engagement. Despite these advantages, the effects of AR on learning outcome varies in different studies and an overview and aggregated outcome on learning anatomy is lacking. Therefore, a meta-analysis on the effect of AR vs. traditional anatomical teaching methods on learning outcome was performed. Systematic database searches were conducted by two independent investigators using predefined inclusion and exclusion criteria. This yielded five papers for meta-analysis totaling 508 participants; 240 participants in the AR-groups and 268 participants in the control groups. (306 females/202 males). Meta-analysis showed no significant difference in anatomic test scores between the AR group and the control group (− 0.765 percentage-points (%-points); P = 0.732). Sub analysis on the use of AR vs. the use of traditional 2D teaching methods showed a significant disadvantage when using AR (− 5.685%-points; P = 0.024). Meta-regression analysis showed no significant co-relation between mean difference in test results and spatial abilities (as assessed by the mental rotations test scores). Student motivation and/or engagement could not be included since studies used different assessment tools. This meta-analysis showed that insufficient evidence is present to conclude AR significantly impacts learning outcome and that outcomes are significantly impacted by students’ spatial abilities. However, only few papers were suitable for meta-analysis, indicating that there is a need for more well-designed, randomized-controlled trials on AR in anatomy education research.

Based on the behavior of the quantum particles, it is possible to formulate mathematical expressions to develop metaheuristic search optimization algorithms. This paper presents three novel quantum-inspired algorithms, which scenario is a particle swarm that is excited by a Lorentz, Rosen–Morse, and Coulomb-like square root potential fields, respectively. To show the computational efficacy of the proposed optimization techniques, the paper presents a comparative study with the classical particle swarm optimization (PSO), genetic algorithm (GA), and firefly algorithm (FFA). The algorithms are used to solve 24 benchmark functions that are categorized by unimodal, multimodal, and fixed-dimension multimodal. As a finding, the algorithm inspired in the Lorentz potential field presents the most balanced computational performance in terms of exploitation (accuracy and precision), exploration (convergence speed and acceleration), and simulation time compared to the algorithms previously mentioned. A deeper analysis reveals that a strong potential field inside a well with weak asymptotic behavior leads to better exploitation and exploration attributes for unimodal, multimodal, and fixed-multimodal functions.

Antimicrobial resistance (AMR) is a global health emergency. Complementary to developing new drugs, AMR can be monitored and controlled through cost-effective active surveillance of resistance. As an initiative to monitor resistance, countries all across the globe are collecting data using a variety of surveillance tools. Moreover, hospitals routinely collect the AMR data for treatment which is being stored in their Laboratory and Hospital Information systems (LIS-HIS). The generated clinical data is collected & stored in various formats, making it very difficult to analyze and generate national reports. To integrate the stored clinical data for predictive modeling and analysis, there is an immediate need for a one-stop data repository capable of importing and exporting data in simple data exchange formats (CSV/Excel). The paper highlights the design & development of i-DIA, a python-based web API to facilitate the interoperability of AMR data by automatically importing the bulk of medical data from CSV files into generic data management and analysis system. The i-DIA has been integrated and tested with the ICMR’s AMR surveillance network on in-house developed software, i-AMRSS. The i-AMRSS is presently collecting data from 31 laboratories across India and i-DIA has been used to import data generated from LIS & HIS of a few hospitals directly into the system. The paper also proposes the complete web-based framework (an extension of i-DIA) integrated with peer-to-peer system architecture.

Due to the audio information of different types of vehicle models are distinct, the vehicle information can be identified by the audio signal of vehicle accurately. In real life, in order to determine the type of vehicle, we do not need to obtain the visual information of vehicles and just need to obtain the audio information. In this paper, we extract and stitching different features from different aspects: Mel frequency cepstrum coefficients in perceptual characteristics, pitch class profile in psychoacoustic characteristics and short-term energy in acoustic characteristics. In addition, we improve the neural networks classifier by fusing the LSTM unit into the convolutional neural networks. At last, we put the novel feature to the hybrid neural networks to recognize different vehicles. The results suggest the novel feature we proposed in this paper can increase the recognition rate by 7%; destroying the training data randomly by superimposing different kinds of noise can improve the anti-noise ability in our identification system; and LSTM has great advantages in modeling time series, adding LSTM to the networks can improve the recognition rate of 3.39%.

For large-scale integrated electronic equipment, the complex operating mechanisms make fault detection very difficult. Therefore, it is important to accurately identify analog circuit faults in a timely manner. To overcome this problem, this paper proposes a novel fault diagnosis method based on the deep belief network (DBN) and restricted Boltzmann machine (RBM) optimized by the gray wolf optimization (GWO) algorithm. First, DBN is used to extract the deep features of the analog circuit output signal. Then, GWO is used to optimize the penalty factor c and kernel parameter g of support vector machine (SVM). Finally, GWO-SVM is used to diagnose the signal features extracted by the DBN. Fault diagnosis simulation was conducted for the Sallen–Key band-pass filter and a four-opamp biquad highpass filter. The experimental results show that compared with the existing algorithms, the algorithm proposed in this paper improves the accuracy of Sallen–Key bandpass filter circuit to 100% and shortens the fault diagnosis time by about 90%; for four-opamp biquad highpass filter, the accuracy rate has increased to 99.68%, and the fault diagnosis time has been shortened by approximately 75%, and reduce hundreds of iterations. Moreover, the experimental results reveal that the proposed fault diagnosis method greatly improves the accuracy of analog circuit fault diagnosis, which solves a major problem in analog circuitry and has great significance for the future development of relevant applications.

In this paper, we propose graph attention based network representation (GANR) which utilizes the graph attention architecture and takes graph structure as the supervised learning information. Compared with node classification based representations, GANR can be used to learn representation for any given graph. GANR is not only capable of learning high quality node representations that achieve a competitive performance on link prediction, network visualization and node classification but it can also extract meaningful attention weights that can be applied in node centrality measuring task. GANR can identify the leading venture capital investors, discover highly cited papers and find the most influential nodes in Susceptible Infected Recovered Model. We conclude that link structures in graphs are not limited on predicting linkage itself, it is capable of revealing latent node information in an unsupervised way once a appropriate learning algorithm, like GANR, is provided.

Grand challenges have become the de facto standard for benchmarking image analysis algorithms. While the number of these international competitions is steadily increasing, surprisingly little effort has been invested in ensuring high quality design, execution and reporting for these international competitions. Specifically, results analysis and visualization in the event of uncertainties have been given almost no attention in the literature. Given these shortcomings, the contribution of this paper is two-fold: (1) we present a set of methods to comprehensively analyze and visualize the results of single-task and multi-task challenges and apply them to a number of simulated and real-life challenges to demonstrate their specific strengths and weaknesses; (2) we release the open-source framework challengeR as part of this work to enable fast and wide adoption of the methodology proposed in this paper. Our approach offers an intuitive way to gain important insights into the relative and absolute performance of algorithms, which cannot be revealed by commonly applied visualization techniques. This is demonstrated by the experiments performed in the specific context of biomedical image analysis challenges. Our framework could thus become an important tool for analyzing and visualizing challenge results in the field of biomedical image analysis and beyond.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Author(s): Dai, Mingzhi; Wang, Weiliang; Wang, Pengjun; Iqbal, Muhammad Zahir; Annabi, Nasim; Amin, Nasir | Abstract: An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Current medical screening and diagnostic procedures have shifted toward recording longer electrocardiogram (ECG) signals, which have traditionally been processed on personal computers (PCs) with high-speed multi-core processors and efficient memory processing. Battery-driven devices are now more commonly used for the same purpose and thus exploring highly efficient, low-power alternatives for local ECG signal collection and processing is essential for efficient and convenient clinical use. Several ECG compression methods have been reported in the current literature with limited discussion on the performance of the compressed and the reconstructed ECG signals in terms of the QRS complex detection accuracy. This paper proposes and evaluates different compression methods based not only on the compression ratio (CR) and percentage root-mean-square difference (PRD), but also based on the accuracy of QRS detection. In this paper, we have developed a lossy method (Methods III) and compared them to the most current lossless and lossy ECG compression methods (Method I and Method II, respectively). The proposed lossy compression method (Method III) achieves CR of 4.5×, PRD of 0.53, as well as an overall sensitivity of 99.78% and positive predictivity of 99.92% are achieved (when coupled with an existing QRS detection algorithm) on the MIT-BIH Arrhythmia database and an overall sensitivity of 99.90% and positive predictivity of 99.84% on the QT database. This work was made possible by NPRP grant #7-684-1-127 from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors. Scopus

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has not been fixed in the paper.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has been fixed in the paper.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has been fixed in the paper.

Agent-based modelling and simulation have been effectively applied to the study of complex biological systems, especially when composed by a large number of interacting entities. Representing biomolecules as autonomous agents allows this approach to bring out the global behaviour of biochemical processes as resulting from local molecular interactions. In this paper, we leverage the capabilities of the agent paradigm to construct an in silico replica of the glycolytic pathway of baker’s yeasts; the aim is to detect the role that long-range electrodynamic forces might have on the rate of glucose oxidation. Experimental evidences have shown that random encounters and short-range potentials might not be sufficient to explain the high efficiency of biochemical reactions in living cells. However, while the latest in vitro studies are limited by the present-day technology, agent-based simulations provide an in silico support to the outcomes hitherto obtained and shed light on behaviours not yet well understood. Our results reveal to be able to grasp properties hard to uncover through other computational methods, such as the effect of electromagnetic potentials on glycolytic oscillations.

In recent years, more and more deep learning frameworks are being applied to hyperspectral image classification tasks and have achieved great results. However, the existing network models have higher model complexity and require more time consumption. Traditional hyperspectral image classification methods tend to ignore the correlation between local spatial features. In this paper, a new hyperspectral image classification method is proposed, which combines two-dimensional Gabor filter with random patch convolution (GRPC) feature extraction to obtain spatial-spectral feature information. The method firstly performs dimensionality reduction through principal component analysis and linear discriminant analysis and extracts the edge texture and spatial information of the image using a Gabor filter for the reduced-dimensional image. Next, the extracted information is convolved with random patches to extract spectral features. Finally, the spatial features and multi-level spectral features are fused to classify the images using the Support Vector Machine classifier. In order to verify the performance of this method, experiments were conducted on three widely used datasets of Indian Pines, Pavia University and Kennedy Space Center. The overall classification accuracy reached 98.09%, 99.64% and 96.53%, which are all higher than other comparison methods. The experimental results reveal the superiority of the proposed method in classification accuracy.

Reservoir computing is a temporal information processing system that exploits artificial or physical dissipative dynamics to learn a dynamical system and generate the target time-series. This paper proposes the use of real superconducting quantum computing devices as the reservoir, where the dissipative property is served by the natural noise added to the quantum bits. The performance of this natural quantum reservoir is demonstrated in a benchmark time-series regression problem and a practical problem classifying different objects based on temporal sensor data. In both cases the proposed reservoir computer shows a higher performance than a linear regression or classification model. The results indicate that a noisy quantum device potentially functions as a reservoir computer, and notably, the quantum noise, which is undesirable in the conventional quantum computation, can be used as a rich computation resource.

Artificial intelligence methods such as deep neural networks promise unprecedented capabilities in healthcare, from diagnosing diseases to prescribing treatments. While this can eventually produce a valuable suite of tools for automating clinical workflows, a critical step forward is to ensure that the predictive models are reliable and to enable a rigorous introspection of their behavior. This has led to the design of explainable AI techniques that are aimed at uncovering the relationships between discernible data signatures and decisions from machine-learned models, and characterizing strengths/weaknesses of models. In this context, the so-called counterfactual explanations that synthesize small, interpretable changes to a given query sample while producing desired changes in model predictions to support user-specified hypotheses (e.g., progressive change in disease severity) have become popular. When a model’s predictions are not well-calibrated (i.e., the prediction confidences are not indicative of the likelihood of the predictions being correct), the inverse problem of synthesizing counterfactuals can produce explanations with irrelevant feature manipulations. Hence, in this paper, we propose to leverage prediction uncertainties from the learned models to better guide this optimization. To this end, we present TraCE (Training Calibration-based Explainers), a counterfactual generation approach for deep models in medical image analysis, which utilizes pre-trained generative models and a novel uncertainty-based interval calibration strategy for synthesizing hypothesis-driven explanations. By leveraging uncertainty estimates in the optimization process, TraCE can consistently produce meaningful counterfactual evidences and elucidate complex decision boundaries learned by deep classifiers. Furthermore, we demonstrate the effectiveness of TraCE in revealing intricate relationships between different patient attributes and in detecting shortcuts, arising from unintended biases, in learned models. Given the widespread adoption of machine-learned solutions in radiology, our study focuses on deep models used for identifying anomalies in chest X-ray images. Using rigorous empirical studies, we demonstrate the superiority of TraCE explanations over several state-of-the-art baseline approaches, in terms of several widely adopted evaluation metrics in counterfactual reasoning. Our findings show that TraCE can be used to obtain a holistic understanding of deep models by enabling progressive exploration of decision boundaries, detecting shortcuts, and inferring relationships between patient attributes and disease severity.

This paper proposes a method that automatically measures non-invasive blood pressure (BP) based on an auscultatory approach using Korotkoff sounds (K-sounds). There have been methods utilizing K-sounds that were more accurate in general than those using cuff pressure signals only under well-controlled environments, but most were vulnerable to the measurement conditions and to external noise because blood pressure is simply determined based on threshold values in the sound signal. The proposed method enables robust and precise BP measurements by evaluating the probability that each sound pulse is an audible K-sound based on a deep learning using a convolutional neural network (CNN). Instead of classifying sound pulses into two categories, audible K-sounds and others, the proposed CNN model outputs probability values. These values in a Korotkoff cycle are arranged in time order, and the blood pressure is determined. The proposed method was tested with a dataset acquired in practice that occasionally contains considerable noise, which can degrade the performance of the threshold-based methods. The results demonstrate that the proposed method outperforms a previously reported CNN-based classification method using K-sounds. With larger amounts of various types of data, the proposed method can potentially achieve more precise and robust results.

Motivated by the detection of cascades of defaults in economy, we developed a detection framework for an endogenous spreading based on causal motifs we define in this paper. We assume that the change of state of a vertex can be triggered by an endogenous or an exogenous event, that the underlying network is directed and that times when vertices changed their states are available. In addition to the data of company defaults, we also simulate cascades driven by different stochastic processes on different synthetic networks. We show that some of the smallest motifs can robustly detect endogenous spreading events. Finally, we apply the method to the data of defaults of Croatian companies and observe the time window in which an endogenous cascade was likely happening., Comment: 12 pages, 4 figures

Geometry images parameterise a mesh with a square domain and store the information in a single chart. A one-to-one correspondence between the 2D plane and the 3D model is convenient for processing 3D models. However, the parameterised vertices are not all located at the intersection of the gridlines the existing geometry images. Thus, errors are unavoidable when a 3D mesh is reconstructed from the chart. In this paper, we propose parameterise surface onto a novel geometry image that preserves the constraint of topological neighbourhood information at integer coordinate points on a 2D grid and ensures that the shape of the reconstructed 3D mesh does not change from supplemented image data. We find a collection of edges that opens the mesh into simply connected surface with a single boundary. The point distribution with approximate blue noise spectral characteristics is computed by capacity-constrained delaunay triangulation without retriangulation. We move the vertices to the constrained mesh intersection, adjust the degenerate triangles on a regular grid, and fill the blank part by performing a local affine transformation between each triangle in the mesh and image. Unlike other geometry images, the proposed method results in no error in the reconstructed surface model when floating-point data are stored in the image. High reconstruction accuracy is achieved when the xyz positions are in a 16-bit data format in each image channel because only rounding errors exist in the topology-preserving geometry images, there are no sampling errors. This method performs one-to-one mapping between the 3D surface mesh and the points in the 2D image, while foldovers do not appear in the 2D triangular mesh, maintaining the topological structure. This also shows the potential of using a 2D image processing algorithm to process 3D models.

Since the outbreak of COVID-19 in 2019, the rapid spread of the epidemic has brought huge challenges to medical institutions. If the pathological region in the COVID-19 CT image can be automatically segmented, it will help doctors quickly determine the patient’s infection, thereby speeding up the diagnosis process. To be able to automatically segment the infected area, we proposed a new network structure and named QC-HC U-Net. First, we combine residual connection and dense connection to form a new connection method and apply it to the encoder and the decoder. Second, we choose to add Hypercolumns in the decoder section. Compared with the benchmark 3D U-Net, the improved network can effectively avoid vanishing gradient while extracting more features. To improve the situation of insufficient data, resampling and data enhancement methods are selected in this paper to expand the datasets. We used 63 cases of MSD lung tumor data for training and testing, continuously verified to ensure the training effect of this model, and then selected 20 cases of public COVID-19 data for training and testing. Experimental results showed that in the segmentation of COVID-19, the specificity and sensitivity were 85.3% and 83.6%, respectively, and in the segmentation of MSD lung tumors, the specificity and sensitivity were 81.45% and 80.93%, respectively, without any fitting.

Sequence recognition of natural scene images has always been an important research topic in the field of computer vision. CRNN has been proven to be a popular end-to-end character sequence recognition network. However, the problem of wide characters is not considered under the setting of CRNN. The CRNN is less effective in recognizing long dense small characters. Aiming at the shortcomings of CRNN, we proposed an improved CRNN network, named CRNN-RES, based on BiLSTM and multiple receptive fields. Specifically, on the one hand, the CRNN-RES uses a dual pooling core to enhance the CNN network’s ability to extract features. On the other hand, by improving the last RNN layer, the BiLSTM is changed to a shared parameter BiLSTM network using recursive residuals, which reduces the number of network parameters and improves the accuracy. In addition, we designed a structure that can flexibly configure the length of the input data sequence in the RNN layer, called the CRFC layer. Comparing the CRNN-RES network proposed in this paper with the original CRNN network, the extensive experiments show that when recognizing English characters and numbers, the parameters of CRNN-RES is 8197549, which decreased 133,752 parameters compare with CRNN. In the public dataset ICDAR 2003 (IC03), ICDAR 2013 (IC13), IIIT 5k-word (IIIT5k), and Street View Text (SVT), the CRNN-RES obtain the accuracy of 96.90%, 89.85%, 83.63%, and 82.96%, which higher than CRNN by 1.40%, 3.15%, 5.43%, and 2.16% respectively.

This paper presents the preparation and measurement of tissue-mimicking head phantom and its validation with the iteratively corrected coherence factor delay-multiply-and-sum (IC-CF-DMAS) algorithm for brain stroke detection. The phantom elements are fabricated by using different chemical mixtures that imitate the electrical properties of real head tissues (CSF, dura, gray matter, white matter, and blood/stroke) over the frequency band of 1–4 GHz. The electrical properties are measured using the open-ended dielectric coaxial probe connected to a vector network analyzer. Individual phantom elements are placed step by step in a three-dimensional skull. The IC-CF-DMAS image reconstruction algorithm is later applied to the phantom to evaluate the effectiveness of detecting stroke. The phantom elements are preserved and measured multiple times in a week to validate the overall performance over time. The electrical properties of the developed phantom emulate the similar properties of real head tissue. Moreover, the system can also effectively detect the stroke from the developed phantom. The experimental results demonstrate that the developed tissue-mimicking head phantom is time-stable, and it shows a good agreement with the theoretical results in detecting and reconstructing the stroke images that could be used in investigating as a supplement to the real head tissue.

Applied Current Thermoacoustic Imaging (ACTAI) is a new imaging method which combines electromagnetic excitation with ultrasound imaging, and takes ultrasonic signal as medium and biological tissue conductivity as detection target. Taking the high contrast advantage of Electrical Impedance Tomography (EIT) and high resolution advantage of ultrasound imaging, ACTAI has broad application prospects in the field of biomedical imaging. Although ACTAI has high excitation efficiency and strong detectable Signal-to-Noise Ratio, yet while under low frequency electromagnetic excitation, it is still a big challenge to reconstruct a high-resolution image of target conductivity. This paper proposes a new method for reconstructing conductivity based on Generative Adversarial Network, and it consists of three main steps: firstly, use Wiener filtering deconvolution to restore the electrical signal output by the ultrasonic probe to a real acoustic signal. Then obtain the initial acoustic source image with filtered backprojection technology. Finally, match the conductivity image with the initial sound source image, which are used as training samples for generating the adversarial network to establish a deep learning model for conductivity reconstruction. After theoretical analysis and simulation research, it is found that by introducing machine learning, the new method can dig out the inverse problem solving model contained in the data, which further reconstruct a high-resolution conductivity image and has strong anti-interference characteristics. The new method provides a new way to solve the problem of conductivity reconstruction in Applied Current Thermoacoustic Imaging.

Dynamic traffic of multicast communication in the Software Defined Network environment focused less though it is more natural and practical. In multicast communication, the traffic is dynamic due to the dynamic group memberships (i.e., participants join and leave the group anytime), which are not explored much in the previous research works. The multicast in dynamic traffic requires a method to handle dynamic group membership and minimum tree alteration for every join and leave of participants from the multicast group. This paper proposes a multicast tree construction algorithm, which considers receiving devices and network capability as base parameters to construct the multicast path. The proposed routing method uses Dijkstra’s Shortest Path algorithm for initial tree formation, identifies a multicast path, and processes the Shortest Path Tree to reduce the overall hop count and path cost. The multicast tree generated by the proposed enables the dynamic join and leaves of participating devices with reduced tree alteration using more common paths to reach the devices. The implementation and results show that the proposed method works efficiently in resource utilization with a reduced hop count and quality for multicast communication in static and dynamic scenarios. Also, the results demonstrate that the proposed method generates a stable common path for multicast communication.

Wound closure with surgical sutures is a critical challenge for flexible endoscopic surgeries. Substantial efforts have been introduced to develop functional and smart surgical sutures to either monitor wound conditions or ease the complexity of knot tying. Although research interests in smart sutures by soft robotic technologies have emerged for years, it is challenging to develop a soft robotic structure that possesses a similar physical structure as conventional sutures while offering a self-tightening knot or anchor to close the wound. This paper introduces a new concept of smart sutures that can be programmed to achieve desired and uniform tension distribution while offering self-tightening knots or automatically deploying secured anchors. The core technology is a soft hydraulic artificial muscle that can be elongated and contracted under applied fluid pressure. Each suture is equipped with a pressure locking mechanism to hold its temporary elongated state and to induce self-shrinking ability. The puncturing and holding force for the smart sutures with anchors are examined. Ex-vivo experiments on fresh porcine stomach and colon demonstrate the usefulness of the new smart sutures. The new approaches are expected to pave the way for the further development of smart sutures that will benefit research, training, and commercialization in the surgical field.

This paper proposes an investigating SARS-CoV-2 inactivation on surfaces with UV-C LED irradiation using our in-house-developed ray-tracing simulator. The results are benchmarked with experiments and Zemax OpticStudio commercial software simulation to demonstrate our simulator's easy accessibility and high reliability. The tool can input the radiant profile of the flexible LED source and accurately yield the irradiance distribution emitted from an LED-based system in 3D environments. The UV-C operating space can be divided into the safe, buffer, and germicidal zones for setting up a UV-C LED system. Based on the published measurement data, the level of SARS-CoV-2 inactivation has been defined as a function of UV-C irradiation. A realistic case of public space, i.e., a food court in Singapore, has been numerically investigated to demonstrate the relative impact of environmental UV-C attenuation on the SARS-CoV-2 inactivation. We optimise a specific UV-C LED germicidal system and its corresponding exposure time according to the simulation results. These ray-tracing-based simulations provide a useful guideline for safe deployment and efficient design for germicidal UV-C LED technology.

Environmental sound classification is one of the important issues in the audio recognition field. Compared with structured sounds such as speech and music, the time–frequency structure of environmental sounds is more complicated. In order to learn time and frequency features from Log-Mel spectrogram more effectively, a temporal-frequency attention based convolutional neural network model (TFCNN) is proposed in this paper. Firstly, an experiment that is used as motivation in proposed method is designed to verify the effect of a specific frequency band in the spectrogram on model classification. Secondly, two new attention mechanisms, temporal attention mechanism and frequency attention mechanism, are proposed. These mechanisms can focus on key frequency bands and semantic related time frames on the spectrogram to reduce the influence of background noise and irrelevant frequency bands. Then, a feature information complementarity is formed by combining these mechanisms to more accurately capture the critical time–frequency features. In such a way, the representation ability of the network model can be greatly improved. Finally, experiments on two public data sets, UrbanSound 8 K and ESC-50, demonstrate the effectiveness of the proposed method.