Sequential Modules Research Articles

Sequential treatment with a TNFR2 agonist and a TNFR1 antagonist improves outcomes in a humanized mouse model for MS

TNF signaling is an essential regulator of cellular homeostasis. Through its two receptors TNFR1 and TNFR2, soluble versus membrane-bound TNF enable cell death or survival in a variety of cell types. TNF-TNFRs signaling orchestrates important biological functions such as inflammation, neuronal activity as well as tissue de- and regeneration. TNF-TNFRs signaling is a therapeutic target for neurodegenerative diseases such as multiple sclerosis (MS) and Alzheimer’s disease (AD), but animal and clinical studies yielded conflicting findings. Here, we ask whether a sequential modulation of TNFR1 and TNFR2 signaling is beneficial in experimental autoimmune encephalomyelitis (EAE), an experimental mouse model that recapitulates inflammatory and demyelinating aspects of MS. To this end, human TNFR1 antagonist and TNFR2 agonist were administered peripherally at different stages of disease development in TNFR-humanized mice. We found that stimulating TNFR2 before onset of symptoms leads to improved response to anti-TNFR1 therapeutic treatment. This sequential treatment was more effective in decreasing paralysis symptoms and demyelination, when compared to single treatments. Interestingly, the frequency of the different immune cell subsets is unaffected by TNFR modulation. Nevertheless, treatment with only a TNFR1 antagonist increases T-cell infiltration in the central nervous system (CNS) and B-cell cuffing at the perivascular sites, whereas a TNFR2 agonist promotes Treg CNS accumulation. Our findings highlight the complicated nature of TNF signaling which requires a timely balance of selective activation and inhibition of TNFRs in order to exert therapeutic effects in the context of CNS autoimmunity.

Relaxed Effective Callback Freedom: A Parametric Correctness Condition for Sequential Modules With Callbacks

Callbacks are an essential mechanism for event-driven programming. Unfortunately, callbacks make reasoning challenging because they introduce behaviors where calls to the module are interleaved. We present a parametric method that, from a particular invariant of the program, allows reducing the problem of verifying the invariant in the presence of callbacks, to the callback-free setting. Intuitively, we allow callbacks to introduce behaviors that cannot be produced by callback free executions, as long as they do not affect correctness. A chief insight is that the user is aware of the potential effect of the callbacks on the program state. To this end, we present a parametric verification technique which accepts this insight as a relation between callback and callback free executions. We implemented our approach and applied it successfully to a large set of real-world programs.

Benefits of repeated alternations – Task-specific vs. task-general sequential adjustments of dual-task order control

An important cognitive requirement in multitasking is the decision of how multiple tasks should be temporally scheduled (task order control). Specifically, task order switches (vs. repetitions) yield performance costs (i.e., task-order switch costs), suggesting that task order scheduling is a vital part of configuring a task set. Recently, it has been shown that this process takes specific task-related characteristics into account: task order switches were easier when switching to a preferred (vs. non-preferred) task order. Here, we ask whether another determinant of task order control, namely the phenomenon that a task order switch in a previous trial facilitates a task order switch in a current trial (i.e., a sequential modulation of task order switch effect) also takes task-specific characteristics into account. Based on three experiments involving task order switches between a preferred (dominant oculomotor task prior to non-dominant manual/pedal task) and a non-preferred (vice versa) order, we replicated the finding that task order switching (in Trial N) is facilitated after a previous switch (vs. repetition in Trial N - 1) in task order. There was no substantial evidence in favor of a significant difference when switching to the preferred vs. non-preferred order and in the analyses of the dominant oculomotor task and the non-dominant manual task. This indicates different mechanisms underlying the control of immediate task order configuration (indexed by task order switch costs) and the sequential modulation of these costs based on the task order transition type in the previous trial.

MS-Net: Learning to assess the malignant status of a lung nodule by a radiologist and her peers.

Automatically assessing the malignant status of lung nodules based on CTscan images can help reduce the workload of radiologists while improving their diagnostic accuracy. Despite remarkable progress in the automatic diagnosis of pulmonary nodules by deep learning technologies, two significant problems remain outstanding. First, end-to-end deep learning solutions tend to neglect the empirical (semantic) features accumulated by radiologists and only rely on automatic features discovered by neural networks to provide the final diagnostic results, leading to questionable reliability, and interpretability. Second, inconsistent diagnosis between radiologists, a widely acknowledged phenomenon in clinical settings, is rarely examined and quantitatively explored by existing machine learning approaches. This paper solves these problems. We propose a novel deep neural network called MS-Net, which comprises two sequential modules: A feature derivation and initial diagnosis module (FDID), followed by a diagnosis refinement module (DR). Specifically, to take advantage of accumulated empirical features and discovered automatic features, the FDID model of MS-Net first derives a range of perceptible features and provides two initial diagnoses for lung nodules; then, these results are fed to the subsequent DR module to refine the diagnoses further. In addition, to fully consider the individual and panel diagnosis opinions, we propose a new loss function called collaborative loss, which can collaboratively optimize the individual and her peers' opinions to provide a more accurate diagnosis. We evaluate the performance of the proposed MS-Net on the Lung Image Database Consortium image collection (LIDC-IDRI). It achieves 92.4% of accuracy, 92.9% of sensitivity, and 92.0% of specificity when panel labels are the ground truth, which is superior to other state-of-the-art diagnosis models. As a byproduct, the MS-Net can automatically derive a range of semantic features of lung nodules, increasing the interpretability of the final diagnoses. The proposed MS-Net can provide an automatic and accurate diagnosis of lung nodules, meeting the need for a reliable computer-aided diagnosis system in clinical practice.

Early motor skill acquisition in healthy older adults: brain correlates of the learning process.

Motor skill learning is a crucial process at all ages. However, healthy aging is often accompanied by a reduction in motor learning capabilities. This study characterized the brain dynamics of healthy older adults during motor skill acquisition and identified brain regions associated with changes in different components of performance. Forty-three subjects participated in a functional magnetic resonance imaging study during which they learned a sequential grip force modulation task. We evaluated the continuous changes in brain activation during practice as well as the continuous performance-related changes in brain activation. Practice of the motor skill was accompanied by increased activation in secondary motor and associative areas. In contrast, visual and frontal areas were less recruited as task execution progressed. Subjects showed significant improvements on the motor skill. While faster execution relied on parietal areas and was inversely associated with frontal activation, accuracy was related to activation in primary and secondary motor areas. Better performance was achieved by the contribution of parietal regions responsible for efficient visuomotor processing and cortical motor regions involved in the correct action selection. The results add to the understanding of online motor learning in healthy older adults, showing complementary roles of specific networks for implementing changes in precision and speed.

An efficient automated vehicle license plate recognition system under image processing

<span lang="EN-US">An automated vehicle license plate recognition system using image processing techniques identifies vehicle numbers without human interference. This system has significant impact because of its good application in various fields like car parking, access control, speed control, automatic toll collection, border security, traffic violence detection and surveillance applications. This paper presents a methodology that is quite simple but at the same time very much efficient and this system consists of four sequential modules which are preprocessing, number plate extraction, number plate character segmentation and character recognition. Preprocessing aims to improve the image quality that is captured in various illumination conditions and stick out outstanding information that we need, which is favorable to subsequent processing including extraction, segmentation and recognition. After preprocessing various morphological operations are applied to extract the desired license plate region. Then for segmentation the bounding box method is applied that segments each letter and number present on the license plate region. Finally, template matching is applied in identifying all segmented characters present in the license plate image. The experimental results showed that the proposed system can recognize license plate characters efficiently with higher accuracy. Using MATLAB software, the proposed method attains recognition accuracy of 94.17%.</span>

Registration of 3D medical images based on unsupervised cooperative cascade of deep networks

In this paper, a deformable registration network (DR-Net) and a multi-scale cascading strategy are designed for the registration of largely deformed 3D medical images. Our DR-Net appears as a U-shaped convolutional neural network with a pyramidal input module (PIM), a light weighted sequential Inception module and an SCAM convolutional attention module. Our multi-scale cooperative cascading strategy integrates the deformation field information within and between sub-networks at different scales to synthesize the cascaded deformation fields. To cooperatively train the cascaded network, not only the output of the final network layer but also the multi-scale outputs from different layers of the decoder in the last cascaded sub-network are used to calculate loss function. As compared with the VoxelMorph and IVTN, the average dice similarity coefficients (Dice) achieved with our DR-Net are 2.4% and 2.5% higher on the Sliver dataset and are 2.5% and 2.4% higher on the LiTS dataset. The average Dice coefficients achieved with our multi-scale cascading strategy of three DR-Nets are 1.6% and 1.9% higher than those of the VM-CR3 and are 1.5% and 1.7% higher than those of the IVTN-CR3 on these two datasets, respectively. These results show that not only our proposed DR-Net itself but also the cascade of them outperform the state-of-the-art methods and their cascades in registration accuracy.

SIIS-SLAM: A Vision SLAM Based on Sequential Image Instance Segmentation

Simultaneous localization and mapping (SLAM) is a fundamental function of intelligent robots. To reduce the influence of dynamic objects on SLAM in dynamic environments, this study pro-poses a visual SLAM based on sequential image segmentation, referred to as SIIS-SLAM. Based on ORB-SLAM3, SIIS-SLAM integrates the sequential image instance segmentation and optical flow dynamic detection module. The sequential image segmentation module is designed to eliminate the effectiveness of dynamic objects in the estimation of relative pose between sequential frames. Specifically, based on the coarse relative pose estimated by ORB-SLAM3 and the box coordinates of instances detected by Mask R-CNN, the sequential image segmentation module effectively improves the speed and accuracy of instance segmentation. Dynamic objects can be effectively detected by combining the instance segmentation results and optical flow module. Filtering the feature points in dynamic objects can improve the accuracy and robustness of SLAM. Experimental results demonstrate that SIIS-SLAM achieves the better accuracy in dynamic environments compared to ORB SLAM3 and other advanced methods.

Collaborative Multilingual Continuous Sign Language Recognition: A Unified Framework

Current continuous sign language recognition systems generally target on a single language. When it comes to the multilingual problem, existing solutions often build separate models based on the same network and then train them with their corresponding sign language corpora. Observing that different sign languages share some low-level visual patterns, we argue that it is beneficial to optimize the recognition model in a collaborative way. With this motivation, we propose the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">first</i> unified framework for multilingual continuous sign language recognition. Our framework consists of a shared visual encoder for visual information encoding, multiple language-dependent sequential modules for long-range temporal dependency learning aimed at different languages, and a universal sequential module to learn the commonality of all languages. An additional language embedding is introduced to distinguish different languages within the shared temporal encoders. Further, we present a max-probability decoding method to obtain the alignment between sign videos and sign words for visual encoder refinement. We evaluate our approach on three continuous sign language recognition benchmarks, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.,</i> RWTH-PHOENIX-Weather, CSL and GSL-SD. The experimental results reveal that our method outperforms the individually trained recognition models. Our method also demonstrates better performance compared with state-of-the-art algorithms.

Network Pharmacology-Based Identification of Key Targets of Ziyin Mingmu Pills Acting on Age-Related Macular Degeneration.

This study is designed to find out the molecular targets of effective Chinese medicine Ziyin Mingmu pills (ZMPs) in treating age-related macular degeneration (AMD) based on network pharmacology and experimental data. A comprehensive network pharmacology strategy that consists of three sequential modules (drug-disease target molecular docking, enrichment analysis, and external verification) was carried out to identify potential targets of ZMPs acting on AMD. The active ingredients of ZMPs targeting 66 genes have effects on the process of AMD. GO and KEGG pathway enrichment analyses suggested that response to oxidative stress, regulation of angiogenesis, and lipid and atherosclerosis might serve as the most important signaling pathways in ZMPs for AMD treatment. Combined with the GSE29801 dataset for further analysis, two key genes, EGFR and VEGFA, were identified. Immune infiltration analysis showed that there was a strong association between EGFR and immune cell content. In addition, images were acquired following 24 h in the scratch experiment showed that ZMPs can reduce the percentage of wound healing distance. The Western blot assay found that ZMPs increased the expression of EGFR and decreased the expression of VEGFA. This study sheds light on some mechanisms of ZMP therapy for AMD, particularly the effect of ZMP on the oxidative stress in RPE and cell survival and angiogenesis in AMD. We propound ZMPs as a promising strategy to intervene in the process of AMD.

Very Lightweight Photo Retouching Network With Conditional Sequential Modulation

Photo retouching aims at improving the aesthetic visual quality of images that suffer from photographic defects, especially for poor contrast, over/under exposure, and inharmonious saturation. In practice, photo retouching can be accomplished by a series of image processing operations. As most commonly-used retouching operations are pixel-independent, i.e., the manipulation on one pixel is uncorrelated with its neighboring pixels, we can take advantage of this property and design a specialized algorithm for efficient global photo retouching. We analyze these global operations and find that they can be mathematically formulated by a Multi-Layer Perceptron (MLP). Based on this observation, we propose an extremely lightweight framework -- Conditional Sequential Retouching Network (CSRNet). Benefiting from the utilization of $1\times1$ convolution, CSRNet only contains less than 37K trainable parameters, which are orders of magnitude smaller than existing learning-based methods. Experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. In addition to achieve global photo retouching, the proposed framework can be easily extended to learn local enhancement effects. The extended model, namely CSRNet-L, also achieves competitive results in various local enhancement tasks. Codes are available at https://github.com/lyh-18/CSRNet.

Impaired Human Cardiac Cell Development due to NOTCH1 Deficiency.

NOTCH1 pathogenic variants are implicated in multiple types of congenital heart defects including hypoplastic left heart syndrome, where the left ventricle is underdeveloped. It is unknown how NOTCH1 regulates human cardiac cell lineage determination and cardiomyocyte proliferation. In addition, mechanisms by which NOTCH1 pathogenic variants lead to ventricular hypoplasia in hypoplastic left heart syndrome remain elusive. CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats)/Cas9 genome editing was utilized to delete NOTCH1 in human induced pluripotent stem cells. Cardiac differentiation was carried out by sequential modulation of WNT signaling, and NOTCH1 knockout and wild-type differentiating cells were collected at day 0, 2, 5, 10, 14, and 30 for single-cell RNA-seq. Human NOTCH1 knockout induced pluripotent stem cells are able to generate functional cardiomyocytes and endothelial cells, suggesting that NOTCH1 is not required for mesoderm differentiation and cardiovascular development in vitro. However, disruption of NOTCH1 blocks human ventricular-like cardiomyocyte differentiation but promotes atrial-like cardiomyocyte generation through shortening the action potential duration. NOTCH1 deficiency leads to defective proliferation of early human cardiomyocytes, and transcriptomic analysis indicates that pathways involved in cell cycle progression and mitosis are downregulated in NOTCH1 knockout cardiomyocytes. Single-cell transcriptomic analysis reveals abnormal cell lineage determination of cardiac mesoderm, which is manifested by the biased differentiation toward epicardial and second heart field progenitors at the expense of first heart field progenitors in NOTCH1 knockout cell populations. NOTCH1 is essential for human ventricular-like cardiomyocyte differentiation and proliferation through balancing cell fate determination of cardiac mesoderm and modulating cell cycle progression. Because first heart field progenitors primarily contribute to the left ventricle, we speculate that pathogenic NOTCH1 variants lead to biased differentiation of first heart field progenitors, blocked ventricular-like cardiomyocyte differentiation, and defective cardiomyocyte proliferation, which collaboratively contribute to left ventricular hypoplasia in hypoplastic left heart syndrome.

Dynamic iterative method for sequential module steady-state modeling and its application to the fluid catalytic cracking unit

BackgroundProcess modeling of chemical systems has important directive significance to the analysis and optimization of actual production processes and the improvement of economic efficiency. However, existing iterative methods struggle with initial value selection and lack of generality when applied in modeling with the sequential module method, making it challenging to solve both unconstrained and constrained iterative problems in the modeling. Therefore, it is necessary to design a new iterative method. MethodsA dynamic iterative method for sequential module steady-state modeling is proposed. The sequential module method is used to establish a steady-state sequential model of a chemical system, and a dynamic feedback link is added outside the model. This feedback link can make its iterative output converge to the next step system output by learning the deviation between two or more steps in the iterative process, thus ensuring the convergence of the process modeling and improving the iteration speed of the modeling. In order to improve the generality of the dynamic iterative method and reduce the difficulty of selecting the initial value of iteration, both proportional and integral actions are added to this method according to the principle of automatic control. Significant FindingsThe modeling results show that adding dynamic feedback links outside the model effectively resolved the algebraic loop problem and improved the speed of system convergence. The inclusion of both proportional and integral actions in the dynamic iterative method effectively reduced the sensitivity to initial value and improved the generality of the method. This method is applied to the fluid catalytic cracking unit reaction-regeneration system and its effectiveness is demonstrated by solving both unconstrained and constrained iterative problems.

Two Novel Pyrene Tetra-Sulfonate Europium Coordination Polymers: Structure Formation Mechanism Analysis and Sequential Modulation Strategy

For the purpose of broadening the understanding of the sulfonic acid coordination mechanism, a coordination system consisting of Eu(III) ion and 1,3,6,8-pyrene tetra-sulfonate (1,3,6,8-PTS) ligand was chosen as the typical research object. By step regulating the volume ratio of mixed solvents and the molar ratio of metal salts to ligands, two pyrene tetra-sulfonate europium coordination polymers, Eu6(μ6-O)(μ3-OH)8(NO3)6(1,3,6,8-H2PTS)(H2O)10 (1) and Eu(NO3)(1,3,6,8-PTS)0.5(H2O)3·0.5bipy (2), were obtained in sequence. Compound 1 shows a 1D chain-like structure interconnected with 1,3,6,8-PTS bridging ligands and rare [Eu6(μ6-O)(μ3-OH)8(NO3)6]2+ cluster nodes, while compound 2 shows a 2D layered structure. Further structural comparison with compound Eu(1,3,6,8-PTS)(H2O)7·4H2O·Hbipy (EuPTSbp-1) was discussed in detail and the structure formation mechanism was analyzed. On this basis, a sequential modulation strategy for pyrene tetra-sulfonate europium coordination polymers was proposed.

Static and Dynamic Isolated Indian and Russian Sign Language Recognition with Spatial and Temporal Feature Detection Using Hybrid Neural Network

The Sign Language Recognition system intends to recognize the Sign language used by the hearing and vocally impaired populace. The interpretation of isolated sign language from static and dynamic gestures is a difficult study field in machine vision. Managing quick hand movement, facial expression, illumination variations, signer variation, and background complexity are amongst the most serious challenges in this arena. While deep learning-based models have been used to accomplish the entirety of the field's state-of-the-art outcomes, the previous issues have not been fully addressed. To overcome these issues, we propose a Hybrid Neural Network Architecture for the recognition of Isolated Indian and Russian Sign Language. In the case of static gesture recognition, the proposed framework deals with the 3D Convolution Net with an atrous convolution mechanism for spatial feature extraction. For dynamic gesture recognition, the proposed framework is an integration of semantic spatial multi-cue feature detection, extraction, and Temporal-Sequential feature extraction. The semantic spatial multi-cue feature detection and extraction module help in the generation of feature maps for Full-frame, pose, face, and hand. For face and hand detection, GradCam and Camshift algorithm have been used. The temporal and sequential module consists of a modified auto-encoder with a GELU activation function for abstract high-level feature extraction and a hybrid attention layer. The hybrid attention layer is an integration of segmentation and spatial attention mechanism. The proposed work also involves creating a novel multi-signer, single, and double-handed Isolated Sign representation dataset for Indian and Russian Sign Language. The experimentation was done on the novel dataset created. The accuracy obtained for Static Isolated Sign Recognition was 99.76%, and the accuracy obtained for Dynamic Isolated Sign Recognition was 99.85%. We have also compared the performance of our proposed work with other baseline models with benchmark datasets, and our proposed work proved to have better performance in terms of Accuracy metrics.

On-Chip Single-Cell Bioelectrical Analysis for Identification of Cell Electrical Phenotyping in Response to Sequential Electric Signal Modulation.

In recent years, an interesting biomarker called membrane breakdown voltage has been examined using artificial planar lipid bilayers. Even though they have great potential to identify cell electrical phenotyping for distinguishing similar cell lines or cells under different physiological conditions, the biomarker has not been evaluated in the context of living cell electrical phenotyping. Herein, we present a single-cell analysis platform to continuously measure the electric response in a large number of cells in parallel using electric frequency and voltage variables. Using this platform, we measured the direction of cell displacement and transparent cell image alteration as electric polarization of the cell responds to signal modulation, extracting the dielectrophoretic crossover frequency and membrane breakdown voltage for each cell, and utilizing the measurement results in the same spatiotemporal environment. We developed paired parameters using the dielectrophoretic crossover frequency and membrane breakdown voltage for each cell and evaluated the paired parameter efficiency concerning the identification of two different breast cancer cells and cell drug response. Moreover, we showed that the platform was able to identify cell electrical phenotyping, which was generated by subtle changes in cholesterol depletion-induced cell membrane integrity disruption when the paired parameter was used. Our platform introduced in this paper is extremely useful for facilitating more accurate and efficient evaluation of cell electrical phenotyping in a variety of applications, such as cell biology and drug discovery.

Structure-Informed Graph Learning of Networked Dependencies for Online Prediction of Power System Transient Dynamics

Online transient analysis plays an increasingly important role in dynamic power grids as the renewable generation continues growing. Traditional numerical methods for transient analysis not only are computationally intensive but also require precise contingency information as input, and therefore, are not suitable for online applications. Existing online transient assessment studies focus on the determination of post-contingency system stability or stability margin. This paper develops a novel graph-learning framework, Deep-learning Neural Representation or DNR, for online prediction, of the time-series trajectories of the system states using initial system responses that can be measured by phasor measurement units (PMUs). The proposed DNR framework consists of two sequential modules: a Network Constructor that captures network dependencies among generators, and a Dynamics Predictor that predicts the system trajectories. The key to improved prediction performance is the introduction of the spatio-temporal message-passing operations into graph neural networks with structural knowledge. Its effectiveness and scalability are validated through comparative studies, demonstrating the prediction performance under different contingency scenarios for systems of different sizes. This framework provides a solution to online predicting post-fault system dynamics based on real-time PMU measurements. Additionally, it can also be applied to facilitate the offline transient simulation without simulating the entire trajectories.

Anomaly Detection of Metro Station Tracks Based on Sequential Updatable Anomaly Detection Framework

The intrusion of foreign objects in tracks, one of the sources of injuries and fatalities in metro stations, can be solved as an anomaly detection task. However, the existing anomaly detection methods rarely consider the importance of updating the new knowledge from false alarm data, resulting in repeated mistakes. These methods are also impractical for edge devices that cannot afford the high calculation cost. A sequential updatable anomaly detection (SUAD) framework is proposed to tackle these problems. This framework is based on the Robbin-Monro algorithm and a fast version of Mahalanobis distance. A well-trained model of SUAD can continue to learn new knowledge through the sequential knowledge update module based on the Robbin-Monro algorithm without reviewing the old data. SUAD utilizes a new Mahalanobis distance calculation method based on principal component analysis. This new method exhibits a fast inference speed with a lighter model size than before. SUAD is evaluated on a self-built Metro Anomaly Detection (MAD) dataset and three public datasets. SUAD achieves an average area under the receiver operating characteristic curve score of 99.4% at image level and 99.6% at pixel level on MAD. SUAD also reduces at least 78% model size and 60% memory usage. Competitive results are also achieved in public datasets, including MVTec AD, beanTech Anomaly Detection, and CIFAR-10.

Adaption and Evaluation of a Self-Efficacy Intervention for Parental Feeding Practices

Background: A healthy parental feeding program consisting of six sequential modules was developed to improve parental feeding behaviours. The six modules focusing on various parental feeding behaviours were found to be moderately effective in changing behaviour. In this study, one of those modules (the self-efficacy module) was systematically adapted and evaluated using Intervention Mapping (IM).Methods: In a literature review (Study 1), the relevance of self-efficacy as a determinant for parental feeding habits was examined. In study 2, the behaviour change techniques used in the original healthy parental feeding program were analysed and adapted to fulfil the related parameters of effectiveness. In study 3, the effectiveness of the new module was pilot-tested among parents (N= 27). Parents received either the original self-efficacy module (group 1), the adapted self-efficacy module (group 2), or no additional module (group 3/control-group). Parental self-efficacy was measured at baseline, post-intervention and at one-week follow-up.Results: In study 1, self-efficacy was identified as a relevant (i.e., important and changeable) determinant for parental feeding habits. In study 2, parameters for effectiveness of the used behaviour change techniques were added where necessary, and texts were changed to improve understanding. In study 3, both the original and new module appeared to increase self-efficacy compared to the no-intervention control group.Discussion: This study was an attempt to adapt existing behaviour change programs based on theory and evidence. However, we were not successful in changing self-efficacy more as compared to the original module.

Arrhythmia Classification and Diagnosis Based on ECG Signal: A Multi-Domain Collaborative Analysis and Decision Approach

Electrocardiogram (ECG) signal plays a key role in the diagnosis of arrhythmia, which will pose a great threat to human health. As an effective feature extraction method, deep learning has shown excellent results in processing ECG signals. However, most of these methods neglect the cooperation between the multi-lead ECG series correlation and intra-series temporal patterns. In this work, a multi-domain collaborative analysis and decision approach is proposed, which makes the classification and diagnosis of arrhythmia more accurate. With this decision, we can realize the transition from the spatial domain to the spectral domain, and from the time domain to the frequency domain, and make it possible that ECG signals can be more clearly detected by convolution and sequential learning modules. Moreover, instead of the prior method, the self-attention mechanism is used to learn the relation matrix between the sequences automatically in this paper. We conduct extensive experiments on eight advanced models in the same field to demonstrate the effectiveness of our method.