Multiple feature selection based on an optimization strategy for causal analysis of health data.

Purpose: Recent advancements in information technology and wearable devices have revolutionized healthcare through health data analysis. Identifying significant relationships in complex health data enhances healthcare and public health strategies. In health analytics, causal graphs are important for investigating the relationships among health features.

Species-specific model based on sequence and structural information for ubiquitination sites prediction.

Ubiquitination is a common post-translational modification of proteins in eukaryotic cells, and it is also a significant method of regulating protein biological function. Computational methods for predicting ubiquitination sites can serve as a cost-effective and time-saving alternative to experimental methods. Existing computational methods often build classifiers based on protein sequence information, physical and chemical properties of amino acids, evolutionary information, and structural parameters.

Weighted gene co-expression network analysis and single-cell sequence analysis uncover immune landscape and reveal hub genes of necroptosis in macrophages in myocardial ischaemia-reperfusion injury.

Myocardial ischaemia-reperfusion injury (MIRI) caused by the treatment of acute myocardial infarction (AMI) is the primary cause of severe ventricular remodelling, heart failure (HF), and high mortality. In recent studies, research on the role of necroptosis in MIRI has focused on cardiomyocytes, but new biomarkers and immunocyte mechanisms of necroptosis are rarely studied. In the present study, weighted gene co-expression network analysis (WGCNA) algorithms were used to establish a weighted gene co-expression network, and Casp1, Hpse, Myd88, Ripk1, and Tpm3 were identified as biological markers of necroptosis using least absolute shrinkage, selection operator (LASSO) regression and support vector machine (SVM) feature selection algorithms.

Blinding and blurring the multi-object tracker with adversarial perturbations.

Adversarial attack reveals a potential imperfection in deep models that they are susceptible to being tricked by imperceptible perturbations added to images. Recent deep multi-object trackers combine the functionalities of detection and association, rendering attacks on either the detector or the association component an effective means of deception. Existing attacks focus on increasing the frequency of ID switching, which greatly damages tracking stability, but is not enough to make the tracker completely ineffective.

Reconstructed Graph Neural Network With Knowledge Distillation for Lightweight Anomaly Detection.

The proliferation of Internet-of-Things (IoT) technologies in modern smart society enables massive data exchange for offering intelligent services. It becomes essential to ensure secure communications while exchanging highly sensitive IoT data efficiently, which leads to high demands for lightweight models or algorithms with limited computation capability provided by individual IoT devices. In this study, a graph representation learning model, which seamlessly incorporates graph neural network (GNN) and knowledge distillation (KD) techniques, named reconstructed graph with global-local distillation (RG-GLD), is designed to realize the lightweight anomaly detection across IoT communication networks.

On-Chip Micro Temperature Controllers Based on Freestanding Thermoelectric Nano Films for Low-Power Electronics.

Multidimensional integration and multifunctional component assembly have been greatly explored in recent years to extend Moore's Law of modern microelectronics. However, this inevitably exacerbates the inhomogeneity of temperature distribution in microsystems, making precise temperature control for electronic components extremely challenging. Herein, we report an on-chip micro temperature controller including a pair of thermoelectric legs with a total area of 50 × 50 μm, which are fabricated from dense and flat freestanding BiTe-based thermoelectric nano films deposited on a newly developed nano graphene oxide membrane substrate.

Information Theoretic Learning-Enhanced Dual-Generative Adversarial Networks With Causal Representation for Robust OOD Generalization.

Recently, machine/deep learning techniques are achieving remarkable success in a variety of intelligent control and management systems, promising to change the future of artificial intelligence (AI) scenarios. However, they still suffer from some intractable difficulty or limitations for model training, such as the out-of-distribution (OOD) issue, in modern smart manufacturing or intelligent transportation systems (ITSs). In this study, we newly design and introduce a deep generative model framework, which seamlessly incorporates the information theoretic learning (ITL) and causal representation learning (CRL) in a dual-generative adversarial network (Dual-GAN) architecture, aiming to enhance the robust OOD generalization in modern machine learning (ML) paradigms.

AffinityVAE: A multi-objective model for protein-ligand affinity prediction and drug design.

In the prediction of protein-ligand affinity, the traditional methods require a large amount of computing resources, and have certain limitations in predicting and simulating the structural changes. Although employing data-driven approaches can yield favorable outcomes in deep learning, it entails a lack of interpretability. Some methods may require additional structural information or domain knowledge to support the interpretation, which may limit their applicability.

Flexible Carbon Nanotube-Epitaxially Grown Nanocrystals for Micro-Thermoelectric Modules.

Flexible thermoelectric materials have attracted increasing interest because of their potential use in thermal energy harvesting and high-spatial-resolution thermal management. However, a high-performance flexible micro-thermoelectric device (TED) compatible with the microelectronics fabrication process has not yet been developed. Here a universal epitaxial growth strategy is reported guided by 1D van der Waals-coupling, to fabricate freestanding and flexible hybrids comprised of single-wall carbon nanotubes and ordered (Bi,Sb) Te nanocrystals.

CDNet: Contrastive Disentangled Network for Fine-Grained Image Categorization of Ocular B-Scan Ultrasound.

Precise and rapid categorization of images in the B-scan ultrasound modality is vital for diagnosing ocular diseases. Nevertheless, distinguishing various diseases in ultrasound still challenges experienced ophthalmologists. Thus a novel contrastive disentangled network (CDNet) is developed in this work, aiming to tackle the fine-grained image categorization (FGIC) challenges of ocular abnormalities in ultrasound images, including intraocular tumor (IOT), retinal detachment (RD), posterior scleral staphyloma (PSS), and vitreous hemorrhage (VH).

Effectiveness, Policy, and User Acceptance of COVID-19 Contact-Tracing Apps in the Post-COVID-19 Pandemic Era: Experience and Comparative Study.

Background: In the post-COVID-19 pandemic era, many countries have launched apps to trace contacts of COVID-19 infections. Each contact-tracing app (CTA) faces a variety of issues owing to different national policies or technologies for tracing contacts.

Objective: In this study, we aimed to investigate all the CTAs used to trace contacts in various countries worldwide, including the technology used by each CTA, the availability of knowledge about the CTA from official websites, the interoperability of CTAs in various countries, and the infection detection rates and policies of the specific country that launched the CTA, and to summarize the current problems of the apps based on the information collected.

A Self-Supervised Learning Based Framework for Eyelid Malignant Melanoma Diagnosis in Whole Slide Images.

Eyelid malignant melanoma (MM) is a rare disease with high mortality. Accurate diagnosis of such disease is important but challenging. In clinical practice, the diagnosis of MM is currently performed manually by pathologists, which is subjective and biased.

Recombinant EGFL7 Mitigated Pressure Overload-Induced Cardiac Remodeling by Blocking PI3K /AKT/ Signaling in Macrophages.

Inflammation and endothelial dysfunction play an essential role in heart failure (HF). Epidermal growth factor-like protein 7 (EGFL7) is upregulated during pathological hypoxia and exerts a protective role. However, it is unclear whether there is a link between abnormal EGFL7 expression and inflammation in overload stress-induced heart failure.

Research progress on multicomponent physical exercise for patients with neurocognitive impairment.

Neurocognitive impairment is a group of clinical syndromes characterized by impaired cognitive function and decreased motor ability. Non-pharmacological interventions such as physical exercise have advantages in the treatment of patients with neurocognitive impairment. Multicomponent exercise is a combination of various physical exercises, including strength training, endurance training, balance training and flexibility training, that can improve gait, balance and cardiopulmonary function by increasing muscle mass, strength and endurance in people with neurocognitive impairment, while also reducing the risk of falls in elders.

Analysis on the Subdivision of Skilled Mowing Movements on Slopes.

Owing to the aging of the rural population in the hilly and mountainous areas of Japan, mowing on narrow ridges and steep slopes is done manually by the elderly-individuals over 65 years of age. Studies have shown that many accidents that occurred during mowing were caused by workers' unstable posture, especially when mowing on steep surfaces where there is a high risk of falling. It is necessary to analyze the body movements of mowing workers to elucidate the elements related to the risk of falls.

AGMB-Transformer: Anatomy-Guided Multi-Branch Transformer Network for Automated Evaluation of Root Canal Therapy.

Accurate evaluation of the treatment result on X-ray images is a significant and challenging step in root canal therapy since the incorrect interpretation of the therapy results will hamper timely follow-up which is crucial to the patients' treatment outcome. Nowadays, the evaluation is performed in a manual manner, which is time-consuming, subjective, and error-prone. In this article, we aim to automate this process by leveraging the advances in computer vision and artificial intelligence, to provide an objective and accurate method for root canal therapy result assessment.

Multiscale Attention Guided Network for COVID-19 Diagnosis Using Chest X-Ray Images.

Coronavirus disease 2019 (COVID-19) is one of the most destructive pandemic after millennium, forcing the world to tackle a health crisis. Automated lung infections classification using chest X-ray (CXR) images could strengthen diagnostic capability when handling COVID-19. However, classifying COVID-19 from pneumonia cases using CXR image is a difficult task because of shared spatial characteristics, high feature variation and contrast diversity between cases.

S-Nitrosylation of Akt by organic nitrate delays revascularization and the recovery of cardiac function in mice following myocardial infarction.

The effects of long-term nitrate therapy are compromised due to protein S-Nitrosylation, which is mediated by nitric oxide (NO). This study is to determine the role of Akt S-Nitrosylation in the recovery of heart functions after ischaemia. In recombinant Akt protein and in HEK293 cells, NO donor decreased Akt activity and induced Akt S-Nitrosylation, but was abolished if Akt protein was mutated by replacing cysteine 296/344 with alanine (Akt-C296/344A).

Learning misclassification costs for imbalanced classification on gene expression data.

Background: Cost-sensitive algorithm is an effective strategy to solve imbalanced classification problem. However, the misclassification costs are usually determined empirically based on user expertise, which leads to unstable performance of cost-sensitive classification. Therefore, an efficient and accurate method is needed to calculate the optimal cost weights.

Tailoring Nanoporous Structures in BiTe Thin Films for Improved Thermoelectric Performance.

Thin-film thermoelectrics (TEs) with unique advantages have triggered great interest in thermal management and energy harvesting technology for ambient temperature microscale systems. Although they have exhibited a good prospect, their unsatisfactory performances still seriously hamper their widespread application. Tailoring the porous structure has been demonstrated to be a facile strategy to significantly reduce thermal conductivity and enhance the figure of merit () of bulk TE materials; however, it is challenging for thin-film TEs.

Enhanced Diagnosis of Pneumothorax with an Improved Real-Time Augmentation for Imbalanced Chest X-rays Data Based on DCNN.

Pneumothorax is a common pulmonary disease that can lead to dyspnea and can be life-threatening. X-ray examination is the main means to diagnose this disease. Computer-aided diagnosis of pneumothorax on chest X-ray, as a prerequisite for a timely cure, has been widely studied, but it is still not satisfactory to achieve highly accurate results.