Heterogeneous Collaborative Learning for Personalized Healthcare Analytics via Messenger Distillation.

The Healthcare Internet-of-Things (IoT) framework aims to provide personalized medical services with edge devices. Due to the inevitable data sparsity on an individual device, cross-device collaboration is introduced to enhance the power of distributed artificial intelligence. Conventional collaborative learning protocols (e.g., sharing model parameters or gradients) strictly require the homogeneity of all participant models. However, real-life end devices have various hardware configurations (e.g., compute resources), leading to heterogeneous on-device models with different architectures. Moreover, clients (i.e., end devices) may participate in the collaborative learning process at different times. In this paper, we propose a Similarity-Quality-based Messenger Distillation (SQMD) framework for heterogeneous asynchronous on-device healthcare analytics. By introducing a preloaded reference dataset, SQMD enables all participant devices to distill knowledge from peers via messengers (i.e., the soft labels of the reference dataset generated by clients) without assuming the same model architecture. Furthermore, the messengers also carry important auxiliary information to calculate the similarity between clients and evaluate the quality of each client model, based on which the central server creates and maintains a dynamic collaboration graph (communication graph) to improve the personalization and reliability of SQMD under asynchronous conditions. Extensive experiments on three real-life datasets show that SQMD achieves superior performance.

High accurate and explainable multi-pill detection framework with graph neural network-assisted multimodal data fusion.

Due to the significant resemblance in visual appearance, pill misuse is prevalent and has become a critical issue, responsible for one-third of all deaths worldwide. Pill identification, thus, is a crucial concern that needs to be investigated thoroughly. Recently, several attempts have been made to exploit deep learning to tackle the pill identification problem. However, most published works consider only single-pill identification and fail to distinguish hard samples with identical appearances. Also, most existing pill image datasets only feature single pill images captured in carefully controlled environments under ideal lighting conditions and clean backgrounds. In this work, we are the first to tackle the multi-pill detection problem in real-world settings, aiming at localizing and identifying pills captured by users during pill intake. Moreover, we also introduce a multi-pill image dataset taken in unconstrained conditions. To handle hard samples, we propose a novel method for constructing heterogeneous a priori graphs incorporating three forms of inter-pill relationships, including co-occurrence likelihood, relative size, and visual semantic correlation. We then offer a framework for integrating a priori with pills' visual features to enhance detection accuracy. Our experimental results have proved the robustness, reliability, and explainability of the proposed framework. Experimentally, it outperforms all detection benchmarks in terms of all evaluation metrics. Specifically, our proposed framework improves COCO mAP metrics by 9.4% over Faster R-CNN and 12.0% compared to vanilla YOLOv5. Our study opens up new opportunities for protecting patients from medication errors using an AI-based pill identification solution.

Multiplex RT Real-Time PCR Based on Target Failure to Detect and Identify Different Variants of SARS-CoV-2: A Feasible Method That Can Be Applied in Clinical Laboratories.

Shortly after its emergence, Omicron and its sub-variants have quickly replaced the Delta variant during the current COVID-19 outbreaks in Vietnam and around the world. To enable the rapid and timely detection of existing and future variants for epidemiological surveillance and diagnostic applications, a robust, economical real-time PCR method that can specifically and sensitively detect and identify multiple different circulating variants is needed. The principle of target- failure (TF) real-time PCR is simple. If a target contains a deletion mutation, then there is a mismatch with the primer or probe, and the real-time PCR will fail to amplify the target. In this study, we designed and evaluated a novel multiplex RT real-time PCR (MPL RT-rPCR) based on the principle of target failure to detect and identify different variants of SARS-CoV-2 directly from the nasopharyngeal swabs collected from COVID-19 suspected cases. The primers and probes were designed based on the specific deletion mutations of current circulating variants. To evaluate the results from the MPL RT-rPCR, this study also designed nine pairs of primers for amplifying and sequencing of nine fragments from the S gene containing mutations of known variants. We demonstrated that (i) our MPL RT-rPCR was able to accurately detect multiple variants that existed in a single sample; (ii) the limit of detection of the MPL RT-rPCR in the detection of the variants ranged from 1 to 10 copies for Omicron BA.2 and BA.5, and from 10 to 100 copies for Delta, Omicron BA.1, recombination of BA.1 and BA.2, and BA.4; (iii) between January and September 2022, Omicron BA.1 emerged and co-existed with the Delta variant during the early period, both of which were rapidly replaced by Omicron BA.2, and this was followed by Omicron BA.5 as the dominant variant toward the later period. Our results showed that SARS-CoV-2 variants rapidly evolved within a short period of time, proving the importance of a robust, economical, and easy-to-access method not just for epidemiological surveillance but also for diagnoses around the world where SARS-CoV-2 variants remain the WHO's highest health concern. Our highly sensitive and specific MPL RT-rPCR is considered suitable for further implementation in many laboratories, especially in developing countries.

Personalized On-Device E-Health Analytics With Decentralized Block Coordinate Descent.

Actuated by the growing attention to personal healthcare and the pandemic, the popularity of E-health is proliferating. Nowadays, enhancement on medical diagnosis via machine learning models has been highly effective in many aspects of e-health analytics. Nevertheless, in the classic cloud-based/centralized e-health paradigms, all the data will be centrally stored on the server to facilitate model training, which inevitably incurs privacy concerns and high time delay. Distributed solutions like Decentralized Stochastic Gradient Descent (D-SGD) are proposed to provide safe and timely diagnostic results based on personal devices. However, methods like D-SGD are subject to the gradient vanishing issue and usually proceed slowly at the early training stage, thereby impeding the effectiveness and efficiency of training. In addition, existing methods are prone to learning models that are biased towards users with dense data, compromising the fairness when providing E-health analytics for minority groups. In this paper, we propose a Decentralized Block Coordinate Descent (D-BCD) learning framework that can better optimize deep neural network-based models distributed on decentralized devices for E-health analytics. As a gradient-free optimization method, Block Coordinate Descent (BCD) mitigates the gradient vanishing issue and converges faster at the early stage compared with the conventional gradient-based optimization. To overcome the potential data scarcity issues for users' local data, we propose similarity-based model aggregation that allows each on-device model to leverage knowledge from similar neighbor models, so as to achieve both personalization and high accuracy for the learned models. Benchmarking experiments on three real-world datasets illustrate the effectiveness and practicality of our proposed D-BCD, where additional simulation study showcases the strong applicability of D-BCD in real-life E-health scenarios.

Incremental Density-Based Clustering on Multicore Processors.

The density-based clustering algorithm is a fundamental data clustering technique with many real-world applications. However, when the database is frequently changed, how to effectively update clustering results rather than reclustering from scratch remains a challenging task. In this work, we introduce IncAnyDBC, a unique parallel incremental data clustering approach to deal with this problem. First, IncAnyDBC can process changes in bulks rather than batches like state-of-the-art methods for reducing update overheads. Second, it keeps an underlying cluster structure called the object node graph during the clustering process and uses it as a basis for incrementally updating clusters wrt. inserted or deleted objects in the database by propagating changes around affected nodes only. In additional, IncAnyDBC actively and iteratively examines the graph and chooses only a small set of most meaningful objects to produce exact clustering results of DBSCAN or to approximate results under arbitrary time constraints. This makes it more efficient than other existing methods. Third, by processing objects in blocks, IncAnyDBC can be efficiently parallelized on multicore CPUs, thus creating a work-efficient method. It runs much faster than existing techniques using one thread while still scaling well with multiple threads. Experiments are conducted on various large real datasets for demonstrating the performance of IncAnyDBC.

Overview of the roles of calcium sensors in plants’ response to osmotic stress signalling.

Calcium signals serve an important function as secondary messengers between cells in various biological processes due to their robust homeostatic mechanism, maintaining an intracellular free Ca2+ concentration. Plant growth, development, and biotic and abiotic stress are all regulated by Ca2+ signals. Ca2+ binding proteins decode and convey the messages encoded by Ca2+ ions. In the presence of high quantities of Mg2+ and monovalent cations, such sensors bind to Ca2+ ions and modify their conformation in a Ca2+ -dependent manner. Calcium-dependent protein kinases (CPKs), calmodulins (CaMs), and calcineurin B-like proteins are all calcium sensors (CBLs). To transmit Ca2+ signals, CPKs, CBLs, and CaMs interact with target proteins and regulate the expression of their genes. These target proteins may be protein kinases, metabolic enzymes, or cytoskeletal-associated proteins. Beyond its role in plant nutrition as a macroelement and its involvement in the plant cell wall structure, calcium modulates many aspects of development, growth and adaptation to environmental constraints such as drought, salinity and osmotic stresses. This review summarises current knowledge on calcium sensors in plant responses to osmotic stress signalling.

Origin of novel coronavirus causing COVID-19: A computational biology study using artificial intelligence.

Origin of the COVID-19 virus (SARS-CoV-2) has been intensely debated in the scientific community since the first infected cases were detected in December 2019. The disease has caused a global pandemic, leading to deaths of thousands of people across the world and thus finding origin of this novel coronavirus is important in responding and controlling the pandemic. Recent research results suggest that bats or pangolins might be the hosts for SARS-CoV-2 based on comparative studies using its genomic sequences. This paper investigates the SARS-CoV-2 origin by using artificial intelligence (AI)-based unsupervised learning algorithms and raw genomic sequences of the virus. More than 300 genome sequences of COVID-19 infected cases collected from different countries are explored and analysed using unsupervised clustering methods. The results obtained from various AI-enabled experiments using clustering algorithms demonstrate that all examined SARS-CoV-2 genomes belong to a cluster that also contains bat and pangolin coronavirus genomes. This provides evidence strongly supporting scientific hypotheses that bats and pangolins are probable hosts for SARS-CoV-2. At the whole genome analysis level, our findings also indicate that bats are more likely the hosts for the COVID-19 virus than pangolins.

Deep learning models for forecasting dengue fever based on climate data in Vietnam.

BACKGROUND: Dengue fever (DF) represents a significant health burden in Vietnam, which is forecast to worsen under climate change. The development of an early-warning system for DF has been selected as a prioritised health adaptation measure to climate change in Vietnam. OBJECTIVE: This study aimed to develop an accurate DF prediction model in Vietnam using a wide range of meteorological factors as inputs to inform public health responses for outbreak prevention in the context of future climate change. METHODS: Convolutional neural network (CNN), Transformer, long short-term memory (LSTM), and attention-enhanced LSTM (LSTM-ATT) models were compared with traditional machine learning models on weather-based DF forecasting. Models were developed using lagged DF incidence and meteorological variables (measures of temperature, humidity, rainfall, evaporation, and sunshine hours) as inputs for 20 provinces throughout Vietnam. Data from 1997-2013 were used to train models, which were then evaluated using data from 2014-2016 by Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). RESULTS AND DISCUSSION: LSTM-ATT displayed the highest performance, scoring average places of 1.60 for RMSE-based ranking and 1.95 for MAE-based ranking. Notably, it was able to forecast DF incidence better than LSTM in 13 or 14 out of 20 provinces for MAE or RMSE, respectively. Moreover, LSTM-ATT was able to accurately predict DF incidence and outbreak months up to 3 months ahead, though performance dropped slightly compared to short-term forecasts. To the best of our knowledge, this is the first time deep learning methods have been employed for the prediction of both long- and short-term DF incidence and outbreaks in Vietnam using unique, rich meteorological features. CONCLUSION: This study demonstrates the usefulness of deep learning models for meteorological factor-based DF forecasting. LSTM-ATT should be further explored for mitigation strategies against DF and other climate-sensitive diseases in the coming years.

Genomic mutations and changes in protein secondary structure and solvent accessibility of SARS-CoV-2 (COVID-19 virus).

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a highly pathogenic virus that has caused the global COVID-19 pandemic. Tracing the evolution and transmission of the virus is crucial to respond to and control the pandemic through appropriate intervention strategies. This paper reports and analyses genomic mutations in the coding regions of SARS-CoV-2 and their probable protein secondary structure and solvent accessibility changes, which are predicted using deep learning models. Prediction results suggest that mutation D614G in the virus spike protein, which has attracted much attention from researchers, is unlikely to make changes in protein secondary structure and relative solvent accessibility. Based on 6324 viral genome sequences, we create a spreadsheet dataset of point mutations that can facilitate the investigation of SARS-CoV-2 in many perspectives, especially in tracing the evolution and worldwide spread of the virus. Our analysis results also show that coding genes E, M, ORF6, ORF7a, ORF7b and ORF10 are most stable, potentially suitable to be targeted for vaccine and drug development.

A soybean calcineurin B-like protein-interacting protein kinase, GmPKS4, regulates plant responses to salt and alkali stresses.

Calcineurin B-like protein-interacting protein kinases (CIPKs) are key elements of plant abiotic stress signaling pathways. CIPKs are SOS2 (Salt Overly Sensitive 2)-like proteins (protein kinase S [PKS] proteins) which all contain a putative FISL motif. It seems that the FISL motif is found only in the SOS2 subfamily of protein kinases. In this study, the full-length cDNA of a soybean CIPK gene (GmPKS4) was isolated and was revealed to have an important role in abiotic stress responses. A qRT-PCR analysis indicated that GmPKS4 expression is upregulated under saline conditions or when exposed to alkali, salt-alkali, drought, or abscisic acid (ABA). A subcellular localization assay revealed the presence of GmPKS4 in the nucleus and cytoplasm. Further studies on the GmPKS4 promoter suggested it affects soybean resistance to various stresses. Transgenic Arabidopsis thaliana and soybean hairy roots overexpressing GmPKS4 had increased proline content as well as high antioxidant enzyme activities but decreased malondialdehyde levels following salt and salt-alkali stress treatments. Additionally, GmPKS4 overexpression activated reactive oxygen species scavenging systems, thereby minimizing damages due to oxidative and osmotic stresses. Moreover, upregulated stress-related gene expression levels were detected in lines overexpressing GmPKS4 under stress conditions. In conclusion, GmPKS4 improves soybean tolerance to salt and salt-alkali stresses. The overexpression of GmPKS4 enhances the scavenging of reactive oxygen species, osmolyte synthesis, and the transcriptional regulation of stress-related genes.

Environmental sampling for SARS-CoV-2 at a reference laboratory and provincial hospital in central Viet Nam, 2020.

OBJECTIVE: To determine whether environmental surface contamination with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) occurred at a provincial hospital in Viet Nam that admitted patients with novel coronavirus disease 2019 (COVID-19) and at the regional reference laboratory responsible for confirmatory testing for SARS-CoV-2 in 2020. METHODS: Environmental samples were collected from patient and staff areas at the hospital and various operational and staff areas at the laboratory. Specimens from frequently touched surfaces in all rooms were collected using a moistened swab rubbed over a 25 cm2 area for each surface. The swabs were immediately transported to the laboratory for testing by real-time reverse transcription polymerase chain reaction (RT-PCR). Throat specimens were collected from staff at both locations and were also tested for SARS-CoV-2 using real-time RT-PCR. RESULTS: During the sampling period, the laboratory tested 6607 respiratory specimens for SARS-CoV-2 from patients within the region, and the hospital admitted 9 COVID-19 cases. Regular cleaning was conducted at both sites in accordance with infection prevention and control (IPC) practices. All 750 environmental samples (300 laboratory and 450 hospital) and 30 staff specimens were negative for SARS-CoV-2. DISCUSSION: IPC measures at the facilities may have contributed to the negative results from the environmental samples. Other possible explanations include sampling late in a patient's hospital stay when virus load was lower, having insufficient contact time with a surface or using insufficiently moist collection swabs. Further environmental sampling studies of SARS-CoV-2 should consider including testing for the environmental presence of viruses within laboratory settings, targeting the collection of samples to early in the course of a patient's illness and including sampling of confirmed positive control surfaces, while maintaining appropriate biosafety measures.

Diversity of microbial community and its metabolic potential for nitrogen and sulfur cycling in sediments of Phu Quoc island, Gulf of Thailand.

Although Phu Quoc island, Gulf of Thailand possesses diverse marine and coastal ecosystems, biodiversity and metabolic capability of microbial communities remain poorly investigated. The aim of our study was to evaluate the biodiversity and metabolic potential of sediment microbial communities in Phu Quoc island. The marine sediments were collected from three different areas and analyzed by using 16S rRNA gene-based amplicon approach. A total of 1,143,939 reads were clustered at a 97% sequence similarity into 8,331 unique operational taxonomic units, representing 52 phyla. Bacteria and archaea occupied averagely around 86% and 14%, respectively, of the total prokaryotic community. Proteobacteria, Planctomycetes, Chloroflexi, and Thaumarchaeota were the dominant phyla in all sediments, which were involved in nitrogen and sulfur metabolism. Sediments harboring of higher nitrogen sources were found to coincide with increased abundance of archaeal phylum Thaumarchaeota. Predictive functional analysis showed high abundance prokaryotic genes associated with nitrogen cycling including nifA-Z, amoABC, nirA, narBIJ, napA, nxrAB, nrfA-K, nirBD, nirS, nirK, norB-Z, nlnA, ald, and ureA-J, based on taxonomic groups detected by 16S rRNA sequencing. Although the key genes involved in sulfur cycling were found to be at low to undetectable levels, the other genes encoding for sulfur-related biological processes were present, suggesting that alternative pathways may be involved in sulfur cycling at our study site. In conclusion, our study for the first time shed light on diversity of microbial communities in Phu Quoc island.

Development and flight performance of a biologically-inspired tailless flapping-wing micro air vehicle with wing stroke plane modulation.

The tailless flapping-wing micro air vehicle (FW-MAV) is one of the most challenging problems in flapping-wing design due to its lack of tail for inherent flight stability. It must be designed in such a way that it can produce proper augmented control moments modulated by a closed-loop attitude controller for active stabilization. We propose a tailless FW-MAV with a wing stroke plane modulation mechanism, namely NUS-Roboticbird, which maneuvers by only using its flapping wings for both propulsion and attitude control. The flying vehicle has four wings comprised by two pairs, and each pair of wings and its stroke plane are driven by a motor and a servo, respectively. Attitude control moments of roll, pitch and yaw are generated by vectoring a pair of thrusts, which result from changing the flapping frequency (or motor speed) and wing stroke plane of the two pairs of wings. Free-flight tests show that the vehicle can climb and descend vertically (throttle control), fly sideways left and right (roll control), fly forwards and backwards (pitch control), rotate clockwise and counter-clockwise (yaw control), hover in mid-air (active self-stabilization), and maneuver in the figure-of-8 and fast forward/backward flight. These abilities are especially important for surveillance and autonomous flight in terms of obstacle avoidance in an indoor environment. Flight test data show that an effective mechanical control mechanism and control gains for attitude-controlled flights for roll, pitch and yaw are achieved, in particular, yaw control. Currently, the vehicle weighing 31 g and having a wingspan of 22 cm can perform fast forward flight at a speed of about 5 m s-1 (18 km h-1) and endure 3.5 min in flight with a useful payload of a 4.5 g onboard camera for surveillance.