Review of single-cell RNA-seq data clustering for cell-type identification and characterization.

In recent years, the advances in single-cell RNA-seq techniques have enabled us to perform large-scale transcriptomic profiling at single-cell resolution in a high-throughput manner. Unsupervised learning such as data clustering has become the central component to identify and characterize novel cell types and gene expression patterns. In this study, we review the existing single-cell RNA-seq data clustering methods with critical insights into the related advantages and limitations. In addition, we also review the upstream single-cell RNA-seq data processing techniques such as quality control, normalization, and dimension reduction. We conduct performance comparison experiments to evaluate several popular single-cell RNA-seq clustering approaches on simulated and multiple single-cell transcriptomic data sets.

Amino acid profile alteration in age-related atrial fibrillation.

BACKGROUND: Amino acids (AAs) are one of the primary metabolic substrates for cardiac work. The correlation between AAs and both atrial fibrillation (AF) and aging has been documented. However, the relationship between AAs and age-related AF remains unclear. METHODS: Initially, the plasma AA levels of persistent AF patients and control subjects were assessed, and the correlations between AA levels, age, and other clinical indicators were explored. Subsequently, the age-related AF mouse model was constructed and the untargeted myocardial metabolomics was conducted to detect the level of AAs and related metabolites. Additionally, the gut microbiota composition associated with age-related AF was detected by a 16S rDNA amplicon sequencing analysis on mouse fecal samples. RESULTS: Higher circulation levels of lysine (Student's t-test, P = 0.001), tyrosine (P = 0.002), glutamic acid (P = 0.008), methionine (P = 0.008), and isoleucine (P = 0.014), while a lower level of glycine (P = 0.003) were observed in persistent AF patients. The feature AAs identified by machine learning algorithms were glutamic acid and methionine. The association between AAs and age differs between AF and control subjects. Distinct patterns of AA metabolic profiles were observed in the myocardial metabolites of aged AF mice. Aged AF mice had lower levels of Betaine, L-histidine, L-alanine, L-arginine, L-Pyroglutamic acid, and L-Citrulline compared with adult AF mice. Aged AF mice also presented a different gut microbiota pattern, and its functional prediction analysis showed AA metabolism alteration. CONCLUSION: This study provided a comprehensive network of AA disturbances in age-related AF from multiple dimensions, including plasma, myocardium, and gut microbiota. Disturbances of AAs may serve as AF biomarkers, and restoring their homeostasis may have potential benefits for the management of age-related AF.

Device therapy for patients with atrial fibrillation and heart failure with preserved ejection fraction.

Device therapy is a nonpharmacological approach that presents a crucial advancement for managing patients with atrial fibrillation (AF) and heart failure with preserved ejection fraction (HFpEF). This review investigated the impact of device-based interventions and emphasized their potential for optimizing treatment for this complex patient demographic. Cardiac resynchronization therapy, augmented by atrioventricular node ablation with His-bundle pacing or left bundle-branch pacing, is effective for enhancing cardiac function and establishing atrioventricular synchrony. Cardiac contractility modulation and vagus nerve stimulation represent novel strategies for increasing myocardial contractility and adjusting the autonomic balance. Left ventricular expanders have demonstrated short-term benefits in HFpEF patients but require more investigation for long-term effectiveness and safety, especially in patients with AF. Research gaps regarding complications arising from left ventricular expander implantation need to be addressed. Device-based therapies for heart valve diseases, such as transcatheter aortic valve replacement and transcatheter edge-to-edge repair, show promise for patients with AF and HFpEF, particularly those with mitral or tricuspid regurgitation. Clinical evaluations show that these device therapies lessen AF occurrence, improve exercise tolerance, and boost left ventricular diastolic function. However, additional studies are required to perfect patient selection criteria and ascertain the long-term effectiveness and safety of these interventions. Our review underscores the significant potential of device therapy for improving the outcomes and quality of life for patients with AF and HFpEF.

Overcoming barriers for left atrial appendage thrombus: a systematic review of left atrial appendage closure.

BACKGROUND: Approximately 90% of intracardial thrombi originate from the left atrial appendage in non-valvular atrial fibrillation patients. Even with anticoagulant therapy, left atrial appendage thrombus (LAAT) still occurs in 8% of patients. While left atrial appendage closure (LAAC) could be a promising alternative, the current consensus considers LAAT a contraindication to LAAC. However, the feasibility and safety of LAAC in patients with LAAT have yet to be determined. METHODS: This systematic review synthesizes published data to explore the feasibility and safety of LAAC for patients with LAAT. RESULTS: This study included a total of 136 patients with LAATs who underwent successful LAAC. The Amulet Amplatzer device was the most frequently utilized device (48.5%). Among these patients, 77 (56.6%) had absolute contraindications to anticoagulation therapy. Cerebral protection devices were utilized by 47 patients (34.6%). Transesophageal echocardiography (TEE) is the primary imaging technique used during the procedure. Warfarin and novel oral anticoagulants were the main anticoagulant medications used prior to the procedure, while dual antiplatelet therapy was primarily used post-procedure. During a mean follow-up period of 13.2 ± 11.5 months, there was 1 case of fatality, 1 case of stroke, 3 major bleeding events, 3 instances of device-related thrombus, and 8 cases of peri-device leakage. CONCLUSIONS: This review highlights the preliminary effectiveness and safety of the LAAC procedure in patients with persistent LAAT. Future large-scale RCTs with varied LAAT characteristics and LAAC device types are essential for evidence-based decision-making in clinical practice.

A high level of uric acid is associated with long-term adverse cardiovascular outcomes in patients who received fractional flow reserve with coronary intermediate stenosis.

BACKGROUND AND AIMS: The role of fractional flow reserve (FFR) in coronary intermediate lesions is widely recommended by guidelines. The effect of uric acid (UA) on cardiovascular events is also well known. However, the relationship between UA and long-term cardiovascular outcomes in patients who received FFR with intermediate lesions remains unknown. METHODS AND RESULTS: We retrospectively included 428 patients who underwent both coronary angiography (CAG) and FFR. Participants were stratified into two groups based on the median UA. The primary endpoint was the composite of major adverse cardiovascular and cerebrovascular events (MACCEs), including repeat revascularization, nonfatal stroke, nonfatal myocardial infarction, and all-cause death. A Cox proportional hazards model was utilized to analyze the association between UA and the prevalence of MACCEs. During a median follow-up of 5.8 years, a higher MACCEs rate occurred in the high UA group compared to the low UA group (16.8% vs. 5.1%, p log-rank<0.01). Elevated UA was independently linked to a higher incidence of MACCEs, whether UA was treated as a categorical or continuous variable (hazard ratio [HR] 2.76, 95% confidence interval [CI] 1.27-6.03 or HR 1.01, 95% CI 1.01-1.02). The restricted cubic spline (RCS) analysis illustrated that the HR for MACCEs increased with increasing UA. CONCLUSION: The present study demonstrates that UA is associated with MACCEs risk and suggests that UA is a reliable predictor of long-term cardiovascular events in coronary intermediate stenosis patients.

Triglyceride to high-density lipoprotein cholesterol ratio associated with long-term adverse clinical outcomes in patients deferred revascularization following fractional flow reserve.

BACKGROUND: Guidelines on coronary intermediate lesions strongly recommend deferred revascularization after detecting a normal fractional flow reserve (FFR). Researches about triglyceride to high-density lipoprotein cholesterol (TG/HDL-C) on cardiovascular diseases has also been well conducted. However, the association of TG/HDL-C and long-term adverse clinical outcomes remains unknown for patients deferred revascularization following FFR. METHODS: This study retrospectively included 374 coronary artery disease (CAD) patients with non-significant coronary lesions diagnosed by coronary angiography (CAG) and FFR. The main outcome measure was the combination of major adverse cardiovascular and cerebrovascular events (MACCEs). All patients were categorized into three subgroups in terms of TG/HDL-C tertiles (T1 < 0.96, 0.96 ≤ T2 < 1.58, T3 ≥ 1.58). Three different Cox regression models were utilized to reveal the association between TG/HDL-C and prevalence of MACCEs. RESULTS: 47 MACCEs were recorded throughout a median monitoring period of 6.6 years. The Kaplan-Meier survival curves showed a higher MACCEs rate occurred in the higher TG/HDL-C group (5.6% vs. 12.9% vs. 19.4%, log-rank P < 0.01). After adjustment, patients in T3 suffered a 2.6-fold risk compared to the T1 group (T3 vs. T1: HR 2.55, 95% CI 1.05-6.21, P = 0.038; T2 vs. T1: HR 1.71, 95% CI 0.65-4.49, P = 0.075; P for trend = 0.001). The restricted cubic spline (RCS) analysis demonstrated that the HR for MACCEs rose as TG/HDL-C increased. Both the receiver operating characteristic (ROC) and time-dependent ROC proved the excellent predictive ability of TG/HDL-C. CONCLUSION: The study illustrates that TG/HDL-C correlates with the risk of MACCEs in CAD patients deferred revascularization following FFR. TG/HDL-C could serve as a dependable predictor of cardiovascular events over the long term in this population.

Physical activity, sedentary behavior, and the risk of frailty and falling: A Mendelian randomization study.

BACKGROUND: Due to inconclusive evidence from observational studies regarding the impact of physical activity (PA) and sedentary behavior on frailty and falling risk, we conducted a two-sample Mendelian randomization analysis to investigate the causal associations between PA, sedentary behavior, and frailty and falls. METHODS: We extracted summary data from genome-wide association studies conducted among individuals of European ancestry, encompassing PA (n = 90 667-608 595), sedentary behavior (n = 372 609-526 725), frailty index (n = 175 226), and falling risk (n = 451 179). Single nucleotide polymorphisms associated with accelerometer assessed fraction >425 milligravities, self-reported vigorous activity, moderate to vigorous physical acticity (MVPA), leisure screen time (LST), and sedentary behavior at work were taken as instrumental variables. The causal effects were primarily estimated using inverse variance weighted methods, complemented by several sensitivity and validation analyses. RESULTS: Genetically predicted higher levels of PA were significantly associated with a reduction in the frailty index (accelerometer assessed fraction >425 milligravities: ß = -0.25, 95% CI = -0.36 to -0.14, p = 1.27 × 10-5 ; self-reported vigorous activity: ß = -0.13, 95% CI = -0.20 to -0.05, p = 7.9 × 10-4 ; MVPA: ß = -0.28, 95% CI = -0.40 to -0.16, p = 9.9 × 10-6 ). Besides, LST was significantly associated with higher frailty index (ß = 0.18, 95% CI = 0.14-0.22, p = 5.2 × 10-20 ) and higher odds of falling (OR = 1.13, CI = 1.07-1.19, p = 6.9 × 10-6 ). These findings remained consistent throughout sensitivity and validation analyses. CONCLUSIONS: Our study offers evidence supporting a causal relationship between PA and a reduced risk of frailty. Furthermore, it underscores the association between prolonged LST and an elevated risk of frailty and falls. Therefore, promoting PA and reducing sedentary behavior may be an effective strategy in primary frailty and falls prevention.

Uncovering the key dimensions of high-throughput biomolecular data using deep learning.

Recent advances in high-throughput single-cell RNA-seq have enabled us to measure thousands of gene expression levels at single-cell resolution. However, the transcriptomic profiles are high-dimensional and sparse in nature. To address it, a deep learning framework based on auto-encoder, termed DeepAE, is proposed to elucidate high-dimensional transcriptomic profiling data in an encode-decode manner. Comparative experiments were conducted on nine transcriptomic profiling datasets to compare DeepAE with four benchmark methods. The results demonstrate that the proposed DeepAE outperforms the benchmark methods with robust performance on uncovering the key dimensions of single-cell RNA-seq data. In addition, we also investigate the performance of DeepAE in other contexts and platforms such as mass cytometry and metabolic profiling in a comprehensive manner. Gene ontology enrichment and pathology analysis are conducted to reveal the mechanisms behind the robust performance of DeepAE by uncovering its key dimensions.

Heterodimeric DNA motif synthesis and validations.

Bound by transcription factors, DNA motifs (i.e. transcription factor binding sites) are prevalent and important for gene regulation in different tissues at different developmental stages of eukaryotes. Although considerable efforts have been made on elucidating monomeric DNA motif patterns, our knowledge on heterodimeric DNA motifs are still far from complete. Therefore, we propose to develop a computational approach to synthesize a heterodimeric DNA motif from two monomeric DNA motifs. The approach is sequentially divided into two components (Phases A and B). In Phase A, we propose to develop the inference models on how two DNA monomeric motifs can be oriented and overlapped with each other at nucleotide level. In Phase B, given the two monomeric DNA motifs oriented, we further propose to develop DNA-binding family-specific input-output hidden Markov models (IOHMMs) to synthesize a heterodimeric DNA motif. To validate the approach, we execute and cross-validate it with the experimentally verified 618 heterodimeric DNA motifs across 49 DNA-binding family combinations. We observe that our approach can even "rescue" the existing heterodimeric DNA motif pattern (i.e. HOXB2_EOMES) previously published on Nature. Lastly, we apply the proposed approach to infer previously uncharacterized heterodimeric motifs. Their motif instances are supported by DNase accessibility, gene ontology, protein-protein interactions, in vivo ChIP-seq peaks, and even structural data from PDB. A public web-server is built for open accessibility and scientific impact. Its address is listed as follows: http://motif.cs.cityu.edu.hk/custom/MotifKirin.

Transmission trend of the COVID-19 pandemic predicted by dendritic neural regression.

In 2020, a novel coronavirus disease became a global problem. The disease was called COVID-19, as the first patient was diagnosed in December 2019. The disease spread around the world quickly due to its powerful viral ability. To date, the spread of COVID-19 has been relatively mild in China due to timely control measures. However, in other countries, the pandemic remains severe, and COVID-19 protection and control policies are urgently needed, which has motivated this research. Since the outbreak of the pandemic, many researchers have hoped to identify the mechanism of COVID-19 transmission and predict its spread by using machine learning (ML) methods to supply meaningful reference information to decision-makers in various countries. Since the historical data of COVID-19 is time series data, most researchers have adopted recurrent neural networks (RNNs), which can capture time information, for this problem. However, even with a state-of-the-art RNN, it is still difficult to perfectly capture the temporal information and nonlinear characteristics from the historical data of COVID-19. Therefore, in this study, we develop a novel dendritic neural regression (DNR) method to improve prediction performance. In the DNR, the multiplication operator is used to capture the nonlinear relationships between input feature signals in the dendrite layer. Considering the complex and large landscape of DNR's weight space, a new scale-free state-of-matter search (SFSMS) algorithm is proposed to optimize the DNR, which combines the state-of-matter search algorithm with a scale-free local search. The SFSMS achieves a better global search ability and thus can effectively reduce the possibility of falling into local minima. In addition, according to Takens's theorem, phase space reconstruction techniques are used to discover the information hidden in the high-dimensional space of COVID-19 data, which further improves the precision of prediction. The experimental results suggest that the proposed method is more competitive in solving this problem than other prevailing methods.

Synergizing CRISPR/Cas9 off-target predictions for ensemble insights and practical applications.

MOTIVATION: The RNA-guided CRISPR/Cas9 system has been widely applied to genome editing. CRISPR/Cas9 system can effectively edit the on-target genes. Nonetheless, it has recently been demonstrated that many homologous off-target genomic sequences could be mutated, leading to unexpected gene-editing outcomes. Therefore, a plethora of tools were proposed for the prediction of off-target activities of CRISPR/Cas9. Nonetheless, each computational tool has its own advantages and drawbacks under diverse conditions. It is hardly believed that a single tool is optimal for all conditions. Hence, we would like to explore the ensemble learning potential on synergizing multiple tools with genomic annotations together to enhance its predictive abilities. RESULTS: We proposed an ensemble learning framework which synergizes multiple tools together to predict the off-target activities of CRISPR/Cas9 in different combinations. Interestingly, the ensemble learning using AdaBoost outperformed other individual off-target predictive tools. We also investigated the effect of evolutionary conservation (PhyloP and PhastCons) and chromatin annotations (ChromHMM and Segway) and found that only PhyloP can enhance the predictive capabilities further. Case studies are conducted to reveal ensemble insights into the off-target predictions, demonstrating how the current study can be applied in different genomic contexts. The best prediction predicted by AdaBoost is up to 0.9383 (AUC) and 0.2998 (PRC) that outperforms other classifiers. This is ascribable to the fact that AdaBoost introduces a new weak classifier (i.e. decision stump) in each iteration to learn the DNA sequences that were misclassified as off-targets until a small error rate is reached iteratively. AVAILABILITY AND IMPLEMENTATION: The source codes are freely available on GitHub at https://github.com/Alexzsx/CRISPR. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A Rainbow-Based Authentical Scheme for Securing Smart Connected Health Systems.

Smart Connected Health Systems (SCHSs) belong to health systems that provide services of health care remotely. They provide the doctors with access to electronic medical records with the aid of medical sensors, smart wearable devices and smart medical instruments. Although SCHSs have many applications in the area of health care, securing massive amount of valuable and sensitive data of the patients and preserving the privacy are challenging. User authentication based on public key cryptographic techniques is playing a crucial role in SCHSs for protecting the privacy of patients. However, quantum computers will break such techniques. Rainbow signature is one of the candidates of the next generation of cryptographic algorithms which can resist attacks on quantum computers. However, it is vulnerable to Differential Power Analysis (DPA) attacks, which is based on information gained from the cryptographic implementations. We present techniques to exploit the countermeasures to protect Rainbow against DPA attacks. We propose a variant of Rainbow with resistance to DPA attacks. First, we take a random vector to randomize the power consumption of private keys during computing the first affine transformation; Second, random variables are adopted during computing central map transformation; Third, we take two random vectors during computing the second affine transformation to randomize the power consumption of private keys. We analyze the efficiency and implement the scheme on hardware. Compared with the related implementations, our scheme is efficient and suitable for signature generations on hardware. Besides, we propose a secure authentical scheme based on the implementation for protecting record of patients in SCHSs.

Multiobjective Multitasking Optimization With Decomposition-Based Transfer Selection.

Multiobjective multitasking optimization (MTO) needs to solve a set of multiobjective optimization problems simultaneously, and tries to speed up their solution by transferring useful search experiences across tasks. However, the quality of transfer solutions will significantly impact the transfer effect, which may even deteriorate the optimization performance with an improper selection of transfer solutions. To alleviate this issue, this article suggests a new multiobjective multitasking evolutionary algorithm (MMTEA) with decomposition-based transfer selection, called MMTEA-DTS. In this algorithm, all tasks are first decomposed into a set of subproblems, and then the transfer potential of each solution can be quantified based on the performance improvement ratio of its associated subproblem. Only high-potential solutions are selected to promote knowledge transfer. Moreover, to diversify the transfer of search experiences, a hybrid transfer evolution method is designed in this article. In this way, more diverse search experiences are transferred from high-potential solutions across different tasks to speed up their convergence. Three well-known benchmark suites suggested in the competition of evolutionary MTO and one real-world problem suite are used to verify the effectiveness of MMTEA-DTS. The experiments validate its advantages in solving most of the test problems when compared to five recently proposed MMTEAs.

Advancing Guideline-Directed Medical Therapy in Heart Failure: Overcoming Challenges and Maximizing Benefits.

The delayed titration of guideline-directed drug therapy (GDMT) is a complex event influenced by multiple factors that often result in poor prognosis for patients with heart failure (HF). Individualized adjustments in GDMT titration may be necessary based on patient characteristics, and every clinician is responsible for promptly initiating GDMT and titrating it appropriately within the patient's tolerance range. This review examines the current challenges in GDMT implementation and scrutinizes titration considerations within distinct subsets of HF patients, with the overarching goal of enhancing the adoption and effectiveness of GDMT. The authors also underscore the significance of establishing a novel management strategy that integrates cardiologists, nurse practitioners, pharmacists, and patients as a unified team that can contribute to the improved promotion and implementation of GDMT.

The prognostic value of prognostic nutritional index in postoperative onset of PAH in children with isolated VSD: a prospective cohort study based on propensity score matching analysis.

Background: The mechanism of pulmonary arterial hypertension (PAH) after surgery/intervention for isolated venticlular septal defect (VSD) in children is unknown. Reliable prognostic indicators for predicting postoperative PAH are urgently needed. Prognostic nutration index (PNI) is widely used to predict postoperative complications and survival in adults, but it is unclear whether it can be used as an indicator of prognosis in children. Methods: A total of 251 children underwent VSD repair surgery or interventional closure in Hunan Children's Hospital from 2020 to 2023 were collected. A 1:1 propensity score matching (PSM) analysis was performed using the nearest neighbor method with a caliper size of 0.2 Logistics regression analysis is used to examine factors associated with the development of PAH. Results: The cut-off value for PNI was determined as 58.0. After 1:1 PSM analysis, 49 patients in the low PNI group were matched with high PNI group. Children in the low PNI group had higher risk of postoperative PAH (P = 0.002) than those in the high PNI group. Multivariate logistics regression analysis showed that PNI (RR: 0.903, 95% CI: 0.816-0.999, P = 0.049) and tricuspid regurgitation velocity (RR: 4.743, 95% CI: 1.131-19.897, P = 0.033) were independent prognostic factors for the development of PAH. Conclusion: PNI can be used as a prognostic indicator for PAH development after surgery/intervention in children with isolated VSD.

Causal relationship between particulate matter and COVID-19 risk: A mendelian randomization study.

Background: Observational studies have linked exposure to fine (PM2.5) and coarse (PM10) particulate matter air pollution with adverse COVID-19 outcomes, including higher incidence and mortality. However, some studies questioned the effect of air pollution on COVID-19 susceptibility, raising questions about the causal nature of these associations. To address this, a less biased method like Mendelian randomization (MR) is utilized, which employs genetic variants as instrumental variables to infer causal relationships in observational data. Method: We performed two-sample MR analysis using public genome-wide association studies data. Instrumental variables correlated with PM2.5 concentration, PM2.5 absorbance, PM2.5-10 concentration and PM10 concentration were identified. The inverse variance weighted (IVW), robust adjusted profile score (RAPS) and generalized summary data-based Mendelian randomization (GSMR) methods were used for analysis. Results: IVW MR analysis showed PM2.5 concentration [odd ratio (OR) = 3.29, 95% confidence interval (CI) 1.48-7.35, P-value = 0.0036], PM2.5 absorbance (OR = 5.62, 95%CI 1.98-15.94, P-value = 0.0012), and PM10 concentration (OR = 3.74, 95%CI 1.52-9.20, P-value = 0.0041) increased the risk of COVID-19 severity after Bonferroni correction. Further validation confirmed PM2.5 absorbance was associated with heightened COVID-19 severity (OR = 6.05, 95%CI 1.99-18.38, P-value = 0.0015 for RAPS method; OR = 4.91, 95%CI 1.65-14.59, P-value = 0.0042 for GSMR method) and hospitalization (OR = 3.15, 95%CI 1.54-6.47, P-value = 0.0018 for RAPS method). No causal links were observed between particulate matter exposure and COVID-19 susceptibility. Conclusions: Our study established a causal relationship between smaller particle pollution, specifically PM2.5, and increased risk of COVID-19 severity and hospitalization. These findings highlight the importance of improving air quality to mitigate respiratory disease progression.

Pulsed field ablation: A promising approach for ventricular tachycardia ablation.

Radiofrequency ablation (RFA) has been a central therapeutic strategy for ventricular tachycardia (VT). However, concerns about its long-term effectiveness and complications have arisen. Pulsed field ablation (PFA), characterized by its nonthermal, highly tissue-selective ablation technique, has emerged as a promising alternative. This comprehensive review delves into the potential advantages and opportunities presented by PFA in the realm of VT, drawing insights from both animal experimentation and clinical case studies. PFA shows promise in generating superior lesions within scarred myocardial tissue, and its inherent repetition dependency holds the potential to enhance therapeutic outcomes. Clinical cases underscore the promise of PFA for VT ablation. Despite its promising applications, challenges such as catheter maneuverability and proarrhythmic effects require further investigation. Large-scale, long-term studies are essential to establish the suitability of PFA for VT treatment.

Competitive Decomposition-Based Multiobjective Architecture Search for the Dendritic Neural Model.

The dendritic neural model (DNM) is computationally faster than other machine-learning techniques, because its architecture can be implemented by using logic circuits and its calculations can be performed entirely in binary form. To further improve the computational speed, a straightforward approach is to generate a more concise architecture for the DNM. Actually, the architecture search is a large-scale multiobjective optimization problem (LSMOP), where a large number of parameters need to be set with the aim of optimizing accuracy and structural complexity simultaneously. However, the issues of irregular Pareto front, objective discontinuity, and population degeneration strongly limit the performances of conventional multiobjective evolutionary algorithms (MOEAs) on the specific problem. Therefore, a novel competitive decomposition-based MOEA is proposed in this study, which decomposes the original problem into several constrained subproblems, with neighboring subproblems sharing overlapping regions in the objective space. The solutions in the overlapping regions participate in environmental selection for the neighboring subproblems and then propagate the selection pressure throughout the entire population. Experimental results demonstrate that the proposed algorithm can possess a more powerful optimization ability than the state-of-the-art MOEAs. Furthermore, both the DNM itself and its hardware implementation can achieve very competitive classification performances when trained by the proposed algorithm, compared with numerous widely used machine-learning approaches.

Adapting Decomposed Directions for Evolutionary Multiobjective Optimization.

Decomposition methods have been widely employed in evolutionary algorithms for tackling multiobjective optimization problems (MOPs) due to their good mathematical explanation and promising performance. However, most decomposition methods only use a single ideal or nadir point to guide the evolution, which are not so effective for solving MOPs with extremely convex/concave Pareto fronts (PFs). To solve this problem, this article proposes an effective method to adapt decomposed directions (ADDs) for solving MOPs. Instead of using one single ideal or nadir point, each weight vector has one exclusive ideal point in our method for decomposition, in which the decomposed directions are adapted during the search process. In this way, the adapted decomposed directions can evenly and entirely cover the PF of the target MOP. The effectiveness of our method is analyzed theoretically and verified experimentally when embedding it into three representative multiobjective evolutionary algorithms (MOEAs), which can significantly improve their performance. When compared to seven competitive MOEAs, the experiments also validate the advantages of our method for solving 39 artificial MOPs with various PFs and one real-world MOP.

Noninvasive Cuffless Blood Pressure Estimation With Dendritic Neural Regression.

Blood pressure (BP) is one of the most important indicators of health. BP that is too high or too low causes varying degrees of diseases, such as renal impairment, cerebrovascular incidents, and cardiovascular diseases. Since traditional cuff-based BP measurement techniques have the drawbacks of patient discomfort and the impossibility of continuous BP monitoring, noninvasive cuffless continuous BP measurement has become a popular topic. The common noninvasive approach uses machine-learning (ML) algorithms to estimate BP by using the features extracted from simultaneous photoplethysmogram (PPG) and electrocardiogram (ECG) signals, such as the pulse transit time and pulse wave velocity. This study investigates the BP estimation performance of the novel dendritic neural regression (DNR) method proposed by us. Unlike conventional neural networks, DNR utilizes the multiplication operator as the excitation function in each dendritic branch, inspired by biological neuron phenomena, and can effectively capture nonlinear relationships between distinct input features. In addition, AMSGrad is used as the optimization algorithm to further enhance the dendritic neural model's performance. The experimental results show that by being fed a combination of the raw features extracted from the ECG and PPG signals and the components of the BP mathematical models, DNR can increase the accuracy of systolic BP, diastolic BP, and mean arterial pressure estimation significantly, which are superior to the state-of-the-art ML techniques. According to the British Hypertension Society protocol, DNR achieves a grade of A for the long-term BP estimation. Considering its architectural simplicity and powerful performance, the proposed method can be regarded as a reliable tool for estimating long-term continuous BP in a noninvasive cuffless way.