Minimax and Biobjective Portfolio Selection Based on Collaborative Neurodynamic Optimization

Distributed nonconvex optimization subject to globally coupled constraints via collaborative neurodynamic optimization

In this paper, a recurrent neural network is proposed for distributed nonconvex optimization subject to globally coupled (in)equality constraints and local bound constraints. Two distributed optimization models, including a resource allocation problem and a consensus-constrained optimization problem, are established, where the objective functions are not necessarily convex, or the constraints do not guarantee a convex feasible set. To handle the nonconvexity, an augmented Lagrangian function is designed, based on which a recurrent neural network is developed for solving the optimization models in a distributed manner, and the convergence to a local optimal solution is proven. For the search of global optimal solutions, a collaborative neurodynamic optimization method is established by utilizing multiple proposed recurrent neural networks and a meta-heuristic rule. A numerical example, a simulation involving an electricity market, and a distributed cooperative control problem are provided to verify and demonstrate the characteristics of the main results.

A Continuous Volatility Forecasting Model Based on Neural Differential Equations and Scale-Similarity

Volatility forecasting is a problem in finance that attracts the attention of both academia and industry. While existing approaches typically utilize a discrete-time latent process that governs the volatility to forecast its future level, volatility is considered to evolve continuously, which makes discrete-time modeling inevitably lose some critical information about the evolution of volatility. In this article, a novel neural-network-based model, Continuous Volatility Forecasting Model, CVFM is proposed to tackle this problem. First, CVFM introduces a continuous-time latent process, whose evolution is modeled with neural differential equations (NDEs), to govern volatility, which effectively captures the continuous evolutionary behavior of volatility in a data-driven way. Second, a scale-similarity-based mechanism is designed to calibrate the evolution equation of the latent process with real-world observations in the absence of high-frequency data. CVFM is tested on six real-world stock index datasets. The main experimental results show that CVFM can significantly outperform existing models in terms of both forecasting accuracy and high-volatility recognition.

Two Novel Noise-Suppression Projection Neural Networks With Fixed-Time Convergence for Variational Inequalities and Applications

This article proposes two novel projection neural networks (PNNs) with fixed-time ( ) convergence to deal with variational inequality problems (VIPs). The remarkable features of the proposed PNNs are convergence and more accurate upper bounds for arbitrary initial conditions. The robustness of the proposed PNNs under bounded noises is further studied. In addition, the proposed PNNs are applied to deal with absolute value equations (AVEs), noncooperative games, and sparse signal reconstruction problems (SSRPs). The upper bounds of the settling time for the proposed PNNs are tighter than the bounds in the existing neural networks. The effectiveness and advantages of the proposed PNNs are confirmed by numerical examples.

Capacitated Clustering via Majorization-Minimization and Collaborative Neurodynamic Optimization

This paper addresses capacitated clustering based on majorization-minimization and collaborative neurodynamic optimization (CNO). Capacitated clustering is formulated as a combinatorial optimization problem. Its objective function consists of fractional terms with intra-cluster similarities in their numerators and cluster cardinalities in their denominators as normalized cluster compactness measures. To obviate the difficulty in optimizing the objective function with factional terms, the combinatorial optimization problem is reformulated as an iteratively reweighted quadratic unconstrained binary optimization problem with a surrogate function and a penalty function in a majorization-minimization framework. A clustering algorithm is developed based on CNO for solving the reformulated problem. It employs multiple Boltzmann machines operating concurrently for local searches and a particle swarm optimization rule for repositioning neuronal states upon their local convergence. Experimental results on ten benchmark datasets are elaborated to demonstrate the superior clustering performance of the proposed approaches against seven baseline algorithms in terms of 21 internal cluster validity criteria.

Supervised Feature Selection via Collaborative Neurodynamic Optimization

As a crucial part of machine learning and pattern recognition, feature selection aims at selecting a subset of the most informative features from the set of all available features. In this article, supervised feature selection is at first formulated as a mixed-integer optimization problem with an objective function of weighted feature redundancy and relevancy subject to a cardinality constraint on the number of selected features. It is equivalently reformulated as a bound-constrained mixed-integer optimization problem by augmenting the objective function with a penalty function for realizing the cardinality constraint. With additional bilinear and linear equality constraints for realizing the integrality constraints, it is further reformulated as a bound-constrained biconvex optimization problem with two more penalty terms. Two collaborative neurodynamic optimization (CNO) approaches are proposed for solving the formulated and reformulated feature selection problems. One of the proposed CNO approaches uses a population of discrete-time recurrent neural networks (RNNs), and the other use a pair of continuous-time projection networks operating concurrently on two timescales. Experimental results on 13 benchmark datasets are elaborated to substantiate the superiority of the CNO approaches to several mainstream methods in terms of average classification accuracy with three commonly used classifiers.

A continuous-time neurodynamic approach in matrix form for rank minimization

This article proposes a continuous-time neurodynamic approach for solving the rank minimization under affine constraints. As opposed to the traditional neurodynamic approach, the proposed neurodynamic approach extends the form of the variables from the vector form to the matrix form. First, a continuous-time neurodynamic approach with variables in matrix form is developed by combining the optimal rank r projection and the gradient. Then, the optimality of the proposed neurodynamic approach is rigorously analyzed by demonstrating that the objective function satisfies the functional property which is called as (2r,4r)-restricted strong convexity and smoothness ((2r,4r)-RSCS). Furthermore, the convergence and stability analysis of the proposed neurodynamic approach is rigorously conducted by establishing appropriate Lyapunov functions and considering the relevant restricted isometry property (RIP) condition associated with the affine transformation. Finally, through experiments involving low-rank matrix recovery under affine transformations and the completion of low-rank real image, the effectiveness of this approach has been demonstrated, along with its superiority compared to the vector-based approach.

Multitrend Conditional Value at Risk for Portfolio Optimization

Trend representation has been attracting more and more attention recently in portfolio optimization (PO) via machine learning methods. It adopts concepts and phenomena from the field of empirical and behavioral finance when little prior knowledge is obtained or strict statistical assumptions cannot be guaranteed. It is used mostly in estimating the expected asset returns, but hardly in measuring risk. To fill this gap, we propose a novel multitrend conditional value at risk (MT-CVaR), which embeds multiple trends and their influences in CVaR. Besides, we propose a novel PO model with this MT-CVaR as the risk metric and then design a solving algorithm based on the interior point method to compute the portfolio. Extensive experiments on six benchmark datasets from diverse financial markets with different frequencies show that MT-CVaR achieves the state-of-the-art investing performance and risk management.

Cardinality Constrained Portfolio Optimization via Alternating Direction Method of Multipliers

Inspired by sparse learning, the Markowitz mean-variance model with a sparse regularization term is popularly used in sparse portfolio optimization. However, in penalty-based portfolio optimization algorithms, the cardinality level of the resultant portfolio relies on the choice of the regularization parameter. This brief formulates the mean-variance model as a cardinality ( l0 -norm) constrained nonconvex optimization problem, in which we can explicitly specify the number of assets in the portfolio. We then use the alternating direction method of multipliers (ADMMs) concept to develop an algorithm to solve the constrained nonconvex problem. Unlike some existing algorithms, the proposed algorithm can explicitly control the portfolio cardinality. In addition, the dynamic behavior of the proposed algorithm is derived. Numerical results on four real-world datasets demonstrate the superiority of our approach over several state-of-the-art algorithms.

An event-triggered collaborative neurodynamic approach to distributed global optimization

In this paper, we propose an event-triggered collaborative neurodynamic approach to distributed global optimization in the presence of nonconvexity. We design a projection neural network group consisting of multiple projection neural networks coupled via a communication network. We prove the convergence of the projection neural network group to Karush-Kuhn-Tucker points of a given global optimization problem. To reduce communication bandwidth consumption, we adopt an event-triggered mechanism to liaise with other neural networks in the group with the Zeno behavior being precluded. We employ multiple projection neural network groups for scattered searches and re-initialize their states using a meta-heuristic rule in the collaborative neurodynamic optimization framework. In addition, we apply the collaborative neurodynamic approach for distributed optimal chiller loading in a heating, ventilation, and air conditioning system.

Sparse Index Tracking With K-Sparsity or ϵ-Deviation Constraint via ℓ0-Norm Minimization

Sparse index tracking, as one of the passive investment strategies, is to track a benchmark financial index via constructing a portfolio with a few assets in a market index. It can be considered as parameter learning in an adaptive system, in which we periodically update the selected assets and their investment percentages based on the sliding window approach. However, many existing algorithms for sparse index tracking cannot explicitly and directly control the number of assets or the tracking error. This article formulates sparse index tracking as two constrained optimization problems and then proposes two algorithms, namely, nonnegative orthogonal matching pursuit with projected gradient descent (NNOMP-PGD) and alternating direction method of multipliers for l0 -norm (ADMM- l0 ). The NNOMP-PGD aims at minimizing the tracking error subject to the number of selected assets less than or equal to a predefined number. With the NNOMP-PGD, investors can directly and explicitly control the number of selected assets. The ADMM- l0 aims at minimizing the number of selected assets subject to the tracking error that is upper bounded by a preset threshold. It can directly and explicitly control the tracking error. The convergence of the two proposed algorithms is also presented. With our algorithms, investors can explicitly and directly control the number of selected assets or the tracking error of the resultant portfolio. In addition, numerical experiments demonstrate that the proposed algorithms outperform the existing approaches.

Event-Triggered Cardinality-Constrained Cooling and Electrical Load Dispatch Based on Collaborative Neurodynamic Optimization

This article addresses event-triggered optimal load dispatching based on collaborative neurodynamic optimization. Two cardinality-constrained global optimization problems are formulated and two event-triggering functions are defined for event-triggered load dispatching in thermal energy and electric power systems. An event-triggered dispatching method is developed in the collaborative neurodynamic optimization framework with multiple projection neural networks and a meta-heuristic updating rule. Experimental results are elaborated to demonstrate the efficacy and superiority of the approach against many existing methods for optimal load dispatching in air conditioning systems and electric power generation systems.

Two-timescale recurrent neural networks for distributed minimax optimization

In this paper, we present two-timescale neurodynamic optimization approaches to distributed minimax optimization. We propose four multilayer recurrent neural networks for solving four different types of generally nonlinear convex-concave minimax problems subject to linear equality and nonlinear inequality constraints. We derive sufficient conditions to guarantee the stability and optimality of the neural networks. We demonstrate the viability and efficiency of the proposed neural networks in two specific paradigms for Nash-equilibrium seeking in a zero-sum game and distributed constrained nonlinear optimization.

Dynamic stock-decision ensemble strategy based on deep reinforcement learning

In a complex and changeable stock market, it is very important to design a trading agent that can benefit investors. In this paper, we propose two stock trading decision-making methods. First, we propose a nested reinforcement learning (Nested RL) method based on three deep reinforcement learning models (the Advantage Actor Critic, Deep Deterministic Policy Gradient, and Soft Actor Critic models) that adopts an integration strategy by nesting reinforcement learning on the basic decision-maker. Thus, this strategy can dynamically select agents according to the current situation to generate trading decisions made under different market environments. Second, to inherit the advantages of three basic decision-makers, we consider confidence and propose a weight random selection with confidence (WRSC) strategy. In this way, investors can gain more profits by integrating the advantages of all agents. All the algorithms are validated for the U.S., Japanese and British stocks and evaluated by different performance indicators. The experimental results show that the annualized return, cumulative return, and Sharpe ratio values of our ensemble strategy are higher than those of the baselines, which indicates that our nested RL and WRSC methods can assist investors in their portfolio management with more profits under the same level of investment risk.

A collaborative neurodynamic optimization algorithm to traveling salesman problem

This paper proposed a collaborative neurodynamic optimization (CNO) method to solve traveling salesman problem (TSP). First, we construct a Hopfield neural network (HNN) with $$n \times n$$ n × n neurons for the n cities. Second, to ensure the convergence of continuous HNN (CHNN), we reformulate TSP to satisfy the convergence condition of CHNN and solve TSP by CHNN. Finally, a population of CHNNs is used to search for local optimal solutions of TSP and the globally optimal solution is obtained using particle swarm optimization. Experimental results show the effectiveness of the CNO approach for solving TSP.

Adipose-Derived Stem Cell Exosomes Inhibit Hypertrophic Scaring Formation by Regulating Th17/Treg Cell Balance

Aiming to reveal the role of ADCS-Exos in secretion of inflammatory factors, Th17 and regulatory T (Treg) cell differentiation from naïve CD4+ T cells in hypertrophic scaring formation and maturation is explored. ELISA, qRT-PCR, and immunoblotting are performed to assay the local inflammatory factors IL-6, IL-10, IL-17A, and TNF-α, and transcriptional factors of RORϒt and Foxp3, in scaring tissue from patients and mice wound models treated with or without ADCS-Exos. Immunohistochemistry staining and immunoblotting are conducted to assay the extracellular matrix (ECM) deposition in vitro and in vivo. The results show that IL-6, IL-10, IL-17A, TNF-α, RORϒt, and Foxp3 are increased on mRNA and protein levels in hypertrophic scaring compared with atrophic scaring and normal skin. Naïve CD4⁺ T cells treated with ADCS-Exos in vitro can produce significantly less IL-6, IL-17A, TNF-α, and RORϒt and more IL-10 and Foxp3 on mRNA and protein levels. In addition, mice in ADSC-Exos-treated group demonstrate less collagen deposition; decreased IL-17A, TNF-α, and RORϒt; and increased IL-10 and Foxp3 production.

Hash Bit Selection Based on Collaborative Neurodynamic Optimization

Hash bit selection determines an optimal subset of hash bits from a candidate bit pool. It is formulated as a zero-one quadratic programming problem subject to binary and cardinality constraints. In this article, the problem is equivalently reformulated as a global optimization problem. A collaborative neurodynamic optimization (CNO) approach is applied to solve the problem by using a group of neurodynamic models initialized with particle swarm optimization iteratively in the CNO. Lévy mutation is used in the CNO to avoid premature convergence by ensuring initial state diversity. A theoretical proof is given to show that the CNO with the Lévy mutation operator is almost surely convergent to global optima. Experimental results are discussed to substantiate the efficacy and superiority of the CNO-based hash bit selection method to the existing methods on three benchmarks.

The Fertility Status of the Married People Living with HIV/AIDS in China

In order to analyze the fertility status of the married people living with human immunodeficiency virus (HIV)/acquired immune deficiency syndrome (AIDS) (PLHA) of reproductive age in China, a sample of married PLHAs aged 22-45 in China is selected by using a stratified cluster sampling method. All participants are face-to-face interviewed with a structured questionnaire. Among them, the fertility status and its influencing factors of 366 PLHAs are statistically analyzed. Experimental results show that married PLHA of reproductive age in China has a high proportion of having children. The fertility status and fertility intention of females are higher than that of males. The proportion of unwanted pregnancies after the HIV + diagnosis of females is high.

Study on the Effect of Hope Theory Combined with Psychological Intervention on the Improvement of Prognosis

In order to evaluate the effect of the hope theory combined with psychological intervention on patients with intracranial aneurysms after surgical treatment, a total of 98 patients with intracranial aneurysm surgery admitted to our hospital from March 2019 to January 2021 were analyzed. According to the random number table method, all patients are divided into two groups: the traditional group and the experimental group. After intracranial aneurysm surgery, the patients of the traditional group and of the joint group are treated with conventional nursing and hope theory combined with psychological intervention nursing mode, respectively. The results demonstrate that the hope theory combined with psychological intervention can improve the level of postoperative patients with intracranial aneurysm life hope, self-efficacy, and postoperative quality of life.

Efficacy and Safety of Radical Resection of Rectal Cancer Combined with Selective Lateral Lymph Node Dissection in the Treatment of Low Rectal Cancer under Meta-analysis

Rectal cancer mostly occurs in the middle and low position in China, and many anatomical evidence has confirmed that Lateral Lymph Node Metastasis (LLNM) exists in middle and low rectal cancer. Laparoscopic surgery can penetrate into the pelvic cavity and magnify and narrow the visual field, which is helpful for lymph node dissection and vascular nerve protection, while it has minimally invasive characteristics and is considered to be more suitable for LLND. Relevant articles published from January 2000 to May 2022 are searched using "Rectal cancer, Lateral lymph node dissection, Radical resection of rectal cancer, Low rectal cancer, Laparoscopic therapy, Treatment of rectal cancer" as test terms, analyzed and assessed using Rev Man 5.3 software and Stata software to assess the risk bias of included references, and heterogeneity among each study is evaluated using Q test and heterogeneity (I2). The experimental results show that there is no heterogeneity among the studies (I2 = 8.46%). The heterogeneity of lymphatic metastasis in the included literature is evaluated, and the results show that there is heterogeneity between the studies (I2 = 52.06%).

Bio-Inspired Machine Learning for Distributed Confidential Multi-Portfolio Selection Problem

The recently emerging multi-portfolio selection problem lacks a proper framework to ensure that client privacy and database secrecy remain intact. Since privacy is of major concern these days, in this paper, we propose a variant of Beetle Antennae Search (BAS) known as Distributed Beetle Antennae Search (DBAS) to optimize multi-portfolio selection problems without violating the privacy of individual portfolios. DBAS is a swarm-based optimization algorithm that solely shares the gradients of portfolios among the swarm without sharing private data or portfolio stock information. DBAS is a hybrid framework, and it inherits the swarm-like nature of the Particle Swarm Optimization (PSO) algorithm with the BAS updating criteria. It ensures a robust and fast optimization of the multi-portfolio selection problem whilst keeping the privacy and secrecy of each portfolio intact. Since multi-portfolio selection problems are a recent direction for the field, no work has been done concerning the privacy of the database nor the privacy of stock information of individual portfolios. To test the robustness of DBAS, simulations were conducted consisting of four categories of multi-portfolio problems, where in each category, three portfolios were selected. To achieve this, 200 days worth of real-world stock data were utilized from 25 NASDAQ stock companies. The simulation results prove that DBAS not only ensures portfolio privacy but is also efficient and robust in selecting optimal portfolios.

Effects of Irrational Use of Antibiotics on Intestinal Health of Children with Extraintestinal Infectious Diseases

The effects of different antibiotic treatment regimens on intestinal function and flora distribution in children with extraintestinal infectious diseases are explored. A total of 150 cases of extraintestinal infectious diseases admitted to our hospital from January 2021 to January 2022 and 50 healthy subjects during the same period were selected for the study. These 150 children were randomly divided into cephalosporin group, piperacillin group, and combined group and were successively treated with ceftazidime, piperacillin, and two drug combination regimens. The efficacy of the drug, intestinal microflora, intestinal mucosal barrier function, and incidence of antibiotic-associated diarrhea (AAD) were compared among the different groups. The experimental results showed that ceftazidime combined with piperacillin can effectively improve the intestinal health of children with extraintestinal infectious diseases but destroy the microecological environment of intestinal flora, affect the intestinal mucosal barrier function, and increase the risk of AAD.

The Status Quo of Criminal Responsibility for Aflatoxin Pollution in China: From the Perspective of Judgment Analysis

With the development of the economy, the food safety problems caused by aflatoxin have become increasingly prominent. With regard to the control of aflatoxin pollution, the Chinese government has promulgated a series of legal documents on food safety related to aflatoxin pollution, such as the formulation of industry standards for allowable limits of aflatoxin and various penalties for violators. Although these measures have achieved good results to some extent, there are still many legal problems. This study reviews the current situation of aflatoxin pollution control in food in China. The court judgment documents related to aflatoxin pollution from January 1st 2014 to January 1st 2020 are investigated to analyze the accountability status of aflatoxin pollution treatment in China. Furthermore, this study mainly cross verified the above problems by means of the literature survey and an organization interview and proposed solutions on the basis of in-depth analysis of their causes. Finally, some suggestions are put forward to solve the problem of aflatoxin pollution accountability in China.

Investigation of the Immunoprotective Effect of Zinc on Ovalbumin Induced BALB/C Male Mice Based on NF-KB Signaling Pathway

Allergic rhinitis is one of the common chronic inflammatory diseases of the nasal mucosa. In order to investigate the effect of zinc on ovalbumin induced allergic rhinitis in BALB/C male mice based on NF-KB signaling pathway, thirty BALB/C male mice are randomly divided into three groups: control group, ovalbumin induced allergic rhinitis asthma group and zinc intervention group. The experimental results show that Zinc supplementation in allergic asthma mice with allergic rhinitis correct the immune response of TH2 cells by inhibiting THE NF-KB signaling pathway, reduce the infiltration of inflammatory cells into lung nasal tissue, and reduce airway co-hyperreactivity to improve the clinical symptoms of asthma and play an immune protective role.

Study on the Correlation between the Prevalence of Venous Thromboembolism in Kazak Pregnant and Lying-In Women in Xinjiang

In order to reveal the correlation between the prevalence of venous thromboembolism in Kazak pregnant and lying-in women in Xinjiang, the polymorphisms in the promoter region and coding region of the TAFI gene and the interaction of environmental factors are investigated. In this study, determination and analysis of anticoagulation indexes are conducted. The activity of antithrombin III and protein C is measured by chromogenic substrate method, and the activity of protein S is measured by coagulation method. Besides, the detection of APC-R is performed by APC-APTT method. The experimental results show that the prevalence rate of hereditary thrombophilia + DVT among Kazak pregnant women in Xinjiang is 33.8%, and the prevalence rates of AT-III deficiency, PC deficiency, PS deficiency, APCR, and Hcy are 17.5%, 16.7%, 22.0%, 23.7%, and 26.8%, respectively. Also, the genotype frequency and allele frequency distribution of each group are in line with Hardy-Weinberg equilibrium (P > 0.05). The comparison result indicates that the gene frequency has reached a genetic balance and is representative of the population. It is clearly evident that the polymorphisms of prothrombin gene rs3136447 and rs5896 may be associated with hereditary thrombophilia in Xinjiang Kazaks.

Analysis of Stress Response and Analgesic Effect of Remazolam Combined with Etomidate in Painless Gastroenteroscopy

In order to explore more ideal intravenous anesthesia drug in clinical practice, the analgesic effect of remazolam combined with etomidate in painless gastroenteroscopy and its effect on stress response is investigated. A total of 100 patients are selected for the gastric disease screening, and they are randomly divided into the single-drug group and composite group, with 50 cases in each group. Etomidate, mazzolone, and etomidate are used to anesthetize the patients, and then, the effects of different solutions on analgesia, sedation, and stress response are compared and analyzed, and the adverse reactions are improved. The etomidate and red horse azole shimron composite etomidate anesthesia were applied, and the comparative analysis of different solutions of analgesic, sedative effect, and response to stress is conducted. Then, the improvement of adverse reactions is analyzed. The experimental results demonstrate that remazolam combined with etomidate anesthesia can reduce the level of pain mediators and enhance the analgesia and sedation effect. Meanwhile, combined anesthesia can reduce the stress response and adverse reactions of patients and shorten the examination period effectively.

Intelligent automatic sleep staging model based on CNN and LSTM

Since electroencephalogram (EEG) is a significant basis to treat and diagnose somnipathy, sleep electroencephalogram automatic staging methods play important role in the treatment and diagnosis of sleep disorders. Due to the characteristics of weak signals, EEG needs accurate and efficient algorithms to extract feature information before applying it in the sleep stages. Conventional feature extraction methods have low efficiency and are difficult to meet the time validity of fast staging. In addition, it can easily lead to the omission of key features owing to insufficient a priori knowledge. Deep learning networks, such as convolutional neural networks (CNNs), have powerful processing capabilities in data analysis and data mining. In this study, a deep learning network is introduced into the study of the sleep stage. In this study, the feature fusion method is presented, and long-term and short-term memory (LSTM) is selected as the classification network to improve the accuracy of sleep stage recognition. First, based on EEG and deep learning network, an automatic sleep phase method based on a multi-channel EGG is proposed. Second, CNN-LSTM is used to monitor EEG and EOG samples during sleep. In addition, without any signal preprocessing or feature extraction, data expansion (DA) can be realized for unbalanced data, and special data and non-general data can be deleted. Finally, the MIT-BIH dataset is used to train and evaluate the proposed model. The experimental results show that the EEG-based sleep phase method proposed in this paper provides an effective method for the diagnosis and treatment of sleep disorders, and hence has a practical application value.

Early Diagnosis and Prediction of Death Risk in Patients with Sepsis by Combined Detection of Serum PCT, BNP, Lactic Acid, and Apache II Score

In order to investigate the expression levels of procalcitonin (PCT), B-type brain natriuretic peptide (BNP), and lactic acid (Lac) in serum of patients with sepsis, a retrospective analysis is conducted. 80 sepsis patients admitted to the ICU of our hospital from January 2019 to June 2020 are selected, and the application value of these factors combined with Apache II score in early diagnosis and prediction of death risk is analyzed. All patients are classified into survival group (n = 57) and death group (n = 23), and examined by blood routine. Lac, PCT, and BNP, and the serum PCT, BNP, and Lac levels were compared between the nonsepsis group and the control group. Furthermore, Acute Physiology and Chronic Health Status scoring System II (Apache II) is applied to evaluate the score difference between the sepsis group and the control group. The ROC curve demonstrates that PCT, BNP, and Lac combined with Apache II score can obtain high value for early diagnosis of sepsis. Compared with nonsepsis patients, the scores of serum Lac, PCT, and BNP and Apache II are significantly higher in sepsis patients. It is clearly evident that the combined detection of those indicators is valuable for early diagnosis and prediction of death, and will be suitable for widespread clinical application.

Sparse signal reconstruction via collaborative neurodynamic optimization

In this paper, we formulate a mixed-integer problem for sparse signal reconstruction and reformulate it as a global optimization problem with a surrogate objective function subject to underdetermined linear equations. We propose a sparse signal reconstruction method based on collaborative neurodynamic optimization with multiple recurrent neural networks for scattered searches and a particle swarm optimization rule for repeated repositioning. We elaborate on experimental results to demonstrate the outperformance of the proposed approach against ten state-of-the-art algorithms for sparse signal reconstruction.

The Correlation between Obstructive Sleep Apnea and Retinal Vein Obstruction: A Meta-Analysis and Systematic Review

Despite of inadequate evidence, previous studies have demonstrated a potential correlation between obstructive sleep apnea (OSA) and retinal vein occlusion (RVO). In this study, a meta-analysis is conducted to investigate the correlation between OSA and RVO. Databases are searched for relevant literatures up to July 14, 2021, including PubMed, Embase, Cochrane, Web of Science, CNKI, WanFang, VIP, and Chinese Biomedical Literature Database (CBM). The odds ratio (OR) and 95% confidence interval (CI) are estimated to evaluate the correlation between OSA and RVO. Six articles were finally enrolled, including 36,086 subjects from 5 case-controlled studies and 1 cohort study. It is clearly evident that the RVO risk is higher among OSA patients than non-OSA patients (OR = 3.24, 95% CI = 3.24). The results of sensitivity analysis indicate that the present meta-analysis is robust and reliable. Furthermore, Egger's test for publication bias is performed with P = 0.195, and the results reveal no significant publication bias. The findings demonstrate that OSA is significantly correlated with RVO, and OSA is a risk factor for RVO.

The Clinical Noteworthiness of Plasma NT-ProBNP Standard in Sufferers with Cardiogenic Cerebral Embolism and Its Diagnostic Value for Such Sufferers

In order to explore the clinical noteworthiness of plasma NT-proBNP standards in sufferers with cardiogenic cerebral embolism and its diagnostic value for such sufferers, a retrospective study is conducted by the clinical data of sufferers with cerebral embolism. 100 sufferers with cerebral embolism admitted to our hospital from January 2018 to December 2020 are selected. According to the heparin-like drug therapy of acute ischemic stroke test (TOAST) classification criteria, they are divided into cardiac sufferers with cerebral embolism set (43 cases) and noncardiac cerebral embolism set (57 cases). The analysis results show the correlation between serum NT-proBNP standard and neurological impairment score. The detection of-proBNP standard can be used as a diagnostic indicator of disease severity and prognosis for sufferers with cardiogenic cerebral embolism.

Effect of Ruanjian Xiaoying Granules on Hashimoto Rats with Depression of Liver and Deficiency of Spleen and Effect on Intestinal Microflora

In order to investigate the effect of Ruanjian Xiaoying Granule, experiments were conducted on the intestinal flora of rats with liver depression and spleen deficiency. 48 SPF grade rats are used as the object, and 12 rats are randomly selected as the normal control group. The Hashimoto rat model of liver depression and spleen deficiency type by drug intervention is constructed by the remaining rats. They are randomly divided into three groups: the model group, the traditional Chinese medicine group, and the Jinshuibao group. The normal group and model group are given 2 ml of distilled water twice a day, and the traditional Chinese medicine group is given the Ruanjian Xiaoying granule group (12.96 g/kg/day) twice a day. The Jinshuibao capsule is dissolved in water and given orally at a dose of 0.45 g/kg/day twice a day. After 12 weeks of intervention, the effect is evaluated, and the levels of serum TGAb, TPOAb, and bacterial diversity are compared. Experimental results show that Ruanjian Xiaoying granules can promote the regulation of flora levels in Hashimoto rats with liver depression and spleen deficiency.

Risk Factors and Distribution Characteristics of Intracranial and Intracranial Artery Stenosis in Young Sufferers with Ischemic Stroke

In order to explore the risk factors of intracranial and intracranial arterial stenosis, the distribution of young ischemic stroke sufferers with intracranial and intracranial arterial stenosis and the related are analyzed. In this study, a total of 213 young sufferers with ischemic stroke (IS) admitted to our hospital from February 2019 to September 2021 are selected. According to the CT diagnosis of intracranial artery stenosis (AS), 213 patients are divided into two groups, with 86 in the AS Group and 127 in the non-AS Group. To analyze the distribution of intracranial and intracranial AS in young patients with ischemic stroke, 86 patients with AS are examined by carotid B-mode ultrasound. Furthermore, a univariate analysis is performed on the relevant indicators of the sufferers in the cancer (CA) set and the two sets without CA, and then, the indicators with statistically extensive disparity were selected for multivariate logistic regression analysis of the risk factors for CA symptoms. The results show 50% of the sufferers with moderate or severe ischemic CA in young adults and 63.95% of the sufferers with intracranial artery stenosis. It is clearly evident that the main risk factors affecting the occurrence of intracranial and intracranial arteries in young IS are hypertension and long-term smoking, long-term drinking, and hyperlipidemia.

Boolean matrix factorization based on collaborative neurodynamic optimization with Boltzmann machines

This paper presents a collaborative neurodynamic approach to Boolean matrix factorization. Based on a binary optimization formulation to minimize the Hamming distance between a given data matrix and its low-rank reconstruction, the proposed approach employs a population of Boltzmann machines operating concurrently for scatter search of factorization solutions. In addition, a particle swarm optimization rule is used to re-initialize the neuronal states of Boltzmann machines upon their local convergence to escape from local minima toward global solutions. Experimental results demonstrate the superior convergence and performance of the proposed approach against six baseline methods on ten benchmark datasets.

A metaheuristic-based framework for index tracking with practical constraints

Recently, numerous investors have shifted from active strategies to passive strategies because the passive strategy approach affords stable returns over the long term. Index tracking is a popular passive strategy. Over the preceding year, most researchers handled this problem via a two-step procedure. However, such a method is a suboptimal global-local optimization technique that frequently results in uncertainty and poor performance. This paper introduces a framework to address the comprehensive index tracking problem (IPT) with a joint approach based on metaheuristics. The purpose of this approach is to globally optimize this problem, where optimization is measured by the tracking error and excess return. Sparsity, weights, assets under management, transaction fees, the full share restriction, and investment risk diversification are considered in this problem. However, these restrictions increase the complexity of the problem and make it a nondeterministic polynomial-time-hard problem. Metaheuristics compose the principal process of the proposed framework, as they balance a desirable tradeoff between the computational resource utilization and the quality of the obtained solution. This framework enables the constructed model to fit future data and facilitates the application of various metaheuristics. Competitive results are achieved by the proposed metaheuristic-based framework in the presented simulation.

A one-layer recurrent neural network for nonsmooth pseudoconvex optimization with quasiconvex inequality and affine equality constraints

As two important types of generalized convex functions, pseudoconvex and quasiconvex functions appear in many practical optimization problems. The lack of convexity poses some difficulties in solving pseudoconvex optimization with quasiconvex constraint functions. In this paper, we propose a one-layer recurrent neural network for solving such problems. We prove that the state of the proposed neural network is convergent from the feasible region to an optimal solution of the given optimization problem. We show that the proposed neural network has several advantages over the existing neural networks for pseudoconvex optimization. Specifically, the proposed neural network is applicable to optimization problems with quasiconvex inequality constraints as well as affine equality constraints. In addition, parameter matrix inversion is avoided and some assumptions on the objective function and inequality constraints in existing results are relaxed. We demonstrate the superior performance and characteristics of the proposed neural network with simulation results in three numerical examples.

Cardinality-constrained portfolio selection based on collaborative neurodynamic optimization

Portfolio optimization is one of the most important investment strategies in financial markets. It is practically desirable for investors, especially high-frequency traders, to consider cardinality constraints in portfolio selection, to avoid odd lots and excessive costs such as transaction fees. In this paper, a collaborative neurodynamic optimization approach is presented for cardinality-constrained portfolio selection. The expected return and investment risk in the Markowitz framework are scalarized as a weighted Chebyshev function and the cardinality constraints are equivalently represented using introduced binary variables as an upper bound. Then cardinality-constrained portfolio selection is formulated as a mixed-integer optimization problem and solved by means of collaborative neurodynamic optimization with multiple recurrent neural networks repeatedly repositioned using a particle swarm optimization rule. The distribution of resulting Pareto-optimal solutions is also iteratively perfected by optimizing the weights in the scalarized objective functions based on particle swarm optimization. Experimental results with stock data from four major world markets are discussed to substantiate the superior performance of the collaborative neurodynamic approach to several exact and metaheuristic methods.