The problem of predicting the three-dimensional (3-D) structure a protein from its one-dimensional sequence has been called "holy grail molecular biology", and it become an important part structural genomics projects. Despite rapid developments in computer technology computational intelligence, remains challenging fascinating. In this paper, to solve we propose multi-objective evolutionary algorithm. We decompose energy function Chemistry at HARvard Macromolecular Mechanics force fields into...

The result of Chinese housing market continues to prosper or not is related the development China, and further it also has an impact on world finance. Thus forecasting house price index very important challenging. In this paper we propose unsupervised learnable neuron model (DNM) by including nonlinear interactions between excitation inhibition dendrites. We use DNM fit House Price Index (HPI) data then forecast trends market. To verify effectiveness DNM, a traditional statistical (i.e.,...

With the rapid development of artificial neural networks, recent studies have shown that dendrites play a vital role in computations. In this study, we propose dendritic neuron model called approximate logic (ALDNM) to solve classification problems. The ALDNM can be divided into four layers: synaptic layer, membrane and soma body. Considering limitation back-propagation (BP) algorithm, employ heuristic optimization social learning particle swarm algorithm (SL-PSO) train ALDNM. order...

Recent neurological studies have shown the importance of dendrites in neural computation. In this paper, a neuron model with dendrite morphology, called logic dendritic (LDNM), is proposed for classification. This consists four layers: synaptic layer, membrane and soma body. After training, LDNM simplified by proprietary pruning mechanisms further transformed into circuit classifier. Moreover, to address high-dimensional challenge, feature selection employed as dimension reduction method...

Background Efficient identification of microbe-drug associations is critical for drug development and solving problem antimicrobial resistance. Traditional wet-lab method requires a lot money labor in identifying potential associations. With machine learning publication large amounts biological data, computational methods become feasible. Methods In this article, we proposed model neighborhood-based inference (NI) restricted Boltzmann (RBM) to predict association (NIRBMMDA) by using...

The development of explainable machine learning methods is attracting increasing attention. Dendritic neuron models have emerged as powerful in recent years. However, providing explainability to a dendritic model has not been explored. In this study, we propose logic (LDNM) and discuss its characteristics. Then, use tree-based called the morphology decision trees (MDT) approximate LDNM gain explainability. Specifically, trained simplified by proprietary structure pruning mechanism. pruned...

The main purpose of this paper is to propose a neuron model based on dendritic mechanisms and phase space reconstruction (PSR) analyze XAUUSD (Gold/U.S. Dollar), EURUSD (Euro Fx/U.S. GBPJPY (British Pound/Japanese Yen), USDJPY (U.S. Dollar/Japanese Yen). We reconstruct the time series exchange rate by using PSR prove that attractors exist for systems constructed. In way, it able us observe obtained intuitively in three-dimensional search space, which make easier characteristics dynamic...

Warts are a prevalent condition worldwide, affecting approximately 10% of the global population. In this study, machine learning method based on dendritic neuron model is proposed for wart-treatment efficacy prediction. To prevent premature convergence and improve interpretability training process, an effective heuristic algorithm, i.e., covariance matrix adaptation evolution strategy (CMA-ES), incorporated as model. Two common datasets efficacy, cryotherapy dataset immunotherapy dataset,...

Predicting the three-dimensional structure of a protein from its amino acid sequence is an important issue in field computational biology and bioinformatics. It remains as unsolved problem attract enormous researchers' interests. Different most conventional methods, we model prediction (PSP) multi-objective optimization problem. A three-objective energy function based on three physical terms designed to evaluate conformation. evolutionary strategy algorithm coupled with preference...

Assessing building energy consumption is of paramount significance in sustainability and efficiency (EE) studies. The development an accurate EE prediction model pivotal for optimizing resources facilitating effective planning. Traditional physical modeling approaches are encumbered by high complexity protracted cycles. In this paper, we introduce a novel evolutionary dendritic neural regression (EDNR) tailored to forecasting residential EE. Acknowledging the vast landscape EDNR weight...

Pneumonia has long been a significant concern in global public health. With the advancement of convolutional neural networks (CNNs), new technological methods have emerged to address this challenge. However, application CNNs pneumonia diagnosis still faces several critical issues. First, datasets used for training models often suffer from insufficient sample sizes and imbalanced class distributions, leading reduced classification performance. Second, although can automatically extract...

Abstract Efficient identification of microbe-drug associations is critical for drug development and solving problem antimicrobial resistance. Traditional wet-lab method requires a lot money labor in identifying potential associations. With machine learning large amounts biological data, computational methods become feasible. In this paper, we proposed model Neighborhood-based Inference (NI) Restricted Boltzmann Machine (RBM) to predict Microbe-Drug Association (NIRBMMDA) by using multisource...

The logic dendritic neuron model (LDNM), which is inspired by natural neurons, has emerged as a novel machine learning in recent years. However, studies have also shown that the classification performance of LDNM restricted backpropagation (BP) algorithm. In this study, we attempt to use heuristic algorithm called gradient-based optimizer (GBO) train LDNM. First, describe architecture Then, propose specific neuronal structure pruning mechanisms for simplifying after training. Later, show how...