Weight Vector Research Articles

Stochastic analysis of frequency-domain adaptive filters

This study investigates the convergence behaviors of a family of frequency-domain adaptive filters (FDAFs) under both exact- and under-modeling situations. The stochastic analysis is conducted by transforming the frequency-domain equations into their time-domain counterparts. We discuss the transient and steady-state convergence behaviors of four FDAF versions, i.e., the constrained FDAFs with and without step-normalization, the unconstrained FDAFs with and without step-normalization, and we also present the upper bounds of step size for mean stability and mean-square stability. Starting from the expression for the steady-state mean weight vector, this study investigates whether the FDAFs can converge to unknown system impulse responses and optimum Wiener solutions. Moreover, we provide the closed-form minimum mean-square error (MMSE) that each FDAF can achieve. The difference between the current work and our previous one is threefold. First, the presented time-domain analysis is much easier to handle and has a more explicit physical meaning than that in the frequency domain. Second, we here consider an arbitrary overlap factor between consecutive blocks, while our previous analysis only focuses on 50% overlap. Third, the presented MMSE expressions and excess mean-square error (EMSE) approximations have not been given before. Simulations reveal high consistency between the experimental and theoretical results.

A decomposition-based multi-objective evolutionary algorithm using infinitesimal method

Multi-Objective Evolutionary Algorithm based on decomposition (MOEA/D) has been extensively employed to address a diverse array of real-world challenges and has shown excellent performance. However, the initial collection of aggregate weight vectors proves unsuitable for multi-objective optimization problems (MOPs) featuring intricate Pareto front (PF) structures, and the solving performance will be greatly affected when MOEA/D solves these irregular MOPs. In light of these challenges, a refined MOEA/D algorithm utilizing infinitesimal method is proposed. This algorithm incorporates the notion of global decomposition stemming from infinitesimal method to streamline the feature information of PF, thereby facilitating the adjustment of the weight vector towards optimal distribution. Consequently, enhancements in resource allocation efficiency and algorithmic performance are achieved. In the empirical investigation, the algorithm’s performance is tested on 28 benchmarks from ZDT,DTLZ and WFG test suits.Wilcoxon’s rank-sum test and Fredman’s test were carried out on performance metrics, which proved that the proposed MOEA/D-DKS was superior to other comparison algorithms.

Environmentally and statistically robust matched-field source localization based on information geometry principles.

Matched-field processing (MFP) achieves underwater source localization by measuring the correlation between the array and replica signals, with traditional MFP being equivalent to estimating the Euclidean distance between the data cross-spectral density matrix (CSDM) and replica matrices. However, in practical applications, random inhomogeneities in the marine environment and inaccurate estimation of CSDM reduce MFP performance. The traditional minimum variance matched-field processor with environmental perturbation constraints perturbs a priori environment parameters to obtain linear constraints and yields the optimal weight vectors as the replica vectors. In this paper, within the framework of information geometry, the geometric properties of CSDMs as semi-positive definite and Hermitian enable CSDMs to be described as points in a Riemannian manifold. Source localization can be achieved by quantifying the similarity between the CSDMs as the geodesic distance between the points on the manifold. This paper introduces a constrained replica CSDM composed of perturbed replica vectors and proposes a robust matched-field processor based on two non-Euclidean distances: the Riemannian distance and the modified Jensen-Shannon distance. Simulations and experimental results demonstrate that the proposed processors are more robust against environmental and statistical mismatches than traditional processors and can also reduce sidelobe level and improve the resolution.

A sampling-based acceleration method for heterogeneous chiplet NoC simulations

To tackle the challenges posed by Moore’s Law, Chiplet technology emerges as a promising solution. Chiplets comprising CPUs and accelerators are connected by Networks-on-Chip (NoC) for large-scale integration and efficient communications. However, the slow simulation speed of NoCs has become a bottleneck, limiting the overall performance of chiplet simulations. Existing solutions only focus on accelerating NoC simulation in homogeneous architecture. In this paper, we introduce a novel TOPSIS-based Heterogeneous Trace Score-sampling method (THTS) for faster NoC simulation in heterogeneous architecture. THTS enables quick and accurate sampling of representative NoC traces. Additionally, we propose a weight exploration model to further enhance sampling accuracy. Compared with the traditional NoC sampling method (NoCLabs), THTS reduces the error of the average packet latency by 22.17% and the total simulation time by 1.6 folds. THTS estimates the NoC performance with an average loss less than 5%, while speeding up the NoC simulation by up to 3 times. In addition, under different weight space sizes, the time required for the weight exploration model to solve the optimal weight vector is within seconds, remarkably speeding up the solution process. Notably, the predicted NoC simulation error under the optimal weight is only 1.42%.

Supporting multi-criteria decision-making processes with unknown criteria weights

Decision support systems are crucial in today’s tech-driven world, assisting decision-makers with complex choices. Determining criteria weights is a paramount aspect, significantly influencing outcomes. Traditionally, criteria weights are derived from objective measures, subjective expert knowledge, or a combination of both, each with its own strengths and limitations. This paper presents a novel approach for addressing unknown criteria relevance by systematically generating weight vectors, thus exploring a broader decision problem space. The proposed methodology is adaptable to various multi-criteria methods, enhancing its applicability across different scenarios. Its effectiveness is empirically validated through two practical examples: Glomerular Filtration Rate (GFR) evaluation and bridge construction method selection, demonstrating its broad applicability. Comparative analysis with existing objective weighting techniques reveals the limitations of current approaches and highlights the improved decision-making capabilities enabled by the proposed method. This research addresses a critical gap in the reliability and robustness of existing methods, particularly in situations with unknown criteria weights. Key contributions include a new decision-making methodology and an innovative ranking formulation using fuzzy sets, with empirical verification strengthening the utility of the approach. This paper offers a promising solution for advancing multi-criteria decision analysis, especially in complex scenarios with uncertain criteria relevance.

A Method for Determining the Importance of Critical Emergency Indicators Based on Multi-granularity Uncertain Language

In view of the complexity of emergencies and the subjectivity of decision-makers, a method of determining key emergency indicators based on multi-granularity uncertainty language is proposed. Firstly, decision members use preferred uncertain language phrases to represent the importance of each key indicator and use transformation functions to carry out the consistent transformation of this multi-granularity uncertain language information. Secondly, the group evaluation vector is obtained by using the extended weighted average operator of uncertainty, and then the weight vector of each key index is obtained by using the decision theory of uncertain language. Finally, an example is given to verify the practicability and effectiveness of the proposed method.

Multi‐Objective Evolutionary Algorithm Based on Decomposition With Orthogonal Experimental Design

ABSTRACTMulti‐objective evolutionary optimisation algorithms (MOEAs) have become a widely adopted way of solving the multi‐objective optimisation problems (MOPs). The decomposition‐based MOEAs demonstrate a promising performance for solving regular MOPs. However, when handling the irregular MOPs, the decomposition‐based MOEAs cannot offer a convincing performance because no intersection between weight vector and the Pareto Front (PF) may lead to the same optimal solution assigned to the different weight vectors. To solve this problem, this paper proposes an MOEA based on decomposition with the orthogonal experimental design (MOEA/D‐OED) that involves the selection operation, Orthogonal Experimental Design (OED) operation, and adjustment operation. The selection operation is to judge the unpromising weight vectors based on the history data of relative reduction values and convergence degree. The OED method based on the relative reduction function could make an explicit guidance for removing the worthless weight vectors. The adjustment operation brings in an estimation indicator of both diversity and convergence for adding new weight vectors into the interesting regions. To verify the versatility of the proposed MOEA/D‐OED, 26 test problems with various PFs are evaluated in this paper. Empirical results have demonstrated that the proposed MOEA/D‐OED outperforms eight representative MOEAs on MOPs with various types of PFs, showing promising versatility. The proposed algorithm shows highly competitive performance on all the various MOPs.

A novel hybrid fuzzy analytical hierarchy process–game theory model for prioritizing factors affecting the deterioration of water pipelines

Water pipes face significant aging and degradation problems due to several pipe-related, soil-related, operational, and environmental factors. Hence, the paramount objective of this research paper is to prioritize the criticality of the factors affecting the deterioration of water pipes in Hong Kong. The framework of the developed model is envisioned based on two main modules, namely weight computation and weight aggregation. The first module incorporates identifying and categorizing water deterioration factors. Then, the relative importance priorities of water deterioration factors are scrutinized using seven weight computation methods. These methods encompass analytical hierarchy process (AHP), Monte Carlo AHP, fuzzy AHP, magnitude-based fuzzy AHP, total difference-based fuzzy AHP, spherical fuzzy AHP and Pythagorean fuzzy AHP. In this regard, fuzzy-based and Monte Carlo-based methods are leveraged to circumvent the critical shortcomings of classical AHP. The performances of weight computation methods are analyzed using statistical evaluation indicators of satisfactory index (SAT) and distance between weights (WD). The second module is a hybrid meta-heuristic-based game theory model designated for compiling the importance weights of deterioration factors obtained from the first module. In this context, a set of widely acclaimed meta-heuristics are exploited and examined for optimizing the significance of deterioration factors. Analytical results exemplified that soil-related factors implicate the deterioration process more than pipe-related, operational-related, and environmental-related factors. It was also inferred that water pressure (6.64%) is the most significant factor influencing water pipe deterioration followed by internal corrosion and protection method (6.11%), and then soil corrosivity (6.05%). On the other hand, length (1.93%), rain deficit (1.97%), and street block length (2.33%) constitute the least influencers on water pipe deterioration. Results also demonstrated that spherical FAHP outperformed other variants of AHP accomplishing SAT and WD of 0.065 and 0.057, respectively. Comparative analysis revealed that particle swarm optimization-based game theory is a better mechanism than the remainder of meta-heuristic-based game theory models in obtaining a more accurate compromised-based weighting vector to the experts’ judgments. It is envisaged that this research can assist the water supplies department in identifying, assessing, and prioritizing the impairment causes of water pipelines in Hong Kong. It can also aid in establishing more accurate deterioration models and more cost-effective maintenance intervention programs.

WLB-DSCA method for strictly non-circular signals in coprime array

Widely linear beamforming (WLB) performs better than conventional adaptive beamforming, however its performance is restricted by array geometry. Coprime array can improve the beamforming performance compared with uniform linear array given the number of sensors. In this paper, a WLB with difference-sum co-array (WLB-DSCA) is devised for strictly non-circular (SNC) signals in coprime array. We vectorize the augmented covariance matrix of coprime array to produce a DSCA. To efficiently exploit all information of continuous and discontinuous virtual sensors in DSCA, we introduce the sparse representation of DSCA. A norm minimization optimization problem is formulated and then solved to localize the SNC signals in DSCA. We formulate a joint covariance and pseudo covariance matrices optimization problem to determine the powers of SNC signals. The augmented interference-plus-noise covariance matrix (AINCM) is reconstructed. Lastly, the augmented weight vector of the proposed WLB-DSCA is computed. Numerical results validate that the proposed WLB-DSCA is capable of handling SNC signals in coprime array.

Double Decomposition and Fuzzy Cognitive Graph-Based Prediction of Non-Stationary Time Series.

Deep learning models, such as recurrent neural network (RNN) models, are suitable for modeling and forecasting non-stationary time series but are not interpretable. A prediction model with interpretability and high accuracy can improve decision makers' trust in the model and provide a basis for decision making. This paper proposes a double decomposition strategy based on wavelet decomposition (WD) and empirical mode decomposition (EMD). We construct a prediction model of high-order fuzzy cognitive maps (HFCM), called the WE-HFCM model, which considers interpretability and strong reasoning ability. Specifically, we use the WD and EDM algorithms to decompose the time sequence signal and realize the depth extraction of the signal's high-frequency, low-frequency, time-domain, and frequency domain features. Then, the ridge regression algorithm is used to learn the HFCM weight vector to achieve modeling prediction. Finally, we apply the proposed WE-HFCM model to stationary and non-stationary datasets in simulation experiments. We compare the predicted results with the autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) models.For stationary time series, the prediction accuracy of the WE-HFCM model is about 45% higher than that of the ARIMA, about 35% higher than that of the SARIMA model, and about 16% higher than that of the LSTM model. For non-stationary time series, the prediction accuracy of the WE-HFCM model is 69% higher than that of the ARIMA and SARIMA models.

A decomposition-based many-objective evolutionary algorithm with Q-learning guide weight vectors update

When dealing with regular, simple Pareto fronts (PFs), the decomposition-based multi-objective optimization algorithm (MOEA/D) performs well by presetting a set of uniformly distributed weight vectors. However, its performance declines when faced with complex and irregular PFs. Many algorithms address this problem by periodically adjusting the distribution of the weight vectors, but these methods do not take into account the performance of the population and are likely to update the weight vectors at the wrong time. In addition, for the SBX crossover operator, the setting of its distribution index will largely affect the exploration and convergence ability of the algorithm, so a single parameter setting will have negative impacts. To tackle these challenges, this paper proposes a method to simultaneously adaptively update weight vectors and optimize SBX parameter via Q-learning(RL-MaOEA/D). In order to make the strategies made by Q-learning more accurate, Two different metrics (CD and NCD) are proposed that capture diversity and convergence of individual and population respectively. RL-MaOEA/D is compared with seven state-of-the-art algorithms on different problems, and the simulation results reflect that the proposed algorithm has better performance.

Adaptive decomposition-based evolutionary algorithm for many-objective optimization with two-stage dual-density judgment

In order to better balance the convergence and diversity of MOEA/D for many objective optimization problems (MaOPs) with various Pareto fronts (PFs), an adaptive decomposition-based evolutionary algorithm for MaOPs with two-stage dual-density judgment is proposed. To solve the problem that weighted Tchebycheff decomposition may produce weakly Pareto optimal solutions when the solution is not unique or the uniqueness is difficult to guarantee, an augmented weighted Tchebycheff decomposition is adopted. To balance the convergence and diversity of non-dominated solutions in the external archive, different sparsity-level evaluations using vector angles or Euclidean distances are used to measure the distribution of solutions at different stages. To improve the diversity of solution sets obtained by MOEA/D for various PFs, an adaptive weight vector adjustment method based on two-stage dual-density judgment is presented. For weight vector addition, the potential search area is found according to the two-stage density judgment, and then a two-stage sparsity level judgment on the solutions of this area is performed for a second density judgment. For weight vector deletion, the degree of crowding is used to delete the weight vectors with a high crowding degree. Compared with nine advanced multi-objective optimization algorithms on DTLZ and WFG problems, the results demonstrate that the performance of the proposed algorithm is significantly better than other algorithms.

Large Margin Weighted k-Nearest Neighbors Label Distribution Learning for Classification.

Label distribution learning (LDL) helps solve label ambiguity and has found wide applications. However, it may suffer from the challenge of objective inconsistency when adopted to classification problems because the learning objective of LDL is inconsistent with that of classification. Some LDL algorithms have been proposed to solve this issue, but they presume that label distribution can be represented by the maximum entropy model, which may not hold in many real-world problems. In this article, we design two novel LDL methods based on the k -nearest neighbors ( k NNs) approach without assuming any form of label distribution. First, we propose the large margin weighted k NN LDL (LW- k NNLDL). It learns a weight vector for the k NN algorithm to learn label distribution and implement a large margin to address the objective inconsistency. Second, we put forward the large margin distance-weighted k NN LDL (LD k NN-LDL) that learns distance-dependent weight vectors to consider the difference in the neighborhoods of different instances. Theoretical results show that our methods can learn any general-form label distribution. Moreover, extensive experimental studies validate that our methods significantly outperform state-of-the-art LDL approaches.

A Kansei engineering-based decision-making method for offline medical service quality evaluation with multidimensional attributes

The evaluation of doctors’ offline medical service quality plays a vital role in evaluating hospital performance. There are two challenges that need to be addressed: (1) Currently, telephone follow-up and questionnaire surveys are the main methods for evaluating the quality of offline (mainly outpatient and inpatient) medical services in hospitals. However, these methods suffer from drawbacks such as low efficiency and resource consumption. (2) There are certain limitations to determining attribute dimensions and weighting patient evaluation attributes based solely on word frequency. To this end, this study proposes a Kansei engineering-based decision-making method for offline medical service quality evaluation with multidimensional attributes. First, this study constructs a medical Kansei lexicon based on speed and cosine similarity. Second, a concept of Kansei utility values is been defined to represent attribute values in medical service quality evaluation. Additionally, this study builds upon the Kano model to obtain the Kano classification of each attribute. On that basis, a novel approach to obtaining the implicit importance of the attributes is proposed. Thus, the weight vector of the attributes can be calculated as the combination of explicit and implicit importance. Finally, the evaluation result is obtained by using the multiattribute decision-making method. The effectiveness of the proposed method is verified through an analysis of online reviews from Haodf.com. The case study reveals that offline patients consider medical ethics and communication skills as the ”must-be” dimension of attributes, medical competence as a one-dimensional attribute, and medical advice and prescriptions as the attractive dimension of attributes. A comparative analysis with the traditional method is conducted to demonstrate the importance of dimensional analysis for offline medical service quality evaluation. The main contributions of this study include the following: (1) A medical Kansei lexicon is constructed based on Kansei engineering, and (2) a novel decision-making framework for medical service evaluation based on both appearance and implicit importance is constructed.

Collaborative Learning and Style-Adaptive Pooling Network for Perceptual Evaluation of Arbitrary Style Transfer.

Although the research of arbitrary style transfer (AST) has achieved great progress in recent years, few studies pay special attention to the perceptual evaluation of AST images that are usually influenced by complicated factors, such as structure-preserving, style similarity, and overall vision (OV). Existing methods rely on elaborately designed hand-crafted features to obtain quality factors and apply a rough pooling strategy to evaluate the final quality. However, the importance weights between the factors and the final quality will lead to unsatisfactory performances by simple quality pooling. In this article, we propose a learnable network, named collaborative learning and style-adaptive pooling network (CLSAP-Net) to better address this issue. The CLSAP-Net contains three parts, i.e., content preservation estimation network (CPE-Net), style resemblance estimation network (SRE-Net), and OV target network (OVT-Net). Specifically, CPE-Net and SRE-Net use the self-attention mechanism and a joint regression strategy to generate reliable quality factors for fusion and weighting vectors for manipulating the importance weights. Then, grounded on the observation that style type can influence human judgment of the importance of different factors, our OVT-Net utilizes a novel style-adaptive pooling strategy guiding the importance weights of factors to collaboratively learn the final quality based on the trained CPE-Net and SRE-Net parameters. In our model, the quality pooling process can be conducted in a self-adaptive manner because the weights are generated after understanding the style type. The effectiveness and robustness of the proposed CLSAP-Net are well validated by extensive experiments on the existing AST image quality assessment (IQA) databases. Our code will be released at https://github.com/Hangwei-Chen/CLSAP-Net.

A graph convolutional neural network model based on fused multi-subgraph as input and fused feature information as output

The graph convolution neural network (GCN)-based node classification model tackles the challenge of classifying nodes in graph data through learned feature representations. However, most existing graph neural networks primarily focus on the same type of edges, which might not accurately reflect the intricate real-world graph structure. This paper introduces a novel graph neural network model, MF-GCN, which integrates subgraphs with various edge types as input and combines feature information from each graph convolutional neural network layer to produce the final output. This model learns node feature representations by separately feeding subgraphs with different edge types into the graph convolutional layer. It then computes the weight vectors for fusing various edge type subgraphs based on the learned node features. Additionally, to efficiently extract feature information, the outputs of each graph convolution layer, without an activation function, are weighted and summed to obtain the final node features. This approach resolves the challenges of determining fusion weights and effectively extracting feature information during subgraph fusion. Experimental results show that the proposed model significantly improves performance on all three datasets, highlighting its effectiveness in node representation learning tasks.

A selective LVQ algorithm for improving instance reduction techniques and its application for text classification

Instance-Based Learning, such as the k Nearest Neighbor (kNN), offers a straightforward and effective solution for text classification. However, as a lazy learner, kNN’s performance heavily relies on the quality and quantity of training instances, often leading to time and space inefficiencies. This challenge has spurred the development of instance-reduction techniques aimed at retaining essential instances and discarding redundant ones. While such trimming optimizes computational demands, it might adversely affect classification accuracy. This study introduces the novel Selective Learning Vector Quantization (SLVQ) algorithm, specifically designed to enhance the performance of datasets reduced through such techniques. Unlike traditional LVQ algorithms that employ random vector weights (codebook vectors), SLVQ utilizes instances selected by the reduction algorithm as the initial weight vectors. Importantly, as these instances often contain nominal values, SLVQ modifies the distances between these nominal values, rather than modifying the values themselves, aiming to improve their representation of the training set. This approach is crucial because nominal attributes are common in real-world datasets and require effective distance measures, such as the Value Difference Measure (VDM), to handle them properly. Therefore, SLVQ adjusts the VDM distances between nominal values, instead of altering the attribute values of the codebook vectors. Hence, the innovation of the SLVQ approach lies in its integration of instance reduction techniques for selecting initial codebook vectors and its effective handling of nominal attributes. Our experiments, conducted on 17 text classification datasets with four different instance reduction algorithms, confirm SLVQ’s effectiveness. It significantly enhances the kNN’s classification accuracy of reduced datasets. In our empirical study, the SLVQ method improved the performance of these datasets, achieving average classification accuracies of 82.55%, 84.07%, 78.54%, and 83.18%, compared to the average accuracies of 76.25%, 79.62%, 66.54%, and 78.19% achieved by non-fine-tuned datasets, respectively.

A Decision-Making Model with Cloud Model, Z-Numbers, and Interval-Valued Linguistic Neutrosophic Sets.

Interval-valued linguistic neutrosophic sets (IVLNSs), Z-numbers, and the trapezium cloud model are powerful tools for expressing uncertainty and randomness. This paper aims to combine these methodologies. First, we review relevant concepts and operators, introducing a novel combination of IVLNSs and Z-numbers, which establishes a new form of expression. Subsequently, we propose the Z-interval-valued linguistic neutrosophic set-trapezium-trapezium cloud (Z-IVLNS-TTC) model, designed to minimize information loss and distortion during quantification. A novel method for calculating the objective weight vector is then developed using multi-objective programming (MOP). Drawing inspiration from the TOPSIS method, we propose a new approach for calculating the distance between Z-IVLNS-TTCs based on the p-norm. Finally, a group decision-making problem is presented to demonstrate the practical application of the proposed method. To validate the effectiveness and feasibility of the method, sensitivity analysis and comparisons with existing approaches are conducted.

Optimization of Interference Suppression Algorithm for Polarization Sensitive Conformal Array in Complex Electromagnetic Environment

With the development of modern electronic technology, the electromagnetic environment is becoming increasingly complex, which poses a severe challenge to the normal work of radar, communication and other systems. Polarization sensitive array can more effectively distinguish and suppress interference signals by using polarization information of electromagnetic waves, and improve the signal-to-noise ratio (SNR) and anti-interference ability of the system. Conformal array can be closely attached to the carrier surface, reducing space occupation and improving signal receiving efficiency and accuracy. However, at present, polarization-sensitive conformal arrays still face technical problems in interference suppression, especially in complex electromagnetic environment, how to optimize interference suppression algorithms to improve system performance has become the research focus. In this paper, an adaptive interference suppression algorithm combining spatial-polarization domain processing is proposed. The algorithm digitally processes the received signal, extracts spatial and polarization domain information, constructs the joint feature vector of the signal in spatial and polarization domain, and designs a joint filter in spatial and polarization domain. The minimum mean square error (MMSE) criterion and the least mean square (LMS) algorithm are used to update the weight vector of the filter in real time, enabling the filter to automatically adapt to changes in the electromagnetic environment and achieve optimal interference suppression. Simulation experiments show that the algorithm exhibits good stability and adaptability under different electromagnetic environments, effectively suppressing interference and extracting the desired signal. Compared with traditional interference suppression algorithms based solely on spatial domain, the joint spatial-polarization domain adaptive interference suppression algorithm significantly improves the interference suppression ratio (ISR) and signal-to-interference-plus-noise ratio (SINR) performance indicators, verifying that the introduction of polarization domain information can enhance the effect of interference suppression.

Machine learning-driven polygenic risk scores for bipolar disorder, depression, and panic disorder

Polygenic Risk Score (PRS) is a computational tech- nique that uses various genomic data to simultaneously analyze an individ- ual’s genetic risk for particular illnesses or traits. However, the traditional PRS computation has a few weaknesses, including its limited capacity to account for just a portion of trait variance, susceptibility to overfitting, and insufficient ability to discriminate among the larger population. Machine Learning (ML) methods offer a promising alternative to the traditional method by avoiding the problem of overfitting and improving accuracy. This study aims to develop an ML model for improved PRS calculation. We used the summary statistics for three mentals diseases, bipolar, depression, and panic disorder, from the Psychiatric Genomics Consortium (PGC) as a disease reference. We also obtained actual genotype data of individuals from OpenSNP, which includes both case and control samples. This data is used for predicting scores. The suggested approach, called Polygenic Risk Score Neural Network (PRSNN), calculates the PRS using weight vectors that estimate the relevance of each single nucleotide polymorphism (SNP) with a particular phenotype by deep learning model as an alternative to the traditional method. This study aims to develop a machine learning model, called PRSNN, for improved calculation of Polygenic Risk Scores (PRS). The PRSNN method outperforms the conventional method in identifying individuals at risk of mental disease. A novel deep-learning approach, named as PRSNN, is proposed for generating PRSs. The results demonstrate that it outperforms the traditional method of computing PRS for complex diseases. Further upgrades for this tool are required to overcome the current limitations, including lack of validation with external data from different ancestries, which may limit the applicability of the PRSNN method across diverse populations, and the small sample size, which may affect the results.