Complex Patterns In Data Research Articles

Harvest Harmony: Integrating Linear and Nonlinear Machine Learning Models for Precision Crop Recommendation

This research presents a comprehensive crop recommendation system that combines linear and nonlinear machine learning models to forecast suitable crops based on soil and environmental factors. The study evaluates the performance of Logistic Regression (linear) alongside Random Forest, Gradient Boosting, and XGBoost (nonlinear models) in delivering accurate crop suggestions. Precision, recall, and F1-score metrics are employed to assess the models' effectiveness. The dataset incorporates vital soil characteristics, such as nitrogen, phosphorus, and potassium levels, and environmental parameters like temperature, humidity, pH, and rainfall. The results demonstrate that while linear models like Logistic Regression offer simplicity, nonlinear models such as XGBoost excel in capturing complex data patterns, providing more precise recommendations. This dual-model strategy empowers farmers to make informed decisions tailored to specific farming conditions, boosting agricultural productivity. The study underscores the importance of integrating both linear and nonlinear machine learning techniques to achieve optimal crop recommendations, encouraging resource efficiency and sustainable agricultural practices.

DeepmiRNATar: A deep learning-based model for miRNA targets prediction

MicroRNAs (miRNAs) play a crucial role in regulating fundamental biological processes such as the cell cycle, differentiation, and apoptosis by directly interacting with multiple genes (mRNAs). This regulatory mechanism has a profound impact on cellular function and the overall physiological condition of an organism. However, the prediction of miRNA-mRNA interactions encounters computational challenges in the field of biology due to the diverse sequences and complex data patterns. To overcome these obstacles, this research effort introduced DeepmiRNATar, a tool designed to precisely pinpoint miRNA targets, offering essential assistance in the realm of disease management. DeepmiRNATar leverages the Word2vec-based DeepLncLoc approach for encoding miRNA sequence characteristics and utilizes the DNABERT pre-trained model for in-depth semantic comprehension of target sequences. Through the integration of TextCNN, BiLSTM, and SpatialConv Attention mechanisms, the model scrutinizes structural features, temporal relationships, and overall interactions within the sequences. Following a series of experimental assessments, DeepmiRNATar attained an impressive AUC of 99.15% on the evaluation dataset, on par with the current leading prediction methodologies. Notably, the precision-recall curve, sensitivity, and F-measure values reached 99.18%, 97.43%, and 95.47%, respectively. Compared to existing miRNA target prediction models, DeepmiRNATar demonstrates a notable enhancement in overall predictive accuracy. The successful creation and experimental validation of the DeepmiRNATar model signify a significant advancement in miRNA target identification technology.

Enhancing discharge prediction over Type-A piano key weirs: An innovative machine learning approach

Piano key weirs (PKWs) are an increasingly popular hydraulic structure due to their higher discharge capacity than linear weirs. Accurately predicting the discharge of PKWs is essential for appropriate design and operation. This study utilized eight Machine Learning algorithms, including non-ensemble and ensemble models to predict the discharge of type-A PKWs. Multiple-Linear-Regression (MLR), Support-Vector-Machine (SVM), Gene-Expression-Programming (GEP), and Artificial-Neural-Network (ANN) were adopted as non-ensemble models. While the ensemble models comprised Random-Forest (RF), Adaptive-Boosting (AdaBoost), Extreme-Gradient-Boosting (XGBoost), and Categorical-Boosting (CatBoost). A total of 476 experimental datasets were collected from previous research considering three critical dimensionless input parameters: PKW key widths, PKW height, and total upstream head. The models were trained on 70 % of the dataset and tested on the remaining 30 %. The hyperparameters of the models were optimized using the Bayesian Optimization technique, with 5-fold cross-validation ensuring high performance. Comprehensive analyses, including visual and quantitative methods, were employed to validate model effectiveness. CatBoost model consistently outperformed the other models, achieving the highest Determination-coefficient (R2 = 0.998) and lowest Root-Mean-Squared-Error (RMSE = 0.002), highlighting its ability to handle complex data patterns and its superior optimization process. XGBoost follows closely behind, showing strong generalization, while ANN and RF perform well, but it's a slight increase in error metrics. The study also incorporated Shapley-Additive-exPlanations (SHAP) and Partial-Dependence-Plot (PDP) analyses, revealing that the total upstream head variable had the most significant impact on the discharge predictions. An interactive Graphical-User-Interface was developed to facilitate practical applications, enabling engineers to predict discharge quickly and economically.

Novel family of probability generating distributions: Properties and data analysis

Abstract Current probability distributions often fall short when modeling lifespan data with non-monotonic hazard rate shapes, highlighting a gap in probability theory. To address this issue, this study introduces the novel family of probability-generating distributions (NP-G) as a solution to capture complex data patterns better. This research aims to develop and validate the NP-G distributions, which include a two-parameter continuous model based on the Weibull distribution. The study extensively explores the mathematical properties of the NP-G distributions, including series expansions of probability density functions, and evaluates various probabilistic measures such as moments, stress strength, mean deviations, entropy measures, and order statistics. Using the maximum likelihood method for parameter estimation and conducting a numerical simulation analysis, the study assesses the performance of the proposed extended exponentiated Weibull model. The findings demonstrate that this new model offers superior fit and accuracy compared to existing distributions when applied to two referenced datasets. This advancement is significant as it provides a more effective tool for analyzing lifespan data with non-monotonic hazard rates, enhancing both theoretical understanding and practical applications in fields such as reliability engineering and survival analysis.

Sustainability and the Innovation Pipeline at Honeywell

PRACTITIONER TAKEAWAYS Honeywell’s sustainability-oriented offerings improve safety, environmental impact, and societal resilience for our customers and the communities they serve. Honeywell’s approach to innovation involves collaborating with partners, life-cycle analyses of products, and navigating the regulatory landscape with science-based evidence and research. Artificial intelligence (AI) can do phenomenal things for sustainability, particularly in applications that involve image analytics or complex data patterns.

Advanced Security Framework for 6G Networks: Integrating Deep Learning and Physical Layer Security

This paper presents an advanced framework for securing 6G communication by integrating deep learning and physical layer security (PLS). The proposed model incorporates multi-stage detection mechanisms to enhance security against various attacks on the 6G air interface. Deep neural networks and a hybrid model are employed for sequential learning to improve classification accuracy and handle complex data patterns. Additionally, spoofing, jamming, and eavesdropping attacks are simulated to refine detection mechanisms. An anomaly detection system is developed to identify unusual signal patterns indicating potential attacks. The results demonstrate that machine learning (ML) and hybrid models outperform conventional approaches, showing improvements of up to 85% in bit error rate (BER) and 24% in accuracy, especially under attack conditions. This research contributes to the advancement of secure 6G communication systems, offering details on effective defence mechanisms against physical layer attacks.

Research on the Application of Computer Technology in Biostatistics

This paper explores the application of computer technology in biostatistics, focusing on the technological advancements and their impact on data management, data processing and analysis, and data visualization. With the development of computer technology, data storage and management methods have significantly improved, particularly with the introduction of database systems and big data technologies, which have greatly enhanced the efficiency and accuracy of handling biostatistical data. Additionally, the application of machine learning and artificial intelligence has made biostatistical data analysis more intelligent and automated, providing new tools for identifying and predicting complex data patterns. Furthermore, advanced data visualization techniques have enhanced the interpretability of statistical results through clear graphical presentations, promoting the application of biostatistics. Through the analysis of specific case studies, this paper demonstrates the practical effects and challenges of computer technology in improving biostatistical research capabilities. Finally, the paper anticipates the future impact of emerging computing technologies, such as quantum computing, on biostatistics and suggests future research directions and recommendations.

Traffic data imputation via knowledge graph-enhanced generative adversarial network

Traffic data imputation is crucial for the reliability and efficiency of intelligent transportation systems (ITSs), forming the foundation for downstream tasks like traffic prediction and management. However, existing deep learning-based imputation methods struggle with two significant challenges: poor performance under high missing data rates and the limited incorporation of external traffic-related factors. To address these challenges, we propose a novel knowledge graph-enhanced generative adversarial network (KG-GAN) for traffic data imputation. Our approach uniquely integrates external knowledge with traffic spatiotemporal dependencies to improve data imputation quality. Specifically, we construct a fine-grained knowledge graph (KG) that differentiates attributes and relationships of external factors such as points of interest (POI) and weather conditions, facilitating more robust knowledge representation learning. We then introduce a knowledge-aware embedding cell (EM-cell) that merges traffic data with these learned external representations, providing richer inputs for the spatiotemporal GAN. Extensive experiments on a large-scale real-world traffic dataset demonstrate that KG-GAN significantly outperforms state-of-the-art methods under various missing data scenarios. Additionally, ablation studies confirm the superior performance gained from incorporating external knowledge, underscoring the importance of this approach in addressing complex missing data patterns.

Enhancing healthcare data integrity: fraud detection using unsupervised learning techniques

Data in healthcare forms the backbone of any treatment and decision-making for patients. However, the data from a healthcare institution can sometimes be prone to abnormalities, thereby putting treatment and patient safety in jeopardy. This paper points to the dire need for reliable anomaly detection systems in the healthcare industry. It employs various unsupervised learning methods, including Isolation Forest, Local Outlier Factor (LOF), K-Nearest Neighbours (KNN), and autoencoder models for detecting abnormalities in healthcare data with better accuracy. Anomaly detection capabilities also allow health providers to reduce risks and provide some assurance of the integrity of the data, as these capabilities are more likely to indicate unusual patient profiles or incorrect test results. Isolation Forest, LOF, and KNN are the preliminary methods for performing anomaly detection in this work, with Isolation Forest yielding the best results. Then, autoencoder models that learn subtle variations and complex patterns in data are employed. This paper seeks to enhance anomaly detection in terms of accuracy and reliability to ensure better healthcare data quality and patient safety.

Hybrid Modeling Techniques for Municipal Solid Waste Forecasting: An Application to OECD Countries

Abstract Accurate forecasting of municipal solid waste (MSW) generation is critical for effective waste management, given the rising volumes of waste posing environmental and public health challenges. This study investigates the efficacy of hybrid forecasting models in predicting MSW generation trends across Organization for Economic Cooperation and Development (OECD) countries. The empirical analysis utilizes five distinct approaches – ARIMA, Theta model, neural networks, exponential smoothing state space (ETS), and TBATS models. MSW data spanning 1995–2021 for 29 OECD nations are analyzed using the hybrid models and benchmarked against individual ARIMA models. The results demonstrate superior predictive accuracy for the hybrid models across multiple error metrics, capturing complex data patterns and relationships missed by individual models. The forecasts project continued MSW generation growth in most countries but reveal nuanced country-level differences as well. The implications for waste management policies include implementing waste reduction and recycling programs, investing in infrastructure and technology, enhancing public education, implementing pricing incentives, rigorous monitoring and evaluation of practices, and multi-stakeholder collaboration. However, uncertainties related to model selection and data limitations warrant acknowledgment. Overall, this study affirms the value of hybrid forecasting models in providing robust insights to inform evidence-based waste management strategies and transition toward sustainability in the OECD region.

Improving the training performance of generative adversarial networks with limited data: Application to the generation of geological models

In the past years, there is a growing interest in the applications of Generative Adversarial Networks (GANs) to generate geological models. Although GANs have proven to be an effective tool to learn and reproduce the complex data patterns present in some geological models, some challenges still remain open. Among others, a well-noticed problem is the need for a large number of samples to ensure high-quality training, which can be prohibitively expensive in some cases. As an attempt to offer a (possibly partial) solution to the aforementioned challenge, in this study, we investigate the feasibility and effectiveness of a zero-centered discriminator regularization technique for improving the performance of a GAN. Additionally, we evaluate an adaptive data augmentation technique to overcome the potential issue of limited training data, for the purpose of generating geologically feasible realizations of hydrocarbon reservoir models. Our findings demonstrate that a combination of the two techniques lead to notable performance improvements of a GAN. Particularly, it is observed that using the adaptive data augmentation technique in a GAN can yield similar results to those obtained by the GAN with a much larger dataset.

Effective data exploration through clustering of local attributive explanations

Machine Learning (ML) has become an essential tool for modeling complex phenomena, offering robust predictions and comprehensive data analysis. Nevertheless, the lack of interpretability in these predictions often results in a closed-box effect, which the field of eXplainable Machine Learning (XML) aims to address. Local attributive XML methods, in particular, provide explanations by quantifying the contribution of each attribute to individual predictions, referred to as influences. This type of explanation is the most acute as it focuses on each instance of the dataset and allows the detection of individual differences. Additionally, aggregating local explanations allows for a deeper analysis of the underlying data. In this context, influences can be considered as a new data space to reveal and understand complex data patterns. We hypothesize that these influences, derived from ML explanations, are more informative than the original raw data, especially for identifying homogeneous groups within the data. To identify such groups effectively, we utilize a clustering approach. We compare clusters formed using raw data against those formed using influences computed by various local attributive XML methods. Our findings reveal that clusters based on influences consistently outperform those based on raw data, even when using models with low accuracy.

Paramps: Convolutional neural networks based on tensor decomposition for heart sound signal analysis and cardiovascular disease diagnosis

Currently, convolutional neural networks have demonstrated outstanding efficiency in heart sound detection and automatic diagnosis of cardiovascular diseases. However, due to the non-stationary nature and complex data patterns caused by environmental noise and stethoscope differences, traditional neural networks are limited in extracting discriminative features. This article proposes a convolutional neural network based on tensor decomposition to address this issue. This model uses a convolutional neural network with four parallel structures to extract audio features of heart sound signals and introduces a tensor network to use tensor decomposition to perform low-rank approximation on the convolutional kernel, compress model parameters, reduce redundancy, and improve performance. When processing feature data, the model divides large areas of features into locally unordered small areas to achieve feature compression and reorganization, ensuring that crucial information is preserved while compressing parameters. The model can accurately capture spatial structural information and critical features by refining the matrix product state layer. Experiments were conducted on the 2016 PhysioNet/CinC Challenge and the Yaseen heart sound public dataset, the experimental results show that the proposed method has an accuracy of 96.4% and 99.2% on two datasets, specificity of 99.1% and 99.8%, demonstrating its excellent generalization ability and diagnostic accuracy.

Differences in ischemic heart disease between males and females using predictive artificial intelligence models

<b>Background: </b>Cardiovascular health and preventative strategies are influenced by the sex of the individuals. To forecast cardiac events or detect ischemic heart disease (IHD) early, machine-learning algorithms can analyze complex patient data patterns. Early detection allows for lifestyle changes, medication management, or invasive treatments to slow disease progression and improve outcomes.<br /> <b>Aim</b>: To compare and predict the differences in the primary sources of IHD burden between males and females in various age groups, geographical regions, death versus alive, and comorbidity levels.<br /> <b>Methods: </b>A predictive and retrospective design was implemented in this study. Electronic health records were extracted, which were equally distributed among males and females with IHD. The dataset consisted of patients who were admitted between 2015 and 2022. Two of the eight models generated by Modeler software were implemented in this study: the Bayesian network model, which achieved the highest area under curve score (0.600), and the Chi-squared automatic interaction detection (CHAID) model, which achieved the highest overall accuracy score (57.199%).<br /> <b>Results: </b>The study sample included 17,878 men and women, 58% of whom had no comorbidities and 1.7% who died. Age, the Charlson comorbidity index score, and geographical location all predicted IHD, but age was more influential. Bayesian network analysis showed that IHD odds were highest in males 40-59 and females 60-79, with the highest mortality risk in females 80-100. North and south Jordan had higher IHD rates and middle-aged males from north and middle governorates had higher IHD rates according to CHAID.<br /> <b>Conclusion: </b>By using artificial intelligence, clinicians can improve patient outcomes, treatment quality, and save lives in the fight against cardiovascular illnesses. To predict IHD early, machine-learning algorithms can analyze complex patient data patterns to improve outcomes.

Active Learning for a Recursive Non-Additive Emulator for Multi-Fidelity Computer Experiments

Computer simulations have become essential for analyzing complex systems, but high-fidelity simulations often come with significant computational costs. To tackle this challenge, multi-fidelity computer experiments have emerged as a promising approach that leverages both low-fidelity and high-fidelity simulations, enhancing both the accuracy and efficiency of the analysis. In this article, we introduce a new and flexible statistical model, the Recursive Non-Additive (RNA) emulator, that integrates the data from multi-fidelity computer experiments. Unlike conventional multi-fidelity emulation approaches that rely on an additive auto-regressive structure, the proposed RNA emulator recursively captures the relationships between multi-fidelity data using Gaussian process priors without making the additive assumption, allowing the model to accommodate more complex data patterns. Importantly, we derive the posterior predictive mean and variance of the emulator, which can be efficiently computed in a closed-form manner, leading to significant improvements in computational efficiency. Additionally, based on this emulator, we introduce four active learning strategies that optimize the balance between accuracy and simulation costs to guide the selection of the fidelity level and input locations for the next simulation run. We demonstrate the effectiveness of the proposed approach in a suite of synthetic examples and a real-world problem. An R package RNAmf for the proposed methodology is provided on CRAN.

Nested Neural Networks: A Novel Approach to Flexible and Deep Learning Architectures

In this paper, we introduce a novel neural network architecture termed Nested Neural Networks (NNN), which incorporates nested layers within a more complex overarching structure. The architecture leverages the concept of internal and external conditions, akin to linguistic structures like Future Perfect and Future Perfect Progressive in English grammar, to create a flexible and deep model. This architecture allows the network to handle complex data patterns with enhanced computational efficiency and memory savings. We demonstrate the effectiveness of NNNs through experiments on benchmark datasets, showcasing their ability to outperform traditional models in terms of accuracy, training efficiency, and adaptability.

Effect of data drift on the performance of machine‐learning models: Seismic damage prediction for aging bridges

AbstractMachine‐learning models play a crucial role in structural seismic risk assessment and facilitate decision‐making by analyzing complex data patterns. However, the dynamic nature of real‐world data introduces challenges, particularly data drift, which can significantly affect model performance. This adversely affects machine‐learning models intended to aid emergency responders and disaster recovery teams. This study primarily focused on assessing the impact of column corrosion‐induced data drift on the performance of machine‐learning models for seismic risk assessment of bridges. The machine‐learning model performance was evaluated with and without considering the impact of corrosion. The results revealed a significant decrease in prediction accuracy when the data drift effect was not considered. To address this challenge, this study proposes integrating principal component analysis‐based anomaly detection to enhance the model performance. The optimized model considering drift demonstrates significant improvements in accuracy across corroded bridges aged 25, 50, and 75 years, with accuracy rates increasing from 90%, 85%, and 81% to 98%, 97%, and 96%, respectively.

A Systematic Review of Real-Time Deep Learning Methods for Image-Based Cancer Diagnostics.

Deep Learning (DL) drives academics to create models for cancer diagnosis using medical image processing because of its innate ability to recognize difficult-to-detect patterns in complex, noisy, and massive data. The use of deep learning algorithms for real-time cancer diagnosis is explored in depth in this work. Real-time medical diagnosis determines the illness or condition that accounts for a patient's symptoms and outward physical manifestations within a predetermined time frame. With a waiting period of anywhere between 5 days and 30 days, there are currently several ways, including screening tests, biopsies, and other prospective methods, that can assist in discovering a problem, particularly cancer. This article conducts a thorough literature review to understand how DL affects the length of this waiting period. In addition, the accuracy and turnaround time of different imaging modalities is evaluated with DL-based cancer diagnosis. Convolutional neural networks are critical for real-time cancer diagnosis, with models achieving up to 99.3% accuracy. The effectiveness and cost of the infrastructure required for real-time image-based medical diagnostics are evaluated. According to the report, generalization problems, data variability, and explainable DL are some of the most significant barriers to using DL in clinical trials. Making DL applicable for cancer diagnosis will be made possible by explainable DL.

Progress on deep learning in genomics.

With the rapid growth of data driven by high-throughput sequencing technologies, genomics has entered an era characterized by big data, which presents significant challenges for traditional bioinformatics methods in handling complex data patterns. At this critical juncture of technological progress, deep learning-an advanced artificial intelligence technology-offers powerful capabilities for data analysis and pattern recognition, revitalizing genomic research. In this review, we focus on four major deep learning models: Convolutional Neural Network(CNN), Recurrent Neural Network(RNN), Long Short-Term Memory(LSTM), and Generative Adversarial Network(GAN). We outline their core principles and provide a comprehensive review of their applications in DNA, RNA, and protein research over the past five years. Additionally, we also explore the use of deep learning in livestock genomics, highlighting its potential benefits and challenges in genetic trait analysis, disease prevention, and genetic enhancement. By delivering a thorough analysis, we aim to enhance precision and efficiency in genomic research through deep learning and offer a framework for developing and applying livestock genomic strategies, thereby advancing precision livestock farming and genetic breeding technologies.

A Hybrid Model for Short-Term Energy Load Prediction Based on Transfer Learning with LightGBM for Smart Grids in Smart Energy Systems

ABSTRACT Electricity load prediction plays a vital role in energy management. The necessity of combining scattered power generation channels of sustainable energy and other substitute resources into distribution grid networks is increasing because of the 4.1 percent rise in world electricity since 2021. The utilization of probability power generators and energy storage is maximized by short-term load prediction methods, which make it possible to anticipate potential energy usage. To facilitate the growth of energy systems in quite a sustainable way, urban energy planners utilize a range of methods and technological advances, including simulation, probability optimization, comprehensive improvement, and modelling techniques for predicting power requirements. Predicting energy consumption at granular time scales (e.g., hourly or sub-hourly intervals) is common practice for short-term energy load prediction. For similar time-series forecasting challenges, the authors have decided to use transfer learning (TL) with light gradient-boosting machine (LightGBM).1 This model can benefit from models trained on larger data sets through TL, which might boost prediction accuracy. Energy prediction and effective resource utilization largely support the accurate transition of energy systems. In this paper, the authors propose a hybrid model for short-term energy load prediction. Based on TL to optimize LightGBM (OLGBM) for smart grids, The proposed model first applies data pre-processing using an abnormal supplement strategy with an immediate deviation selection technique. This phase eliminates the missing values and extracts the required features. The second phase uses a TL-OLGBM with hyperparameters. The TL method helps to learn the dynamic time scale and complex data patterns, and the hyperparameters are tuned via the Bayesian optimization technique, which addresses the challenge of short-term load forecasting (STLF) and increases forecasting accuracy. Finally, an optimized LightGBM model is applied, combining the time and energy features to predict effective energy forecasting. The proposed model gained a 2.834589 mean absolute percentage error (MAPE) value and a 0.9706495 GINI index after execution on the prescribed data set. We compare the performance of the proposed model with other comparable models, and the simulation outcomes show that the model can generate the best results for MAPE, accuracy, and root-mean-square deviation (RMSE).