K-nearest Neighbor Algorithm Research Articles

Application of K-Nearest Neighbor Algorithm for Consumer Behaviour Identification and Product Personalisation Based on Big Data Analysis

The rapid digital transformation has fundamentally altered the retail industry, presenting challenges such as shifting consumer behavior and intensified market competition. This research explores the application of the K-Nearest Neighbor (KNN) algorithm for identifying consumer behavior and developing product personalization systems based on big data insights. Utilizing a dataset comprising 10,000 transaction records from January to December 2023 and 5,302 product types, we implemented the KNN algorithm to predict consumer purchases. The data was processed into 89,908 distinct transaction records. Our evaluation, using 5-fold cross-validation, demonstrated that the optimal performance of the KNN model was achieved with 𝑘=10, yielding a precision of 0.8319, recall of 0.8311, and an F1-score of 0.8312. These findings highlight the effectiveness of KNN in enhancing consumer satisfaction through precise product recommendations. This study provides strategic insights for modern retailers aiming to leverage AI and big data to remain competitive and meet evolving consumer expectations.

A new binary classifier robust on noisy domains based on kNN algorithm

Classification is an effective technique commonly used in data analysis by systematically arranging groups or categories according to established criteria. The classifier's success relies on the classifier itself and the quality of the data. However, in real-world applications, it is inevitable for datasets to contain mislabeled instances, which may cause misclassification challenges that classifiers have to handle. This study aims for a quantitative assessment of the classification of noisy data through a new kNN-based classification algorithm and to increase the performance of classical kNN by efficiently classifying the data. We perform various numerical experiments on real-world data sets to prove our new algorithm's performance. We obtain high standards of accuracy levels on various noisy datasets. We propose that this new technique can provide high standard accuracy levels in binary classification problems. We compared the new kNN and classical kNN algorithms in various noise levels (10%, 20%, 30%, and 40%) on distinct datasets by measuring in terms of test accuracy. Also, we compared our new algorithm with popular classification algorithms and in the vast majority, we obtained better test accuracy results.

Application of machine learning in predicting health perception through military personnel's sense of empowerment.

The promotion of health and provision of care services for new recruits are issues of constant concern for military leaders and healthcare providers, as they are crucial to maintaining and operating military forces. The enhancement of military personnel's empowerment has been recognized as a core value in promoting health perception. However, the pathways between military personnel's sense of empowerment and health perception have not been thoroughly explored. The primary aim of this study is to examine the predictive power of different dimensions of empowerment (personal, interpersonal, and socio-political) on new recruits' health perception, and to further observe differences among subgroups, which will help us grasp the nuances of future health intervention measures. The research data were extracted from the "Military Career Development Study," analyzing personal empowerment data from Wave 1 (W1) and perceived health data from Wave 2 (W2) (N = 2,232). In terms of analytical methods, five ML classifiers, including Decision Tree, Random Forest, Support Vector Machine, AdaBoost, and k-Nearest Neighbors (KNN) algorithms, were used for prediction in both the full sample and subsamples (gender and socioeconomic status). Results show that among the five ML classifiers, the Decision Tree performed best overall, achieving a prediction accuracy of 95.4%. The results by gender show that the ML models perform best for both males and females with the Decision Tree and Random Forest methods. For the Decision Tree, the accuracy rates were 94.9% for males and 95.1% for females; the F1 scores were 92.9% for males and 93.2% for females. For the Random Forest, the accuracy rates were 94.9% for males and 95.4% for females; the F1 scores were 92.7% for males and 93.2% for females. Regarding SES, the Decision Tree and Random Forest methods performed best. In the SES Low group, both methods achieved a prediction accuracy of 95.6% and an F1 score of 93.7%; in the SES high group, they achieved a prediction accuracy of 95.4% and an F1 score of 93.3%. However, the contribution of different dimensions of empowerment features varied significantly among subgroups. These findings can provide important information on the differences in health perception among military personnel.

A Multi-Spatial Scale Ocean Sound Speed Prediction Method Based on Deep Learning

As sound speed is a fundamental parameter of ocean acoustic characteristics, its prediction is a central focus of underwater acoustics research. Traditional numerical and statistical forecasting methods often exhibit suboptimal performance under complex conditions, whereas deep learning approaches demonstrate promising results. However, these methodologies fall short in adequately addressing multi-spatial coupling effects and spatiotemporal weighting, particularly in scenarios characterized by limited data availability. To investigate the interactions across multiple spatial scales and to achieve accurate predictions, we propose the STA-ConvLSTM framework that integrates spatiotemporal attention mechanisms with convolutional long short-term memory neural networks (ConvLSTM). The core concept involves accounting for the coupling effects among various spatial scales while extracting temporal and spatial information from the data and assigning appropriate weights to different spatiotemporal entities. Furthermore, we introduce an interpolation method for ocean temperature and salinity data based on the KNN algorithm to enhance dataset resolution. Experimental results indicate that STA-ConvLSTM provides precise predictions of sound speed. Specifically, relative to the measured data, it achieved a root mean square error (RMSE) of approximately 0.57 m/s and a mean absolute error (MAE) of about 0.29 m/s. Additionally, when compared to single-dimensional spatial analysis, incorporating multi-spatial scale considerations yielded superior predictive performance.

Sentiment Analysis of Hate Speech against DPR-RI on Twitter Using Naive Bayes and KNN Algorithms

According to surveys, the rise in social media users has resulted in an increase of hate speech, and Twitter is one of the most popular platforms for this type of speech. The tweet feature on Twitter enables users to make repeated instances of hate speech, making Twitter data very intriguing to analyze. This study aims to investigate whether a tweet contains hate speech towards the Indonesian House of Representatives (DPR-RI). The research employed crawling techniques to gather data from Twitter using the Twitter API feature. The Naïve Bayes algorithm was applied, and the results were compared with the accuracy of the K-Nearest Neighbor. After preprocessing, the total data obtained was 1,494, with 956 test data and 538 training data. The study revealed that Twitter users' sentiment towards DPR-RI was 49.2% positive and 50.8% negative sentiment when tested using Naïve Bayes. Meanwhile, KNN showed 23.4% positive and 76.6% negative sentiment. The high negative sentiment in both classifiers suggests that Twitter users frequently express hate speech towards DPR-RI. Naïve Bayes algorithm showed the highest prediction accuracy at 98.32%, while the K-Nearest Neighbor algorithm had an accuracy of only 62.84%.

Multimodal Operation Data Mining for Grid Operation Violation Risk Prediction

With the continuous expansion of the power grid, the issue of operational safety has attracted increasing attention. In power grid operation control, unauthorized operations are one of the primary causes of personal accidents. Therefore, preventing and monitoring unauthorized actions by power grid operators is of critical importance. First, multimodal violation data are integrated through information systems, such as the power grid management platform, to construct a historical case database. Next, word vectors for three types of operation-related factors are generated using natural language processing techniques, and key vectors are selected based on generalized correlation coefficients using mutual information, enabling effective dimensionality reduction. Independent component analysis is then employed for feature extraction and further dimensionality reduction, allowing for the effective characterization of operational scenarios. For each historical case, a risk score is derived from a violation risk prediction model constructed using the Random Forests (RF) algorithm. When a high-risk score is identified, the K-Nearest Neighbor (KNN) algorithm is applied to locate similar scenarios in the historical case database where violations may have occurred. Real-time violation risk assessment is performed for each operation, providing early warnings to operators, thereby reducing the likelihood of violations, and enhancing the safety of power grid operations.

A Brownian Motion Restricted K-Nearest Neighbor Algorithm for Indoor Positioning

A Brownian Motion Restricted K-Nearest Neighbor Algorithm for Indoor Positioning

Comparative Analysis of Fall Detection Using Artificial Neural Networks (ANN) and K-Nearest Neighbors (KNN) Algorithms

Fall detection is a critical area of research due to its implications for public health, particularly among older adults more vulnerable to fall-related injuries. This study explores the application of pervasive computing and machine learning algorithms in detecting falls using accelerometer and gyroscope sensors. Leveraging a dataset obtained from smartphone sensors, the study employs data processing techniques and classification algorithms, including K-Nearest Neighbors (KNN) and Artificial Neural Networks (ANN), to differentiate fall events from other activities. Evaluation metrics such as accuracy, precision, recall, and F1-score are utilized to assess the performance of the models. The results demonstrate the effectiveness of both the ANN and KNN models in accurately predicting fall detection with high precision and recall scores. The study highlights the potential of pervasive computing systems and machine learning methods to enhance fall detection capabilities, contributing to the development of proactive measures for ensuring the safety and well-being of individuals at risk of falls. Future research directions include exploring alternative algorithms and sensor modalities to improve fall detection systems further.

An accurate roughness prediction in milling processes through analytical evaluation and KNN regression approach

An accurate roughness prediction in milling processes through analytical evaluation and KNN regression approach

LocustLens: leveraging environmental data fusion and machine learning for desert locust swarm prediction

The desert locust is one of the most destructive locusts recorded in human history, and it has caused significant food shortages, monetary losses, and environmental calamities. Prediction of locust attacks is complicated as it depends on various environmental and geographical factors. This research aims to develop a machine-learning model for predicting desert locust attacks in 42 countries that considers three predictors: soil moisture, maximum temperature, and precipitation. We developed the Global Locust Attack Database for 42 countries (GLAD42) by integrating TerraClimate’s environmental data with locust swarm attack data from the Food and Agriculture Organization (FAO). To improve the usability of spatial data, reverse geocoding which is the process of converting geographic coordinates (longitude and latitude) into human-readable location names (such as countries and regions) was employed. This step enhances the clarity and interpretability of the data by providing meaningful geographic context. This study’s initial dataset focused on instances where locust attacks were recorded (positive class). To ensure a comprehensive analysis, we also incorporated negative class instances, representing periods (specific years and months) in the same countries and regions where locust attacks did not occur. This research utilizes the benefits of lazy learners by employing the K-nearest neighbor algorithm (K-NN), which provides high accuracy and the benefit of no time-consuming retraining even if real-time updated data is periodically added to the system. This research also focuses on building an eco-friendly machine learning model by evaluating carbon emissions from ML models. The results obtained from LocustLens are compared with other machine learning models, including baseline–K-NN, decision trees (DT), Logistic regression (LR), AdaBoost Classifier, BaggingClassifier, and support vector classifier (SVC). LocustLens outperformed all competitors with an accuracy of 98%, while baseline-K-NN achieved 96%, SVC gave 91%, DT gave 97%, AdaBoost has accuracy of 91%, BaggingClassifier gave 94% and LR gave 83%, respectively. Carbon emissions from RAM and CPU electricity consumption are measured in kg gCO2. They are a minimum for AdaBoost Classifier equal to 0.02 and 0.07 for DT and a maximum of 9.03 for SVC. The carbon footprint of LocustLens is 4.87 kg gCO2.

A Novel Non-Contact Multi-User Online Indoor Positioning Strategy Based on Channel State Information

The IEEE 802.11bf-based wireless fidelity (WiFi) indoor positioning system has gained significant attention recently. It is important to recognize that multi-user online positioning occurs in real wireless environments. This paper proposes an indoor positioning sensing strategy that includes an optimized preprocessing process and a new machine learning (ML) method called NKCK. The NKCK method can be broken down into three components: neighborhood component analysis (NCA) for dimensionality reduction, K-means clustering, and K-nearest neighbor (KNN) classification with cross-validation (CV). The KNN algorithm is particularly suitable for our dataset since it effectively classifies data based on proximity, relying on the spatial relationships between points. Experimental results indicate that the NKCK method outperforms traditional methods, achieving reductions in error rates of 82.4% compared to naive Bayes (NB), 85.0% compared to random forest (RF), 72.1% compared to support vector machine (SVM), 64.7% compared to multilayer perceptron (MLP), 50.0% compared to density-based spatial clustering of applications with noise (DBSCAN)-based methods, 42.0% compared to linear discriminant analysis (LDA)-based channel state information (CSI) amplitude fingerprinting, and 33.0% compared to principal component analysis (PCA)-based approaches. Due to the sensitivity of CSI, our multi-user online positioning system faces challenges in detecting dynamic human activities, such as human tracking, which requires further investigation in the future.

Attendance Marking using Face Detection

The demand for automated attendance management systems has significantly increased in educational institutions and corporate environments where manual methods are prone to inefficiencies and errors. This paper presents a real-time, facial recognition-based attendance system developed using Flask, OpenCV, and machine learning techniques. The system employs OpenCV’s Haar Cascade classifier for face detection and the K-Nearest Neighbours (KNN) algorithm for face recognition. During user registration, the system captures 10 images per individual to ensure robust recognition across various facial expressions. The web interface, built using Flask, facilitates user interaction for managing attendance records stored in CSV format. The system achieves an accuracy of 92% under optimal lighting conditions, though performance decreases to 80% in low-light environments. Recognition is completed in approximately 2 seconds, making the system suitable for real-time applications in classrooms or offices. Despite handling real-time image streaming efficiently, challenges such as reduced accuracy when handling obstructions like masks or glasses remain. Future enhancements will explore the integration of deep learning models, such as Convolutional Neural Networks (CNNs), to improve robustness and scalability. This system demonstrates the potential of facial recognition technology for automating attendance tracking, with significant applications in both educational and corporate sectors

Analysis of Naïve Bayes and K-Nearest Neighbors Algorithms for Classifying Fishermen Aid Eligibility

This article analyzes the use of data mining with Naïve Bayes and K-Nearest Neighbor (KNN) algorithms to build classification models and evaluate their performance in identifying fishermen eligible for aid. The study aims to compare the effectiveness of these algorithms in handling imbalanced datasets using the Synthetic Minority Over-sampling Technique (SMOTE). The research applies SMOTE to improve the balance of the dataset before classification. Without SMOTE, Naïve Bayes achieved an accuracy of 97.01%, precision of 94.16%, recall of 96.67%, and F1-score of 95.39%. KNN, on the other hand, reached an accuracy of 94.04%, precision of 94.53%, recall of 86.00%, and F1-score of 90.06%. After applying SMOTE, both algorithms improved: Naïve Bayes attained an accuracy of 98.33%, precision of 96.86%, recall of 100.00%, and F1-score of 98.49%, while KNN reached an accuracy of 96.90%, precision of 97.72%, recall of 96.19%, and F1-score of 96.94%. The results show that Naïve Bayes, with SMOTE, outperforms KNN in managing data imbalance and accurately classifying eligible fishermen for aid.

Adaptive Tabu Search Algorithm Based on Quantum Dwelling and KNN Classifier for Creative Game Selection in Preschool Education

In order to select the best creative games for preschool education more quickly and accurately, a method for selecting creative games for preschool education based on tabu search tabu search (TS) algorithm is proposed. The TS algorithm is improved by using quantum population, and an adaptive neighborhood mapping mechanism is formed to dynamically adjust the tabu length and accelerate the convergence of the algorithm. The KNN algorithm is used to calculate the initial solution of the characteristics of preschool creative games, and the quantum adaptive optimization tabu search algorithm is used to iterate from the initial solution, and the subset of feature vectors containing feature weights and feature selection vectors is continuously searched as the input of KNN classifier. The improved objective function is used as a guide to combine the selection results of classifiers by simple voting, and the output of the selection results of creative games in preschool education is realized. Experiments show that this method can select more critical features of creative games in preschool education at a faster speed while ensuring the accuracy of the selection results. At the same time, the improved tabu search algorithm has faster convergence speed and better search performance, and can recommend creative games that are most suitable for preschool education according to the actual situation.

Collaborative filtering recommendation based on K-nearest neighbor and non-negative matrix factorization algorithm

Collaborative filtering recommendation based on K-nearest neighbor and non-negative matrix factorization algorithm

Jamming Attacks Detection Based on IGWO for Optimization of Fast Correlation-Based Feature extraction in Wireless Communication

Background: Wireless networks are essential communication technologies that prevent cable installation prices and burdens. Because of this technology's pervasive usage, wireless network safety is a significant problem. Owing to distributed and open wireless medium aspects, attackers might use different jamming methods to exploit physical and MAC layer protocol vulnerabilities. In addition, jamming attacks require to be accurately grouped so that suitable countermeasures can be considered. Given the potential severity of such attacks, precisely identifying and classifying them is critical for implementing effective responses. The motivation for this paper is the need to improve the detection and categorization of jamming signals using modern machine learning algorithms, consequently enhancing wireless network security and reliability. Objective: In this paper, we compare some machine learning models' efficiency for diagnosing jamming signals. Methods: Such algorithms refer to support vector machine (SVM) and k-nearest neighbors (KNN). We checked the signal features that recognize jamming signals. After the jamming attack model, the developed grey wolf optimizer version known as IGWO (improved grey wolf optimizer) has been discussed for feature extraction of software usability. Four separate metrics were employed as features to detect jamming attacks in order to evaluate the machine learning models. This novel feature extraction method is crucial for improving the accuracy of jamming detection. Results: The measurements of these parameters were gathered through a simulation of a real setting. And generated a large dataset using these parameters. Conclusion: The simulation results illustrate that the KNN algorithm based on jamming detection could diagnose jammers having a minimal likelihood of false alarms and a high level of accuracy.

Bearing Life Prediction Model for Electromechanical Equipment by Integrating Deep Neural Network and K-Nearest Neighbor Algorithm and Its Application

Bearing Life Prediction Model for Electromechanical Equipment by Integrating Deep Neural Network and K-Nearest Neighbor Algorithm and Its Application

A Machine Learning–Based Ergonomic Assessment of Wireless Hand Control System for Lower‐Limb Disabled Tractor Operators and Abled Female Agricultural Workers

ABSTRACTTractor being the most used power source for agricultural operations needs hand control (HC) and foot control (FC) to maneuver it. FCs restrict lower‐limb disabled agricultural workers from participating in tractor operation, and high requirement of actuation forces to operate FCs may create overexertion and early fatigue to female agricultural workers. Therefore, a sensor‐based HC system has been developed to assist them in tractor operation with minimal actuating force. This study focuses on ergonomic assessment of the HC system to assess the suitability for the abled and disabled agricultural workers, including physiological, psychophysical, and muscle fatigue parameters. Heart rate (HR) of abled male and female, and disabled male and female was observed in the range of 83–118, 85–117, 93–118, and 92–114 beats/min, respectively, during tractor operation. Energy expenditure rate (EER) during tractor operation with FCs (9.7–17.4 kJ/min) was observed higher than with the HC system (7.3–16.5 kJ/min). Body parts discomfort was observed highest for the right hand of all the subjects (4.9–5.3) and maximum overall discomfort was experienced by abled females during the operation with FCs (5.4) as they have to exert higher force. The root mean square (RMS) value of the electromyography signal obtained for extensor digitorum muscle was found to be higher for all the subjects and with both HC and FC (abled male, 17.37–40.43 µV; abled female, 14.76–45.29 µV; disabled male, 15.49–40.23 µV; disabled female, 30.32–54.29 µV) than other upper arm muscles middle deltoid, flexor carpi radialis, and brachioradialis. Muscle workload for all the selected muscles of all the subjects was observed within the recommended limit during the tractor operation with a developed HC system (< 30%). Categorization of overall discomfort rating (ODR) of the subjects using HR, EER, and RMS through machine learning algorithms such as k‐nearest neighbor (KNN), random forest classifier, and support vector machine predicted the ODR with accuracies in the range of 77%–83%. KNN algorithm was found to be most accurate with prediction accuracy of 83%. The developed HC system provides assistantship to the lower‐limb disabled agricultural workers (1%–100% disability of lower limbs) and allows female workers to operate the tractor with minimal physical exertion.

Statistical models for classification by handedness of Olympic Trap shooters in digital training services and remote coaching

AbstractIn this paper, we address the problem of classification by handedness of Olympic Trap shooters applying statistical methods to newly available data gathered from the field. We assess the performance of binary classification models based on KNN and Binary Regression, with both symmetric and asymmetric link functions, in a context characterized by unbalanced data. Our results show promising classification performance, suitable for first non-critical applications in data driven training services and remote coaching, encouraging further future research.

Reaching machine learning leverage to advance performance of electrocatalytic CO2 conversion in non-aqueous deep eutectic electrolytes

Deep eutectic electrolytes (DEEs) show promise for future electrochemical systems due to their adjustable buffer capacities. This study utilizes machine learning algorithms to analyse the carbon dioxide reduction reaction (CO2RR) in DEEs with a buffer capacity of approximately 10.21 mol/pH. The objective is to minimize undesired hydrogen evolution reactions (HER) and render CO2RR dominant in a membrane cell. The CO2RR process was found to be non-adiabatic, as the time of nuclear motion for CO32− in K2CO3 product, through CO2●− trapping, is 0.368 femtoseconds shorter than the 1.856 × 10−3s charge transfer relaxation time. Microkinetic analysis reveals that the rate of CO2RR to CO2●− is 2.14 × 103 mol/cm2/s2 with a rate constant of 2.1 × 1010 cm/s. Our findings demonstrate that ensemble and k-Nearest Neighbours algorithms learn the CO2RR dataset, achieving a prediction accuracy of over 99%. The models were verified visually and quantitatively by overlaying predicted and experimental dataset. Diagnostic and SHAP analyses highlighted the gradient boost ensemble algorithm, predicting asymptotic current densities of -4.114 mA/cm2 or -13.340 mA/cm2, with high turnover frequencies (TOF) of 3.79 × 1010 h-1 or 12.30 × 1010 h-1 for CO2●− or K2CO3 generation on silver electrodes, respectively. These results consider both accuracy and robustness against overfitting, providing an opportunity to optimize future non-aqueous electrolytes for convenient TOF measurements at industrially relevant current densities.