K-nearest Neighbor Algorithm Research Articles

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.

A Machine Learning Approach for Modeling the Spatial-temporal Propagation Pattern of COVID-19

Abstract. Predicting infections resulting from epidemiological contagions involves a complex therapeutic endeavor that necessitates the consideration of various factors within the available data. COVID-19, a globally recognized highly dangerous disease, presents an opportunity to effectively understand its patterns and spatial determinants to combat similar ailments. This study seeks to employ a deep neural network and several machine learning techniques to identify the crucial factors influencing COVID-19 infections and to forecast the spatial-temporal spread of the disease. Previous research has focused on predicting outcomes using a limited set of 8 patient variables. To contribute to this field, the current investigation analyzes a dataset comprising 47,029 records of infected individuals who sought medical attention, with 18,433 of them testing positive for the coronavirus and requiring hospitalization. The study explores the prediction of illness and hospitalization needs based on geographical locations by utilizing machine learning algorithms such as Random Forest, Naive Bayes, Decision Tree, and K-Nearest Neighbor. The machine learning process commences with input data (comprising the 47,029 records), enabling the machine to identify patterns within the dataset and subsequently make informed decisions based on these patterns and insights gained. The primary objective is to allow the machine to autonomously learn and refine its predictions without human intervention. Applying these algorithms to COVID-19 data for spatial-temporal prediction revealed that the Random Forest algorithm achieved the highest accuracy of 0.84, while the Simple Bayes algorithm exhibited the lowest accuracy at 0.50. Additionally, the study compared random forest, decision tree, simple bayes, and K-nearest neighbor algorithms to predict the severity of road accidents.

Bag of Feature-Based Ensemble Subspace KNN Classifier in Muscle Ultrasound Diagnosis of Diabetic Peripheral Neuropathy

Muscle ultrasound quantification is a valuable complementary diagnostic tool for diabetic peripheral neuropathy (DPN), enhancing physicians’ diagnostic capabilities. Quantitative assessment is generally regarded as more reliable and sensitive than visual evaluation, which often necessitates specialized expertise. This work develops a computer-aided diagnostic (CAD) system based on muscle ultrasound that integrates the bag of features (BOF) and an ensemble subspace k-nearest neighbor (KNN) algorithm for DPN detection. The BOF creates a histogram of visual word occurrences to represent the muscle ultrasound images and trains an ensemble classifier through cross-validation, determining optimal parameters to improve classification accuracy for the ensemble diagnosis system. The dataset includes ultrasound images of six muscles from 53 subjects, consisting of 27 control and 26 patient cases. An empirical analysis was conducted for each binary classifier based on muscle type to select the best vocabulary tree properties or K values for BOF. The result indicates that ensemble subspace KNN classification, based on the bag of features, achieved an accuracy of 97.23%. CAD systems can effectively diagnose muscle pathology, thereby addressing limitations and identifying issues in individuals with diabetes. This research underscores muscle ultrasound as a promising diagnostic tool to aid physicians in making accurate diagnoses, streamlining workflow, and uncovering muscle-related complications in DPN patients.

Manipulator with Integrated Flexible Tactile Sensing Arrays for Kiwifruit Ripeness and Size Classification.

Fruit grading for ripeness and size is an essential process in the supply chain. Incorrect grading can easily lead to spoiled and degraded fruits entering the market, reducing consumers' confidence in purchasing. At the same time, it is easy to cause the fruit supply chain to reduce profits, unreasonable resource allocation, and related practitioners' income. The current mainstream machine vision grading and manual grading in the production line have dilemmas such as susceptibility to environmental interference, inconsistent grading standards, high cost, and labor shortage. To overcome these problems, this study proposes an integrated flexible tactile sensing array (3 × 4) manipulator for efficient, stable, low-cost, and accurate ripeness and size grading of kiwifruit. The flexible sensing manipulator grasps the kiwifruit, detects the hardness of the kiwifruit by relying on tactile sensing, and determines the ripeness level based on the hardness. The size of the kiwifruit is also differentiated according to whether there is a significant change in the resistance of the topmost sensing unit of the flexible pressure sensor array. The 0, 1, 2, 3, 4, and 5 anomalies that may occur in actual production were tested and combined with machine learning KNN, SVM, and RF algorithms for data modeling and grading. The results show that the lowest accuracy of 0, 1, 2, 3, 4, and 5 possible outliers is 86.67% (KNN), 95.83% (SVM), and 92.5% (RF), respectively. KNN has the lowest classification effect, and SVM has the best. This study overcomes the drawbacks of inefficient destructive detection and unstable manual detection and makes up for the vulnerability of single machine vision to interference from environmental factors. This study can alleviate the challenges caused by fruit wastage and promote the sustainable production and consumption of the fruit industry chain.

Boosting Algorithms for the Accident Severity Classification

<div><i>Background:</i> Road accident severity estimation is a critical aspect of road safety analysis and traffic management. Accurate severity estimation contributes to the formulation of effective road safety policies. Knowledge of the potential consequences of certain behaviors or conditions can contribute to safer driving practices. Identifying patterns of high-severity accidents allows for targeted improvements in terms of overall road safety. <i>Objective:</i> This study focuses on analyzing road accidents by utilizing real data, i.e., US road accidents open database called “CRSS.” It employs advanced machine learning models such as boosting algorithms such as LGBM, XGBoost, and CatBoost to predict accident severity classification based on various parameters. The study also aims to contribute to road safety by providing predictive insights for stakeholders, functional safety engineering community, and policymakers using KABCO classification systems. The article includes sections covering theoretical methodology, data analysis, model development, evaluation, performance metrics, and implications for improving road safety measures by comparing the performance of different boosting algorithms on the CRSS dataset. This study aims to identify the most effective machine learning algorithm to integrate into our product line in the near future, enabling accurate prediction of both accident severity and occurrence. <i>Results and Conclusions:</i> This study addresses challenges in evaluating performance metrics for different severity classes within unbalanced datasets, emphasizing the impact of dominant classes like Class O (O = no apparent injury) on overall accuracy. The investigation reveals the limitations and conservatism associated with imbalanced data in boosting models, hinting at a potential ceiling in their performance around 80%. Comparative analysis of algorithms, including CatBoost, XGBoost, and LGBM, demonstrates comparable performance even in the case of applying KNN algorithm for pre-processing, based on various metrics, especially accuracy, <i>F</i><sub>1</sub>-score, ROC-AUC, and PR-AUC for all severity classes. XGBoost with KNN algorithm did not show any significant performance improvement compared to the XGBoost without KNN algorithm. The study includes performance metrics, such as <i>F</i><sub>1</sub>-score, CM upper triangle, ROC-AUC, and PR-AUC applied to an accident analysis case study. Future work directions involve extending the application of CatBoost, XGBoost, and other algorithms to diverse datasets, exploring the capabilities of deep neural networks, refining dataset preparation for accuracy improvement, and creating unified tools for hazard analysis and risk assessment.</div>

The application of improved DTW algorithm in sports posture recognition

Sports posture recognition plays a crucial role in modern sports science and training. Posture recognition and analysis plays a positive role in improving sports quality and ensuring sports safety. However, existing recognition technologies still have poor recognition and accuracy in large amounts of posture data. Therefore, to further improve the performance of the existing posture recognition techniques, this study assumes that postures during movement can be effectively represented through the time series of skeletal key points, and the local similarity of these postures can be captured through the Dynamic Time Warping (DTW) algorithm. Based on this assumption, the existing DTW algorithm is improved by introducing the K-Nearest Neighbor (KNN) algorithm and combining it with Principal Component Analysis (PCA) for feature dimensionality reduction. A novel algorithmic model for postures recognition is proposed. The experimental results showed that the improved algorithm performed well in postures recognition rate and accuracy. Especially, when the k value was 5, the recognition rate reached up to 89%, and the accuracy reached 87%. Compared with the existing algorithm, the improved KNN-DTW algorithm has significant improvement in accuracy and computational efficiency. In summary, the new algorithm shows significant advantages in terms of accuracy and stability, providing a powerful tool for the analysis of athletic postures in the field of sports. Meanwhile, this research result has important application prospects in fields such as sports training, sports medicine, and virtual reality.

Organizing planning knowledge for automated vehicles and intelligent transportation systems

AbstractIntelligent Transportation Systems (ITS) are crucial for developing fully automated vehicles. While significant progress has been made with advanced driver assistance systems and automation technology, challenges remain, such as improving traffic information, enhancing planning and control systems, and developing better decision‐making capabilities. Despite these hurdles, the potential benefits of ITS are so many that its challenges have attracted substantial industrial investment and research groups interested in the automated driving field. In this work, a methodology based on state space search for planning knowledge integration is proposed. The main goal of the proposal is to provide a planning system with the necessary information to perform properly any task related to lateral and longitudinal control, path following, trajectory generation, arbitration and behavior execution by localizing the vehicle with respect to a high‐level road plan. To this end, this research compares cutting‐edge methods for rapidly finding the K nearest neighbor in relatively high dimensional road plans constructed from the traffic information stored in a high definition map. During the experimentation phase, promising real‐time results have been obtained for fast KNN algorithms, leading to a robust tree index‐based methodology for decision making in self‐driving vehicles combining path planning, trajectory tracking, trajectory creation, knowledge aggregation and precise vehicle control.

Implementation of K-Nearest Neigbors for Prediction of Motorcycle Service Waiting Times in Develop Tech

This research examines the application of the K-Nearest Neighbors (KNN) algorithm to predict wait times at Develop Tech, a workshop that offers affordable services but has longer spare parts wait times compared to official workshops. The research method used is descriptive quantitative, involving data collection and processing. In this study, the KNN algorithm is utilized to predict wait times by measuring distances between data points using and performing voting based on the K value to determine the final prediction. Testing on 100 data points demonstrated that KNN could predict wait times very accurately, achieving 100% accuracy, precision, and recall at certain K values. The data was split into 80% for training and 20% for testing, a method commonly used in machine learning research to ensure a balance between training data and validation. The results indicate that the KNN algorithm is reliable for predicting wait times with optimal performance at K values between 3 and 10. These findings support the conclusion that the KNN algorithm functions effectively in predicting wait times at the workshop.

A novel ranked k-nearest neighbors algorithm for missing data imputation

Missing data is a common problem in many domains that rely on data analysis. The k Nearest Neighbors imputation method has been widely used to address this issue, but it has limitations in accurately imputing missing values, especially for datasets with small pairwise correlations and small values of k. In this study, we proposed a method, Ranked k Nearest Neighbors imputation that uses a similar approach to k Nearest Neighbor, but utilizing the concept of Ranked set sampling to select the most relevant neighbors for imputation. Our results show that the proposed method outperforms the standard k nearest neighbor method in terms of imputation accuracy both in case of Missing Completely at Random and Missing at Random mechanism, as demonstrated by consistently lower MSIE and MAIE values across all datasets. This suggests that the proposed method is a promising alternative for imputing missing values in datasets with small pairwise correlations and small values of k. Thus, the proposed Ranked k Nearest Neighbor method has important implications for data imputation in various domains and can contribute to the development of more efficient and accurate imputation methods without adding any computational complexity to an algorithm.

Increasing Student Interest in Learning through the Implementation of the K-Nearest Neighbor Algorithm in Classifying Learning Preferences at SMAN 1 Kraksaan

This research examines the effectiveness of implementing the K-Nearest Neighbor (KNN) algorithm in classifying student learning preferences and its impact on increasing interest in learning at SMAN 1 Kraksaan. The main aim of the research is to optimize learning methods through personalization based on individual student preferences. The study involved 560 students of SMAN 1 Kraksaan, with data including variables of age, gender, academic grades, daily study time, attendance and participation in class. The KNN algorithm is used to classify students' learning preferences into visual, auditory, kinesthetic, and reading/writing categories. The learning method is then adjusted based on the results of this classification. The results show that the KNN algorithm is able to classify student learning preferences with an accuracy of 80.36%. After implementing personalized learning methods, there was a significant increase in students' interest in learning, with an average increase of 1.76 points on a 10-point scale. Paired t-test analysis showed a statistically significant difference between interest in learning before and after intervention (p < 0.0001). This research concludes that the implementation of the KNN algorithm in classifying learning preferences can help increase students' interest in learning effectively. These findings emphasize the importance of personalization in education and demonstrate the potential of integrating machine learning in the pedagogical process to improve learning outcomes.

Analisis KNN untuk Tempat Rekomendasi Tempat Wisata Sumba Barat

The growth of the internet has influenced the tourism industry because the internet makes it easier for individuals to obtain reviews about places to visit and because the internet is a tool used by tourist site managers to assess the quality of their offerings. The increase in the number of tourists of almost two million in just three years in West Sumba is proof of this influence. Social media is a tool that people use to interact with each other online; some people have multiple accounts on platforms such as Instagram, WhatsApp, Facebook, Telegram, Twitter, and so on. Tourists can receive recommendations for tourist attractions based on price and type of trip desired through a tourist attraction recommendation system that uses the KNN algorithm. Three factors were used in this research: activity, type of tourism, and type of price. An accuracy of 63.16% is found in the test results using the KNN algorithm and the Rapid Miner application with a K value of 5. The analysis results show that the K-Nearest Neighbor (K-NN) approach can be used as a guideline for recommending tourist destinations to visitors in West Sumba.

Integration of 3D-QSAR, molecular docking, and machine learning techniques for rational design of nicotinamide-based SIRT2 inhibitors

Selective inhibitors of sirtuin-2 (SIRT2) are increasingly recognized as potential therapeutics for cancer and neurodegenerative diseases. Derivatives of 5-((3-amidobenzyl)oxy)nicotinamides have been identified as some of the most potent and selective SIRT2 inhibitors reported to date (​Ai et al., 2016​; ​Ai et al., 2023​, ​Baroni et al., 2007​). In this study, a 3D-QSAR (3D-Quantitative Structure-Activity Relationship) model was developed using a dataset of 86 nicotinamide-based SIRT2 inhibitors from the literature, along with GRIND-derived pharmacophore models for selected inhibitors. External validation parameters emphasized the reliability of the 3D-QSAR model in predicting SIRT2 inhibition within the defined applicability domain. The interpretation of the 3D-QSAR model facilitated the generation of GRIND-derived pharmacophore models, which in turn enabled the design of novel SIRT2 inhibitors. Furthermore, based on molecular docking results for the SIRT1–3 isoforms, two classification models were developed: a SIRT1/2 model using the Naive Bayes algorithm and a SIRT2/3 model using the k-nearest neighbors algorithm, to predict the selectivity of inhibitors for SIRT1/2 and SIRT2/3. External validation parameters of the selectivity models confirmed their predictive power. Ultimately, the integration of 3D-QSAR, selectivity models and prediction of ADMET properties facilitated the identification of the most promising selective SIRT2 inhibitors for further development.

Diagnosis of Schizophrenia Using EEG Sensor Data: A Novel Approach with Automated Log Energy-Based Empirical Wavelet Reconstruction and Cepstral Features.

Schizophrenia (SZ) is a severe mental disorder characterised by disruptions in cognition, behaviour, and perception, significantly impacting an individual's life. Traditional SZ diagnosis methods are labour-intensive and prone to errors. This study presents an innovative automated approach for detecting SZ acquired through electroencephalogram (EEG) sensor signals, aiming to improve diagnostic efficiency and accuracy. We utilised Fast Independent Component Analysis to remove artefacts from raw EEG sensor data. A novel Automated Log Energy-based Empirical Wavelet Reconstruction (ALEEWR) technique was introduced to reconstruct decomposed modes based on their variability, ensuring effective extraction of meaningful EEG signatures. Cepstral-based features-cepstral activity, cepstral mobility, and cepstral complexity-were used to capture the power, rate of change, and irregularity of the cepstrum of preprocessed EEG signals. ANOVA-based feature selection was applied to refine these features before classification using the K-Nearest Neighbour (KNN) algorithm. Our approach achieved an exceptional accuracy of 99.4%, significantly surpassing previous methods. The proposed ALEEWR and cepstral analysis demonstrated high precision, sensitivity, and specificity in the automated diagnosis of schizophrenia. This study introduces a highly accurate and efficient method for SZ detection using EEG technology. The proposed techniques offer significant improvements in diagnostic accuracy, with potential implications for enhancing SZ diagnosis and patient care through automated systems.