Weighted K-nearest Neighbor Research Articles

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.

Machine learning for air quality index (AQI) forecasting: shallow learning or deep learning?

In this study, several machine learning (ML) models consisting of shallow learning (SL) models (e.g., random forest (RF), K-nearest neighbor (KNN), weighted K-nearest neighbor (WKNN), support vector machine (SVM), artificial neural network (ANN), and deep learning (DL) models (e.g., long short-term memory (LSTM), gated recurrent unit (GRU), recurrent neural network (RNN), and convolutional neural network (CNN)) have been employed for predicting air pollution and its classification. The models were selected based on factors such as prediction accuracy, model generalization, model complexity, and training time. Our study focuses on analyzing and predicting the air quality index (AQI) using daily PM10 concentration as natural pollutants and nine meteorological parameters from March 2013 to February 2022 in Zabol. We also utilized the information gain (IG) method for feature selection. Several measures including accuracy, F1 score, precision, recall, and the area under the curve (AUC), are computed to assess model performance. This study demonstrates the efficacy of DL models, particularly CNN, in predicting the AQI with remarkable accuracy. Our findings reveal that all models effectively classify air quality levels, with an AUC of 0.95 for the good class in both DL and ANN models, significantly outperforming SL models. The AUC values for the hazardous and moderate classes of DL models were also impressive, at 0.90 and 0.83, respectively, underscoring their effectiveness in critical classifications. In terms of performance, CNN achieved an accuracy of 0.60, leading the models, while RF followed closely at 0.58. RNN, GRU, ANN, and SVM each reached an accuracy of 0.57, demonstrating a competitive edge. LSTM and WKNN recorded an accuracy of 0.55, and KNN was slightly lower at 0.53. These results highlight the superior capabilities of DL models in addressing complex air quality classifications, providing invaluable insights for policymakers. By leveraging these advanced techniques, stakeholders can implement more effective strategies to combat air pollution and safeguard public health. It is worth noting that irregular monitoring of air quality data may affect the robustness of our predictions, highlighting the need for more consistent data collection to ensure an accurate representation of pollution levels.

A rapid fingerprint positioning method based on deep convolutional neural network for MIMO-OFDM systems

The combination of fingerprint positioning and 5G (the 5th Generation Mobile Communication Technology) offers broader application prospects for indoor positioning technology, but also brings challenges in real-time performance. In this paper, we propose a fingerprint positioning method based on a deep convolutional neural network (DCNN) using a classification approach in a single-base station scenario for massive multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) systems. We introduce an angle-delay domain fingerprint matrix that simplifies the computation process and increases the location differentiation. The cosine distance is chosen as the fingerprint similarity criterion due to its sensitivity to angular differences. First, the DCNN model is used to determine the sub-area to which the mobile terminal belongs, and then the weighted K-nearest neighbor (WKNN) matching algorithm is used to estimate the position within the sub-area. The positioning performance is simulated in a DeepMIMO indoor environment, showing that the classification DCNN method reduces the positioning time by 77.05% compared to the non-classification method, with only a 1.08% increase in average positioning error.

Enhancing induction machine fault detection through machine learning: Time and frequency analysis of vibration signals

The integration of machine learning algorithms into fault diagnosis is regarded as an advanced and effective method for detecting electrical system faults. Vibration signals are identified as valuable and easily accessible data for fault identification in electrical machines. In this study, experiments were conducted to assemble a dataset consisting of 525 × 3 instances, each containing 200 three-axis vibration signal measurements. These measurements were obtained from a laboratory test bench equipped with a customized winding three-phase induction machine. Instead of directly analyzing the vibration signals, a feature extraction approach was employed, calculating a comprehensive set of statistical, harmonic, and impulsive features from the time domain (e.g., ShapeFactor, SINAD, ClearanceFactor, ImpulseFactor, CrestFactor, Kurtosis, Skewness, THD, Std, RMS, Mean, PeakValue, SNR), along with spectral features from the frequency domain (e.g., Peak Frequencies, Amplitudes, BandPower). To improve model efficiency, Analysis of Variance (ANOVA) was applied to select only the most significant features, with F-statistics used to rank feature importance. Features with higher F-statistics were prioritized for their ability to explain more variance in motor fault classification. This selective approach reduced model complexity, helping to minimize overfitting and focus on features that had a substantial impact on predictive accuracy. By concentrating on these high-impact features, a balance between simplicity and performance was achieved. These selected features were then used to train five machine learning classifiers: Ensemble (Bagged Trees), Quadratic Support Vector Machine, Weighted K-Nearest Neighbors, Efficient Logistic Regression, and Neural Networks. The performance of these classifiers was evaluated using various metrics, with validation accuracy rates ranging from 78.3% to 98.8%. A comparative study with similar works in the literature was conducted, demonstrating that high performances were obtained with the proposed approach while maintaining computational efficiency.

Predicting the effectiveness of binaural beats on working memory.

Working memory is vital for short-term information processing. Binaural beats can enhance working memory by improving attention and memory consolidation through neural synchronization. However, individual differences in cognitive and neuronal functioning affect effectiveness of binaural beats, necessitating personalized approaches. This study aimed to develop a machine learning model to predict binaural beats's effectiveness on working memory using electroencephalography. Sixty healthy participants underwent a 5-min electroencephalography recording, an initial working memory evaluation, 15 min of binaural beats stimulation, and a subsequent working memory evaluation using digit span tests of increasing difficulty. Recall accuracy and response times were measured. Differential scores from pre-evaluation and post-evaluation labeled participants as active or inactive to binaural beats stimulation. electroencephalography data, recorded using 14 electrodes, provided brain activity estimates across theta, alpha, beta, and gamma frequency bands, resulting in 56 features (14 channels × 4 bands) for the machine learning model. Several classifiers were tested to identify the most effective model. The weighted K-nearest neighbors model achieved the highest accuracy (90.0%) and area under the receiver operating characteristic curve (92.24%). Frontal and parietal electroencephalography channels in theta and alpha bands were crucial for classification. This study's findings offer significant clinical insights, enabling informed interventions and preventing resource inefficiency.

SPLHRNMTF: robust orthogonal non-negative matrix tri-factorization with self-paced learning and dual hypergraph regularization for predicting miRNA-disease associations

MicroRNAs (miRNAs) have been demonstrated to be closely related to human diseases. Studying the potential associations between miRNAs and diseases contributes to our understanding of disease pathogenic mechanisms. As traditional biological experiments are costly and time-consuming, computational models can be considered as effective complementary tools. In this study, we propose a novel model of robust orthogonal non-negative matrix tri-factorization (NMTF) with self-paced learning and dual hypergraph regularization, named SPLHRNMTF, to predict miRNA-disease associations. More specifically, SPLHRNMTF first uses a non-linear fusion method to obtain miRNA and disease comprehensive similarity. Subsequently, the improved miRNA-disease association matrix is reformulated based on weighted k-nearest neighbor profiles to correct false-negative associations. In addition, we utilize L2,1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$L_{2,1}$$\\end{document} norm to replace Frobenius norm to calculate residual error, alleviating the impact of noise and outliers on prediction performance. Then, we integrate self-paced learning into NMTF to alleviate the model from falling into bad local optimal solutions by gradually including samples from easy to complex. Finally, hypergraph regularization is introduced to capture high-order complex relations from hypergraphs related to miRNAs and diseases. In 5-fold cross-validation five times experiments, SPLHRNMTF obtains higher average AUC values than other baseline models. Moreover, the case studies on breast neoplasms and lung neoplasms further demonstrate the accuracy of SPLHRNMTF. Meanwhile, the potential associations discovered are of biological significance.

Indoor fingerprint localization algorithm based on WKNN and LightGBM-GA

Abstract WiFi-based indoor fingerprint localization is widely used in indoor localization owing to its high accuracy and low deployment costs. Changes in the indoor signal environment directly affect localization accuracy. To improve localization accuracy and stability, this paper proposes a novel indoor fingerprint localization algorithm based on Weighted K-Nearest Neighbors (WKNN) and an enhanced Light Gradient Boosting Machine (LightGBM). First, in the offline phase, Gaussian filtering and K-Nearest Neighbors-Random Forest information completion algorithm with fusion of Euclidean and Manhattan distances are used to remove outliers from the fingerprint database dataset and fill in missing fingerprint information, ensuring the integrity of the fingerprint database. During the online phase, the fingerprint database is divided into training and testing sets. The LightGBM algorithm is used for modeling. Additionally, Genetic Algorithm (GA) is use d to optimize the parameters of LightGBM algorithm to find the best parameters by fitness evaluation. Then, the nearest neighbor set found by the WKNN algorithm is introduced into the LightGBM-GA model. Combining the predictions from the standalone LightGBM algorithm and performing weighted fusion yields the final predicted coordinates. The experiments are conducted in 8 m × 10 m laboratory containing 5 access points and 80 reference points to collect the Received Signal Strength Indication values of 5 WiFi hotspots. The experimental results show that the average localization error of the proposed algorithm is 1.11 m, which is reduced by 6.7%–38.3% compared to K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGBoost), LightGBM, KNN + XGBoost, WKNN + LightGBM, and WKNN + XGBoost-GA localization algorithms. The localization curve is smoother, and the cumulative distribution function converges faster. Moreover, the localization time is reduced by 13.3%–36.7%, effectively enhancing localization accuracy and decreasing localization time.

Kruskal Wallis and mRMR Feature Selection based Online Signature Verification System using Multiple SVM and KNN

Signature verification is a very important research area. Signature has been widely accepted as a person authentication method for centuries. It is mostly used in financial transactions, document authentication and agreements. It is more susceptible to being forged than any other biometrics. Online signature verification is used in real-time applications like e-commerce, online resource access, online financial transactions, physical access into a restricted area and many more. In order to achieve high efficiency in online signature verification systems, feature extraction and feature selection play a significant role. A suitable signature verification system is needed to prevent forgery and accept the genuine signer. We have extracted 30 global features from all 40 signers for verification. Here, k fold cross-validation technique is used to enhance the model's performance on unseen data. User-specific feature selection and ranking are done using Kruskal Wallis and Minimum Redundancy Maximum Relevance (mRMR) algorithm to hunt which performs better in our case. Kruskal-Wallis method tests if two or more classes have an equal median and gives the value of P based on which discriminative features are selected, whereas the mRMR algorithm ranks the whole feature set according to its importance. It evaluates the relevance of a feature and penalizes redundancy. Finally, multiple SVM and KNN classifiers are trained and tested with various selected features using Kruskal Wallis and mRMR to determine which combination performs best for the online signature verification system. Our model is trained, validated and tested on the SVC 2004 Task 1 database, which consists of skill forgery signatures. Here, one to one verification is done using each user's genuine and skill forgery signatures, which is the hardest to detect. Best average testing accuracy achieved in our case is 90.25% using Weighted KNN and Kruskal Wallis selected 15 features.

Enhanced WiFi/Pedestrian Dead Reckoning Indoor Localization Using Artemisinin Optimization-Particle Swarm Optimization-Particle Filter

WiFi fingerprint-based positioning is a method for indoor localization with the advent of widespread deployment of WiFi and the Internet of Things. However, single WiFi fingerprint positioning has the problems of mismatch, unstable signal strength and limited accuracy. Aiming to address these issues, this paper proposes the fusion algorithm combining WiFi and pedestrian dead reckoning (PDR). Firstly, the particle swarm optimization (PSO) model is utilized to optimize the weighted k-nearest neighbors (WKNN) in the WiFi part. Additionally, the artemisinin optimization (AO) algorithm is used to optimize the particle filter (PF) to improve the fusion effect of the WiFi and PDR. Finally, to thoroughly validate the localization performance of the proposed algorithm, we designed experiments involving two scenarios with four smartphone gestures: calling, dangling, handheld, and pocketed. The experimental results unequivocally indicate that the positioning error of AO-PSO-PF algorithm is lower than that of other algorithms including PDR, WiFi, PF, APF, and FPF. The average positioning errors for the two experiments are 0.95 m and 1.42 m, respectively.

Hyperspectral reflectance and machine learning for multi-site monitoring of cotton growth

Hyperspectral measurements can help with rapid decision-making and collecting data across multiple locations. However, there are multiple data processing methods (Savisky-Golay [SG], first derivative [FD], and normalization) and analyses (partial least squares regression [PLS], weighted k-nearest neighbor [KKNN], support vector machine [SVM], and random forest [RF]) that can be used to determine the best relationship between physical measurements and hyperspectral data. In the current study, FD was the best method for data processing and SVM was the best model for predicting average cotton (Gossypium spp. Malvaceae) height and nodes. However, the combination of FD and RF were best at predicting cotton leaf area index, canopy cover, and chlorophyll content across the growing season. Additionally, results from models developed by both SVM and RF were closely related to pseudo-CHIME satellite wavebands, where in-situ hyperspectral data were matched to the spectral resolutions of a future hyperspectral satellite. The information and results presented will aid producers and other members of the cotton industry to make rapid and meaningful decisions that could result in greater yield and sustainable intensification.

Investigation of condition monitoring system for grid connected photovoltaic (GCPV) system with power electronics converters using machine learning techniques

Power systems protection has become more vital in recent years to ensure stability, reliability, security, and power quality due to the exponential growth of grid-connected photovoltaic (GCPV) systems. As a result, several nations have set new grid codes for the grid integration of PV plant installations to overcome these concerns. Investigating Fault Ride Through (FRT) capacity is one of the primary criteria for grid codes. For 3-phase GCPV systems, fault detection and classification approaches are proposed in this study. Firstly, different faults that occurred in the GCPV system are categorized and compared, with the critical and analytical evaluation of grid codes, particularly FRT requirements such as Low Voltage Ride Through (LVRT) and High Voltage Ride Through (HVRT) for different nations. Further, a detailed classification and a comparison of the existing FRT techniques are presented for better control methods based on system complexity, detection accuracy, and other evolutionary criteria. To ensure smooth grid operation, accurate fault detection and condition monitoring of the systems are required. This paper discusses a machine learning (ML) based technique for detecting faults in 3-phase GCPV systems. Multi-peak phenomena caused by FRT capabilities and anti-islanding detection are the main problems experienced while integrating a PV system into the local grid. The fault classification technique is developed using weighted K-nearest neighbor (WKNN) and fine Gaussian support vector machine (FGSVM) based ML approaches utilizing Wavelet Transform. The proposed ML-based findings show that the fault detection algorithm-based classification accuracy has significantly improved.

Indoor unknown radio transmitter localization using improved RSSD and grey correlation degree

Abstract Accurate location of unknown radio transmitter (URT) is the key to secure wireless communication. Since the fingerprint positioning methods based on received signal strength difference (RSSD) can adapt to the diversity of transmitting power and frequency, RSSD has become a popular scheme for locating the unknown radio transmitter. However, the RSSD is obtained by subtracting the RSS from two different access points (APs), so the interference of noise on the RSS is inherited and amplified by the RSSD. Besides, the need for more APs to ensure positioning accuracy leads to an increase in hardware costs. In this paper, a RSSD-based fuzzy weight grey correlation degree positioning algorithm, called FUZZY-GREY, is proposed to reduce the interference of noise, save AP hardware cost and improve the positioning accuracy. Firstly, online RSSD vector is improved by using fuzzy weight to reduce the noise interference. Secondly, the RSSD-based grey correlation coefficient is designed to calculate the correlation degree of the corresponding RSSD and ensure data integrity. Finally, a RSSD-based grey correlation degree scheme combining with fuzzy weight is proposed to select optimal reference points (RPs). Simulation and experimental results show that the proposed algorithm has better positioning performance than weighted k-nearest neighbor (WKNN), maximum correlation coefficient estimation (MCORE), Naive Bayes and support vector machine (SVM) in the case of different selected K numbers, grid distances, noise levels and AP numbers.

Autonomous and reliable fingerprint map maintenance for indoor positioning system

In WiFi-based crowdsourced fingerprinting indoor positioning systems (IPS), the signal space of WiFi APs changes over time. To autonomously maintain a highly reliable localization accuracy, the fingerprint database needs regular maintenance and updates. However, this process is labor-intensive and time-consuming due to the appearance of faulty access points (APs) in crowdsourced samples received from target clients, which are mainly used for autonomous maintenance and updates. Additionally, if some APs are relocated, removed, or replaced in the indoor environment after fingerprint map construction, it can severely impact IPS accuracy. In this paper, we present Dynamic Online Fingerprint Learning with Altered APs status-aware and updating (DOFLAAU) for IPS. Our systematic methodology involves several key steps. First, we employ the Modified Group Method of Data Handling (GMDH) neural network regression for autonomous AP status monitoring and alteration detection. Next, we perform autonomous APs subset sample selection using a modified Thomson model, followed by outlier feature detection and removal based on the weighted sample density rate. Thirdly, we propose a dynamic online fingerprint map updating model using the cosine similarity distance metric. Lastly, we adopted an effective signal distance-based weighted k-nearest neighbor algorithm to improve IPS accuracy. The experiment results validate the efficiency and effectiveness of our proposed algorithms in terms of better localization accuracy compared to peer algorithms.

Density peaks clustering based on Gaussian fuzzy neighborhood with noise parameter

Density peak clustering (DPC) is an effective clustering method known for its robustness, non-iterative nature, and hybrid approach. However, it is not without limitations: (a) the determination of the cutoff distance (dc) relies on human experience, which can significantly impact the clustering outcome; (b) DPC does not take into account the local structure of the data when computing local densities; (c) it employs a crisp kernel for density computation; (d) the performance of DPC is affected by chain reactions; and (e) DPC often struggles to handle noisy data. In order to address these limitations, this paper proposes a novel approach called DPC based on Gaussian fuzzy neighborhood with noise parameter (DPC-GFNN). The proposed method leverages a Gaussian fuzzy kernel to enhance the separation between clusters and mitigates the influence of outliers through an adjustable noise parameter (λ). DPC-GFNN utilizes a k-nearest neighbor graph based on density to label highly dense regions. This technique effectively avoids chain reactions by assigning accurate labels to points in border areas, enabling proper clustering of data with diverse shapes and densities. To evaluate the effectiveness of DPC-GFNN, a series of experiments are conducted on both real-world and synthetic datasets. The experimental results demonstrate that DPC-GFNN exhibits superior robustness and clustering accuracy compared to other modified variants of DPC including DPC based on k-nearest neighbors (DPC-KNN), improved DPC (IDPC), DPC based on density backbone and fuzzy neighborhood (DPC-DBFN), and DPC based on fuzzy weighted k-nearest neighbors (FKNN).

Fingerprint-Based Localization Enabled by Low-Rank Matrix Reconstruction in Intelligent Reflective Surface-Assisted Networks

The intelligent reflective surface (IRS) is a novel network node that consists of a large-scale passive reflective array to obtain a customized reflected wave direction by modulating the amplitude phase, which can be easily deployed to change the wireless signal propagation environment and enhance the communication performance under a non-line-of-sight (NLOS) environment, where location services cannot perform accurately. In this study, a low-rank matrix reconstruction-enabled fingerprint-based localization algorithm for IRS-assisted networks is proposed. Firstly, a 5G positioning system based on IRSs is constructed using multiple IRSs deployed to reflect signals. This enables the base station to overcome the influence of NLOS and receive the positioning signal of the point to be positioned. Then, the angular domain power expectation matrix of the received signal is extracted as a fingerprint to form a partial fingerprint database. Next, the complete fingerprint database is reconstructed using the low-rank matrix fitting algorithm, thereby considerably reducing the workload of building the fingerprint database. Finally, maximal ratio combining is used to increase the gap between the fingerprint data, and the Weighted K-Nearest Neighbor (WKNN) algorithm is used to match the fingerprint data and estimate the location of the points to be located. The simulation results demonstrate the feasibility of the proposed method to achieve sub-meter accuracy in an NLOS environment.

Optimal fusion of features from decomposed ultrasound RF data with adaptive weighted ensemble classifier to improve breast lesion classification

Early diagnosis plays a crucial role in successful treatment of breast tumors and reduced mortality. In this study, considering the complementary advantages between features and combined with the improvement of classifiers, fusion of optimal complexity and texture features from decomposed ultrasound radio frequency (RF) data is proposed to improve breast lesion classification performance. In this method, three complexity features and four texture features were extracted from the ring regions of interest for breast lesions in all decomposed RF sub-images and their combinations. Selection techniques based on analysis of feature relevance, redundancy, and interaction (FRRI) were used to determine the optimal feature sets (FS–FRRI). Finally, three classifiers with the best performance (weighted k-nearest neighbor, bagged tree, Gaussian Naive Bayes (NB)) were selected based on FS-FRRI. The three classifiers were integrated using the bagging method, and each classifier was adaptively weighted according to the genetic algorithm during the integration to classify breast lesions. The proposed method was evaluated using the Open Access Series of Breast Ultrasonic Data, with 10-fold cross-validation. The experimental results demonstrated that optimal performance was obtained by the FS–FRRI-based adaptive weighted ensemble classifier, with an accuracy of 97%, a sensitivity of 99%, a specificity of 96%, and an area under the receiver operating curve value of 0.97. Fusion of optimal complexity and texture features from decomposed ultrasound RF data with an adaptive weighted ensemble classifier can help improve breast lesion classification performance, which has great potential to assist clinicians in accurate diagnosis of breast lesions.

Aspect Based Sentiment Analysis of Beauty Products Using Neighbor Weighted K-Nearest Neighbor

This research aims to test the performance of Neighbor Weighted K-Nearest Neighbor (NWKNN) in handling imbalanced datasets in the case of aspect-based sentiment analysis. The data used in this research are beauty product reviews from the Kaggel site. Data obtained from 2,449 reviews. Every product review before entering the classification stage, goes through preprocessing. In this research, the preprocessing stages consist of casefolding, cleaning, tokenization, normalization, stemming, convert negation, and stopword removal processes. So that the preprocessing results can be processed by a classification algorithm, each review that has been preprocessed is included in feature extraction. The feature extraction method used in this research is TF-IDF. The results of feature extraction are included in the classification process. In this research, each review went through a classification process several times. Because in this research, multilabel handling uses binary relevance techniques. Each classification uses NWKNN. Classification was carried out four times according to the aspects used in this research, namely: price, packaging, effectiveness and aroma. So each classification produces a polarity for each aspect, namely: positive, negative, or non-sentimental. The results of performance testing with Confusion Matrix showed that NWKNN's performance was higher than KNN's for each aspect, in terms of f1-score. Where the optimal e and k values for the NWKNN method are k=40 and e=2. This shows that NWKNN proves to perform better when the dataset is imbalanced compared to KNN.

A feature weighted K-nearest neighbor algorithm based on association rules

A feature weighted K-nearest neighbor algorithm based on association rules

Smart hydropower management: utilizing machine learning and deep learning method to enhance dam’s energy generation efficiency

AbstractRenewable energy sources and hydroelectric power generation in large parts of the electricity market are crucial as environmental pollution worsens . Utilizing meteorological data from the region, where the Hirfanlı Dam is located, this study employs machine learning (ML) and introduces a novel hybrid Genetic Grey Wolf Optimizer (GGW0)-based Convolutional Neural Network/Recurrent Neural Network (CNN/RNN) regression technique to predict hydroelectric power production (PP). In the first section of the study, various ML techniques SVR (Support Vector Regression), ELM (Extreme Learning Machine), RFR (Random Forest Regression), ANN (Artificial Neural Networks) and WKNNR (Weighted K-Nearest Neighbor) are presented with the Principal Component Analysis (PCA) method and the minimum–maximum method in the normalization of the features. A novel GGWO and CNN/RNN model)-Long Short-Term Memory (LSTM) regression technique is introduced in the second section. GGWO is used to select features, while the proposed CNN/RNN-LSTM model is employed for feature extraction and prediction of PP. The study demonstrates that the ELM algorithm in Method I outperforms other ML models, achieving a correlation coefficient (r) of 0.977 and the mean absolute error (MAE) of 0.4 with the best feature subset. Additionally, the proposed CNN/RNN hybrid model in Method II yields even better results, with r and MAE values of 0.9802 and 0.314, respectively. The research contributes to the field of renewable energy prediction, and the results can aid in efficient decision making for electricity generation and resource management.

An Optimum Load Forecasting Strategy (OLFS) for Smart Grids Based on Artificial Intelligence

Recently, the application of Artificial Intelligence (AI) in many areas of life has allowed raising the efficiency of systems and converting them into smart ones, especially in the field of energy. Integrating AI with power systems allows electrical grids to be smart enough to predict the future load, which is known as Intelligent Load Forecasting (ILF). Hence, suitable decisions for power system planning and operation procedures can be taken accordingly. Moreover, ILF can play a vital role in electrical demand response, which guarantees a reliable transitioning of power systems. This paper introduces an Optimum Load Forecasting Strategy (OLFS) for predicting future load in smart electrical grids based on AI techniques. The proposed OLFS consists of two sequential phases, which are: Data Preprocessing Phase (DPP) and Load Forecasting Phase (LFP). In the former phase, an input electrical load dataset is prepared before the actual forecasting takes place through two essential tasks, namely feature selection and outlier rejection. Feature selection is carried out using Advanced Leopard Seal Optimization (ALSO) as a new nature-inspired optimization technique, while outlier rejection is accomplished through the Interquartile Range (IQR) as a measure of statistical dispersion. On the other hand, actual load forecasting takes place in LFP using a new predictor called the Weighted K-Nearest Neighbor (WKNN) algorithm. The proposed OLFS has been tested through extensive experiments. Results have shown that OLFS outperforms recent load forecasting techniques as it introduces the maximum prediction accuracy with the minimum root mean square error.