Decomposition aided attention-based recurrent neural networks for multistep ahead time-series forecasting of renewable power generation

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e1795 - e1795

Published: Jan. 18, 2024

Renewable energy plays an increasingly important role in our future. As fossil fuels become more difficult to extract and effectively process, renewables offer a solution the ever-increasing demands of world. However, shift toward renewable is not without challenges. While reliable means storage that can be converted into usable energy, are dependent on external factors used for generation. Efficient often relying batteries have limited number charge cycles. A robust efficient system forecasting power generation from sources help alleviate some difficulties associated with transition energy. Therefore, this study proposes attention-based recurrent neural network approach generated sources. To networks make accurate forecasts, decomposition techniques utilized applied time series, modified metaheuristic introduced optimized hyperparameter values networks. This has been tested two real-world datasets covering both solar wind farms. The models by metaheuristics were compared those produced other state-of-the-art optimizers terms standard regression metrics statistical analysis. Finally, best-performing model was interpreted using SHapley Additive exPlanations.

Language: Английский

---

Tuning attention based long-short term memory neural networks for Parkinson’s disease detection using modified metaheuristics

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Feb. 21, 2024

Parkinson's disease (PD) is a progressively debilitating neurodegenerative disorder that primarily affects the dopaminergic system in basal ganglia, impacting millions of individuals globally. The clinical manifestations include resting tremors, muscle rigidity, bradykinesia, and postural instability. Diagnosis relies mainly on evaluation, lacking reliable diagnostic tests being inherently imprecise subjective. Early detection PD crucial for initiating treatments that, while unable to cure chronic condition, can enhance life quality patients alleviate symptoms. This study explores potential utilizing long-short term memory neural networks (LSTM) with attention mechanisms detect based dual-task walking test data. Given performance significantly inductance by architecture training parameter choices, modified version recently introduced crayfish optimization algorithm (COA) proposed, specifically tailored requirements this investigation. proposed optimizer assessed publicly accessible real-world gait dataset, results demonstrate its promise, achieving an accuracy 87.4187 % best-constructed models.

Language: Английский

---

Addressing Internet of Things security by enhanced sine cosine metaheuristics tuned hybrid machine learning model and results interpretation based on SHAP approach

PeerJ Computer Science, Journal Year: 2023, Volume and Issue: 9, P. e1405 - e1405

Published: June 30, 2023

An ever increasing number of electronic devices integrated into the Internet Things (IoT) generates vast amounts data, which gets transported via network and stored for further analysis. However, besides undisputed advantages this technology, it also brings risks unauthorized access data compromise, situations where machine learning (ML) artificial intelligence (AI) can help with detection potential threats, intrusions automation diagnostic process. The effectiveness applied algorithms largely depends on previously performed optimization, i.e., predetermined values hyperparameters training conducted to achieve desired result. Therefore, address very important issue IoT security, article proposes an AI framework based simple convolutional neural (CNN) extreme (ELM) tuned by modified sine cosine algorithm (SCA). Not withstanding that many methods addressing security issues have been developed, there is always a possibility improvements proposed research tried fill in gap. introduced was evaluated two ToN intrusion datasets, consist traffic generated Windows 7 10 environments. analysis results suggests model achieved superior level classification performance observed datasets. Additionally, conducting rigid statistical tests, best derived interpreted SHapley Additive exPlanations (SHAP) findings be used experts enhance systems.

Language: Английский

---

Performance evaluation of metaheuristics-tuned recurrent neural networks for electroencephalography anomaly detection

Frontiers in Physiology, Journal Year: 2023, Volume and Issue: 14

Published: Nov. 14, 2023

Electroencephalography (EEG) serves as a diagnostic technique for measuring brain waves and activity. Despite its precision in capturing electrical activity, certain factors like environmental influences during the test can affect objectivity accuracy of EEG interpretations. Challenges associated with interpretation, even advanced techniques to minimize artifact influences, significantly impact accurate interpretation findings. To address this issue, artificial intelligence (AI) has been utilized study analyze anomalies signals epilepsy detection. Recurrent neural networks (RNNs) are AI specifically designed handle sequential data, making them well-suited precise time-series tasks. While methods, including RNNs (ANNs), hold great promise, their effectiveness heavily relies on initial values assigned hyperparameters, which crucial performance concrete assignment. tune RNN performance, selection hyperparameters is approached typical optimization problem, metaheuristic algorithms employed further enhance process. The modified hybrid sine cosine algorithm developed used improve hyperparameter optimization. facilitate testing, publicly available real-world data utilized. A dataset constructed using captured from healthy archived patients confirmed be affected by epilepsy, well an active seizure. Two experiments have conducted generated dataset. In first experiment, models were tasked detection anomalous second experiment required segment normal, activity detect occurrences seizures data. Considering modest sample size (one 158 points) classification demonstrated decent outcomes. Obtained outcomes compared those other cutting-edge metaheuristics rigid statistical validation, results’ performed.

Language: Английский

---

Sentiment classification for insider threat identification using metaheuristic optimized machine learning classifiers

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 28, 2024

This study examines the formidable and complex challenge of insider threats to organizational security, addressing risks such as ransomware incidents, data breaches, extortion attempts. The research involves six experiments utilizing email, HTTP, file content data. To combat threats, emerging Natural Language Processing techniques are employed in conjunction with powerful Machine Learning classifiers, specifically XGBoost AdaBoost. focus is on recognizing sentiment context malicious actions, which considered less prone change compared commonly tracked metrics like location time access. enhance detection, a term frequency-inverse document frequency-based approach introduced, providing more robust, adaptable, maintainable method. Moreover, acknowledges significant impact hyperparameter selection classifier performance employs various contemporary optimizers, including modified version red fox optimization algorithm. proposed undergoes testing three simulated scenarios using public dataset, showcasing commendable outcomes.

Language: Английский

---

Parkinsons Detection from Gait Time Series Classification Using Modified Metaheuristic Optimized Long Short Term Memory

Neural Processing Letters, Journal Year: 2025, Volume and Issue: 57(1)

Published: Feb. 7, 2025

Language: Английский

---

Enhancing feature selection for multi-pose facial expression recognition using a hybrid of quantum inspired firefly algorithm and artificial bee colony algorithm

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 7, 2025

Facial expression recognition (FER) has advanced applications in various disciplines, including computer vision, Internet of Things, and artificial intelligence, supporting diverse domains such as medical escort services, learning analysis, fatigue detection, human-computer interaction. The accuracy these systems is utmost concern depends on effective feature selection, which directly impacts their ability to accurately detect facial expressions across poses. This research proposes a new hybrid approach called QIFABC (Hybrid Quantum-Inspired Firefly Artificial Bee Colony Algorithm), combines the Algorithm (QIFA) with (ABC) method enhance selection for multi-pose system. proposed algorithm uses attributes both QIFA ABC algorithms search space exploration, thereby improving robustness features FER. firefly agents initially move toward brightest until identified, then transition algorithm, targeting positions highest nectar quality. In order evaluate efficacy also conducted using QIFA, FA, algorithms. evaluated are utilized classifying face by utilizing deep neural network model, ResNet-50. presented FER system been tested benchmark datasets, RaF (Radboud Faces) KDEF (Karolinska Directed Emotional Faces). Experimental results show that ResNet50 achieves an 98.93%, 94.11%, 91.79% front, diagonal, profile poses dataset, respectively, 98.47%, 93.88%, 91.58% dataset.

Language: Английский

---

Decomposition Aided Bidirectional Long-Short-Term Memory Optimized by Hybrid Metaheuristic Applied for Wind Power Forecasting

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 30 - 42

Published: Jan. 1, 2024

Language: Английский

---

Anomaly Detection in Electroencephalography Readings Using Long Short-Term Memory Tuned by Modified Metaheuristic

Algorithms for intelligent systems, Journal Year: 2024, Volume and Issue: unknown, P. 133 - 148

Published: Jan. 1, 2024

Language: Английский

---

Tuning Natural Language Processing by Altered Metaheuristics Algorithm for Phishing Email Identification

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 265 - 282

Published: Jan. 1, 2025

Language: Английский

---