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

---

Intrusion detection in metaverse environment internet of things systems by metaheuristics tuned two level framework

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

Published: Jan. 28, 2025

Internet of Things (IoT) is one the most important emerging technologies that supports Metaverse integrating process, by enabling smooth data transfer among physical and virtual domains. Integrating sensor devices, wearables, smart gadgets into environment enables IoT to deepen interactions enhance immersion, both crucial for a completely integrated, data-driven Metaverse. Nevertheless, because devices are often built with minimal hardware connected Internet, they highly susceptible different types cyberattacks, presenting significant security problem maintaining secure infrastructure. Conventional techniques have difficulty countering these evolving threats, highlighting need adaptive solutions powered artificial intelligence (AI). This work seeks improve trust in edge integrated study revolves around hybrid framework combines convolutional neural networks (CNN) machine learning (ML) classifying models, like categorical boosting (CatBoost) light gradient-boosting (LightGBM), further optimized through metaheuristics optimizers leveraged performance. A two-leveled architecture was designed manage intricate data, detection classification attacks within networks. thorough analysis utilizing real-world network dataset validates proposed architecture's efficacy identification specific variants malevolent assaults, classic multi-class challenge. Three experiments were executed open public, where top models attained supreme accuracy 99.83% classification. Additionally, explainable AI methods offered valuable supplementary insights model's decision-making supporting future collection efforts enhancing systems.

Language: Английский

---

Novel hybrid classifier based on fuzzy type-III decision maker and ensemble deep learning model and improved chaos game optimization

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(7), P. 10197 - 10234

Published: May 5, 2024

Abstract This paper presents a unique hybrid classifier that combines deep neural networks with type-III fuzzy system for decision-making. The ensemble incorporates ResNet-18, Efficient Capsule network, ResNet-50, the Histogram of Oriented Gradients (HOG) feature extraction, neighborhood component analysis (NCA) selection, and Support Vector Machine (SVM) classification. innovative inputs fed into come from outputs mentioned networks. system’s rule parameters are fine-tuned using Improved Chaos Game Optimization algorithm (ICGO). conventional CGO’s simple random mutation is substituted wavelet to enhance CGO while preserving non-parametricity computational complexity. ICGO was evaluated 126 benchmark functions 5 engineering problems, comparing its performance well-known algorithms. It achieved best results across all except 2 functions. introduced applied seven malware datasets consistently outperforms notable like AlexNet, GoogleNet, network in 35 separate runs, achieving over 96% accuracy. Additionally, classifier’s tested on MNIST Fashion-MNIST 10 runs. show new excels accuracy, precision, sensitivity, specificity, F1-score compared other recent classifiers. Based statistical analysis, it has been concluded propose method exhibit significant superiority examined algorithms methods. source code available publicly at https://nimakhodadadi.com/algorithms-%2B-codes . Graphical abstract

Language: Английский

---

Parkinson’s Disease Induced Gain Freezing Detection using Gated Recurrent Units Optimized by Modified Crayfish Optimization Algorithm

Published: Jan. 18, 2024

Parkinson's disease belongs to the group of health problems that are incurable but can be mitigated if treated properly. While there is no way curing damage caused by disease, patient's life quality improved diagnosed and properly on time. The role artificial intelligence (AI) in medicine increasing. Deep learning algorithms may utilized automatically detect freezing gait episodes. This study focused diagnosis based disturbances which affected this disease. A hybrid deep machine AI solution employs gated recurrent unit (GRU) neural network optimized a swarm between crayfish optimization algorithm firefly has been proposed. proposed compared other high-performing establish objective grounds for comparison. framework results overall best performance confirms made improvements. best-constructed model attained an accuracy 87.08%.

Language: Английский

---

Machine learning and deep learning for user authentication and authorization in cybersecurity: A state-of-the-art review

Computers & Security, Journal Year: 2024, Volume and Issue: 140, P. 103747 - 103747

Published: Feb. 12, 2024

Language: Английский

---

Detecting Parkinson’s disease from shoe-mounted accelerometer sensors using convolutional neural networks optimized with modified metaheuristics

PeerJ Computer Science, Journal Year: 2024, Volume and Issue: 10, P. e2031 - e2031

Published: May 13, 2024

Neurodegenerative conditions significantly impact patient quality of life. Many do not have a cure, but with appropriate and timely treatment the advance disease could be diminished. However, many patients only seek diagnosis once condition progresses to point at which life is impacted. Effective non-invasive readily accessible methods for early can considerably enhance affected by neurodegenerative conditions. This work explores potential convolutional neural networks (CNNs) gain freezing associated Parkinson’s disease. Sensor data collected from wearable gyroscopes located sole patient’s shoe record walking patterns. These patterns are further analyzed using accurately detect abnormal The suggested method assessed on public real-world dataset parents as well individuals control group. To improve accuracy classification, an altered variant recent crayfish optimization algorithm introduced compared contemporary metaheuristics. Our findings reveal that modified (MSCHO) outperforms other in accuracy, demonstrated low error rates high Cohen’s Kappa, precision, sensitivity, F1-measures across three datasets. results suggest CNNs, combined advanced techniques, early, conditions, offering path

Language: Английский

---

A comprehensive and systematic literature review on intrusion detection systems in the internet of medical things: current status, challenges, and opportunities

Artificial Intelligence Review, Journal Year: 2025, Volume and Issue: 58(4)

Published: Jan. 30, 2025

Language: Английский

---

Cloud computing load prediction by decomposition reinforced attention long short-term memory network optimized by modified particle swarm optimization algorithm

Annals of Operations Research, Journal Year: 2023, Volume and Issue: unknown

Published: Dec. 15, 2023

Language: Английский

---

PSO-ACO-based bi-phase lightweight intrusion detection system combined with GA optimized ensemble classifiers

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(10), P. 14835 - 14890

Published: Aug. 6, 2024

Language: Английский

---

Advanced RIME architecture for global optimization and feature selection

Journal Of Big Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: June 18, 2024

Abstract The article introduces an innovative approach to global optimization and feature selection (FS) using the RIME algorithm, inspired by RIME-ice formation. algorithm employs a soft-RIME search strategy hard-RIME puncture mechanism, along with improved positive greedy resist getting trapped in local optima enhance its overall capabilities. also Binary modified (mRIME), binary adaptation of address unique challenges posed FS problems, which typically involve spaces. Four different types transfer functions (TFs) were selected for issues, their efficacy was investigated CEC2011 CEC2017 tasks related disease diagnosis. results proposed mRIME tested on ten reliable algorithms. advanced architecture demonstrated superior performance tasks, providing effective solution complex problems various domains.

Language: Английский

---