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

PeerJ Computer Science, Год журнала: 2024, Номер 10, С. e2031 - e2031

Опубликована: Май 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

Язык: Английский

---

Securing transactions: a hybrid dependable ensemble machine learning model using IHT-LR and grid search

Cybersecurity, Год журнала: 2024, Номер 7(1)

Опубликована: Ноя. 2, 2024

Abstract Financial institutions and businesses face an ongoing challenge from fraudulent transactions, prompting the need for effective detection methods. Detecting credit card fraud is crucial identifying preventing unauthorized transactions. While incidents are relatively rare, they can result in substantial financial losses, particularly due to high monetary value associated with Timely of enables investigators take swift actions mitigate further losses. However, investigation process often time-consuming, limiting number alerts that be thoroughly examined each day. Therefore, primary objective a model provide accurate while minimizing false alarms missed cases. In this paper, we introduce state-of-the-art hybrid ensemble (ENS) dependable machine learning (ML) intelligently combines multiple algorithms proper weighted optimization using grid search, including decision tree (DT), random forest (RF), K-nearest neighbor (KNN), multilayer perceptron (MLP), enhance identification. To address data imbalance issue, employ instant hardness threshold (IHT) technique conjunction logistic regression (LR), surpassing conventional approaches. Our experiments conducted on publicly available dataset comprising 284,807 The proposed achieves impressive accuracy rates 99.66%, 99.73%, 98.56%, 99.79%, perfect 100% DT, RF, KNN, MLP ENS models, respectively. outperforms existing works, establishing new benchmark detecting transactions high-frequency scenarios. results highlight effectiveness reliability our approach, demonstrating superior performance metrics showcasing its exceptional potential real-world applications.

Язык: 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, Год журнала: 2023, Номер unknown

Опубликована: Дек. 15, 2023

Язык: Английский

---

Potential of Coupling Metaheuristics-Optimized-XGBoost and SHAP in Revealing PAHs Environmental Fate

Toxics, Год журнала: 2023, Номер 11(4), С. 394 - 394

Опубликована: Апрель 21, 2023

Polycyclic aromatic hydrocarbons (PAHs) refer to a group of several hundred compounds, among which 16 are identified as priority pollutants, due their adverse health effects, frequency occurrence, and potential for human exposure. This study is focused on benzo(a)pyrene, being considered an indicator exposure PAH carcinogenic mixture. For this purpose, we have applied the XGBoost model two-year database pollutant concentrations meteorological parameters, with aim identify factors were mostly associated observed benzo(a)pyrene describe types environments that supported interactions between other polluting species. The data collected at energy industry center in Serbia, vicinity coal mining areas power stations, where maximum concentration period reached 43.7 ngm-3. metaheuristics algorithm has been used optimize hyperparameters, results compared models tuned by eight cutting-edge algorithms. best-produced was later interpreted applying Shapley Additive exPlanations (SHAP). As indicated mean absolute SHAP values, temperature surface, arsenic, PM10, total nitrogen oxide (NOx) appear be major affecting its environmental fate.

Язык: Английский

---

The XGBoost Approach Tuned by TLB Metaheuristics for Fraud Detection

Опубликована: Янв. 1, 2023

The recent pandemic had a major impact on online transactions.With this trend, credit card fraud increased.For the solution to problem authors explore existing solutions and propose an optimized solution.The is based extreme gradient boosting algorithm (XGBoost) teaching-learning-based-optimization algorithm.The dataset optimizes hyperparameters of XGBoost which utilized as main driver for evaluation was performed among other similar techniques that have solved successfully in past.Standard performance metrics were applied are accuracy, recall, precision, Matthews correlation coefficient, area under curve.The result research presents dominant proposed outperformed all compared overall.

Язык: Английский

---