Energy Usage Forecasting Model Based on Long Short-Term Memory (LSTM) and eXplainable Artificial Intelligence (XAI)

Information, Год журнала: 2023, Номер 14(5), С. 265 - 265

Опубликована: Апрель 29, 2023

The accurate forecasting of energy consumption is essential for companies, primarily planning procurement. An overestimated or underestimated value may lead to inefficient usage. Inefficient usage could also financial consequences the company, since it will generate a high cost production. Therefore, in this study, we proposed an model and parameter analysis using long short-term memory (LSTM) explainable artificial intelligence (XAI), respectively. A public dataset from steel company was used study evaluate our models compare them with previous results. results showed that achieved lowest root mean squared error (RMSE) scores by up 0.08, 0.07, 0.07 single-layer LSTM, double-layer bi-directional In addition, interpretability XAI revealed two parameters, namely leading current reactive power number seconds midnight, had strong influence on output. Finally, expected be useful industry practitioners, providing LSTM offering insight policymakers leaders so they can make more informed decisions about resource allocation investment, develop effective strategies reducing consumption, support transition toward sustainable development.

Язык: Английский

---

Deep learning in medicine: advancing healthcare with intelligent solutions and the future of holography imaging in early diagnosis

Multimedia Tools and Applications, Год журнала: 2024, Номер unknown

Опубликована: Июль 5, 2024

Язык: Английский

---

A rapid review of machine learning approaches for telemedicine in the scope of COVID-19

Artificial Intelligence in Medicine, Год журнала: 2022, Номер 129, С. 102312 - 102312

Опубликована: Апрель 30, 2022

Язык: Английский

---

Fog-Based Smart Cardiovascular Disease Prediction System Powered by Modified Gated Recurrent Unit

Diagnostics, Год журнала: 2023, Номер 13(12), С. 2071 - 2071

Опубликована: Июнь 15, 2023

The ongoing fast-paced technology trend has brought forth ceaseless transformation. In this regard, cloud computing long proven to be the paramount deliverer of services such as power, software, networking, storage, and databases on a pay-per-use basis. is big proponent internet things (IoT), furnishing computation storage requisite address internet-of-things applications. With proliferating IoT devices triggering continual data upsurge, cloud-IoT interaction encounters latency, bandwidth, connectivity restraints. inclusion decentralized distributed fog layer amidst extends cloud's processing, networking close end users. This hierarchical edge-fog-cloud model distributes intelligence, yielding optimal solutions while tackling constraints like massive volume, delay, security vulnerability. healthcare domain, warranting time-critical functionalities, can reap benefits from cloud-fog-IoT interplay. research paper propounded fog-assisted smart system diagnose heart or cardiovascular disease. It combined fuzzy inference (FIS) with recurrent neural network model's variant gated unit (GRU) for pre-processing predictive analytics tasks. proposed showcases substantially improved performance results, classification accuracy at 99.125%. major processing happening layer, it observed that work reveals optimized results concerning delays in terms response time, jitter, compared cloud. Deep learning models are adept handling sophisticated tasks, particularly analytics. Time-critical applications deep learning's exclusive potential furnish near-perfect coupled merits model, revealed by experimental results.

Язык: Английский

---

Uncovering the determinants of brain functioning, behavior and their interplay in the light of context

European Journal of Neuroscience, Год журнала: 2024, Номер 60(5), С. 4687 - 4706

Опубликована: Апрель 1, 2024

Abstract Notwithstanding the huge progress in molecular and cellular neuroscience, our ability to understand brain develop effective treatments promoting mental health is still limited. This can be partially ascribed reductionist, deterministic mechanistic approaches neuroscience that struggle with complexity of central nervous system. Here, I introduce Context theory constrained systems proposing a novel role contextual factors genetic, neural substrates determining functioning behavior. entails key conceptual implications. First, context main driver behavior states. Second, substrates, from genes areas, have no direct causal link complex behavioral responses as they combined multiple ways produce same response different impinge on substrates. Third, biological play distinct roles behavior: drives behavior, constrain repertoire implemented. Fourth, since interface between system environment, it privileged level control orchestration functioning. Such implications are illustrated through Kitchen metaphor brain. theoretical framework calls for revision concepts psychiatry, including causality, specificity individuality. Moreover, at clinical level, proposes inducing changes interventions having highest impact reorganize human mind achieve long‐lasting improvement health.

Язык: Английский

---

Deep-SDM: A Unified Computational Framework for Sequential Data Modeling Using Deep Learning Models

Software, Год журнала: 2024, Номер 3(1), С. 47 - 61

Опубликована: Фев. 28, 2024

Deep-SDM is a unified layer framework built on TensorFlow/Keras and written in Python 3.12. The aligns with the modular engineering principles for design development strategy. Transparency, reproducibility, recombinability are framework’s primary criteria. platform can extract valuable insights from numerical text data utilize them to predict future values by implementing long short-term memory (LSTM), gated recurrent unit (GRU), convolution neural network (CNN). Its end-to-end machine learning pipeline involves sequence of tasks, including exploration, input preparation, model construction, hyperparameter tuning, performance evaluations, visualization results, statistical analysis. complete process systematic carefully organized, import selection, encapsulating it into whole. multiple subroutines work together provide user-friendly conducive that easy use. We utilized Nepal Stock Exchange (NEPSE) index validate its reproducibility robustness observed impressive results.

Язык: Английский

---

A Comprehensive Review of Machine Learning Algorithms and Its Application in Groundwater Quality Prediction

Archives of Computational Methods in Engineering, Год журнала: 2024, Номер unknown

Опубликована: Июнь 24, 2024

Язык: Английский

---

Condition-based monitoring techniques and algorithms in 3d printing and additive manufacturing: a state-of-the-art review

Progress in Additive Manufacturing, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 15, 2024

Язык: Английский

---

An Ontological Model based on Machine Learning for Predicting Breast Cancer

International Journal of Advanced Computer Science and Applications, Год журнала: 2022, Номер 13(7)

Опубликована: Янв. 1, 2022

Breast cancer is mostly a female disease, but it may affect men as well even at considerably lower percentage. An automated diagnosis system should be built for early detection because manual breast takes long time. Doctors have lately achieved significant advances in the identification and treatment of order to decrease rate mortality caused by latter. Researchers, on other hand, are analysing large amounts complicated medical data employing combination statistical machine learning methodologies assist clinicians predicting cancer. Various approaches, including ontology-based Machine Learning methods, played an essential role science building that can identify This study examines evaluates most popular algorithms, besides ontological model based Learning. Among classification methods investigated were Naive Bayes, Decision Tree, Logistic Regression, Support Vector Machine, Artificial Neural Network, Random Forest, k-Nearest Neighbours. The dataset utilized has 683 instances available download from Kaggle website. findings assessed using performance measures generated confusion matrix, such F-Measure, Accuracy, Precision, Recall. ontology surpassed all techniques, according results.

Язык: Английский

---

Data-Driven Innovations: Transforming Healthcare through Machine Learning Integration

Journal of Machine and Computing, Год журнала: 2025, Номер unknown, С. 356 - 364

Опубликована: Янв. 3, 2025

Today's healthcare sector generates an unprecedented amount of data, creating a promising junction between data mining and machine learning. This research aims to achieve two key goals. First, it effortlessly integrates AI into clinical decision-support systems improve treatment regimens. The emphasis is on individualizing medicines, increasing effectiveness, minimizing side effects. main goal optimize methods using AI. also examines how learning may hospital operations. objective involves improving logistical administration, planning, resource allocation boost operational efficiency, lower costs, enhance access high-quality care. study rigorously investigates data-driven approaches revolutionize system the synergy medicine, focusing current trends advances. medical applications that demonstrate learning's ability change delivery. illuminate approaches' potential advance patient-centeredness, financial sustainability, efficiency in healthcare.

Язык: Английский

---