Estimation of HbA1c for DMT2 risk prediction on the Mexican population based in Artificial Neural Networks DOI Creative Commons
Alexis Alonso-Bastida,

Marisol Cervantes-Bobadilla,

Dolores Azucena Salazar-Piña

et al.

Journal of King Saud University - Computer and Information Sciences, Journal Year: 2023, Volume and Issue: 36(1), P. 101905 - 101905

Published: Dec. 31, 2023

In this paper, the main objective is to estimate percentage of glycosylated hemoglobin through an easily accessible computational platform risk generating type 2 diabetes mellitus in Mexican population. The estimation tool developed artificial neural network model, which was trained and validated according a population sample 1120 people between 18 59 years old. model inputs were gender, age, body mass index, waist circumference, weekly food consumption, family history, whether person suffers from any chronic degenerative disease other than T2DM. We used as output, estimated dynamic glucose model. results present coefficient determination 99%, demonstrating acceptable performance aid for health personnel, seeks generate first approximation glycemic status those communities with high marginalization index prevention strategies.

Language: Английский

Conditional random <i>k</i> satisfiability modeling for <i>k</i> = 1, 2 (CRAN2SAT) with non-monotonic Smish activation function in discrete Hopfield neural network DOI Creative Commons
Nurshazneem Roslan, Saratha Sathasivam, Farah Liyana Azizan

et al.

AIMS Mathematics, Journal Year: 2024, Volume and Issue: 9(2), P. 3711 - 3956

Published: Jan. 1, 2024

<abstract> <p>The current development of logic satisfiability in discrete Hopfield neural networks (DHNN)has been segregated into systematic and non-systematic logic. Most the research tends to improve logical rules various extents, such as introducing ratio a negative literal flexible hybrid structure that combines structures. However, existing rule exhibited drawback concerning impact within structure. Therefore, this paper presented novel class called conditional random <italic>k</italic> for = 1, 2 while intentionally disregarding both positive literals second-order clauses. The proposed was embedded network with ultimate goal minimizing cost function. Moreover, non-monotonic Smish activation function has introduced aim enhancing quality final neuronal state. performance new compared other state art conjunction five different types functions. Based on findings, obtained lower learning error, highest total neuron variation <italic>TV</italic> 857 lowest average Jaccard index, <italic>JSI</italic> 0.5802. On top that, highlights its capability DHNN based result improvement <italic>Zm</italic> <italic>TV</italic>. is consistently throughout all function, showing outperforms functions terms <italic>TV.</italic> This presents an alternative strategy mining technique. finding will be particular interest especially areas artificial network, function.</p> </abstract>

Language: Английский

Citations

1
A novel optimized hybrid machine learning model to enhance the prediction accuracy of hourly building energy consumption DOI
Rajasekar Thota, Nidul Sinha

Energy Sources Part A Recovery Utilization and Environmental Effects, Journal Year: 2024, Volume and Issue: 46(1), P. 9112 - 9135

Published: July 15, 2024

Language: Английский

Citations

1
Application of generalized hopfield neural network for the steady state analysis of self-excited induction generators DOI

S. Sundaramoorthy,

R. Essaki raj

Applied Soft Computing, Journal Year: 2023, Volume and Issue: 151, P. 111145 - 111145

Published: Dec. 14, 2023

Language: Английский

Citations

2
Exploring the efficacy of a supervised learning approach in 3 satisfiability reverse analysis method DOI
Nur ‘Afifah Rusdi, Nurul Atiqah Romli, Gaeithry Manoharam

et al.

AIP conference proceedings, Journal Year: 2024, Volume and Issue: 3158, P. 030009 - 030009

Published: Jan. 1, 2024

Language: Английский

Citations

0
Logic mining model in 3-satisfiability reverse analysis into discrete hopfield neural network DOI
Gaeithry Manoharam, Nurul Atiqah Romli, Suad Abdeen

et al.

AIP conference proceedings, Journal Year: 2024, Volume and Issue: 3158, P. 050003 - 050003

Published: Jan. 1, 2024

Language: Английский

Citations

0
Pediatric pneumonia detection using vision transformer DOI
Denis Eka Cahyani, Faisal Farris Setyawan, Anjar Dwi Hariadi

et al.

AIP conference proceedings, Journal Year: 2024, Volume and Issue: 3203, P. 040001 - 040001

Published: Jan. 1, 2024

Language: Английский

Citations

0
An enzyme-inspired specificity in deep learning model for sleep stage classification using multi-channel PSG signals input: Separating training approach and its performance on cross-dataset validation for generalizability DOI Creative Commons
Nantawachara Jirakittayakorn, Yodchanan Wongsawat, Somsak Mitrirattanakul

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 182, P. 109138 - 109138

Published: Sept. 20, 2024

Language: Английский

Citations

0
Examining Emotional Reactions to the COVID‐19 Crisis Through Twitter Data Analysis: A Comparative Study of Classification Techniques DOI Creative Commons

Saira Yaqub,

Muhammad Shoaib, Abdul Jaleel

et al.

Applied Computational Intelligence and Soft Computing, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

COVID‐19 has significantly impacted peoples’ mental health because of isolation and social distancing measures. It practically impacts every segment people’s daily lives causes a medical problem that spreads throughout the entire world. This pandemic caused an increased emotional distress. Since everyone been affected by epidemic physically, emotionally, financially, it is crucial to examine comprehend reactions as crisis affects health. study uses Twitter data understand what people feel during pandemic. We collected about isolation, preprocessed text, then classified tweets into various emotion classes. The are using twarc library academic researcher account labeled Vader analyzer after preprocessing. trained five machine learning models, namely, support vector (SVM), Naïve Bayes, KNN, decision tree, logistic regression find patterns trends in emotions. individuals analyzed. applied precision, recall, F 1‐score, accuracy evaluation metrics, which shows SVM performed best among other models. Our results show isolated felt emotions, out which, fear, sadness, surprise were most common. gives insights impact power understanding outcomes. findings can be used develop targeted interventions strategies address toll

Language: Английский

Citations

0
Intrusion detection system in cloud computing by utilizing VTR-HLSTM based on deep learning DOI Open Access

Valavan Woothukadu Thirumaran,

Nalini Joseph, G. Umarani Srikanth

et al.

Indonesian Journal of Electrical Engineering and Computer Science, Journal Year: 2024, Volume and Issue: 33(3), P. 1829 - 1829

Published: Feb. 16, 2024

<div>Cloud computing (CC) is a rapidly developing IT approach with intrusion detection system being crucial tool for safeguarding virtual networks and machines from potential threats, thereby mitigating security concerns in the cloud environment. The (IDS) demands significant improvements, primarily based on optimizing performance bolstering measures. This research aims to implement an IDS utilizing deep learning (DL) method. DL model promising technique widely used detect intrusions. implemented hierarchical long short-term memory (HLSTM) method’s evaluated feature selection through variance threshold-based regression (VTR) two network datasets: Bot-IoT lab-knowledge discovery data mining (NSL-KDD). paper concludes use of resulting high performance. Moreover, method NSL-KDD datasets obtains respective accuracies 99.50% 0.995. It compared existing methods namely, ensemble ID CC DL, LeNet, fuzzy neural Honey Bader algorithm privacy-preserving ID, improved metaheuristics logic-based security, beluga whale-tasmanian devil optimization convolutional (CNN) TL, chronological slap swarm algorithm-based belief (DBN), dragonfly invasive weed optimization-based Shepard CNN.</div>

Language: Английский

Citations

0
A New Strategy to Modify Hopfield by Using XOR Operation DOI Creative Commons
Rusul Hussein Hasan

Baghdad Science Journal, Journal Year: 2024, Volume and Issue: 21(9), P. 3052 - 3052

Published: Feb. 20, 2024

تعد شبكة هوبفيلد واحدة من أسهل الأنواع الشبكات العصبية، تركيب الشبكة يكون كل خلية عصبية في تتصل بالخلية الأخرى، وبالتالي تسمى العصبية المتصلة بالكامل. بالإضافة إلى ذلك، يعتبر هذا النوع ذاكرة ارتباطية تلقائية، نظرًا لأن تقوم بإرجاع النمط فور التعرف عليه، فإن هذه بها العديد القيود، بما ذلك سعة الذاكرة، والتباين، والمتعامد بين الأنماط، والاوزان المتماثلة، والحد الأدنى. البحث يقترح استراتيجية جديدة لتصميم الهوبفيلد باستخدام عملية XOR ؛ حيث تم اقتراح إستراتيجية لحل القيود خلال خوارزمية جديدة، الاستراتيجية سيزيد تحسين أداء تعديل بنية الشبكة، ومراحل التدريب والتقارب ، وان المقترحة تعتمد على حجم النمط. و تتجنب تعلم نمط مشابه عدة مرات، تظهر قابليتها أنماط مشوهة بالضوضاء، وسعة تخزينها غير محدودة وحل مشكلة المعكوس. أظهرت التجارب أن الطريقة لها نتائج جيدة تجنب غالبية قيود هوبفيلد. يتعلم عدد لا حصر له الأنماط بأحجام مختلفة مع الحفاظ نسبة ضوضاء مناسبة.

Citations

0