An Evidence-Based Study of Diabetes Prevention and Management with NLP and Deep Learning DOI
Vimal Vidyadharan, Mohammad Hamdan,

A.M.S. Zalzala

et al.

2021 IEEE Symposium Series on Computational Intelligence (SSCI), Journal Year: 2021, Volume and Issue: unknown, P. 1 - 8

Published: Dec. 5, 2021

Diabetes Mellitus - or type 2 diabetes is one of the fastest growing global health emergencies 21st century, affecting around 9.3% world's adult population and impacting economy. As there no known methodology for controlling chronic condition, early-stage detection prevention advocated. Researchers have successfully used data mining machine learning techniques to generate models early related risks in countries where public records (electronic otherwise) are easily available. Such cannot be effectively applied communities incomplete non-existing such as underserved India. This paper proposes a system built from datasets captured filed research with representative communities. approach advocates use Natural Language Processing Deep Learning qualitative conduct an evidence-based study management. The presents theoretical formulations, model experimentations, automated coding systems, algorithm testing validate results.

Language: Английский

Explainable Multimodal Machine Learning for Engagement Analysis by Continuous Performance Test DOI
Muhammad Arifur Rahman, David Brown, Nicholas Shopland

et al.

Lecture notes in computer science, Journal Year: 2022, Volume and Issue: unknown, P. 386 - 399

Published: Jan. 1, 2022

Language: Английский

Citations

38
Enhancing biofeedback-driven self-guided virtual reality exposure therapy through arousal detection from multimodal data using machine learning DOI Creative Commons
Muhammad Arifur Rahman, David Brown, Mufti Mahmud

et al.

Brain Informatics, Journal Year: 2023, Volume and Issue: 10(1)

Published: June 21, 2023

Virtual reality exposure therapy (VRET) is a novel intervention technique that allows individuals to experience anxiety-evoking stimuli in safe environment, recognise specific triggers and gradually increase their perceived threats. Public-speaking anxiety (PSA) prevalent form of social anxiety, characterised by stressful arousal generated when presenting an audience. In self-guided VRET, participants can tolerance reduce anxiety-induced PSA over time. However, creating such VR environment determining physiological indices or distress open challenge. Environment modelling, character creation animation, psychological state determination the use machine learning (ML) models for stress detection are equally important, multi-disciplinary expertise required. this work, we have explored series ML with publicly available data sets (using electroencephalogram heart rate variability) predict states. If detect arousal, trigger calming activities allow cope overcome distress. Here, discuss means effective selection parameters detection. We propose pipeline model problem different parameter settings context virtual therapy. This be extended other domains interest where crucial. Finally, implemented biofeedback framework VRET successfully provided feedback as brain laterality index from our acquired multimodal anxiety.

Language: Английский

Citations

21
Cross-Content Recommendation between Movie and Book using Machine Learning DOI
Afra Nawar,

Nazia Tabassum Toma,

Shamim Al Mamun

et al.

Published: Oct. 13, 2021

Machine learning-driven recommendation systems are widely used in today's growing digital world. Existing movie and book recommender work using a collaborative approach, which can result lack of fresh diverse content reduced surprise factor. There is also no platform providing recommendations across different contents, such as for books from movies vice versa. In this paper, our main goal to introduce cross-content system based on the descriptions identifying similarities natural language processing machine learning algorithms. We processed combined dataset two types generated TF-IDF vector apply three algorithms: K-means clustering, hierarchical cosine similarity. being known research similar with ground truth labels, we applied subjective reasoning evaluate results system.

Language: Английский

Citations

33
Towards Machine Learning Driven Self-guided Virtual Reality Exposure Therapy Based on Arousal State Detection from Multimodal Data DOI
Muhammad Arifur Rahman, David Brown, Nicholas Shopland

et al.

Lecture notes in computer science, Journal Year: 2022, Volume and Issue: unknown, P. 195 - 209

Published: Jan. 1, 2022

Language: Английский

Citations

23
Speech Emotion Recognition: An Empirical Analysis of Machine Learning Algorithms Across Diverse Data Sets DOI
Mostafiz Ahammed, Rubel Sheikh,

Farah Hossain

et al.

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 32 - 46

Published: Jan. 1, 2024

Language: Английский

Citations

1
Amharic spoken digits recognition using convolutional neural network DOI Creative Commons
Tewodros Alemu Ayall, Changjun Zhou, Huawen Liu

et al.

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

Published: May 4, 2024

Abstract Spoken digits recognition (SDR) is a type of supervised automatic speech recognition, which required in various human–machine interaction applications. It utilized phone-based services like dialing systems, certain bank operations, airline reservation and price extraction. However, the design SDR challenging task that requires development labeled audio data, proper choice feature extraction method, best performing model. Even if several works have been done for languages, such as English, Arabic, Urdu, etc., there no developed Amharic spoken dataset (AmSDD) to build (AmSDR) model language, official working language government Ethiopia. Therefore, this study, we new AmSDD contains 12,000 utterances 0 (Zaero) 9 (zet’enyi) were recorded from 120 volunteer speakers different age groups, genders, dialects who repeated each digit ten times. Mel frequency cepstral coefficients (MFCCs) Mel-Spectrogram methods used extract trainable features signal. We conducted experiments on AmSDR using classical learning algorithms Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF) baseline. To further improve performance AmSDR, propose three layers Convolutional Neural Network (CNN) architecture with Batch normalization. The results our show proposed CNN outperforms baseline scores an accuracy 99% 98% MFCCs features, respectively.

Language: Английский

Citations

1
Dimensionality Reduction in Handwritten Digit Recognition DOI
Mayesha Bintha Mizan, Muhammad Sayyedul Awwab, Anika Tabassum

et al.

Lecture notes in networks and systems, Journal Year: 2023, Volume and Issue: unknown, P. 35 - 50

Published: Jan. 1, 2023

Language: Английский

Citations

2
Classification of Cancer Types Based on RNA HI-SEQ Data Using Dimensionality Reduction DOI
Zannatul Ferdous Tunny, MD Abir Hasan Munna, Mohammad Shahadat Hossain

et al.

Communications in computer and information science, Journal Year: 2024, Volume and Issue: unknown, P. 309 - 324

Published: Jan. 1, 2024

Language: Английский

Citations

0
Cepstral and acoustic ternary pattern based hybrid feature extraction approach for end-to-end bangla speech recognition DOI
Mohit Dua,

Akanksha Akanksha,

Shelza Dua

et al.

Journal of Ambient Intelligence and Humanized Computing, Journal Year: 2023, Volume and Issue: 14(12), P. 16903 - 16919

Published: Oct. 9, 2023

Language: Английский

Citations

1
Accurate Prediction of Lysine Methylation Sites Using Evolutionary and Structural-Based Information DOI Creative Commons
Md. Easin Arafat,

Md. Wakil Ahmad,

S.M. Shovan

et al.

Cognitive Computation, Journal Year: 2024, Volume and Issue: 16(3), P. 1300 - 1320

Published: May 1, 2024

Abstract Methylation is considered one of the proteins’ most important post-translational modifications (PTM). Plasticity and cellular dynamics are among many traits that regulated by methylation. Currently, methylation sites identified using experimental approaches. However, these methods time-consuming expensive. With use computer modelling, can be quickly accurately, providing valuable information for further trial investigation. In this study, we propose a new machine-learning model called MeSEP to predict incorporates both evolutionary structural-based information. To build model, first extract structural features from PSSM SPD2 profiles, respectively. We then employ Extreme Gradient Boosting (XGBoost) as classification sites. address issue imbalanced data bias towards negative samples, SMOTETomek-based hybrid sampling method. The was validated on an independent test set (ITS) 10-fold cross-validation (TCV) lysine method achieved: accuracy 82.9% in ITS 84.6% TCV; precision 0.92 0.94 area under curve values 0.90 F1 score 0.81 0.83 MCC 0.67 0.70 TCV. significantly outperformed previous studies found literature. standalone toolkit all its source codes publicly available at https://github.com/arafatro/MeSEP .

Language: Английский

Citations

0