Design and development of foot worn piezoresistive sensor for knee pain analysis with supervised machine learning algorithms based on gait pattern

Arumugaraja, M.; Padmapriya, B.; Poornachandra, S.

doi:10.1016/j.measurement.2022.111603

Cited by 9 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Machine Learning (ML) merupakan bagian dari AI yang memiliki kumpulan beragam algoritma yang mampu membuat penentuan model persamaan atau fungsi keputusan untuk prediksi, klasifikasi, clustering atau lainnya secara otomatis oleh mesin atau sistem komputasi digital dari hasil pembelajaran data (Arumugaraja et al, 2022;Cassoli et al, 2021). Salah satu Machine Learning yang paling cepat proses komputasinya adalah algortima Extreme Learning Machine (ELM).…”

Section: Machine Learningunclassified

Pengembangan Auto-AI Model Generatif Analisis Kompleksitas Waktu Algoritma Untuk Data Multi-Sensor IoT Pada Node-RED Menggunakan Extreme Learning Machine

Cholissodin

Syauqy²,

Firmanda³

et al. 2022

JTIIK

View full text Add to dashboard Cite

Awal mulanya, algoritma hanya dipakai untuk solusi penyelesaian persamaan matematika sederhana, seperti aljabar, aritmatika, probabilitas, dan lainnya yang lebih banyak dikerjakan secara manual dan membutuhkan waktu dan upaya yang cukup tinggi seperti pada kasus penghitungan nilai kompleksitas waktu algoritma dengan model rumus T(n), baik untuk algoritma non-rekursif maupun rekursif. Namun dengan perkembangan teknologi komputer untuk AI, Machine Learning maupun Deep Learning, algoritma dengan basis AI tersebut, dalam penelitian ini dikembangkan untuk menemukan solusi general persamaan model T(n) secara otomatis dari desain algoritma sederhana atau kompleks. Langkah dalam penelitian digunakan pembuatan model generatif berbasis algoritma Extreme Learning Machine (ELM) berdasarkan pencatatan nilai waktu komputasi pada beberapa kali pengujian untuk mengotomasi penentuan model persamaan kompleksitas waktu algoritma secara general baik untuk pencarian best case, worst case maupun average case untuk non-rekursif, dan base case dan recurrent case untuk rekursif, maupun keduanya. Hasil komparasi nilai T(n) dari ELM, yang tercepat atau terkecil waktu komputasinya digunakan sebagai rekomendasi algoritma untuk pengolahan data multi-sensor pada Internet of Things (IoT) simulator maupun non-simulator menggunakan Node-RED dengan tambahan platform yaitu flespi dan Heroku, sebagai solusi general untuk semua jenis kasus dan analisis algoritmanya. Berdasarkan pengujian didapatkan selisih nilai antara data aktual dengan hasil prediksi dalam ukuran nilai rata-rata MAPE sebesar 11,90%, yang menunjukkan nilai kesalahan yang cukup kecil. AbstractInitially, algorithms were only used for solving simple mathematical equations such as algebra, arithmetic, probability, and others that were mostly carried out manually and required quite a lot of time and effort as in the case of calculating the value of the time complexity of the algorithm with the formula model of T(n), both for non-recursive and recursive algorithms. However, with the development of computer technology for AI, both Machine Learning and Deep Learning, the AI-based algorithms in this study were developed to identify general solutions to the T(n) model equation automatically from simple or complex algorithm designs. The steps in the study are utilized to create a generative model based on the Extreme Learning Machine (ELM) algorithm according to the recording of computational time values on several tests to automate the determination of time complexity equation model of the algorithm in general including the search of best cases, worst cases, and average cases for non-recursive, and base cases and recurrent cases for recursive, as well as algorithms that contain both. The results of the comparison of T(n) values from ELM revealed that the fastest or smallest computational time is used as the algorithm recommendations for multi-sensor data processing in the Internet of Things (IoT) simulators and non-simulators by utilizing Node-RED with additional platforms i.e., flespi and Heroku, as a general solution for the entire types of cases and analysis of their algorithms. Based on the tests that have been carried out, the difference in value between the actual data and the prediction results in the size of the MAPE average value of 11.90%, which shows a fairly small error value.

show abstract

Section: Machine Learningunclassified

Pengembangan Auto-AI Model Generatif Analisis Kompleksitas Waktu Algoritma Untuk Data Multi-Sensor IoT Pada Node-RED Menggunakan Extreme Learning Machine

Cholissodin

Syauqy²,

Firmanda³

et al. 2022

JTIIK

View full text Add to dashboard Cite

show abstract

“…Applying the KNN classification by Arumugaraja et al [18] to analyze and monitor the gait of people with arthritis, trauma, and degenerative movement disorders, the KNN learning model produces 99.4% accuracy in detecting knee pain. Still in the field of health, research conducted by Sallam et al [19] discusses the increasing prevalence of acute lymphoblastic leukemia, the classification models used include RF, support vector machine (SVM), KNN, and Naive Bayes (NB) show that this method is effective in improving classification accuracy.…”

mentioning

confidence: 99%

The object detection model uses combined extraction with KNN and RF classification

Kurniati,

Manongga,

Sembiring

et al. 2024

IJEECS

View full text Add to dashboard Cite

Object detection plays an important role in various fields. Developing detection models for 2D objects that experience rotation and texture variations is a challenge. In this research, the initial stage of the proposed model integrates the gray-level co-occurrence matrix (GLCM) and local binary patterns (LBP) texture feature extraction to obtain feature vectors. The next stage is classifying features using k-nearest neighbors (KNN) and random forest (RF), as well as voting ensemble (VE). System testing used a dataset of 4,437 2D images, the results for KNN accuracy were 92.7% and F1-score 92.5%, while RF performance was lower. Although GLCM features improve performance on both algorithms, KNN is more consistent. The VE approach provides the best performance with an accuracy of 93.9% and an F1-score of 93.8%, this shows the effectiveness of the ensemble technique in increasing object detection accuracy. This study contributes to the field of object detection with a new approach combining GLCM and LBP as feature vectors as well as VE for classification.

show abstract

Scalogram-Based Gait Abnormalities Classification Using Deep Convolutional Networks for Neurological and Non-Neurological Disorders

Negi,

Pandey,

Sharma

et al. 2024

J. Med. Biol. Eng.

View full text Add to dashboard Cite

Design and development of foot worn piezoresistive sensor for knee pain analysis with supervised machine learning algorithms based on gait pattern

Cited by 9 publications

References 25 publications

Pengembangan Auto-AI Model Generatif Analisis Kompleksitas Waktu Algoritma Untuk Data Multi-Sensor IoT Pada Node-RED Menggunakan Extreme Learning Machine

Pengembangan Auto-AI Model Generatif Analisis Kompleksitas Waktu Algoritma Untuk Data Multi-Sensor IoT Pada Node-RED Menggunakan Extreme Learning Machine

The object detection model uses combined extraction with KNN and RF classification

Scalogram-Based Gait Abnormalities Classification Using Deep Convolutional Networks for Neurological and Non-Neurological Disorders

Contact Info

Product

Resources

About