Human Regular Activities Recognition Using Convolutional Neural Network DOI Open Access

Sharmin Akther,

Ayat Ullah Nahid

Asian Journal of Research in Computer Science, Journal Year: 2023, Volume and Issue: unknown, P. 44 - 55

Published: Feb. 7, 2023

Capturing commonly occurring behaviors is a tough issue in computer vision. A few of them are recreation, touring, leisure pursuits, and religious practice. comprehensive effort has already been dedicated to this aspect deal with issue. In work, we recreated dataset five categories, including household activities, farming, exercise, sports, occupation, identify human daily actions. This collection 4328 colored images total, among 630 set aside for testing, 3698 training. Deep learning standard image-based strategies being explored address the issues. paper, have designed deep paradigm classify regular activities beings. To characterize people's chores, use CNN model, one greatest tools visual identification. We also chosen two already-trained VGG16 ResNet50 models. When compare our model existing techniques, investigation's findings demonstrate that suggested network better recognition accuracy 91%. Additionally, observed varies throughout different epochs, after 25 epochs got stable results from model. The reader may find article instructive grasping models various recognizing applications.

Language: Английский

Utilization of Deep Convolutional Neural Networks for Accurate Chest X-Ray Diagnosis and Disease Detection DOI Open Access
Mukesh Mann,

Rakesh P. Badoni,

Harsh Soni

et al.

Interdisciplinary Sciences Computational Life Sciences, Journal Year: 2023, Volume and Issue: 15(3), P. 374 - 392

Published: March 26, 2023

Language: Английский

Citations

15
Predictive Artificial Intelligence Model for Detecting Dental Age Using Panoramic Radiograph Images DOI Creative Commons
Sumayh S. Aljameel,

Lujain Althumairy,

Basmah Albassam

et al.

Big Data and Cognitive Computing, Journal Year: 2023, Volume and Issue: 7(1), P. 8 - 8

Published: Jan. 10, 2023

Predicting dental development in individuals, especially children, is important evaluating maturity and determining the factors that influence of teeth growth jaws. Dental can be accelerated patients with an skeletal rate related to pattern as a child. The age (DA) individual essential dentist for planning treatment relation maxillofacial growth. A deep-learning-based regression model was developed this study using panoramic radiograph images predict DA. dataset included 529 samples radiographs collected from hospital at Imam Abdulrahman Bin Faisal university Saudi Arabia. Different deep learning methods were applied implement model, including Xception, VGG16, DenseNet121, ResNet50. results indicated Xception had best performance, error 1.417 6–11 group. proposed assist appropriate based on their DA rather than chronological age.

Language: Английский

Citations

13
EfficientNets transfer learning strategies for histopathological breast cancer image analysis DOI
Sakinat Oluwabukonla Folorunso, Joseph Bamidele Awotunde,

Yagateela Pandu Rangaiah

et al.

Advances in Complex Systems, Journal Year: 2023, Volume and Issue: 15(02)

Published: April 5, 2023

Breast cancer (BC) is one of the major principal sources high mortality among women worldwide. Consequently, early detection essential to save lives. BC can be diagnosed with different modes medical images such as mammography, ultrasound, computerized tomography, biopsy, and magnetic resonance imaging. A histopathology study (biopsy) that results in often performed help diagnose analyze BC. Transfer learning (TL) a machine-learning (ML) technique reuses method initially built for task applied model new task. TL aims enhance assessment desired learners by moving knowledge contained another but similar source domain. challenge small dataset domain reduced build learners. plays role image analysis because this immense property. This paper focuses on use methods investigation classification detection, preprocessing, pretrained models, ML models. Through empirical experiments, EfficientNets neural network architectures models were built. The support vector machine eXtreme Gradient Boosting (XGBoost) learned dataset. result showed comparative good performance EfficientNetB4 XGBoost. An outcome based accuracy, recall, precision, F1_Score XGBoost 84%, 0.80, 0.83, 0.81, respectively.

Language: Английский

Citations

10
Enhancing Human Posture Detection with Hybrid Deep VGG16 and Attention Mechanism Network DOI Open Access
Roseline Oluwaseun Ogundokun, Rytis Maskeliūnas,

Federick Oscar

et al.

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 1209 - 1218

Published: Jan. 1, 2025

Language: Английский

Citations

0
Abnormal Sitting Posture Recognition Using Skeletal Framework and Deep Learning Techniques DOI

K. Gayathri,

A. Piriyadharshini,

B. Thejesswini

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Hardware Deployable Edge AI Solution for Posture Classification using mmWave Radar and Low Computation Machine Learning Model DOI
Yash Pratap Singh, Aham Gupta, Devansh Chaudhary

et al.

IEEE Sensors Journal, Journal Year: 2024, Volume and Issue: 24(16), P. 26836 - 26844

Published: Aug. 15, 2024

Language: Английский

Citations

2
Inception V3 Based Approach for the Recognition of Age-related macular degeneration Disease DOI
Roseline Oluwaseun Ogundokun, AbdulRahman Tosho Abdulahi, Ajiboye Raimot Adenike

et al.

Published: April 5, 2023

Millions of people around the world are infected with age-related macular degeneration (AMD) disease. It is not easily detected in intermediate stage, as it typically asymptomatic. Moreover, ideal learning trends for AMD professional advice identifying those who at this stage condition, instructing them on ways to screen early diagnosis choroidal neovascular level before significant vision loss incurred, and encouraging think about taking nutritional supplements that may lessen likelihood condition will extend from mature phase. However, conventional identification disease can be time-intensive necessitates knowledgeably competent individuals carry out task. Since retinal fundus images have proven beneficial detecting AMD, automated methods detection retina developed by applying a novel application deep transfer (DTL) leverage artificial intelligence advances. In investigation, convolutional neural networks (DCNN) specifically trained evaluation were contrasted (DTL), different (DL) technique included common characteristics diagnostic grader. order differentiate between Normal was used 2-class classification issue. The study proposed using models, compared DTL model. model approach yielded an accuracy of96.41%, area under receiver operator curve (AUC) 0.9633, precision 94.24%, specificity 94.82% false positive rate (FPR) 0.0518 test dataset, which specified considerable agreement gold standard Age-related Eye Disease investigation data set. Implementing automatic DTL-founded scans yield outcomes par human effectiveness. This research confirms techniques could perform task current administration self-sufficient knowledgeable graders take into account expenses inspection or surveillance, availability medical care, effective therapeutics resolve advancement AMD.

Language: Английский

Citations

4
A Point Cloud-Based Non-Intrusive Approach for Human Posture Classification by Utilizing 77 GHz FMCW Radar and Deep Learning Models DOI
Pranjal Mahajan, Devansh Chaudhary, Mujeev Khan

et al.

2022 IEEE International Symposium on Circuits and Systems (ISCAS), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 5

Published: May 19, 2024

Language: Английский

Citations

1
A smart healthcare system using IoT and machine learning DOI
Roseline Oluwaseun Ogundokun, Muhtahir O. Oloyede, Hakeem Babalola Akande

et al.

Advances in computers, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Language: Английский

Citations

1
Ergonomic investigations on novel dynamic postural estimator using blaze pose and transfer learning DOI

Vigneswaran Chidambaram,

Madhan Mohan Gopalsamy,

Vignesh Raja M

et al.

Ergonomics, Journal Year: 2023, Volume and Issue: 67(2), P. 240 - 256

Published: June 2, 2023

The aim is to develop a computer-based assessment model for novel dynamic postural evaluation using RULA. present study proposed camera-based, three-dimensional (3D) human pose estimation 'BlazePose' with data set of 50,000 action-level-based images. was investigated the Deep Neural Network (DNN) and Transfer Learning (TL) approach. has been trained evaluate posture high accuracy, precision, recall each output prediction class. can quickly analyse ergonomics online offline promising accuracy 94.12%. A estimator blaze transfer learning assessed accuracy. subjected constant muscle loading factor foot support score that could one person good image clarity at time.

Language: Английский

Citations

3