Mohd Halim Mohd NoorUniversiti Sains Malaysia | USM · School of Computer Science
Mohd Halim Mohd Noor
PhD
About
28
Publications
7,759
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
276
Citations
Citations since 2017
Introduction
An academic at the School of Computer Sciences. My area of interest is machine learning and deep learning for pervasive computing and computer vision.
Skills and Expertise
Additional affiliations
February 2018 - present
July 2008 - February 2018
Universiti Teknologi MARA (Pulau Pinang)
Position
- Lecturer
Education
February 2014 - January 2017
December 2005 - October 2008
February 2001 - December 2004
Publications
Publications (28)
The recent advancement of deep learning methods has seen a significant increase in recognition accuracy in many important applications such as human activity recognition. However, deep learning methods require a vast amount of sensor data to automatically extract the most salient features for activity classification. Therefore, in this paper, a uni...
Wearable technology offers a prospective solution to the increasing demand for activity monitoring in pervasive healthcare. Feature extraction and selection are crucial steps in activity recognition since it determines the accuracy of activity classification. However, existing feature extraction and selection methods involve manual feature engineer...
Temporal Action Localization (TAL) is an important task of various computer vision topics such as video understanding, summarization, and analysis. In the real world, the videos are long untrimmed and contain multiple actions, where the temporal boundaries annotations are required in the fully-supervised learning setting for classification and loca...
Human activity recognition has gained interest from the research community due to the advancements in sensor technology and the improved machine learning algorithm. Wearable sensors have become more ubiquitous, and most of the wearable sensor data contain rich temporal structural information that describes the distinct underlying patterns and relat...
Human Activity Recognition (HAR) is an essential task in various applications such as pervasive healthcare, smart environment, and security and surveillance. The need to develop accurate HAR systems has motivated researchers to propose various recognition models, feature extraction methods, and datasets. A lot of comprehensive surveys have been don...
Colorectal cancer occurs in the rectal of humans, and early detection has been proved to reduce its mortality rate. Colonoscopy is the standard used in detecting the presence of polyps in the rectal, and accurate segmentation of the polyps from colonoscopy images often provides helpful information for early diagnosis and treatment. Although existin...
With the development of deep learning, numerous models have been proposed for human activity recognition to achieve state‐of‐the‐art recognition on wearable sensor data. Despite the improved accuracy achieved by previous deep learning models, activity recognition remains a challenge. This challenge is often attributed to the complexity of some spec...
Machine learning approaches have been used to develop suicide attempt predictive models recently and have been shown to have a good performance. However, those proposed models have difficulty interpreting and understanding why an individual has suicidal attempts. To overcome this issue, the identification of features such as risk factors in predict...
Background
Early detection and prediction of suicidal behaviour are key factors in suicide control. In conjunction with recent advances in the field of artificial intelligence, there is increasing research into how machine learning can assist in the detection, prediction and treatment of suicidal behaviour. Therefore, this study aims to provide a c...
Conditional Generative Adversarial Networks (CGAN) have shown great promise in generating synthetic data for sensor-based activity recognition. However, one key issue concerning existing CGAN is the design of the network architecture that affects sample quality. This study proposes an effective CGAN architecture that synthesizes higher quality samp...
![Figure 2: Alexnet Architecture [26]](publication/366049300/figure/fig1/AS:11431281104958661@1670333785118/Alexnet-Architecture-26_Q320.jpg)
![Figure 3: VGG16 Architecture [27]](publication/366049300/figure/fig2/AS:11431281104958662@1670333785166/VGG16-Architecture-27_Q320.jpg)
![Figure 4: Overall Schema of InceptionNetv4 [28]](publication/366049300/figure/fig3/AS:11431281105022009@1670333785249/Overall-Schema-of-InceptionNetv4-28_Q320.jpg)
![Figure 6. Deep Residual Networks [31]](publication/366049300/figure/fig5/AS:11431281104958663@1670333785633/Deep-Residual-Networks-31_Q320.jpg)
Waste or trash management is receiving increased attention for intelligent and sustainable development, particularly in developed and developing countries. The waste or trash management system comprises several related processes that carry out various complex functions. Recently, interest in deep learning (DL) has increased in providing alternative...
Facial expression recognition (FER) is the task of determining a person’s current emotion. It plays an important role in healthcare, marketing, and counselling. With the advancement in deep learning algorithms like Convolutional Neural Network (CNN), the system’s accuracy is improving. A hybrid CNN and k-Nearest Neighbour (KNN) model can improve FE...
Building classification models in activity recognition is based on the concept of exchangeability. While splitting the dataset into training and test sets, we assume that the training set is exchangeable with the test set and expect good classification performance. However, this assumption is invalid due to subject variability of the training and t...
At the advanced stage of Parkinson’s disease, patients may suffer from ‘freezing of gait’ episodes: a debilitating condition wherein a patient’s “feet feel as though they are glued to the floor.” The objective, continuous monitoring of the gait of Parkinson’s disease patients with wearable devices has led to the development of many freezing of gait...
The increase in the availability of wearable devices offers a prospective solution to the increasing demand for elderly human activity monitoring, in the essence of improving the independent living standard of the growing population of elderly humans. With all the availability of the wearable devices fully embedded with sensors that are being used...
Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue,...
Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue,...
Deep learning approaches have attracted a lot of attention in the automatic detection of Covid-19 and transfer learning is the most common approach. However, majority of the pre-trained models are trained on color images, which can cause inefficiencies when fine-tuning the models on Covid-19 images which are often grayscale. To address this issue,...
Current suicide risk assessments for predicting suicide attempts are time consuming, of low predictive value and have inadequate reliability. This paper aims to develop a predictive model for suicide attempts among patients with depression using machine learning algorithms as well as presents a comparative study on single predictive models with ens...
This paper investigates the fusion of wearable and ambient sensors for recognizing activities of daily living in a smart home setting using ontology. The proposed approach exploits the advantages of both types of sensing to resolve uncertainties due to missing sensor data. The resulting system is able to infer activities which cannot be inferred wi...
Abstract Ontology-based activity recognition is gaining interest due to its expressiveness and comprehensive reasoning mechanism. An obstacle to its wider use is that the imperfect observations result in failure of recognizing activities. This paper proposes a novel reasoning algorithm for activity recognition in smart environments. The algorithm i...
Previous studies on physical activity recognition have utilized various fixed window sizes for signal segmentation targeting specific activities. Naturally, an optimum window size varies depending on the characteristics of activity signals and fixed window size will not produce good segmentation for all activities. This paper presents a novel appro...
Previous studies on physical activity recognition have utilized various fixed window sizes for signal segmentation selected based on past experiments and hardware limitations. Specifically, there is no optimum fixed window size because it is subject to the characteristics of the activity signals. This paper presents a novel approach of activity sig...
Projects
Project (1)
1. To develop a robust wearable sensor-based activity recognition system using a single tri-axial accelerometer that provides context information on the physical activity of the user.
2. To develop an algorithm that handles uncertainty due to missing sensor data in dense sensing-based activity recognition.
3. To develop a sensor fusion technique that combines context information from wearable and ambient sensors.
