KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Intraraprasit, Monthon

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    FILTER PRUNING BASED ON LOCAL GRADIENT ACTIVATION MAPPING IN CONVOLUTIONAL NEURAL NETWORKS
    (2023-12-01)
    Intraraprasit, Monthon
    ;
    Chitsobhuk, Orachat
    Convolutional Neural Network (CNN) is a well-known Deep learning model utilized extensively in the field of computer vision. The structure of convolutional neural networks is quite complicated and necessitates a substantial amount of computational time and storage resources. As a result, it is difficult to adopt a CNN model on a resource-constraint device. Model pruning can help to reduce computation time and storage re-quirements. In this research, we propose a filter pruning technique based on Localized Gradient Activation heatmaP (LGAP) for the purpose of pruning CNNs. Analyzing a filter based on statistical criterion of single neuron can lead to a loss in spatial relations within the filter activation itself, the relationship to target prediction, as well as the relationship among filters in that specific layer. To minimize the limitations, we evaluate the significance of a filter through the spatial information of local gradient activation related to the target prediction in terms of the layer-wise loss of the investigated filter. The effect of loss of an investigated filter demonstrates the significance or insignificance of the filter. Our pruning criteria ensure that these significant filters are preserved, while maintaining the model accuracy. The performance of our pruning method was validated using VGG-16 and ResNet-50. With pruning ratio of 50%, VGG-16 tends to decrease 1.66% of its accuracy, 3.6× of FLOP and 3.9× of storage reduction. For ResNet-50, with 50% pruning ratio, the results show that Top-1 and Top-5 of our pruning techniques outperform all the baseline techniques with a reduction of top-1 accuracy by 3.56%, top-5 accuracy by 1.89%, Floating Point Operation by 2.3×, and storage by 2.05×.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Filter Pruning with Convolutional Approximation Small Model Framework
    (2023-09-01)
    Intraraprasit, Monthon
    ;
    Chitsobhuk, Orachat
    Convolutional neural networks (CNNs) are extensively utilized in computer vision; however, they pose challenges in terms of computational time and storage requirements. To address this issue, one well-known approach is filter pruning. However, fine-tuning pruned models necessitates substantial computing power and a large retraining dataset. To restore model performance after pruning each layer, we propose the Convolutional Approximation Small Model (CASM) framework. CASM involves training a compact model with the remaining kernels and optimizing their weights to restore feature maps that resemble the original kernels. This method requires less complexity and fewer training samples compared to basic fine-tuning. We evaluate the performance of CASM on the CIFAR-10 and ImageNet datasets using VGG-16 and ResNet-50 models. The experimental results demonstrate that CASM surpasses the basic fine-tuning framework in terms of time acceleration (3.3× faster), requiring a smaller dataset for performance recovery after pruning, and achieving enhanced accuracy.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Interaction Behavior of Older Adults with Immersive Virtual Reality Application for Cognitive Training
    (2018-09-11)
    Intraraprasit, Monthon
    ;
    Sunhem, Wisuwat
    ;
    Jinjakam, Chompoonuch
    Nowadays, older adults face health problems. The main problem is decreasing our brain skills. Memory, visuospatial skill, and cognitive functions are considered to be essence of the brain skills. These capabilities can performance by applying cognitive training or brain training. Currently, virtual reality (VR) technology is applied to cognitive training application. The results of training can be analyzed after several weeks, but it is a lack of interaction behavior analysis of older adults with VR application. The behavior analysis helps to design efficient program training, in other words, we can utilize better VR application with older adults who do not familiar with current technology. Moreover, we can understand behavior of older adult via VR application for their brain ability. VR application can be designed and kept log files for interaction behavior analysis. The algorithm for preliminary analysis is machine learning. Machine learning can predict score that measures brain's ability from the dataset. We adopted 2 models in this research. The first model is to predict the scores of visual short-term memory, called VSTM-model. The second model is to predict the scores of visuospatial skill, called VS-model. We performed baseline regression and support vector regression algorithm for score prediction of behavior. Root mean squared error is selected to measure performance of the algorithm; root mean squared error of baseline regression equal to 0.3012 in VSTM-model and 1.2427 in VS-model, and root mean squared error of support vector regression equal to 0.2876 in VSTM-model and 1.0536 in VS-model.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Item,
    Cognitive training using immersive Virtual Reality
    (2017-12-19)
    Intraraprasit, Monthon
    ;
    Phanpanya, Phanuthon
    ;
    Jinjakam, Chompoonuch
    Normal adult becomes memory decline when increasing age. Memory decline can change from normal aging to mild cognitive impairment (MCI) and then Alzheimer's disease dementia. In order to reduce the risk of dementia, the cognitive training or brain training is needed. Cognitive training can stimulate the ability of normal person's memory for keeping ability of memory prompt when increasing age. Virtual Reality (VR) technology can be used to establish VR application for cognitive training. This paper proposes VR application for cognitive training that uses a head-mounted display for a full immersive device with VR controllers. This VR application is designed for training in visual memory and visuospatial under the psychiatrist's guidance. There were 45 participants in this experiment. All participants were tested memory ability of remember things and places from first practicing and evaluated satisfaction after using our VR application from satisfactory form. This experiment can help to determine the difficulty level in the next training and suitability of activity. The time duration of recall memory related to difficulty level in VR application (correlation coefficient, p = 0.379, 0.010). Furthermore, the satisfied evaluation of participants using VR application was 'satisfied' and 'very satisfied' in each difficulty level in VR application that Cronbach's alpha = 0.743.