KMITL

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

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
Determining the Optimal Parameters for Preventing Backward Falls Using a Human Movement Dataset: An Investigative Study
(2024-01-01)
Yoneyama, Keito R.
;
Sermswan, Anawat
;
Jansri, Ukkrit
;
Srisuttee, Ratakorn
Falls are a major health concern, particularly for the elderly, as they often lead to severe injuries like hip fractures. Fortunately, there are a lot of publicly available datasets that can offer valuable insights regarding the mechanics of falls and activities of daily living. This study aims to determine the optimal prevention threshold for backward falls using available datasets, thereby avoiding any fall-related injuries. The methodology employed in this study involves identifying downward trends of acceleration and angular velocity on the graph. The Pythagorean Theorem is used to calculate the resultant acceleration, while differences are computed to determine the changes in angular velocity. The results from 150 samples shows that the acceleration for the prevention threshold range is between 3.016m/s<sup>2</sup> - 4.308 m/s<sup>2</sup>and the average angular velocity is 0.522 rad/s - 0.746 rad/s which not only prevents a person from falling backward but will also be able to distinguish between activities of daily living. In conclusion, using existing dataset can offer essential knowledge into fall detection and serves as a foundation for determining the optimal fall prevention threshold.
Some of the metrics are blocked by your
consent settings
Effect of Class Weights on Imbalanced Classes in Bi-directional LSTM Training for Sleep Apnea Classification
(2024-01-01)
Jansri, Ukkrit
;
Tretriluxana, Suradej
Sleep apnea, which is defined as the repetitive cessations of breathing during sleep, is the common disorder worldwide. The cost and the process of sleep test to obtain the polysomnogram is not optimal for sleep apnea screening in the large population. A deep learning model was developed to classify the normal and apnea events in a single time-series signal exported from the US National Institute of Health (NIH) sponsored database. Our challenge was to train the model with imbalanced dataset between normal and abnormal respiratory events. Three different methods, Synthetic Minority Over-sampling Technique (SMOTE), Random Under-Sampling (RUS), and the Class Weights (CW) were chosen to improve the model performance over the original data on five selected signals from polysomnographic dataset. The binary classification outputs were evaluated by four metrics. Our results showed (1) Matthews Correlation Coefficient was highest (MCC= 0.1385) in the Class Weights method on the nasal airflow signal. (2) Cohen's Kappa score, was highest (k= 0.0819) in SMOTE technique on the abdominal signal, followed by the Class Weights method on the abdominal signal (k= 0.0687) and RUS technique on nasal airflow signal (k= 0.0441). (3) F1-score was highest (F1= 11.89%) in SMOTE technique on the abdominal signal, followed by the Class Weights method on nasal airflow signal (F1 = 11.17%) and RUS technique on nasal airflow signal (F1= 9.16%). The findings suggest that the Class Weights method on nasal airflow and the Class Weights method on abdominal signal were the two combinations to be used in the DL model.
Some of the metrics are blocked by your
consent settings
The Possible Sarcopenia Associated with Independent Walking Older Adults
(2023-05-01)
Raksadawan, Natte
;
Sermswan, Anawat
;
Jansri, Ukkrit
The amount of skeletal muscle mass and mobility function increase during the childhood, peak at young adult, and then decline after middle age. Older adults with low skeletal mass and mobility function are associated with reduced physical performance. The older adult with a low level of mobility function, regardless of the amount of muscle mass, is defined as "possible sarcopenia". This study aims 1) to characterize the current state of the physical and mobility function at the peak levels of these parameters among young adults 2) to characterize their deterioration rates during middle-age and older-age years and older adults; and 3) to study the prevalence of possible sarcopenia among older adults. The cross-sectional study of anthropometric parameters, body compositions, and mobility assessments was conducted from independent walking young, middle, and older age adults in the community. Young adult male had higher levels of physical and mobility function than female. The changes in physical and mobility function during middle age were subtle. Older age male (female) lost skeletal muscle mass at-0.125 (-0.0190) kg/year, grip strength at-0.495 (-0.307) kg per year, and gait speed at-0.007 (-0.013) m/sec per year, respectively. The prevalence of possible sarcopenia in older age independent walking adults, determined by low grip strength, was 19.4%. The prevalence increased with advancing age.
Some of the metrics are blocked by your
consent settings
Comparing the performances of deep learning model with different signals underlying resampling techniques to classify sleep apnea
(2023-01-01)
Jansri, Ukkrit
;
Tretriluxana, Suradej
Millions of people around the world are suffering from long term Sleep Apnea. Full scale sleep test is costly and time-consuming. This paper, using deep learning model, chose a single candidate signal from multi-channel polysomnogram data for sleep apnea screening. Nature of data, however, shows an imbalance class of dataset between normal and apneic events. To increase the binary classification output performance, two resampling techniques; Synthetic Minority Over-sampling Technique (SMOTE) and Random Under-Sampling (RUS), were employed in Bidirectional Long Short-Term Memory (Bi-LSTM) model training. One hundred polysomnography (PSG) records were randomly selected from the Multi-Ethic of Atherosclerosis (MESA) database in this study. They were trained under three conditions; original, SMOTE and RUS datasets. Our results showed (1) Cohen's kappa score was greater in resampling (SMOTE, RUS) datasets than original one. (2) Between the resampling techniques, metrices in SMOTE were better than ones in RUS. (3) Within SMOTE, the abdominal belt was the best among other signals with Cohen's kappa score of 0.2078 and 58.99% in F1-score. These findings suggested that abdominal belt was the best candidate signal for sleep apnea screening.
Some of the metrics are blocked by your
consent settings
Effect of Resampling Techniques on Deep Learning Model Training in Sleep Apnea Classification
(2022-01-01)
Jansri, Ukkrit
;
Tretriluxana, Suradej
This study is using deep learning model to classify the respiratory events of Sleep Disordered Breathing (SDB) data. Our pilot results showed the missed identification in some classes even the total accuracy is high. This is the result of unbalanced training dataset given to the model. Two different resampling techniques; Synthetic Minority Over-sampling Technique (SMOTE) and Random Under-Sampling (RUS), were introduced to balance the data. One hundred overnight nasal airflow signals were randomly selected from NIH funded polysomnography database. They were used to train and test these two algorithms with Bi-directional Long Short-Term Memory (Bi-LSTM) model. The results showed greater agreement index when compared between with and without data resampling process. However, SMOTE in sum performed better than RUS (93.72% vs 70.01% in overall accuracy and 0.91 vs 0.55 in Cohen's kappa). It demonstrates that the over-sampling technique is more powerful than under-sampling one. Other resampling techniques will be investigated to make the robust conclusion.
Some of the metrics are blocked by your
consent settings
Automatic Sleep Data Scoring by Artificial Intelligence: A Pilot Study in Thai Population
(2021-04-01)
Jansri, Ukkrit
;
Chirakalwasan, Naricha
;
Chaitusaney, Busarakum
;
Busayakanon, Supasuta
;
Khongjui, Thamonwan
Sleep apnea, a sleep-disordered breathing (SDB), is defined as repeatedly intermittent cessation of breathing during sleep. It causes various life-threatening diseases. The American Academy of Sleep Medicine (AASM) releases the manual for sleep data scoring. Patients with SDB are prescribed to be monitored at the sleep clinic where several physiological data are recorded, called polysomnogram (PSG). The massive PSG data must be scored by the well-trained expert before being diagnosed by the physician. Our research is to use the Artificial Intelligence (AI) in sleep data scoring, particularly in respiratory events detection. Three ready-made Convolution Neural Networks (CNN); AlexNet, ResNet-50, and VGG-16, with transfer learning were applied to classify 5 overnight PSG data from Chulalongkorn hospital. Our preliminary results showed that all networks provide higher classification result in European Data Format (EDF) than in the text (ASCII) formats (71% vs 54%). The ResNet-50 model structure performed better than the other two networks on both data formats. As expected, the visualized (EDF) data is better than the unconditioned (ASCII) data. Our future development is modifying learning model to increase the scoring performance from more recruited PSG data.
Some of the metrics are blocked by your
consent settings
Neural hyperactivity in the amygdala induced by chronic treatment of rats with analgesics may elucidate the mechanisms underlying psychiatric comorbidities associated with medication-overuse headache
(2017-01-03)
Wanasuntronwong, Aree
;
Jansri, Ukkrit
;
Srikiatkhachorn, Anan
Background: Patients with medication-overuse headache suffer not only from chronic headache, but often from psychiatric comorbidities, such as anxiety and depression. The mechanisms underlying these comorbidities are unclear, but the amygdala is likely to be involved in their pathogenesis. To investigate the mechanisms underlying the comorbidities we used elevated plus maze and open field tests to assess anxiety-like behavior in rats chronically treated with analgesics. We measured the electrical properties of neurons in the amygdala, and examined the cortical spreading depression (CSD)-evoked expression of Fos in the trigeminal nucleus caudalis (TNC) and amygdala of rats chronically treated with analgesics. CSD, an analog of aura, evokes Fos expression in the TNC of rodents suggesting trigeminal nociception, considered to be a model of migraine. Results: Increased anxiety-like behavior was seen both in elevated plus maze and open field tests in a model of medication overuse produced in male rats by chronic treatment with aspirin or acetaminophen. The time spent in the open arms of the maze by aspirin- or acetaminophen-treated rats (53 ± 36.1 and 37 ± 29.5 s, respectively) was significantly shorter than that spent by saline-treated vehicle control rats (138 ± 22.6 s, P < 0.001). Chronic treatment with the analgesics increased the excitability of neurons in the central nucleus of the amygdala as indicated by their more negative threshold for action potential generation (-54.6 ± 5.01 mV for aspirin-treated, -55.2 ± 0.97 mV for acetaminophen-treated, and -31.50 ± 5.34 mV for saline-treated rats, P < 0.001). Chronic treatment with analgesics increased the CSD-evoked expression of Fos in the TNC and amygdala [18 ± 10.2 Fos-immunoreactive (IR) neurons per slide in the amygdala of rats treated with aspirin, 11 ± 5.4 IR neurons per slide in rats treated with acetaminophen, and 4 ± 3.7 IR neurons per slide in saline-treated control rats, P < 0.001]. Conclusions: Chronic treatment with analgesics can increase the excitability of neurons in the amygdala, which could underlie the anxiety seen in patients with medication-overuse headache.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results