Filtering by
- All Subjects: Learning
- Creators: Harrington Bioengineering Program
Colorimetric assays are an important tool in point-of-care testing that offers several advantages to traditional testing methods such as rapid response times and inexpensive costs. A factor that currently limits the portability and accessibility of these assays are methods that can objectively determine the results of these assays. Current solutions consist of creating a test reader that standardizes the conditions the strip is under before being measured in some way. However, this increases the cost and decreases the portability of these assays. The focus of this study is to create a machine learning algorithm that can objectively determine results of colorimetric assays under varying conditions. To ensure the flexibility of a model to several types of colorimetric assays, three models were trained on the same convolutional neural network with different datasets. The images these models are trained on consist of positive and negative images of ETG, fentanyl, and HPV Antibodies test strips taken under different lighting and background conditions. A fourth model is trained on an image set composed of all three strip types. The results from these models show it is able to predict positive and negative results to a high level of accuracy.
The purpose of this study is to know whether the primary motor cortex (M1) plays a role in the sensorimotor memory. It was hypothesized that temporary disruption of the M1 following the learning to minimize a tilt using a ‘L’ shaped object would negatively affect the retention of sensorimotor memory and thus reduce interference between the memory acquired in one context and the visual cues to perform the same task in a different context.
Significant findings were shown in blocks 1, 2, and 4. In block 3, subjects displayed insignificant amount of learning. However, it cannot be concluded that there is full interference in block 3. Therefore, looked into 3 effects in statistical analysis: the main effects of the blocks, the main effects of the trials, and the effects of the blocks and trials combined. From the block effects, there is a p-value of 0.001, and from the trial effects, the p-value is less than 0.001. Both of these effects indicate that there is learning occurring. However, when looking at the blocks * trials effects, we see a p-value of 0.002 < 0.05 indicating significant interaction between sensorimotor memories. Based on the results that were found, there is a presence of interference in all the blocks but not enough to justify the use of TMS in order to reduce interference because there is a partial reduction of interference from the control experiment. It is evident that the time delay might be the issue between context switches. By reducing the time delay between block 2 and 3 from 10 minutes to 5 minutes, I will hope to see significant learning to occur from the first trial to the second trial.
Along with aging, sleep deprivation is correlated with learning deficits. Research has shown that a lack of sleep negatively impacts motor skill learning and consolidation. Since there is a link between sleep and learning, as well as learning and the reticulospinal system, these observations raise the question: does sleep deprivation underlie reticulospinal delays? We hypothesized that sleep deprivation was correlated to a slower startle response, indicating a delayed reticulospinal system. Our objectives were to observe the impact of sleep deprivation on 1) the startle response (characterized by muscle onset latency and percentage of startle responses elicited) and 2) functional performance (to determine whether subjects were sufficiently sleep deprived).
21 young adults participated in two experimental sessions: one control session (8-10 hour time in bed opportunity for at least 3 nights prior) and one sleep deprivation session (0 hour time in bed opportunity for one night prior). The same protocol was conducted during each session. First, subjects were randomly exposed to 15 loud, startling acoustic stimuli of 120 dB. Electromyography (EMG) data measured muscle activity from the left and right sternocleidomastoid (LSCM and RSCM), biceps brachii, and triceps brachii. To assess functional performance, cognitive, balance, and motor tests were also administered. The EMG data were analyzed in MATLAB. A generalized linear mixed model was performed on LSCM and RSCM onset latencies. Paired t-tests were performed on the percentage of startle responses elicited and functional performance metrics. A p-value of less than 0.05 indicated significance.
Thirteen out of 21 participants displayed at least one startle response during their control and sleep deprived sessions and were further analyzed. No differences were found in onset latency (RSCM: control = 75.87 ± 21.94ms, sleep deprived = 82.06 ± 27.47ms; LSCM: control = 79.53 ± 17.85ms, sleep deprived = 78.48 ± 20.75ms) and percentage of startle responses elicited (control = 84.10 ± 15.53%; sleep deprived = 83.59 ± 18.58%) between the two sessions. However, significant differences were observed in reaction time, TUG with Dual time, and average balance time with the right leg up. Our data did not support our hypothesis; no significant differences were seen between subjects’ startle responses during the control and sleep deprived sessions. However, sleep deprivation was indicated with declines were observed in functional performance. Therefore, we concluded that sleep deprivation may not affect the startle response and underlie delays in the reticulospinal system.
movement to become faster, more accurate and efficient, declines with age. Initial skill acquisition is dominated by cortical structures; however as learning proceeds, literature from
rodents and songbirds suggests that there is a transition away from cortical execution. Recent
evidence indicates that the reticulospinal system plays an important role in integration and
retention of learned motor skills. The brainstem has known age-rated deficits including cell
shrinkage & death. Given the role of the reticulospinal system in skill acquisition and older
adult’s poor capacity to learn, it begs the question: are delays in the reticulospinal system
associated with older adult’s poor capacity to learn?
Our objective was to evaluate if delays in the reticulospinal system (measured via the
startle reflex) and corticospinal system (measured via Transcranial Magnetic Stimulation (TMS) are correlated to impairment of motor learning in older adults. We found that individuals with fast startle responses resembling those of younger adults show the most improvement and retention while individuals with delayed startle responses show the least. We also found that there was no relationship between MEP latencies and improvement and retention. Moreover, linear regression analysis indicated that startle onset latency exists within a continuum of learning outcomes suggesting that startle onset latency may be a sensitive measure to predict learning deficits in older adults. As there exists no method to determine an individual’s relative learning capacity, these results open the possibility of startle, which is an easy and inexpensive behavioral measure and can be used to determine learning deficits in older adults to facilitate better dosing during rehabilitation therapy.
Our objective was to evaluate if delays in the reticulospinal system (measured via the startle reflex) are correlated to impairment of motor learning in older adults. We found that individuals with fast startle responses resembling those of younger adults show the most learning and retention of that learning while individuals with delayed startle responses show the least. Moreover, linear regression analysis indicated that startle onset latency exists within a continuum of learning outcomes suggesting that startle onset latency may be a sensitive measure to predict learning deficits in older adults. As there exists no method to determine an individual’s relative learning capacity, these results open the possibility of startle, which is an easy and inexpensive behavioral measure, being used to predict learning deficits in older adults to facilitate better dosing during rehabilitation therapy.
Carbohydrate counting has been shown to improve HbA1c levels for people with diabetes. However, the learning curve and inconvenience of carbohydrate counting make it difficult for patients to adhere to it. A deep learning model is proposed to identify food from an image, where it can help the user manage their carbohydrate counting. This early model has a 68.3% accuracy of identifying 101 different food classes. A more refined model in future work could be deployed into a mobile application to identify food the user is about to consume and log it for easier carbohydrate counting.