Slim LSTM NETWORKS: LSTM_6 and LSTM_C6

Akandeh, Atra; Salem, Fathi M.

doi:10.1109/mwscas.2019.8884912

Cited by 14 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This would be useful for user authentication because it is likely that the same child would be using a mobile device over a given bout of time and training the model with behavior from earlier in the bout would enhance model performance. However, LSTM models are computationally intensive [68], which is why more parsimonious techniques were used in this preliminary study.…”

Section: Discussionmentioning

confidence: 99%

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Finnegan,

Weaver,

Yang

et al. 2024

Human Behavior and Emerging Technologies

View full text Add to dashboard Cite

Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted how children engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing the accuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a given device but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioral biometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied to address this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad sensor data to identify the unique user of the device in a sample of children ages 6 to 11. Data was collected opportunistically from nine participants (8.2 ± 1.75 years, 5 female) in the sedentary portion of two semistructured physical activity protocols. SensorLog was downloaded onto study iPads and collected data from the accelerometer, gyroscope, and magnetometer sensors while the participant interacted with the iPad. Five machine learning models, logistic regression (LR), support vector machine, neural net (NN), k-nearest neighbors (k-NN), and random forest (RF), were trained using 57 features generated from the sensor output to perform multiclass classification. A train-test split of 80%–20% was used for model fitting. Model performance was evaluated using F1 score, accuracy, precision, and recall. Model performance was high, with F1 scores ranging from 0.75 to 0.94. RF and k-NN had the highest performance across metrics, with F1 scores of 0.94 for both models. This study highlights the potential of using existing mobile device sensors to continuously identify the user of a device in the context of screen time measurement. Future research should explore the performance of this technology in larger samples of children and in free-living environments.

show abstract

Section: Discussionmentioning

confidence: 99%

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Finnegan,

Weaver,

Yang

et al. 2024

Human Behavior and Emerging Technologies

View full text Add to dashboard Cite

show abstract

“…LSTM is a type of RNN layer that can effectively process sequential data, such as time series or text [ 57 ]. The bidirectional variant of LSTM processes the input sequence in both forward and backward directions, allowing the model to capture dependencies in both past and future contexts.…”

Section: Methodsmentioning

confidence: 99%

Detecting Minor Symptoms of Parkinson’s Disease in the Wild Using Bi-LSTM with Attention Mechanism

Skaramagkas,

Boura,

Spanaki

et al. 2023

Sensors

View full text Add to dashboard Cite

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by motor and nonmotor impairment with various implications on patients’ quality of life. Since currently available therapies are only symptomatic, identifying individuals with prodromal, preclinical, or early-stage PD is crucial, as they would be ideal candidates for future disease-modifying therapies. Our analysis aims to develop a robust model for accurate PD detection using accelerometer data collected from PD and non-PD individuals with mild or no tremor during phone conversations. An open-access dataset comprising accelerometer recordings from 22 PD patients and 11 healthy controls (HCs) was utilized. The data were preprocessed to extract relevant time-, frequency-, and energy-related features, and a bidirectional long short-term memory (Bi-LSTM) model with attention mechanism was employed for classification. The performance of the model was evaluated using fivefold cross-validation, and metrics of accuracy, precision, recall, specificity, and f1-score were computed. The proposed model demonstrated high accuracy (98%), precision (99%), recall (98%), specificity (96%), and f1-score (98%) in accurately distinguishing PD patients from HCs. Our findings indicate that the proposed model outperforms existing approaches and holds promise for detection of PD with subtle symptoms, like tremor, in the wild. Such symptoms can present in the early or even prodromal stage of the disease, and appropriate mobile-based applications may be a practical tool in real-life settings to alert individuals at risk to seek medical assistance or give patients feedback in monitoring their symptoms.

show abstract

“…The main function of LSTM to solve the vanishing gradient is caused by the gradient getting smaller until the last layer of the weight value is unchanged, which causes it never to get a better result or converge. On the other hand, the increasing gradient causes the weighting values in several layers to increase too, so the optimization algorithm becomes divergent or is called an exploding gradient [2,[14][15][16][17].…”

Section: Fig 1 Recurrent Neural Network (Rnn) Conceptmentioning

confidence: 99%

The development of simultaneous transducer ultrasonic with dual-transducer to measure flow velocity in the pipe

Wiranata,

Kurniadi

2023

Eureka: PE

View full text Add to dashboard Cite

There are still several obstacles to calculating fluid flow rate measurement on custody transfer, such as the distribution of one-phase fluid flow rate, less sTable pressure, and fluid flow rate changes, which are still the main problems in the process of a measuring system. To calculate the flow rate of one phase fluid, there is a method often used, namely transit time. In practice, the transit time works to send the ultrasonic pulse from upstream to downstream, which had to have a delay because the transducer must switch the function of a transducer to become transmitter or receiver. So, this paper proposed a new strategy of measurement multipath ultrasonic flowmeter (UFLW) with a simultaneous transit time method using a dual transmitter and receiver. The simultaneous method is a measuring technique that utilizes a pair of ultrasonic transducers as both trigger and receiver. The first transducer serves as the transmitter, while the second functions as the receiver, capturing the signal at the same time without changing their positions or roles. In order to implement the configuration setup, let’s try to use 3 paths configuration with 6 pairs of transducers, 3 on the upstream and 3 on the downstream. To estimate the flow velocity, let’s use long short-term memory (LSTM), which is one of the recurrent neural networks (RNN) architectures in the deep learning algorithm, and to evaluate the performance, let’s use the Bland-Altman plot and root mean squared error (RMSE) and validation loss of the LSTM model. The result shows RMSE 0.289 from the actual flow velocity, which means an LTSM with simultaneous multipath ultrasonic can reduce the error between prediction and actual measurement

show abstract

Slim LSTM NETWORKS: LSTM_6 and LSTM_C6

Cited by 14 publications

References 13 publications

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Advancing Objective Mobile Device Use Measurement in Children Ages 6–11 Through Built-In Device Sensors: A Proof-of-Concept Study

Detecting Minor Symptoms of Parkinson’s Disease in the Wild Using Bi-LSTM with Attention Mechanism

The development of simultaneous transducer ultrasonic with dual-transducer to measure flow velocity in the pipe

Contact Info

Product

Resources

About