A Comparison of Unidirectional and Bidirectional LSTM Networks for Human Activity Recognition

Alawneh, Luay; Mohsen, Belal; Al-Zinati, Mohammad; Shatnawi, Ahmed S.; Al‐Ayyoub, Mahmoud

doi:10.1109/percomworkshops48775.2020.9156264

Cited by 35 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantage of using an LSTM network over a recurrent neural network (RNN) is that LSTM can capture the temporal dependency of input sequences during the training process [ 21 , 34 ]. An LSTM network is an RNN that prevents the long-term dependency problem by utilizing gates and calculating a hidden state with an enhanced function [ 17 ]. The building blocks of LSTM networks are LSTM cells, which means that an LSTM layer consists of recurrently connected cells [ 16 , 17 , 34 ].…”

Section: Methodsmentioning

confidence: 99%

“…For example, an original RNN is incapable of remembering past data, while a long short-term memory (LSTM) network is a modified version of RNN-based networks capable of remembering and learning from past data [ 16 ]. This means that LSTMs are suitable for making a prediction model when the datasets are in the form of time series due to their ability to learn temporal dependencies by employing a gating mechanism for data analysis [ 17 ]. Moreover, LSTM solves the vanishing gradient problem, unlike the original RNN [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Analyte Concentrations from Electrochemical Aptasensor Signals Using LSTM Recurrent Networks

et al. 2022

View full text Add to dashboard Cite

Nanomaterial-based aptasensors are useful devices capable of detecting small biological species. Determining suitable signal processing methods can improve the identification and quantification of target analytes detected by the biosensor and consequently improve the biosensor’s performance. In this work, we propose a data augmentation method to overcome the insufficient amount of available original data and long short-term memory (LSTM) to automatically predict the analyte concentration from part of a signal registered by three electrochemical aptasensors, with differences in bioreceptors, analytes, and the signals’ lengths for specific concentrations. To find the optimal network, we altered the following variables: the LSTM layer structure (unidirectional LSTM (LSTM) and bidirectional LSTM (BLSTM)), optimizers (Adam, RMSPROP, SGDM), number of hidden units, and amount of augmented data. Then, the evaluation of the networks revealed that the highest original data accuracy increased from 50% to 92% by exploiting the data augmentation method. In addition, the SGDM optimizer showed a lower performance prediction than that of the ADAM and RMSPROP algorithms, and the number of hidden units was ineffective in improving the networks’ performances. Moreover, the BLSTM nets showed more accurate predictions than those of the ULSTM nets on lengthier signals. These results demonstrate that this method can automatically detect the analyte concentration from the sensor signals.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting Analyte Concentrations from Electrochemical Aptasensor Signals Using LSTM Recurrent Networks

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This enables the network to have the sequence information in both directions and is known to perform better than unidirectional LSTM models in other sequence modeling tasks. [86][87][88] The specific RNN model employed here had three bidirectional LSTM layers with 4dimensional hidden states followed by a fully connected linear layer. The model was again trained on the sequence vectors.…”

Section: F Representation Learningmentioning

confidence: 99%

Predicting aggregate morphology of sequence-defined macromolecules with Recurrent Neural Networks

Bhattacharya¹,

Kleeblatt²,

Statt³

et al. 2022

Preprint

View full text Add to dashboard Cite

Self-assembly of dilute sequence-defined macromolecules is a complex phenomenon in which the local arrangement of chemical moieties leads to the formation of a long-range structure. The dependence of this structure on the sequence necessarily implies that a mapping between the two exists, yet it has been difficult to model so far. Predicting the aggregation behavior of these macromolecules is challenging due to the lack of effective order parameters, a vast design space, inherent variability, and high computational costs associated with currently available simulation techniques. Here, we accurately predict the morphology of aggregates self-assembled from sequence-defined macromolecules using supervised machine learning. We find that regression models with implicit representation learning perform significantly better than those based on engineered features such as k-mer counting, and a Recurrent-Neural-Network-based regressor performs the best. Further, we demonstrate the high-throughput screening of monomer sequences using the regression model to identify candidates for self-assembly into selected morphologies. Our strategy is shown to successfully identify multiple suitable sequences in every test we performed, so we hope the insights gained here can be extended to other increasingly complex design scenarios in the future, such as the design of sequences under polydispersity and at varying environmental conditions.

show abstract

“…We specifically used LSTM layers in a bidirectional architecture, i.e., the network included forward and backward LSTM layers that were simultaneously trained, so that both time directions (past and future) were considered and contributed to the outcome [33]. The bidirectional architecture improved model performance in problems dealing with inertial sensor data, e.g., in [25], or in [39]. In the gait analysis domain, double integration with linear dedrifting or direct and reverse integration are typically applied to bound integration errors, considering that the foot should have a velocity of zero in the initial and final instants of the stride [19,40,41].…”

Section: Network Architecturementioning

confidence: 99%

A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors

Guimar�ães

Sousa

Correia

2021

Sensors

View full text Add to dashboard Cite

Gait performance is an important marker of motor and cognitive decline in older adults. An instrumented gait analysis resorting to inertial sensors allows the complete evaluation of spatiotemporal gait parameters, offering an alternative to laboratory-based assessments. To estimate gait parameters, foot trajectories are typically obtained by integrating acceleration two times. However, to deal with cumulative integration errors, additional error handling strategies are required. In this study, we propose an alternative approach based on a deep recurrent neural network to estimate heel and toe trajectories. We propose a coordinate frame transformation for stride trajectories that eliminates the dependency from previous strides and external inputs. Predicted trajectories are used to estimate an extensive set of spatiotemporal gait parameters. We evaluate the results in a dataset comprising foot-worn inertial sensor data acquired from a group of young adults, using an optical motion capture system as a reference. Heel and toe trajectories are predicted with low errors, in line with reference trajectories. A good agreement is also achieved between the reference and estimated gait parameters, in particular when turning strides are excluded from the analysis. The performance of the method is shown to be robust to imperfect sensor-foot alignment conditions.

show abstract

A Comparison of Unidirectional and Bidirectional LSTM Networks for Human Activity Recognition

Cited by 35 publications

References 22 publications

Predicting Analyte Concentrations from Electrochemical Aptasensor Signals Using LSTM Recurrent Networks

Predicting Analyte Concentrations from Electrochemical Aptasensor Signals Using LSTM Recurrent Networks

Predicting aggregate morphology of sequence-defined macromolecules with Recurrent Neural Networks

A Deep Learning Approach for Foot Trajectory Estimation in Gait Analysis Using Inertial Sensors

Contact Info

Product

Resources

About