More Like this

1. LSTM Filter for Smart Agriculture

   https://doi.org/10.1016/j.procs.2022.10.152  

   Kim, Junwhan; Yu, Byunggu; O'Hara, Sabin (January 2022, Procedia Computer Science)

   Enormous amounts of data are generated each day by sensor devices. In agriculture, these devices continuously monitor numerous environmental properties in the fields of aquaponics, hydroponics, and soil-based food production. Data stream mining is the process of extracting data from continuous, rapidly sampled data sources. The data accuracy that can be achieved in data stream mining is highly dependent on the algorithm chosen to suppress noise. For threshold-based automation, an actuator can be activated when the value of sensor data is above a permissible threshold. Noise from sensors may activate the actuator. Several statistical and machine learning-based noise- suppression algorithms have been proposed in the literature. The proposed LSTM (Long Short-Term Memory) filter performs better noise suppression than other traditional filters – Kalman and moving average filters. The LSTM filter is installed in our threshold-based aquaponics automation to maximize sustainable food production at minimum cost. 

   more » « less
2. η-LSTM: Co-Designing Highly-Efficient Large LSTM Training via Exploiting Memory-Saving and Architectural Design Opportunities

   https://doi.org/10.1109/ISCA52012.2021.00051  

   Zhang, Xingyao; Xia, Haojun; Zhuang, Donglin; Sun, Hao; Fu, Xin; Taylor, Michael B.; Leon Song, Shuaiwen (June 2021, ACM/IEEE International Symposium on Computer Architecture)
3. Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach

   https://doi.org/10.1029/2023SW003763  

   Jeong, Se‐Heon; Lee, Woo Kyoung; Kil, Hyosub; Jang, Soojeong; Kim, Jeong‐Heon; Kwak, Young‐Sil (January 2024, Space Weather)

   Abstract This study evaluates the performance of deep learning approach in the prediction of the ionospheric total electron content (TEC) during magnetically quiet periods. Two deep learning techniques, long short‐term memory (LSTM) and convolutional LSTM (ConvLSTM), are employed to predict TEC values 24 hr ahead in the vicinity of the Korean Peninsula (26.5°–40°N, 121°–134.5°E). The LSTM method predicts TEC at a single point based on time series of data at that point, whereas the ConvLSTM method simultaneously predicts TEC values at multiple points using spatiotemporal distribution of TEC. Both the LSTM and ConvLSTM models are trained using the complete regional TEC maps reconstructed by applying the Deep Convolutional Generative Adversarial Network–Poisson Blending (DCGAN‐PB) method to observed TEC data. The training period spans from 2002 to 2018, and the model performance is evaluated using 2019 data. Our results show that the ConvLSTM method outperforms the LSTM method, generating more reliable TEC maps with smaller root mean square errors when compared to the ground truth (DCGAN‐PB TEC maps). This outcome indicates that deep learning models can improve the prediction accuracy of TEC at a specific point by taking into account spatial information of TEC. We conclude that ConvLSTM is a reliable and efficient approach for the prompt ionospheric prediction. 

   more » « less
4. LSTM Forecasts for Smart Home Electricity Usage

   https://doi.org/10.1109/ICRERA49962.2020.9242804  

   Alden, Rosemary E; Gong, Huangjie; Ababei, Cristinel; Ionel, Dan M (September 2020, IEEE)
5. Robust ECG R-peak detection using LSTM

   https://doi.org/10.1145/3341105.3373945  

   Laitala, Juho; Jiang, Mingzhe; Syrjälä, Elise; Naeini, Emad Kasaeyan; Airola, Antti; Rahmani, Amir M.; Dutt, Nikil D.; Liljeberg, Pasi (March 2020, Proceedings of the 35th Annual ACM Symposium on Applied Computing)