Deep learning based models are relatively large, and it is hard to deploy such models on resource-limited devices such as mobile phones and embedded devices. One possible solution is knowledge distillation whereby a smaller model (student model) is trained by utilizing the information from a larger model (teacher model). In this paper, we present an outlook of knowledge distillation techniques applied to deep learning models. To compare the performances of different techniques, we propose a new metric called distillation metric which compares different knowledge distillation solutions based on models' sizes and accuracy scores. Based on the survey, some interesting conclusions are drawn and presented in this paper including the current challenges and possible research directions.
Traffic signs are essential for the safe and efficient movement of vehicles through the transportation network. Poor sign visibility can lead to accidents. One of the key properties used to measure the visibility of a traffic sign is retro-reflection, which indicates how much light a traffic sign reflects back to the driver. The retro-reflection of the traffic sign degrades over time until it reaches a point where the traffic sign has to be changed or repaired. Several studies have explored the idea of modeling the sign degradation level to help the authorities in effective scheduling of sign maintenance. However, previous studies utilized simpler models and proposed multiple models for different combinations of the sheeting type and color used for the traffic sign. In this study, we present a neural network based deep learning model for traffic sign retro-reflectivity prediction. Data utilized in this study was collected using a handheld retro-reflectometer GR3 from field surveys of traffic signs. Sign retro-reflective measurements (i.e., the RA values) were taken for different sign sheeting brands, grades, colors, orientation angles, observation angles, and aging periods. Feature-based sensitivity analysis was conducted to identify variables’ relative importance in determining retro-reflectivity. Results show that the sheeting color and observation angle were the most significant variables, whereas sign orientation was the least important. Considering all the features, RA prediction results obtained from one-hot encoding outperformed other models reported in the literature. The findings of this study demonstrate the feasibility and robustness of the proposed neural network based deep learning model in predicting the sign retro-reflectivity.
Unlike sub-metering, which requires individual appliances to be equipped with their own meters, non-intrusive load monitoring (NILM) use algorithms to discover appliance individual consumption from the aggregated overall energy reading. Approaches that uses low frequency sampled data are more applicable in a real world smart meters that has typical sampling capability of ≤ 1Hz. In this paper, a systematic literature review on deep-learning-based approaches for NILM problem is conducted, aiming to analyse the four key aspects pertaining to deep learning adoption. This includes deep learning model adoption, features selection that are used to train the model, used data set and model accuracy. In our study, analyses the performance of four different deep learning approaches, namely, denoising autoencoder (DAE), recurrent long short-term memory (LSTM) , Recurrent gate recurrent unit (GRU), and sequence to point. Our experiments will be conducted using the two data sets, namely, REDD and UK-DALE. According to our analysis, the sequence to point model has achieved the best results with an average mean absolute error (MAE) of 14.98 watt when compared to other counterpart algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.