@inproceedings{mapadafe:2024:gem,

title = {Benchmarking MLCommons Tiny Audio Denoising with Deployability Constraints},

author = {Armin Mazinani and Danilo Pietro Pau and Luca Davoli and Gianluigi Ferrari},

doi = {10.1109/GEM61861.2024.10585695},

issn = {2766-6530},

year  = {2024},

date = {2024-07-11},

urldate = {2024-01-01},

booktitle = {2024 IEEE Gaming, Entertainment, and Media Conference (GEM)},

pages = {1-4},

address = {Turin, Italy},

abstract = {Speech enhancement is a critical field in audio signal processing given its essentiality to overcome obstacles related to loud and damaged speech signals. Due to the revolutionary capa-bilities of Deep Learning (DL) models, there has been significant interest on benchmarking them and studying their suitability for tiny embedded systems. In this paper, we thoroughly examine the growing field of voice improvement, with a specific emphasis on the use of DL-based techniques under consideration by the MLCommons standardization. In particular, among the others, the Legendre Memory Unit (LMU) model achieves an average Scale-Invariant Signal-to-Distortion Ratio (SISDR) on 8.613 in 627 KiB of FLASH memory, making it deployable on tiny microcontrollers by requiring only 7 ms per inference run.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{madapafe:2023:iotais,

title = {Accurate Classification of Sport Activities Under Tiny Deployability Constraints},

author = {Armin Mazinani and Luca Davoli and Danilo Pietro Pau and Gianluigi Ferrari},

doi = {10.1109/IoTaIS60147.2023.10346056},

issn = {2832-1383},

year  = {2023},

date = {2023-12-14},

urldate = {2023-01-01},

booktitle = {2023 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)},

pages = {261-267},

address = {Bali, Indonesia},

abstract = {Human Activity Recognition (HAR) plays a prominent role in various domains, such as healthcare, surveillance, and sports. In this paper, our goal is to identify the most accurate Deep Learning (DL) algorithm under tiny deployability constraints. Our results show that a Recurrent Neural Network (RNN) given by the combination of a one-dimensional Convolutional Neural Network (ID-CNN) with Bi-directional Gated Recurrent Unit (Bi-GRU) is the most attractive solution, with respect to Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and the recently introduced Legendre Memory Unit (LMU). The algorithm performance is investigated over a publicly available dataset consisting of 19 different daily activities. According to the obtained results, 1D-CNN-BiGRU has an average accuracy within 0.2% of that of BiGRU (the RNN with highest accuracy) with an execution time more than 4 times shorter.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{madafe:2023:brains,

title = {Deep Learning-Based Cryptocurrency Price Prediction: A Comparative Analysis},

author = {Armin Mazinani and Luca Davoli and Gianluigi Ferrari},

doi = {10.1109/BRAINS59668.2023.10317011},

year  = {2023},

date = {2023-11-17},

urldate = {2023-01-01},

booktitle = {2023 5th Conference on Blockchain Research & Applications for Innovative Networks and Services (BRAINS)},

pages = {1-8},

address = {Paris, France},

abstract = {In recent years, cryptocurrencies have gained a lot of popularity in the financial markets and now, in addition to investing on them, it is possible to use them as a common currency to meet daily needs. Given the complex nature of financial markets and their reliance on different parameters to determine stocks' and assets' prices, the ability to predict prices is important for investment decisions, especially with respect to cryptocurrencies. To this end, Deep Learning (DL)-based algorithms can be viable solutions, owing to their use as time series forecasting tools. In this paper, we investigate the applicability of DL algorithms to forecast the prices of three cryptocurrencies, namely Bitcoin, Ethereum, and Ripple. We evaluate the performance of the proposed approach, in terms of short-term and long-term prediction accuracy (considering proper error metrics).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{madapafe:2023:icitri,

title = {Air Quality Estimation with Embedded AI-Based Prediction Algorithms},

author = {Armin Mazinani and Luca Davoli and Danilo Pietro Pau and Gianluigi Ferrari},

doi = {10.1109/ICITRI59340.2023.10249864},

year  = {2023},

date = {2023-09-19},

urldate = {2023-09-19},

booktitle = {2023 International Conference on Information Technology Research and Innovation (ICITRI)},

pages = {87-92},

address = {Jakarta, Indonesia},

abstract = {Air pollution is one of the main criticalities in cities with large populations. Therefore, accurate air quality prediction is crucial to control the environmental pollution and to maintain healthy living conditions for the citizens. To this end, particulate matters (e.g., PM2.5) have been recognised as one of the most important pollutants with a detrimental impact on human health. In this paper, we investigate the trade-off between estimation accuracy and computational complexity of Machine Learning (ML) and Deep Learning (DL) algorithms in predicting air pollution (in terms of PM2.5 concentration), in order to investigate their applicability to Internet of Things (IoT)-oriented applications. Six DL methods are implemented and evaluated, considering various time lags. DL approaches are shown to outperform ML approaches—in the DL case, two distinct optimizers, namely ADAM and Root Mean Squared Propagation (RMSProp), are considered. Among all algorithms evaluated, GRU had a RMSE of 20.02, while SimpleRNN reduced the MACs number by 98.90% over GRU and with an accuracy drop of 7.5%.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}