EcoCloud - Gestion

Center

Related publications (91)

M2D2: Maximum-Mean-Discrepancy Decoder for Temporal Localization of Epileptic Brain Activities

Amir Aminifar, Alireza Amirshahi, David Atienza Alonso, Anthony Hitchcock Thomas

Recent years have seen growing interest in leveraging deep learning models for monitoring epilepsy patients based on electroencephalographic (EEG) signals. However, these approaches often exhibit poor generalization when applied outside of the setting in which training data was collected. Furthermore, manual labeling of EEG signals is a time-consuming process requiring expert analysis, making fine-tuning patient-specific models to new settings a costly proposition. In this work, we propose the Maximum-Mean-Discrepancy Decoder (M2D2) for automatic temporal localization and labeling of seizures in long EEG recordings to assist medical experts. We show that M2D2 achieves 76.0% and 70.4% of F1-score for temporal localization when evaluated on EEG data gathered in a different clinical setting than the training data. The results demonstrate that M2D2 yields substantially higher generalization performance than other state-of-the-art deep learning-based approaches.

2022

A Semi-Supervised Algorithm for Improving the Consistency of Crowdsourced Datasets: The COVID-19 Case Study on Respiratory Disorder Classification

David Atienza Alonso, Lara Orlandic, Tomas Teijeiro Campo

Cough audio signal classification is a potentially useful tool in screening for respiratory disorders, such as COVID-19. Since it is dangerous to collect data from patients with such contagious diseases, many research teams have turned to crowdsourcing to quickly gather cough sound data, as it was done to generate the COUGHVID dataset. The COUGHVID dataset enlisted expert physicians to diagnose the underlying diseases present in a limited number of uploaded recordings. However, this approach suffers from potential mislabeling of the coughs, as well as notable disagreement between experts. In this work, we use a semi-supervised learning (SSL) approach to improve the labeling consistency of the COUGHVID dataset and the robustness of COVID-19 versus healthy cough sound classification. First, we leverage existing SSL expert knowledge aggregation techniques to overcome the labeling inconsistencies and sparsity in the dataset. Next, our SSL approach is used to identify a subsample of re-labeled COUGHVID audio samples that can be used to train or augment future cough classification models. The consistency of the re-labeled data is demonstrated in that it exhibits a high degree of class separability, 3x higher than that of the user-labeled data, despite the expert label inconsistency present in the original dataset. Furthermore, the spectral differences in the user-labeled audio segments are amplified in the re-labeled data, resulting in significantly different power spectral densities between healthy and COVID-19 coughs, which demonstrates both the increased consistency of the new dataset and its explainability from an acoustic perspective. Finally, we demonstrate how the re-labeled dataset can be used to train a cough classifier. This SSL approach can be used to combine the medical knowledge of several experts to improve the database consistency for any diagnostic classification task.

2022

Adaptive R-Peak Detection on Wearable ECG Sensors for High-Intensity Exercise

David Atienza Alonso, Elisabetta De Giovanni, Grégoire Millet, Tomas Teijeiro Campo

Objective: Continuous monitoring of biosignals via wearable sensors has quickly expanded in the medical and wellness fields. At rest, automatic detection of vital parameters is generally accurate. However, in conditions such as high-intensity exercise, sudden physiological changes occur to the signals, compromising the robustness of standard algorithms. Methods: Our method, called BayeSlope, is based on unsupervised learning, Bayesian filtering, and non-linear normalization to enhance and correctly detect the R peaks according to their expected positions in the ECG. Furthermore, as BayeSlope is computationally heavy and can drain the device battery quickly, we propose an online design that adapts its robustness to sudden physiological changes, and its complexity to the heterogeneous resources of modern embedded platforms. This method combines BayeSlope with a lightweight algorithm, executed in cores with different capabilities, to reduce the energy consumption while preserving the accuracy. Results: BayeSlope achieves an F1 score of 99.3% in experiments during intense cycling exercise with 20 subjects. Additionally, the online adaptive process achieves an F1 score of 99% across five different exercise intensities, with a total energy consumption of 1.55 ± 0.54 mJ. Conclusion: We propose a highly accurate and robust method, and a complete energy-efficient implementation in a modern ultra-low-power embedded platform to improve R peak detection in challenging conditions, such as during high-intensity exercise. Significance: The experiments show that BayeSlope outperforms state-of-the-art QRS detectors up to 8.4% in F1 score, while our online adaptive method can reach energy savings up to 38.7% on modern heterogeneous wearable platforms.

2022

Full System Exploration of On-Chip Wireless Communication on Many-Core Architectures

Giovanni Ansaloni, David Atienza Alonso, Joshua Alexander Harrison Klein, Rafael Medina Morillas, Yasir Mahmood Qureshi, Marina Zapater Sancho

In order to develop sustainable and more powerful information technology (IT) infrastructures, the challenges posed by the "memory wall" are critical for the design of high-performance and high-efficiency many-core computing systems. In this context, recent advances in the integration of nano-antennas, enabling novel short-distance communication paradigms, promise disruptive gains. To gauge their potential benefit for the next-generation of many-core server designs, it is crucial to explore the impact of wireless communication links from a whole-system viewpoint, considering complex architectures and applications characteristics. To this end, in this work we introduce an extension to the popular gem5 full system-level simulator, enabling the simulation of many-core platforms featuring on-chip wireless channels. This new extension allows the flexible investigation of different combinations of wireless and wired interconnects, as well as diverse connection protocols. We showcase its capabilities by performing an architectural exploration, targeting a multi-core system executing image inference using an AlexNet Neural Network benchmark. A 2.3x speedup is obtained when implementing wireless communication between cores instead of traditional on-chip wired interconnects.

2022

Machine-Learning Based Monitoring of Cognitive Workload in Rescue Missions with Drones

Adriana Arza Valdes, David Atienza Alonso, Ricardo Andres Chavarriaga Lozano, Dario Floreano, Ping-Keng Jao

In search and rescue missions, drone operations are challenging and cognitively demanding. High levels of cognitive workload can affect rescuers’ performance, leading to failure with catastrophic outcomes. To face this problem, we propose a machine learning algorithm for real-time cognitive workload monitoring to understand if a search and rescue operator has to be replaced or if more resources are required. Our multimodal cognitive workload monitoring model combines the information of 25 features extracted from physiological signals, such as respiration, electrocardiogram, photoplethysmogram, and skin temperature, acquired in a noninvasive way. To reduce both subject and day inter-variability of the signals, we explore different feature normalization techniques, and introduce a novel weighted-learning method based on support vector machines suitable for subject-specific optimizations. On an unseen test set acquired from 34 volunteers, our proposed subject-specific model is able to distinguish between low and high cognitive workloads with an average accuracy of 87.3% and 91.2% while controlling a drone simulator using both a traditional controller and a new-generation controller, respectively.

2022

An Accuracy-Driven Compression Methodology to Derive Efficient Codebook-Based CNNs

Giovanni Ansaloni, David Atienza Alonso, Miguel Peon Quiros, Flavio Ponzina

Codebook-based optimizations are a class of algorithmic-level transformations able to effectively reduce the computing and memory requirements of Convolutional Neural Networks (CNNs). This approach tightly limits the number of unique weights in each layer, allowing the storage of employed values in codebooks containing a small number of floating-point entries. Then, CNN models are represented as low-bitwidth indexes of such codebooks. This work introduces a novel iterative methodology to find highly beneficial schemes trading off accuracy and model compression in codebook-based CNNs. Our strategy can retrieve non-uniform solutions driven by an accuracy constraint embedded in the optimization loop. Our results indicate that, for a 1% accuracy degradation, our methodology can compress baseline floating-point CNN models up to 19x. Moreover, by reducing the number of memory accesses, our strategy increases energy efficiency and improves inference performance by up to 91%.

2022

Thermal and Voltage-Aware Performance Management of 3D MPSoCs with Flow Cell Arrays and Integrated SC Converters

Giovanni Ansaloni, David Atienza Alonso, Alexandre Sébastien Julien Levisse, Halima Najibi, Marina Zapater Sancho

Flow cell arrays (FCAs) concurrently provide efficient on-chip liquid cooling and electrochemical power generation. This technology is especially promising for three-dimensional multi-processor systems-on-chip (3D MPSoCs) realized in deeply scaled technologies, which present very challenging power and thermal requirements. Indeed, FCAs effectively improve power delivery network (PDN) performance, particularly if switched capacitor (SC) converters are employed to decouple the flow cells and the systems-on-chip voltages, allowing each to operate at their optimal point. Nonetheless, the design of FCA-based solutions entails non-obvious considerations and trade-offs, stemming from their dual role in governing both the thermal and power delivery characteristics of 3D MPSoCs. Showcasing them in this paper, we explore multiple FCA design configurations and demonstrate that this technology can decrease the temperature of a heterogeneous 3D MPSoC by 78°C, and its total power consumption by 46%, compared to a high-performance cold-plate based liquid cooling solution. At the same time, FCAs enable up to 90% voltage drop recovery across dies, using SC converters occupying a small fraction of the chip area. Such outcomes provide an opportunity to boost 3D MPSoC computing performance by increasing the operating frequency of dies. Leveraging these results, we introduce a novel temperature and voltage-aware model predictive control (MPC) strategy that optimizes power efficiency during run-time. We achieve application-wide speed-ups of up to 16% on various machine learning (ML), data mining, and other high-performance benchmarks while keeping the 3D MPSoC temperature below 83°C and voltage drops below 5%.

2022

Error Resilient In-Memory Computing Architecture for CNN Inference on the Edge

Giovanni Ansaloni, David Atienza Alonso, Alexandre Sébastien Julien Levisse, Flavio Ponzina, Marco Antonio Rios

The growing popularity of edge computing has fostered the development of diverse solutions to support Artificial Intelligence (AI) in energy-constrained devices. Nonetheless, comparatively few efforts have focused on the resiliency exhibited by AI workloads (such as Convolutional Neural Networks, CNNs) as an avenue towards increasing their run-time efficiency, and even fewer have proposed strategies to increase such resiliency. We herein address this challenge in the context of Bit-line Computing architectures, an embodiment of the in-memory computing paradigm tailored towards CNN applications. We show that little additional hardware is required to add highly effective error detection and mitigation in such platforms. In turn, our proposed scheme can cope with high error rates when performing memory accesses with no impact on CNNs accuracy, allowing for very aggressive voltage scaling. Complementary, we also show that CNN resiliency can be increased by algorithmic optimizations in addition to architectural ones, adopting a combined ensembling and pruning strategy that increases robustness while not inflating workload requirements. Experiments on different quantized CNN models reveal that our combined hardware/software approach enables the supply voltage to be reduced to just 650mV, decreasing the energy per inference up to 51.3%, without affecting the baseline CNN classification accuracy.

2022

Multi-Centroid Hyperdimensional Computing Approach for Epileptic Seizure Detection

David Atienza Alonso, Una Pale, Tomas Teijeiro Campo

Long-term monitoring of patients with epilepsy presents a challenging problem from the engineering perspective of real-time detection and wearable devices design. It requires new solutions that allow continuous unobstructed monitoring and reliable detection and prediction of seizures. A high variability in the electroencephalogram (EEG) patterns exists among people, brain states, and time instances during seizures, but also during non-seizure periods. This makes epileptic seizure detection very challenging, especially if data is grouped under only seizure (ictal) and non-seizure (inter-ictal) labels. Hyperdimensional (HD) computing, a novel machine learning approach, comes in as a promising tool. However, it has certain limitations when the data shows a high intra-class variability. Therefore, in this work, we propose a novel semi-supervised learning approach based on a multi-centroid HD computing. The multi-centroid approach allows to have several prototype vectors representing seizure and non-seizure states, which leads to significantly improved performance when compared to a simple single-centroid HD model. Further, real-life data imbalance poses an additional challenge and the performance reported on balanced subsets of data is likely to be overestimated. Thus, we test our multi-centroid approach with three different dataset balancing scenarios, showing that performance improvement is higher for the less balanced dataset. More specifically, up to 14% improvement is achieved on an unbalanced test set with 10 times more non-seizure than seizure data. At the same time, the total number of sub-classes is not significantly increased compared to the balanced dataset. Thus, the proposed multi-centroid approach can be an important element in achieving a high performance of epilepsy detection with real-life data balance or during online learning, where seizures are infrequent.

2022

Exploration of Hyperdimensional Computing Strategies for Enhanced Learning on Epileptic Seizure Detection

David Atienza Alonso, Una Pale, Tomas Teijeiro Campo

Wearable and unobtrusive monitoring and prediction of epileptic seizures has the potential to significantly increase the life quality of patients, but is still an unreached goal due to challenges of real-time detection and wearable devices design. Hyperdimensional (HD) computing has evolved in recent years as a new promising machine learning approach, especially when talking about wearable applications. But in the case of epilepsy detection, standard HD computing is not performing at the level of other state-of-the-art algorithms. This could be due to the inherent complexity of the seizures and their signatures in different biosignals, such as the electroencephalogram (EEG), the highly personalized nature, and the disbalance of seizure and non-seizure instances. In the literature, different strategies for improved learning of HD computing have been proposed, such as iterative (multi-pass) learning, multi-centroid learning and learning with sample weight ("OnlineHD"). Yet, most of them have not been tested on the challenging task of epileptic seizure detection, and it stays unclear whether they can increase the HD computing performance to the level of the current state-of-the-art algorithms for wearable devices, such as random forests. Thus, in this paper, we implement different learning strategies and assess their performance on an individual basis, or in combination, regarding detection performance and memory and computational requirements. Results show that the best-performing algorithm, which is a combination of multi-centroid and multi-pass, can indeed reach the performance of the random forest model on a highly unbalanced dataset imitating a real-life epileptic seizure detection application.

2022