Search

Self-driving systems execute an ensemble of different self-driving workloads on embedded systems in an end-to-end manner, subject to functional and performance requirements. To enable exploration, optimization, and end-to-end evaluation on different embedded platforms, system designers critically need a benchmark suite that enables flexible and seamless configuration of self-driving scenarios, which realistically reflects real-world self-driving workloads’ unique characteristics. Existing CPU and GPU embedded benchmark suites typically (1) consider isolated applications, (2) are not sensor-driven, and (3) are unable to support emerging self-driving applications that simultaneously utilize CPUs and GPUs with stringent timing requirements. On the other hand, full-system self-driving simulators (e.g., AUTOWARE, APOLLO) focus on functional simulation, but lack the ability to evaluate the self-driving software stack on various embedded platforms. To address design needs, we present Chauffeur, the first open-source end-to-end benchmark suite for self-driving vehicles with configurable representative workloads. Chauffeur is easy to configure and run, enabling researchers to evaluate different platform configurations and explore alternative instantiations of the self-driving software pipeline. Chauffeur runs on diverse emerging platforms and exploits heterogeneous onboard resources. Our initial characterization of Chauffeur on different embedded platforms – NVIDIA Jetson TX2 and Drive PX2 – enables comparative evaluation of these GPU platforms in executing an end-to-end self-driving computational pipeline to assess the end-to-end response times on these emerging embedded platforms while also creating opportunities to create application gangs for better response times. Chauffeur enables researchers to benchmark representative self-driving workloads and flexibly compose them for different self-driving scenarios to explore end-to-end tradeoffs between design constraints, power budget, real-time performance requirements, and accuracy of applications.

Users of embedded and cyber-physical systems expect dependable operation for an increasingly diverse set of applications and environments. Reactive self-diagnosis techniques either use unnecessarily conservative guardbands, or do not prevent catastrophic failures. In this letter, we utilize machine-learning techniques to design a prediction engine in order to predict failures on-device in the embedded systems. We evaluate our prediction engine’s effectiveness for predicting temperature behavior on a mobile system-on-chip and propose a realizable hardware implementation for the use-case.

Quantum computers are imminent threat to secure signal processing because they can break the contemporary public-key cryptography schemes in polynomial time. Ring learning with error (RLWE) lattice-based cryptography (LBC) is considered as the most versatile and efficient family of post-quantum cryptography (PQC). Polynomial multiplication is the most compute-intensive routine in the RLWE schemes. Convolutions and Number Theoretic Transform (NTT) are two common methods to perform the polynomial multiplication. In this paper, we explore the energy efficiency of different polynomial multipliers, NTT-based and convolution-based, on GPU and FPGA. When synthesized on a Zynq UltraScale+ FPGA, our NTT-based and convolution-based designs achieve on average 5.1x and 22.5x speedup over state-of-the-art. Our convolution-based design, on a Zynq UltraScale+ FPGA, can generate more than 2x signatures per second by CRYSTALS-Dilithium. The designed NTT-based multiplier on NVIDIA Jetson TX2 is 1.2x and 2x faster than our baseline NTT-based multiplier on FPGA for polynomial degrees of 512 and 1024, respectively. Our explorations and guidelines can help designers choose proper implementations to realize quantum-resistant signal processing.

Physiological response is an automatic reaction that triggers a physical response to a stimulus such as stress, emotion, pain, etc. Examples include changes in heart rate, respiration, perspiration, and eye pupil dilation. Electrodermal Activity (EDA), also known as Galvanic Skin Response (GSR), measures changes in perspiration by detecting the changes in electrical conductivity of skin. Previous studies have already shown that EDA is one of the leading indicators for a stimulus. However, the EDA signal itself is not trivial to analyze. To detect different stimuli in human subjects, variety of features are extracted from EDA signals such as the number of peaks, max peak amplitude, to name a few, showing the prevalence of this signal in bio-medical as well as ubiquitous and wearable computing research. In this paper, we present an open-source Python toolkit for EDA signal preprocessing and statistical and automatic feature extraction. To the best of our knowledge, this is the first effort for developing a versatile and generic tool to extract any number of automatic features from EDA signals. We evaluate our toolkit using different machine learning algorithms applied to the Wearable Stress and Affect Detection (WESAD) dataset. Our results show higher validation accuracy for a stress detection task using the the features automatically extracted by pyEDA.

Spin transfer torque magnetic RAM (STT-MRAM) technology is one of the most promising alternative for static RAM (SRAM) for implementing on-chip memories. Compared with SRAMs, STT-MRAMs benefit from higher density and near-zero leakage power, nonetheless they impose high energy consumption for reliable write operations. However, in many applications, absolute data integrity is not required; thus, acting on the current applied in the write operations may represent a novel knob for disciplined approximate computing to obtain energy saving with a minimal quality loss in applications’ outputs. This article proposes CAST, a hardware/software approach to adjust the energy/quality of write operations in STT-MRAM caches in multicore systems based on the content of requested write operations. CAST utilizes fine-grained cache-line-level actuation knobs with different levels of quality for individual write operations. This unique feature of STT-MRAMs allows to avoid interapplication actuation interference suffered by SRAMs, and makes the approach particularly suitable for systems running multiple applications with mixed accuracy sensitivity. Moreover, CAST exploits another peculiarity of STT-MRAMs represented by the asymmetry and transition-dependency of the write error rate, to further tune in a fine-grained manner the write current to achieve an additional energy saving, even in full-accurate applications. Our evaluations on workloads of full-approximate, mixed-criticality, and full-accurate applications demonstrate up to 57%, 34%, and 21% energy savings over a baseline STT-MRAM cache, respectively, with an acceptable quality of the generated outputs.

Recent advances in pervasive Internet of Things technologies and edge computing have opened new avenues for development of ubiquitous health monitoring applications. Delivering an acceptable level of usability and accuracy for these healthcare Internet of Things applications requires optimization of both system-driven and data-driven aspects, which are typically done in a disjoint manner. Although decoupled optimization of these processes yields local optima at each level, synergistic coupling of the system and data levels can lead to a holistic solution opening new opportunities for optimization. In this article, we present an edge-assisted resource manager that dynamically controls the fidelity and duration of sensing w.r.t. changes in the patient’s activity and health state, thus fine-tuning the trade-off between energy efficiency and measurement accuracy. The cornerstone of our proposed solution is an intelligent low-latency real-time controller implemented at the edge layer that detects abnormalities in the patient’s condition and accordingly adjusts the sensing parameters of a reconfigurable wireless sensor node. We assess the efficiency of our proposed system via a case study of the photoplethysmography-based medical early warning score system. Our experiments on a real full hardware-software early warning score system reveal up to 49% power savings while maintaining the accuracy of the sensory data.

Autonomous systems are able to make decisions and potentially take actions without direct human intervention, which requires some knowledge about the system and its environment as well as goal-oriented reasoning. In computer systems, one can derive such behavior from the concept of a rational agent with autonomy (“control over its own actions”), reactivity (“react to events from the environment”), proactivity (“act on its own initiative”), and sociality (“interact with other agents”) as fundamental properties [1] . Autonomous systems will undoubtedly pervade into our everyday lives, and we will find them in a variety of domains and applications including robotics, transportation, health care, communications, and entertainment to name a few. The articles in this month’s special issue cover concepts and fundamentals, architectures and techniques, and applications and case studies in the exciting area of self-awareness in autonomous systems.

Real-time physiological data collection and analysis play a central role in modern well-being applications. Personalized classifiers and detectors have been shown to outperform general classifiers in many contexts. However, building effective personalized classifiers in everyday settings - as opposed to controlled settings - necessitates the online collection of a labeled dataset by interacting with the user. This need leads to several challenges, ranging from building an effective system for the collection of the signals and labels, to developing strategies to interact with the user and building a dataset that represents the many user contexts that occur in daily life. Based on a stress detection use case, this paper (1) builds a system for the real-time collection and analysis of photoplethysmogram, acceleration, gyroscope, and gravity data from a wearable sensor, as well as self-reported stress labels based on Ecological Momentary Assessment (EMA), and (2) collects and analyzes a dataset to extract statistics of users' response to queries and the quality of the collected signals as a function of the context, here defined as the user's activity and the time of the day., Accepted to ACM GoodIT'21

Many-core systems rely on the advantages of the latest Complementary Metal Oxide Semiconductor (CMOS) technologies to increase the number of cores. However, this improvement comes at the cost of higher power dissipation, which prevents full use of the chip. To continue improving performance on future many-core systems, Resource Management (RM) becomes imperative to handle multi-objective and conflicting requirements such as power, performance, resilience, among others. In this task, RM can use both hardware (e.g., dynamic voltage and frequency scaling) and software actuators (e.g., task remapping). However, the complexity of synchronizing available actuators to follow a particular goal while avoiding actuation overlapping is a remaining challenge. This paper evaluates the power impact of each actuator and provides insights that will help engineers develop appropriate resource management heuristics to improve self-adaptable many-core systems. A state-of-the-art comparison shows that no related work provides or details the same comprehensiveness of actuation methods concerning power consumption. Our proposal is validated in a many-core system described in a true clock-cycle accurate model. Regarding hardware actuators, the results show the power profiling at the core level and detail the contribution of each hardware component. Furthermore, results of software actuators evidence that task events present a more significant power impact on the ratio of active and idle cores changes.

The typical workload of many-core systems produces peaks and valleys of resources utilization throughout the time. The power capping limits the full system utilization in a workload peak, but also creates a power slack to apply different resource management (RM) policy in a valley phase. Related works do not consider this workload behavior, by proposing RMs with fixed goals. This work proposes a hierarchical adaptive Multi-Objective Resource Management (MORM) for many-core systems under a power cap. MORM works with dynamic workloads, which presents peaks and valleys of utilization. The hierarchical approach allows clusters of processing elements (PEs) to execute applications according to different objectives simultaneously. A cluster can drive the PEs to optimize either performance or energy. MORM can dynamically shift the goals of a cluster according to the workload behavior. Comparison with a state-of-the-art RM optimized for single objective shows that MORM achieves equivalent results in a workload valley while outperforming up to 37.19–49.03% the performance in a workload peak regardless of the power cap. The comparison reveals relevant features to be considered in large many-core systems: hierarchical organization, multi-task mapping, and joint adaptability between software (remapping) and hardware (DVFS) actuation.

Spin-Torque Transfer Magnetic RAM (STT-RAM), one of the emerging nonvolatile memory (NVM) technologies explored as the replacement for SRAM memory architectures, is particularly promising due to the fast access speed, high integration density, and zero standby power consumption. Recently, hybrid deigns with SRAM and STT-RAM buffers for routers in Network-on-Chip (NoC) systems have been widely implemented to maximize the mutually complementary characteristics of different memory technologies, and leverage the efficiency of intra-router latency and system power consumption. With the realization of Processing-in-Memory enabled by STT-RAM, in this paper, we novelly offload the execution from processors to the STT-RAM based on-chip routers to improve the application performance. On top of the hybrid buffer design in routers, we further present system-level approaches, including an ILP model and polynomial-time heuristic algorithms, to fine-tune the application mapping and scheduling on NoCs, with the objectives of improving system performance-energy efficiency. Network overhead caused by flit conflict in conventional communication circumstances can be ideally avoided by computing the contended flits in intermediate routers; meanwhile, the pressure of heavy workload on processors can be relieved by transferring partial operations to routers, such that network latency and system power consumption can be significantly reduced. Experimental results demonstrate that application schedule length and system energy consumption can be reduced by 35.62, 32.87 percent on average, respectively, in extensive evaluation experiments on PARSEC benchmark applications. In particular, the achievements of application performance and energy efficiency, averagely 36.44 and 33.19 percent, for the CNN application AlexNet have verified the practicability and effectiveness of our presented approaches.

The zebrafish (Dario rerio) has proven to be an excellent animal model for biological research owing to its small size, low cost for maintenance, short generation time, amenable genetics, and optical transparency. Zebrafish have been extensively used in cardiovascular studies in which mutant lines with cardiovascular defects were introduced and analyzed. Despite the small size, technological advances have paved the way to effectively assess cardiac functions of zebrafish. Here, we present a novel art for long-term simultaneous monitoring and analysis of electrocardiogram (ECG) in multiple zebrafish with controlled environment. The system helps minimize the effect of anesthetic drug and temperature to cardiac rhythm side effects as well as save time and efforts by 40-50 fold compared with the conventional approach. We further employed the system to study the Na+ sensitivity in the development of sinus arrest in Tg(SCN5A-D1275N) fish, a study model of the sick sinus syndrome, as well as the relationship between this variant and drug administration. The novel ECG system developed in this study holds promise to greatly accelerate other cardiovascular studies and drug screening using zebrafish.

Purpose We aimed to understand the relationship between exercise and stress among socioeconomically at-risk women who participated in a home visitation service during pregnancy and postpartum. Methods A mixed-methods design was used to support and supplement quantitative data using qualitative data. Convenience sampling was used to collect data from at-risk women via questionnaires and follow-up interviews. The Perceived Stress Scale was used to assess stress. Frequency and duration of exercise were assessed based on the American College of Obstetricians and Gynecologists exercise guidelines. Regression analyses examined the association between stress and exercise controlling for covariates. Content analysis was used to understand women's stress management experiences. Results N = 114 women completed the questionnaire and a subgroup of 11 received follow-up interviews. Greater frequency of exercise was significantly associated with lower levels of stress. Approximately one-third of women reported experiencing significant stress. Talking to their husband or partner was the most used and exercise was the least used coping strategy. Many women recognized the importance of managing stress and benefits of exercise, but were hindered by barriers such as feeling tired, preventing them from exercising. Clinical implications A personalized and safe exercise program has the potential to be a low-cost stress management strategy for women during pregnancy and postpartum.

IoT applications demand higher Quality of Experience (QoE) to deliver satisfactory services to the end-users. Variable user behavior, diverse application requirements, and dynamic system constraints exacerbate the QoE delivery challenge. Situational-awareness encapsulates the constraints at the user, application, and system levels, quantifiably reflecting system dynamics. Such models can manage diversity among multiple layers of the system stack while improving QoE. In this paper, we investigate the diverse set of requirements and opportunities in edge paradigm that vary over time using health monitoring applications. Towards address this challenge, we propose a situational-awareness model that enables intelligent orchestration of IoT applications across networked and distributed hardware platforms.

Background There is a strong demand for an accurate and objective means of assessing acute pain among hospitalized patients to help clinicians provide pain medications at a proper dosage and in a timely manner. Heart rate variability (HRV) comprises changes in the time intervals between consecutive heartbeats, which can be measured through acquisition and interpretation of electrocardiography (ECG) captured from bedside monitors or wearable devices. As increased sympathetic activity affects the HRV, an index of autonomic regulation of heart rate, ultra–short-term HRV analysis can provide a reliable source of information for acute pain monitoring. In this study, widely used HRV time and frequency domain measurements are used in acute pain assessments among postoperative patients. The existing approaches have only focused on stimulated pain in healthy subjects, whereas, to the best of our knowledge, there is no work in the literature building models using real pain data and on postoperative patients. Objective The objective of our study was to develop and evaluate an automatic and adaptable pain assessment algorithm based on ECG features for assessing acute pain in postoperative patients likely experiencing mild to moderate pain. Methods The study used a prospective observational design. The sample consisted of 25 patient participants aged 18 to 65 years. In part 1 of the study, a transcutaneous electrical nerve stimulation unit was employed to obtain baseline discomfort thresholds for the patients. In part 2, a multichannel biosignal acquisition device was used as patients were engaging in non-noxious activities. At all times, pain intensity was measured using patient self-reports based on the Numerical Rating Scale. A weak supervision framework was inherited for rapid training data creation. The collected labels were then transformed from 11 intensity levels to 5 intensity levels. Prediction models were developed using 5 different machine learning methods. Mean prediction accuracy was calculated using leave-one-out cross-validation. We compared the performance of these models with the results from a previously published research study. Results Five different machine learning algorithms were applied to perform a binary classification of baseline (BL) versus 4 distinct pain levels (PL1 through PL4). The highest validation accuracy using 3 time domain HRV features from a BioVid research paper for baseline versus any other pain level was achieved by support vector machine (SVM) with 62.72% (BL vs PL4) to 84.14% (BL vs PL2). Similar results were achieved for the top 8 features based on the Gini index using the SVM method, with an accuracy ranging from 63.86% (BL vs PL4) to 84.79% (BL vs PL2). Conclusions We propose a novel pain assessment method for postoperative patients using ECG signal. Weak supervision applied for labeling and feature extraction improves the robustness of the approach. Our results show the viability of using a machine learning algorithm to accurately and objectively assess acute pain among hospitalized patients. International Registered Report Identifier (IRRID) RR2-10.2196/17783

Background Accurate, objective pain assessment is required in the health care domain and clinical settings for appropriate pain management. Automated, objective pain detection from physiological data in patients provides valuable information to hospital staff and caregivers to better manage pain, particularly for patients who are unable to self-report. Galvanic skin response (GSR) is one of the physiologic signals that refers to the changes in sweat gland activity, which can identify features of emotional states and anxiety induced by varying pain levels. This study used different statistical features extracted from GSR data collected from postoperative patients to detect their pain intensity. To the best of our knowledge, this is the first work building pain models using postoperative adult patients instead of healthy subjects. Objective The goal of this study was to present an automatic pain assessment tool using GSR signals to predict different pain intensities in noncommunicative, postoperative patients. Methods The study was designed to collect biomedical data from postoperative patients reporting moderate to high pain levels. We recruited 25 participants aged 23-89 years. First, a transcutaneous electrical nerve stimulation (TENS) unit was employed to obtain patients' baseline data. In the second part, the Empatica E4 wristband was worn by patients while they were performing low-intensity activities. Patient self-report based on the numeric rating scale (NRS) was used to record pain intensities that were correlated with objectively measured data. The labels were down-sampled from 11 pain levels to 5 different pain intensities, including the baseline. We used 2 different machine learning algorithms to construct the models. The mean decrease impurity method was used to find the top important features for pain prediction and improve the accuracy. We compared our results with a previously published research study to estimate the true performance of our models. Results Four different binary classification models were constructed using each machine learning algorithm to classify the baseline and other pain intensities (Baseline [BL] vs Pain Level [PL] 1, BL vs PL2, BL vs PL3, and BL vs PL4). Our models achieved higher accuracy for the first 3 pain models than the BioVid paper approach despite the challenges in analyzing real patient data. For BL vs PL1, BL vs PL2, and BL vs PL4, the highest prediction accuracies were achieved when using a random forest classifier (86.0, 70.0, and 61.5, respectively). For BL vs PL3, we achieved an accuracy of 72.1 using a k-nearest-neighbor classifier. Conclusions We are the first to propose and validate a pain assessment tool to predict different pain levels in real postoperative adult patients using GSR signals. We also exploited feature selection algorithms to find the top important features related to different pain intensities. International Registered Report Identifier (IRRID) RR2-10.2196/17783

Electrocardiogram (ECG) is routinely used to identify key cardiac events such as changes in ECG intervals (PR, ST, QT, etc.), as well as capture critical vital signs such as heart rate (HR) and heart rate variability (HRV). The gold standard ECG requires clinical measurement, limiting the ability to capture ECG in everyday settings. Photoplethysmography (PPG) offers an out-of-clinic alternative for non-invasive, low-cost optical capture of cardiac physiological measurement in everyday settings, and is increasingly used for health monitoring in many clinical and commercial wearable devices. Although ECG and PPG are highly correlated, PPG does not provide much information for clinical diagnosis. Recent work has applied machine learning algorithms to generate ECG signals from PPG, but requires expert domain knowledge and heavy feature crafting to achieve good accuracy. We propose P2E-WGAN: a pure end-to-end, generalizable deep learning model using a conditional Wasserstein generative adversarial network to synthesize ECG waveforms from PPG. Our generative model is capable of augmenting the training data to alleviate the data-hungry problem of machine learning methods. Our model trained in the subject independent mode can achieve the average root mean square error of 0.162, Frechet distance of 0.375, and Pearson's correlation of 0.835 on a normalized real-world dataset, demonstrating the effectiveness of our approach.

Emerging data suggest that the effects of infection with SARS-CoV-2 are far reaching extending beyond those with severe acute disease. Specifically, the presence of persistent symptoms after apparent resolution from COVID-19 have frequently been reported throughout the pandemic by individuals labeled as “long-haulers”. The purpose of this study was to assess for symptoms at days 0-10 and 61+ among subjects with PCR-confirmed SARS-CoV-2 infection. The University of California COvid Research Data Set (UC CORDS) was used to identify 1407 records that met inclusion criteria. Symptoms attributable to COVID-19 were extracted from the electronic health record. Symptoms reported over the previous year prior to COVID-19 were excluded, using nonnegative matrix factorization (NMF) followed by graph lasso to assess relationships between symptoms. A model was developed predictive for becoming a long-hauler based on symptoms. 27% reported persistent symptoms after 60 days. Women were more likely to become long-haulers, and all age groups were represented with those aged 50 ± 20 years comprising 72% of cases. Presenting symptoms included palpitations, chronic rhinitis, dysgeusia, chills, insomnia, hyperhidrosis, anxiety, sore throat, and headache among others. We identified 5 symptom clusters at day 61+: chest pain-cough, dyspnea-cough, anxiety-tachycardia, abdominal pain-nausea, and low back pain-joint pain. Long-haulers represent a very significant public health concern, and there are no guidelines to address their diagnosis and management. Additional studies are urgently needed that focus on the physical, mental, and emotional impact of long-term COVID-19 survivors who become long-haulers.

Digital Health-Enabled Community-Centered Care (D-CCC) represents a pioneering vision for the future of community-centered care. Utilizing an artificial intelligence-enabled closed-loop digital health platform designed for, and with, community health workers, D-CCC enables timely and individualized delivery of interventions by community health workers to the communities they serve. D-CCC has the potential to transform the current landscape of manual, episodic and restricted community health worker-delivered care and services into an expanded, digitally interconnected and collaborative community-centered health and social care ecosystem which centers around a digitally empowered community health workforce of the future.

Pregnancy is a unique time when many mothers gain awareness of their lifestyle and its impacts on the fetus. High-quality care during pregnancy is needed to identify possible complications early and ensure the mother’s and her unborn baby’s health and well-being. Different studies have thus far proposed maternal health monitoring systems. However, they are designed for a specific health problem or are limited to questionnaires and short-term data collection methods. Moreover, the requirements and challenges have not been evaluated in long-term studies. Maternal health necessitates a comprehensive framework enabling continuous monitoring of pregnant women. In this paper, we present an Internet-of-Things (IoT)-based system to provide ubiquitous maternal health monitoring during pregnancy and postpartum. The system consists of various data collectors to track the mother’s condition, including stress, sleep, and physical activity. We carried out the full system implementation and conducted a real human subject study on pregnant women in Southwestern Finland. We then evaluated the system’s feasibility, energy efficiency, and data reliability. Our results show that the implemented system is feasible in terms of system usage during nine months. We also indicate the smartwatch, used in our study, has acceptable energy efficiency in long-term monitoring and is able to collect reliable photoplethysmography data. Finally, we discuss the integration of the presented system with the current healthcare system.

Internet of Things (IoT) paradigm raises challenges for devising efficient strategies that offload applications to the fog or the cloud layer while ensuring the optimal response time for a service. Traditional computation offloading policies assume the response time is only dominated by the execution time. However, the response time is a function of many factors including contextual parameters and application characteristics that can change over time. For the computation offloading problem, the majority of existing literature presents efficient solutions considering a limited number of parameters (e.g., computation capacity and network bandwidth) neglecting the effect of the application characteristics and dataflow configuration. In this paper, we explore the impact of the computation offloading on total application response time in three-layer IoT systems considering more realistic parameters, e.g., application characteristics, system complexity, communication cost, and dataflow configuration. This paper also highlights the impact of a new application characteristic parameter defined as Output-Input Data Generation (OIDG) ratio and dataflow configuration on the system behavior. In addition, we present a proof-of-concept end-to-end dynamic computation offloading technique, implemented in a real hardware setup, that observes the aforementioned parameters to perform real-time decision-making.

Due to the consistent pressing quest of larger on-chip memories and caches of multicore and manycore architectures, Spin Transfer Torque Magnetic RAM (STT-MRAM or STT-RAM) has been proposed as a promising technology to replace classical SRAMs in near-future devices. Main advantages of STT-RAMs are a considerably higher transistor density and a negligible leakage power compared with SRAM technology. However, the drawback of this technology is the high probability of errors occurring especially in write operations. Such errors are asymmetric and transition-dependent, where 0 → 1 is the most critical one, and is high subjected to the amount and current (voltage) supplied to the memory during the write operation. As a consequence, STT-RAMs present an intrinsic trade-off between energy consumption vs. reliability that needs to be properly tuned w.r.t. the currently running application and its reliability requirement. This chapter proposes FlexRel, an energy-aware reliability improvement architectural scheme for STT-RAM cache memories. FlexRel considers a memory architecture provided with Error Correction Codes (ECCs) and a custom current regulator for the various cache ways and conducts a trade-off between reliability and energy consumption. FlexRel cache controller dynamically profiles the number of 0 → 1 transitions of each individual bit write operation in a cache block and based on that selects the most-suitable cache way and current level to guarantee the necessary error rate threshold (in terms of occurred write errors) while minimizing the energy consumption. We experimentally evaluated the efficiency of FlexRel against the most efficient uniform protection scheme from reliability, energy, area, and performance perspectives. Experimental simulations performed by using gem5 has demonstrated that while FlexRel satisfies the given error rate threshold, it delivers up to 13.2% energy saving. From the area footprint perspective, FlexRel delivers up to 7.9% cache ways’ area saving. Furthermore, the performance overhead of the FlexRel algorithm which changes the traffic patterns of the cache ways during the executions is 1.7%, on average.

Emerging adulthood is a period marked by tremendous growth and opportunity, but also of significant risk. It is during this phase that the majority of major disease processes have their onset and also the time during which individuals develop habits for adaptive ways of managing stress and help-seeking when necessary. Recent work has demonstrated the feasibility of estimating stress levels through monitoring of physiological signs of sympathetic nervous system activity (e.g., heart rate, heart rate variability, respiration rate, galvanic skin response, etc.) using wearable devices. However, this method of objective monitoring only captures changes in internal states but not the contextual factors – such as mental activity and social interactions – that are critical for diagnosis, treatment and prevention of mental health problems that may follow from the long-term effects of stress. Thus, there is a fundamental need to capture higher-level life events and contextual information to enable root cause analysis for treatment and prevention. The proposed case study is part of a larger pilot study in which we intensely follow a small sample of college students over the course of 9-months during an historic and tumultuous year in which COVID-19 disrupted daily living to understand contextual factors relevant to their mental health while capturing mood, sleep, physical activity, and physiology. In this case study, we showcase a single participant as support for the feasibility and potential of this approach for understanding more personalized models for mental health and treatment.

Noninvasive, and continuous physiological sensing enabled by novel wearable sensors is generating unprecedented diagnostic insights in many medical practices. However, the limited battery capacity of these wearable sensors poses a critical challenge in extending device lifetime in order to prevent omission of informative events. In this work, we exploit the inherent sparsity of physiological signals to intelligently enable selective transmission of these signals and thereby improve the energy efficiency of wearable sensors. We propose STINT, a selective transmission framework that generates a sparse representation of the raw signal based on domain-specific knowledge, and which can be integrated into a wide range of resource-constrained embedded sensing IoT platforms. STINT employs a neural network (NN) for selective transmission: the NN identifies, and transmits only the informative parts of the raw signal, thereby achieving low power operation. We validate STINT and establish its efficacy in the domain of IoT for energy-efficient physiological monitoring, by testing our framework on EcoBP - a novel miniaturized, and wireless continuous blood pressure sensor. Early experimental results on the EcoBP device demonstrate that the STINT-enabled EcoBP sensor outperforms the native platform by 14% of sensor energy consumption, with room for additional energy savings via complementary bluetooth and wireless optimizations.

Complex Internet of Things (IoT) applications such as Healthcare IoT include a variety of compute, data, and communication kernel intensities and have diverse sensitivities of QoS requirements including latency, throughput, availability, accuracy, etc. Ensuring QoS requirements for the applications requires a comprehensive tool to perform efficient full-stack analysis. Per our observation, the literature lacks a simulator capable of supporting a full-stack communication-computation co-simulation of an IoT system. Furthermore, IoT system behavior can dramatically change during run-time due to variation in status and context. Therefore, such a system must be dynamically controlled over time. In this paper, for the first time, we propose a full-stack framework to co-simulate communication and computation aspects of an IoT system in a dynamic scenario. We integrate a Transmission Control Protocol (TCP) latency model with the iFogSim simulator. We conduct a health-care IoT-based case study to evaluate the framework. The framework is open-sourced and available on GitHub in the following repository: https://github.com/HealthSciTech/Dynamic iFogSim.

Background Assessment of pain is critical to its optimal treatment. There is a high demand for accurate objective pain assessment for effectively optimizing pain management interventions. However, pain is a multivalent, dynamic, and ambiguous phenomenon that is difficult to quantify, particularly when the patient’s ability to communicate is limited. The criterion standard of pain intensity assessment is self-reporting. However, this unidimensional model is disparaged for its oversimplification and limited applicability in several vulnerable patient populations. Researchers have attempted to develop objective pain assessment tools through analysis of physiological pain indicators, such as electrocardiography, electromyography, photoplethysmography, and electrodermal activity. However, pain assessment by using only these signals can be unreliable, as various other factors alter these vital signs and the adaptation of vital signs to pain stimulation varies from person to person. Objective pain assessment using behavioral signs such as facial expressions has recently gained attention. Objective Our objective is to further the development and research of a pain assessment tool for use with patients who are likely experiencing mild to moderate pain. We will collect observational data through wearable technologies, measuring facial electromyography, electrocardiography, photoplethysmography, and electrodermal activity. Methods This protocol focuses on the second phase of a larger study of multimodal signal acquisition through facial muscle electrical activity, cardiac electrical activity, and electrodermal activity as indicators of pain and for building predictive models. We used state-of-the-art standard sensors to measure bioelectrical electromyographic signals and changes in heart rate, respiratory rate, and oxygen saturation. Based on the results, we further developed the pain assessment tool and reconstituted it with modern wearable sensors, devices, and algorithms. In this second phase, we will test the smart pain assessment tool in communicative patients after elective surgery in the recovery room. Results Our human research protections application for institutional review board review was approved for this part of the study. We expect to have the pain assessment tool developed and available for further research in early 2021. Preliminary results will be ready for publication during fall 2020. Conclusions This study will help to further the development of and research on an objective pain assessment tool for monitoring patients likely experiencing mild to moderate pain. International Registered Report Identifier (IRRID) DERR1-10.2196/17783

Traumatic Brain Injury (TBI) is highly prevalent, affecting ~1% of the U.S. population, with lifetime economic costs estimated to be over $75 billion. In the U.S., there are about 50,000 deaths annually related to TBI, and many others are permanently disabled. However, it is currently unknown which individuals will develop persistent disability following TBI and what brain mechanisms underlie these distinct populations. The pathophysiologic causes for those are most likely multifactorial. Electroencephalogram (EEG) has been used as a promising quantitative measure for TBI diagnosis and prognosis. The recent rise of advanced data science approaches such as machine learning and deep learning holds promise to further analyze EEG data, looking for EEG biomarkers of neurological disease, including TBI. In this work, we investigated various machine learning approaches on our unique 24-hour recording dataset of a mouse TBI model, in order to look for an optimal scheme in classification of TBI and control subjects. The epoch lengths were 1 and 2 minutes. The results were promising with accuracy of ~80–90% when appropriate features and parameters were used using a small number of subjects (5 shams and 4 TBIs). We are thus confident that, with more data and studies, we would be able to detect TBI accurately, not only via long-term recordings but also in practical scenarios, with EEG data obtained from simple wearables in the daily life.

Quantum computers promise to solve hard mathematical problems such as integer factorization and discrete logarithms in polynomial time, making standardized public-key cryptosystems insecure. Lattice-Based Cryptography (LBC) is a promising post-quantum public key cryptographic protocol that could replace standardized public key cryptography, thanks to the inherent post-quantum resistant properties, efficiency, and versatility. A key mathematical tool in LBC is the Number Theoretic Transform (NTT), a common method to compute polynomial multiplication. It is the most compute-intensive routine and requires acceleration for practical deployment of LBC protocols. In this paper, we propose CryptoPIM, a high-throughput Processing In-Memory (PIM) accelerator for NTT-based polynomial multiplier with the support of polynomials with degrees up to 32k. Compared to the fastest FPGA implementation of an NTT-based multiplier, CryptoPIM achieves on average 31x throughput improvement with the same energy and only 28% performance reduction, thereby showing promise for practical deployment of LBC.

The invasive method of fetal electrocardiogram (fECG) monitoring is widely used with electrodes directly attached to the fetal scalp. There are potential risks such as infection and, thus, it is usually carried out during labor in rare cases. Recent advances in electronics and technologies have enabled fECG monitoring from the early stages of pregnancy through fECG extraction from the combined fetal/maternal ECG (f/mECG) signal recorded non-invasively in the abdominal area of the mother. However, cumbersome algorithms that require the reference maternal ECG as well as heavy feature crafting makes out-of-clinics fECG monitoring in daily life not yet feasible. To address these challenges, we proposed a pure end-to-end deep learning model to detect fetal QRS complexes (i.e., the main spikes observed on a fetal ECG waveform). Additionally, the model has the residual network (ResNet) architecture that adopts the novel 1-D octave convolution (OctConv) for learning multiple temporal frequency features, which in turn reduce memory and computational cost. Importantly, the model is capable of highlighting the contribution of regions that are more prominent for the detection. To evaluate our approach, data from the PhysioNet 2013 Challenge with labeled QRS complex annotations were used in the original form, and the data were then modified with Gaussian and motion noise, mimicking real-world scenarios. The model can achieve a F1 score of 91.1% while being able to save more than 50% computing cost with less than 2% performance degradation, demonstrating the effectiveness of our method.

Quantum computers threaten to break public-key cryptography schemes such as DSA and ECDSA in polynomial time, which poses an imminent threat to secure signal processing. Ring learning with error (RLWE) lattice-based cryptography (LBC) is one of the most promising families of post-quantum cryptography (PQC) schemes in terms of efficiency and versatility. Two conventional methods to compute polynomial multiplication, the most compute-intensive routine in the RLWE schemes, are convolutions and Number Theoretic Transform (NTT).In this work, we explore the energy efficiency of polynomial multiplier using systolic architecture for the first time. As an early exploration, we design two high-throughput systolic array polynomial multipliers, including NTT-based and convolution-based, and compare them to our low-cost sequential (non-systolic) NTT-based multiplier. Our sequential NTT-based multiplier achieves 3x speedup over the state-of-the-art FGPA implementation of the polynomial multiplier in the NewHope-Simple key exchange mechanism on a low-cost Artix7 FPGA. When synthesized on a Zynq UltraScale+ FPGA, the NTT-based systolic and convolution-based systolic designs achieve on average 1.7x and 7.5x speedup over our sequential NTT-based multiplier respectively, which can lead to generating over 2x more signatures per second by CRYSTALS-Dilithium, a PQC digital signature scheme. These explorations help designers select the right PQC implementations for making future signal processing applications quantum-resistant.

The advent of quantum computing threatens to break many classical cryptographic schemes, leading to innovations in public key cryptography that focus on post-quantum cryptography primitives and protocols resistant to quantum computing threats. Lattice-based cryptography is a promising post-quantum cryptography family, both in terms of foundational properties as well as in its application to both traditional and emerging security problems such as encryption, digital signature, key exchange, and homomorphic encryption. While such techniques provide guarantees, in theory, their realization on contemporary computing platforms requires careful design choices and tradeoffs to manage both the diversity of computing platforms (e.g., high-performance to resource constrained), as well as the agility for deployment in the face of emerging and changing standards. In this work, we survey trends in lattice-based cryptographic schemes, some recent fundamental proposals for the use of lattices in computer security, challenges for their implementation in software and hardware, and emerging needs for their adoption. The survey means to be informative about the math to allow the reader to focus on the mechanics of the computation ultimately needed for mapping schemes on existing hardware or synthesizing part or all of a scheme on special-purpose har dware.

Photoplethysmography (PPG) as a non-invasive and low-cost technique plays a significant role in wearable Internet-of-Things based health monitoring systems, enabling continuous health and well-being data collection. As PPG monitoring is relatively simple, non-invasive, and convenient, it is widely used in a variety of wearable devices (e.g., smart bands, smart rings, smartphones) to acquire different vital signs such as heart rate and pulse rate variability. However, the accuracy of such vital signs highly depends on the quality of the signal and the presence of artifacts generated by other resources such as motion. This unreliable performance is unacceptable in health monitoring systems. To tackle this issue, different studies have proposed motion artifacts reduction and signal quality assessment methods. However, they merely focus on improvements in the results and signal quality. Therefore, they are unable to alleviate erroneous decision making due to invalid vital signs extracted from the unreliable PPG signals. In this paper, we propose a novel PPG quality assessment approach for IoT-based health monitoring systems, by which the reliability of the vital signs extracted from PPG quality is determined. Therefore, unreliable data can be discarded to prevent inaccurate decision making and false alarms. Exploiting a Convolutional Neural Networks (CNN) approach, a hypothesis function is created by comparing heart rate in the PPG with corresponding heart rate values extracted from ECG signal. We implement a proof-of-concept IoT-based system to evaluate the accuracy of the proposed approach.

Sleep is a composite of physiological and behavioral processes that undergo substantial changes during and after pregnancy. These changes might lead to sleep disorders and adverse pregnancy outcomes. Several studies have investigated this issue; however, they were restricted to subjective measurements or short-term actigraphy methods. This is insufficient for a longitudinal maternal sleep quality evaluation. A longitudinal study: 1) requires a long-term data collection approach to acquire data from everyday routines of mothers and 2) demands a sleep quality assessment method exploiting a large volume of multivariate data to assess sleep adaptations and overall sleep quality. In this paper, we present an Internet-of-Things-based long-term monitoring system to perform an objective sleep quality assessment. We conduct longitudinal monitoring, where 20 pregnant mothers are remotely monitored for six months of pregnancy and one month postpartum. To evaluate sleep quality adaptations, we: 1) extract several sleep attributes and study their variations during the monitoring and 2) propose a semi-supervised machine learning approach to create a personalized sleep model for each subject. The model provides an abnormality score, which allows an explicit representation of the sleep quality in a clinical routine, reflecting possible sleep quality degradation with respect to her own data. Sleep data of 13 participants (out of 20) are included in our analysis, as their data are adequate for the study, including 172.15±33.29 days of sleep data per person. Our fine-grained objective measurements indicate that the sleep duration and sleep efficiency are deteriorated in pregnancy and notably in postpartum. In comparison to the mid of the second trimester, the sleep model indicates the increase of sleep abnormality at the end of pregnancy (2.87 times) and postpartum (5.62 times). We also show that the model enables individualized and effective care for sleep disturbances during pregnancy, as compared to a baseline method.

This paper explores the challenges of HCI work within multidisciplinary research projects across health sciences, social sciences, and engineering, through discussion of a specific case study research project focused on supporting under-resourced pregnant women. Capturing the perspectives of community-based health care workers (N=14) using wearable technology for servicing pregnant women provided insight into considerations for technology for this specific population. Methods of inquiry included design and development of a prototype wearable and mobile system as well as self-report via a survey detailing their experience with the system and how it can possibly benefit their duties of monitoring their pregnant patients. The process outcomes of this work, however, provide broader insight into the challenges of conducting this kind of interdisciplinary work that remain despite decades of effort and financial investment to support interdisciplinary research, particularly in health informatics and interactive technologies for health.

Detecting QRS complexes or R-peaks from the electrocardiogram (ECG) is the basis for heart rate determination and heart rate variability analysis. Over the years, multiple different methods have been proposed as solutions to this problem. Vast majority of the proposed methods are traditional rule based algorithms that are vulnerable to noise. We propose a new R-peak detection method that is based on the Long Short-Term Memory (LSTM) network. LSTM networks excel at temporal modelling tasks that include long-term dependencies, making it suitable for ECG analysis. Additionally, we propose data generator for creating noisy ECG data that is used to train the robust R-peak detector. Our initial testing shows that the proposed method outperforms traditional algorithms while the greatest competitive edge is achieved with the noisy ECG signals.

We present PyCARL, a PyNN-based common Python programming interface for hardware-software co-simulation of spiking neural network (SNN). Through PyCARL, we make the following two key contributions. First, we provide an interface of PyNN to CARLsim, a computationally-efficient, GPU-accelerated and biophysically-detailed SNN simulator. PyCARL facilitates joint development of machine learning models and code sharing between CARLsim and PyNN users, promoting an integrated and larger neuromorphic community. Second, we integrate cycle-accurate models of state-of-the-art neuromorphic hardware such as TrueNorth, Loihi, and DynapSE in PyCARL, to accurately model hardware latencies that delay spikes between communicating neurons and degrade performance. PyCARL allows users to analyze and optimize the performance difference between software-only simulation and hardware-software co-simulation of their machine learning models. We show that system designers can also use PyCARL to perform design-space exploration early in the product development stage, facilitating faster time-to-deployment of neuromorphic products. We evaluate the memory usage and simulation time of PyCARL using functionality tests, synthetic SNNs, and realistic applications. Our results demonstrate that for large SNNs, PyCARL does not lead to any significant overhead compared to CARLsim. We also use PyCARL to analyze these SNNs for a state-of-the-art neuromorphic hardware and demonstrate a significant performance deviation from software-only simulations. PyCARL allows to evaluate and minimize such differences early during model development., 10 pages, 25 figures. Accepted for publication at International Joint Conference on Neural Networks (IJCNN) 2020

MPSoCs increasingly depend on adaptive resource management strategies at runtime for efficient utilization of resources when executing complex application workloads. In particular, conflicting demands for adequate computation performance and power-/energy-efficiency constraints make desired application goals hard to achieve. We present a hierarchical, cross-layer hardware/software resource manager capable of adapting to changing workloads and system dynamics with zero initial knowledge. The manager uses rule-based reinforcement learning classifier tables (LCTs) with an archive-based backup policy as leaf controllers. The LCTs directly manipulate and enforce MPSoC building block operation parameters in order to explore and optimize potentially conflicting system requirements (e.g., meeting a performance target while staying within the power constraint). A supervisor translates system requirements and application goals into per-LCT objective functions (e.g., core instructions-per-second (IPS). Thus, the supervisor manages the possibly emergent behavior of the low-level LCT controllers in response to 1) switching between operation strategies (e.g., maximize performance vs. minimize power; and 2) changing application requirements. This hierarchical manager leverages the dual benefits of a software supervisor (enabling flexibility), together with hardware learners (allowing quick and efficient optimization). Experiments on an FPGA prototype confirmed the ability of our approach to identify optimized MPSoC operation parameters at runtime while strictly obeying given power constraints.

Dark silicon is the phenomenon that a fraction of many-core chip has to be turned off or run in a low-power state in order to maintain the safe chip temperature. System-level thermal management techniques normally map application on non-adjacent cores, while communication efficiency among these cores will be oppositely affected over conventional network-on-chip (NoC). Recently, SMART NoC architecture is proposed, enabling single-cycle multi-hop bypass channels to be built between distant cores at runtime, to reduce communication latency. However, communication efficiency of SMART NoC will be diminished by communication contention, which will in turn decrease system performance. In this paper, we first propose an Integer-Linear Programming (ILP) model to properly address communication problem, which generates the optimal solutions with the consideration of inter-processor communication. We further present a novel heuristic algorithm for task mapping in dark silicon many-core systems, called TopoMap, on top of SMART architecture, which can effectively solve communication contention problem in polynomial time. With fine-grained consideration of chip thermal reliability and inter-processor communication, presented approaches are able to control the reconfigurability of NoC communication topology in task mapping and scheduling. Thermal-safe system is guaranteed by physically decentralized active cores, and communication overhead is reduced by the minimized communication contention and maximized bypass routing. Performance evaluation on PARSEC shows the applicability and effectiveness of the proposed techniques, which achieve on average 42.5 and 32.4 percent improvement in communication and application performance, and 32.3 percent reduction in system energy consumption, compared with state-of-the-art techniques. TopoMap only introduces 1.8 percent performance difference compared to ILP model and is more scalable to large-size NoCs. Accepted version

Power capping are increasingly being deployed in modern processors to meet performance/power requirements of new workloads. These computing systems are limited in their power dissipation, demanding a dependable power management scheme to guarantee the system’s efficiency and dependability. Although several ad-hoc and heuristic power management approaches can be found in the literature, their main shortcoming is the lack of formal guarantees to ensure dependability of the processors. Control-theoretic approaches promise flexibility and robustness for DVFS strategies. However, the creation of a responsive yet stable controller requires the often neglected tasks of proper system identification and performance analysis for target applications. This paper presents dependability evaluation of Single-Input Single-Output (SISO) controllers for power capping on single-core as well as multi-core processor architectures. We evaluate responsiveness of different class of applications to computer system control inputs (i.e., DVFS). We illustrate the feasibility of SISO controllers for power capping using the Sniper simulator running PARSEC, SPLASH2 and a set of custom microbenchmarks. Based on our observations, we provide guidelines for developing stable and robust SISO controllers for power capping, show the scenarios where simple classic SISO controllers might not be effective, and identify early symptoms that may result in instability for power capping controllers.

Modern mobile heterogeneous platforms have GPUs integrated with multicore processors to enable execution of high-end graphics-intensive games. However, these gaming applications consume significant power due to heavy utilization of CPU---GPU resources, which drains battery resources that are critical for mobile devices. While dynamic voltage and frequency scaling (DVFS) techniques have been exploited previously for dynamic power management, contemporary techniques do not fully exploit the memory access footprint for graphics-intensive gaming applications, missing opportunities for energy efficiency. In this paper, we present MEMCOP, a memory-aware cooperative CPU---GPU DVFS governor that considers both the memory access footprint as well as the CPU/GPU frequency to improve energy efficiency of high-end mobile game workloads. Our experimental results on real games and synthetic game workloads show that our MEMCOP game governor achieves on average 18 and 9% improvement of energy efficiency with minor degradation of performance compared to default governors and state-of-the-art game governors.

Heart-rate estimation is a fundamental feature of modern wearable devices. In this paper we propose a machine intelligent approach for heart-rate estimation from electrocardiogram (ECG) data collected using wearable devices. The novelty of our approach lies in (1) encoding spatio-temporal properties of ECG signals directly into spike train and using this to excite recurrently connected spiking neurons in a Liquid State Machine computation model; (2) a novel learning algorithm; and (3) an intelligently designed unsupervised readout based on Fuzzy c-Means clustering of spike responses from a subset of neurons (Liquid states), selected using particle swarm optimization. Our approach differs from existing works by learning directly from ECG signals (allowing personalization), without requiring costly data annotations. Additionally, our approach can be easily implemented on state-of-the-art spiking-based neuromorphic systems, offering high accuracy, yet significantly low energy footprint, leading to an extended battery life of wearable devices. We validated our approach with CARLsim, a GPU accelerated spiking neural network simulator modeling Izhikevich spiking neurons with Spike Timing Dependent Plasticity (STDP) and homeostatic scaling. A range of subjects are considered from in-house clinical trials and public ECG databases. Results show high accuracy and low energy footprint in heart-rate estimation across subjects with and without cardiac irregularities, signifying the strong potential of this approach to be integrated in future wearable devices., Comment: 51 pages, 12 figures, 6 tables, 95 references. Under submission at Elsevier Neural Networks

Traditional approaches for managing software-programmable memories (SPMs) do not support sharing of distributed on-chip memory resources and, consequently, miss the opportunity to better utilize those memory resources. Managing on-chip memory resources in many-core embedded systems with distributed SPMs requires runtime support to share memory resources between various threads with different memory demands running concurrently. Runtime SPM managers cannot rely on prior knowledge about the dynamically changing mix of threads that will execute and therefore should be designed in a way that enables SPM allocations for any unpredictable mix of threads contending for on-chip memory space. This article proposes ShaVe-ICE , an operating-system-level solution, along with hardware support, to virtualize and ultimately share SPM resources across a many-core embedded system to reduce the average memory latency. We present a number of simple allocation policies to improve performance and energy. Experimental results show that sharing SPMs could reduce the average execution time of the workload up to 19.5% and reduce the dynamic energy consumed in the memory subsystem up to 14%.

Background The physical and emotional well-being of women is critical for healthy pregnancy and birth outcomes. The Two Happy Hearts intervention is a personalized mind-body program coached by community health workers that includes monitoring and reflecting on personal health, as well as practicing stress management strategies such as mindful breathing and movement. Objective The aims of this study are to (1) test the daily use of a wearable device to objectively measure physical and emotional well-being along with subjective assessments during pregnancy, and (2) explore the user’s engagement with the Two Happy Hearts intervention prototype, as well as understand their experiences with various intervention components. Methods A case study with a mixed design was used. We recruited a 29-year-old woman at 33 weeks of gestation with a singleton pregnancy. She had no medical complications or physical restrictions, and she was enrolled in the Medi-Cal public health insurance plan. The participant engaged in the Two Happy Hearts intervention prototype from her third trimester until delivery. The Oura smart ring was used to continuously monitor objective physical and emotional states, such as resting heart rate, resting heart rate variability, sleep, and physical activity. In addition, the participant self-reported her physical and emotional health using the Two Happy Hearts mobile app–based 24-hour recall surveys (sleep quality and level of physical activity) and ecological momentary assessment (positive and negative emotions), as well as the Perceived Stress Scale, Center for Epidemiologic Studies Depression Scale, and State-Trait Anxiety Inventory. Engagement with the Two Happy Hearts intervention was recorded via both the smart ring and phone app, and user experiences were collected via Research Electronic Data Capture satisfaction surveys. Objective data from the Oura ring and subjective data on physical and emotional health were described. Regression plots and Pearson correlations between the objective and subjective data were presented, and content analysis was performed for the qualitative data. Results Decreased resting heart rate was significantly correlated with increased heart rate variability (r=–0.92, P Conclusions The Two Happy Hearts intervention prototype shows promise for potential use by underserved pregnant women.

Mobile platforms are increasingly using Heterogeneous Multiprocessor Systems-on-Chip (HMPSoCs) with differentiated processing cores and GPUs to achieve high performance for graphics-intensive applications such as mobile games. Traditionally, separate CPU and GPU governors are deployed in order to achieve energy efficiency through Dynamic Voltage Frequency Scaling (DVFS) but miss opportunities for further energy savings through coordinated system-level application of DVFS. We present a cooperative CPU-GPU DVFS strategy (called Co-Cap) that orchestrates energy-efficient CPU and GPU DVFS through synergistic CPU and GPU frequency capping to avoid frequency overprovisioning while maintaining desired performance. Unlike traditional approaches that target a narrow set of mobile games, our Co-Cap approach is applicable across a wide range of microbenchmarks and mobile games. Our methodology employs a systematic training phase using fine-grained refinement steps with evaluations of frequency capping tables followed by a deployment phase, allowing deployment across a wide range of microbenchmarks and mobile games with varying graphics workloads. Our experimental results across multiple sets of over 200 microbenchmarks and 40 mobile games show that Co-Cap improves energy per frame by on average 8.9% (up to 18.3%) and 7.8% (up to 27.6%) (16.6% and 15.7% in CPU-dominant applications) and achieves minimal frames-per-second (FPS) loss by 0.9% and 0.85% (1.3% and 1.5% in CPU-dominant applications) on average in training and deployment sets, respectively, compared to the default CPU and GPU governors, with negligible overhead in execution time and power consumption on the ODROID-XU3 platform.

This letter proposes a system architecture for a scalable software-assisted memory (SAM) hierarchy for emerging manycore embedded systems. Our SAM hierarchy overcomes the coherence overhead and inflexibility of purely hardware-managed memory hierarchies in adapting to variable workloads. Our preliminary results show opportunities for energy saving and performance improvement through: 1) a hybrid software-programmable memory (SPM)/cache local memory adaptable to the application’s memory characteristics; 2) SPM-based management of shared data; and 3) virtualizing and sharing the on-chip memory space between concurrently running applications. Primary experimental results show opportunities to reduce the execution time and the memory hierarchy energy consumption by up to 23% and 7%, respectively, depending on the workload.

The Internet of Things (IoT) paradigm holds significant promises for remote health monitoring systems. Due to their life- or mission-critical nature, these systems need to provide a high level of availability and accuracy. On the one hand, centralized cloud-based IoT systems lack reliability, punctuality and availability (e.g., in case of slow or unreliable Internet connection), and on the other hand, fully outsourcing data analytics to the edge of the network can result in diminished level of accuracy and adaptability due to the limited computational capacity in edge nodes. In this paper, we tackle these issues by proposing a hierarchical computing architecture, HiCH, for IoT-based health monitoring systems. The core components of the proposed system are 1) a novel computing architecture suitable for hierarchical partitioning and execution of machine learning based data analytics, 2) a closed-loop management technique capable of autonomous system adjustments with respect to patient’s condition. HiCH benefits from the features offered by both fog and cloud computing and introduces a tailored management methodology for healthcare IoT systems. We demonstrate the efficacy of HiCH via a comprehensive performance assessment and evaluation on a continuous remote health monitoring case study focusing on arrhythmia detection for patients suffering from CardioVascular Diseases (CVDs).

Due to the difficulties and complications in the quantitative assessment of traumatic brain injury (TBI) and its increasing relevance in today&rsquo, s world, robust detection of TBI has become more significant than ever. In this work, we investigate several machine learning approaches to assess their performance in classifying electroencephalogram (EEG) data of TBI in a mouse model. Algorithms such as decision trees (DT), random forest (RF), neural network (NN), support vector machine (SVM), K-nearest neighbors (KNN) and convolutional neural network (CNN) were analyzed based on their performance to classify mild TBI (mTBI) data from those of the control group in wake stages for different epoch lengths. Average power in different frequency sub-bands and alpha:theta power ratio in EEG were used as input features for machine learning approaches. Results in this mouse model were promising, suggesting similar approaches may be applicable to detect TBI in humans in practical scenarios.

In this work, we propose methods to design flexible and energy-efficient hardware accelerators for ring learning with error (RLWE) lattice-based cryptographic protocols, such as key agreement and digital signature. We apply the proposed methods to design the first programmable DMA-based family of accelerators for the Number Theoretic Transform (NTT), a commonly used kernel inside variants of RLWE protocols NewHope and Kyber. We validate our methods by integrating the accelerators into an HLS-based System on Chip (SoC) simulator. Experiments confirm the suitability of the flexible DMA-based accelerators for their use as part of lattice-based schemes. Our proposed designs are capable of executing new variants of lattice-based schemes with superior energy efficiency compared to executing the scheme entirely on the main processor, but without modifying the hardware acceleration platform. Performance improvements are up to 2x, energy consumption improves up to 1.9x, and energy-delay product (EDP) improves up to 3.9x. Together with such improved energy efficiency and performance, the flexibility inherent in our accelerators provides insights for, while reducing the risk of early adoption of lattice-based PQC cryptographic protocols in hardware products.

Neuromorphic hardware with non-volatile memory (NVM) can implement machine learning workload in an energy-efficient manner. Unfortunately, certain NVMs such as phase change memory (PCM) require high voltages for correct operation. These voltages are supplied from an on-chip charge pump. If the charge pump is activated too frequently, its internal CMOS devices do not recover from stress, accelerating their aging and leading to negative bias temperature instability (NBTI) generated defects. Forcefully discharging the stressed charge pump can lower the aging rate of its CMOS devices, but makes the neuromorphic hardware unavailable to perform computations while its charge pump is being discharged. This negatively impacts performance such as latency and accuracy of the machine learning workload being executed. In this paper, we propose a novel framework to exploit workload-specific performance and lifetime trade-offs in neuromorphic computing. Our framework first extracts the precise times at which a charge pump in the hardware is activated to support neural computations within a workload. This timing information is then used with a characterized NBTI reliability model to estimate the charge pump's aging during the workload execution. We use our framework to evaluate workload-specific performance and reliability impacts of using 1) different SNN mapping strategies and 2) different charge pump discharge strategies. We show that our framework can be used by system designers to explore performance and reliability trade-offs early in the design of neuromorphic hardware such that appropriate reliability-oriented design margins can be set., 4 pages, 5 figures, 13 references, accepted for publication at IEEE Computer Architecture Letters