DHDina Hussein

Dina Hussein

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dina Hussein has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Trading-Off Performance and Sustainability in Internet of Things: An Uncertainty-Aware Hierarchical Energy Management Approach

    by Dina Hussein, Chibuike Ugwu, Ganapati Bhat, Janardhan Doppa

    Internet of things (IoT) devices have been heralded as a key technology to enable several high-impact applications, such as healthcare, remote environmental monitoring, and digital agriculture. However, they suffer from energy sustainability challenges due to small form-factor and batteries. Recent research has proposed to integrate energy harvesting (EH) technologies into IoT devices. However, ambient sources are highly stochastic in nature, which introduces new challenges in IoT energy management (EM) since the decisions must account for the associated uncertainty. To this end, this article presents a multi-target conformal prediction algorithm to provide provably correct uncertainty estimation of future energy prediction for multiple future time steps. Prediction of energy alone is not sufficient since we must use the predictions along with uncertainty estimates in an energy management algorithm to make energy consumption decisions. A common approach in IoT devices is to follow energy-neutral operation (ENO), whereby the energy consumed in a given period is equal to the harvested energy. However, this may lead to low performance in cases where the energy harvest is insufficient. To resolve this, we propose to design a suite of policies that can tradeoff performance and energy sustainability. Moreover, the proposed approach includes a charging management policy that aims to introduce additional energy into the system when the energy harvest is low to maintain system performance. Evaluations with two real-world datasets show that the proposed conformal prediction algorithm achieves the desired coverage level of 90% for all users. The energy management policies achieve performance that is within 10% of an optimal Oracle that has the knowledge of future energy harvest. Moreover, evaluation of the charging management policy shows that it provides additional energy only when EH values are low. Finally, measurements on an IoT device show that the proposed algorithms are light-weight and consume less than 10 mJ per decision.

  • Open Access

    Sustainable Wearables for Health Applications and Beyond via Uncertainty-Aware Energy Management

    by Dina Hussein, Chibuike E. Ugwu, Ganapati Bhat, Janardhan Rao Doppa

    Achieving good health and well-being through lower mortality rates of non-communicable diseases and early warning of health risks are key goals of United Nations (UN). Wearable internet of things (IoT) are one of the most promising technology to achieve these goals through their ubiquitous monitoring of key health indicators and in-situ data processing. However, small form-factor of wearable devices constrains the battery capacity, thus requiring frequent recharging or battery replacements, which lowers their adoption rate and benefits. Augmentation of battery energy by scavenging ambient sources, such as light, is a promising solution to improve operating lifetime of IoT devices. However, ambient energy sources are highly uncertain, making energy management (EM) challenging. To handle these challenges, this paper presents a novel uncertainty-aware EM approach. First, we develop a conformal prediction-based method for future energy harvest (EH) that provides small uncertainty regions with provable coverage guarantees (true output vector is within the region). The EH uncertainty regions are then leveraged in an EM algorithm that uses overhead-aware sampling to evaluate the quality of multiple decisions with varying EH before making a decision using a lightweight machine learning model. Experiments on two diverse real-world datasets with 10 users show that conformal prediction achieves more than 90% coverage with tight prediction intervals; and the EM algorithm produces decisions that are, on average, within 2 Joules of an optimal Oracle.


  • Open Access

    Sensor-Aware Data Imputation for Time-Series Machine Learning on Low-Power Wearable Devices

    by Dina Hussein, Taha Belkhouja, Ganapati Bhat, Jana Doppa

    Wearable devices that have low-power sensors, processors, and communication capabilities are gaining wide adoption in several health applications. The machine learning algorithms on these devices assume that data from all sensors are available during runtime. However, data from one or more sensors may be unavailable due to energy or communication challenges. This loss of sensor data can result in accuracy degradation of the application. Prior approaches to handle missing data, such as generative models or training multiple classifiers for each combination of missing sensors are not suitable for low-energy wearable devices due to their high overhead at runtime. In contrast to prior approaches, we present an energy-efficient approach, referred to as Sensor-Aware iMputation (SAM), to accurately impute missing data at runtime and recover application accuracy. SAM first uses unsupervised clustering to obtain clusters of similar sensor data patterns. Next, it learns inter-relationship between clusters to obtain imputation patterns for each combination of clusters using a principled sensor-aware search algorithm. Using sensor data for clustering before choosing imputation patterns ensures that the imputation is aware of sensor data observations. Experiments on seven diverse wearable sensor-based time-series datasets demonstrate that SAM is able to maintain accuracy within 5% of the baseline with no missing data when one sensor is missing. We also compare SAM against generative adversarial imputation networks (GAIN), transformers, and k-nearest neighbor methods. Results show that SAM outperforms all three approaches on average by more than 25% when two sensors are missing with negligible overhead compared to the baseline.


  • EMI: Energy Management Meets Imputation in Wearable IoT Devices

    by Dina Hussein, Nuzhat Yamin, Ganapati Bhat

    Wearable and Internet of Things (IoT) devices are becoming popular in several applications, such as health monitoring, wide area sensing, and digital agriculture. These devices are energy-constrained due to limited battery capacities. As such, IoT devices harvest energy from the environment and manage it to prolong operation of the system. Stochastic nature of ambient energy, coupled with small battery sizes may lead to insufficient energy for obtaining data from all sensors. As a result, sensors either have to be duty cycled or subsampled to meet the energy budget. However, machine learning (ML) models for these applications are typically trained with the assumption that data from all sensors are available, leading to loss in accuracy. To overcome this, we propose a novel approach that combines data imputation with energy management (EM). Data imputation aims to substitute missing data with appropriate values so that complete sensor data are available for application processing, while EM makes energy budget decisions on the devices. We use the energy budget to obtain complete data from as many sensors as possible and turn off other sensors instead of duty cycling all sensors. Then, we use a low-overhead imputation technique for unavailable sensors and use them in ML models. Evaluations with six diverse datasets show that the proposed EM with imputation approach achieves 25%–55% higher accuracy when compared to duty cycling or subsampling without using additional energy.


  • Open Access

    Energy-Efficient Missing Data Imputation in Wearable Health Applications: A Classifier-aware Statistical Approach

    by Dina Hussein, Taha Belkhouja, Ganapati Bhat, Janardhan Rao Doppa

    Wearable devices are being increasingly used in high-impact health applications including vital sign monitoring, rehabilitation, and movement disorders. Wearable health monitoring can aid in the United Nations social development goal of healthy lives by enabling early warning, risk reduction, and management of health risks. Health tasks on wearable devices employ multiple sensors to collect relevant parameters of user’s health and make decisions using machine learning (ML) algorithms. The ML algorithms assume that data from all sensors are available for the health monitoring tasks. However, the applications may encounter missing or incomplete data due to user error, energy limitations, or sensor malfunction. Missing data results in significant loss of accuracy and quality of service. This paper presents a novel Classifier-Aware iMputation (CAM) approach to impute missing data such that classifier accuracy for health tasks is not affected. Specifically, CAM employs unsupervised clustering followed by a principled search algorithm to uncover imputation patterns that maintain high accuracy. Evaluations on seven diverse health tasks show that CAM achieves accuracy within 5% of the baseline with no missing data when one sensor is missing. CAM also achieves significantly higher accuracy compared to generative approaches with negligible energy overhead, making it suitable for wide range of wearable applications.


  • Open Access

    SensorGAN: A Novel Data Recovery Approach for Wearable Human Activity Recognition

    by Dina Hussein, Ganapati Bhat

    Human activity recognition (HAR) and more broadly, activities of daily life recognition using wearable devices, have the potential to transform a number of applications including mobile healthcare, smart homes, and fitness monitoring. Recent approaches for HAR use multiple sensors on various locations on the body to achieve higher accuracy for complex activities. While multiple sensors increase the accuracy, they are also susceptible to reliability issues when one or more sensors are unable to provide data to the application due to sensor malfunction, user error, or energy limitations. Training multiple activity classifiers that use a subset of sensors is not desirable since it may lead to reduced accuracy for applications. To handle these limitations, we propose a novel generative approach that recovers the missing data of sensors using data available from other sensors. The recovered data is then used to seamlessly classify activities. Experiments using three publicly available activity datasets show that with data missing from one sensor, the proposed approach achieves accuracy that is within 10% of the accuracy with no missing data. Moreover, implementation on a wearable device prototype show that the proposed approach takes about 1.5 ms for recovering data in the w-HAR dataset, which results in an energy consumption of 606 μJ. The low energy consumption ensures that SensorGAN is suitable for effectively recovering data in tinyML applications on energy-constrained devices.


  • Open Access

    CIM: A Novel Clustering-based Energy-Efficient Data Imputation Method for Human Activity Recognition

    by Dina Hussein, Ganapati Bhat

    Human activity recognition (HAR) is an important component in a number of health applications, including rehabilitation, Parkinson’s disease, daily activity monitoring, and fitness monitoring. State-of-the-art HAR approaches use multiple sensors on the body to accurately identify activities at runtime. These approaches typically assume that data from all sensors are available for runtime activity recognition. However, data from one or more sensors may be unavailable due to malfunction, energy constraints, or communication challenges between the sensors. Missing data can lead to significant degradation in the accuracy, thus affecting quality of service to users. A common approach for handling missing data is to train classifiers or sensor data recovery algorithms for each combination of missing sensors. However, this results in significant memory and energy overhead on resource-constrained wearable devices. In strong contrast to prior approaches, this paper presents a clustering-based approach (CIM) to impute missing data at runtime. We first define a set of possible clusters and representative data patterns for each sensor in HAR. Then, we create and store a mapping between clusters across sensors. At runtime, when data from a sensor are missing, we utilize the stored mapping table to obtain most likely cluster for the missing sensor. The representative window for the identified cluster is then used as imputation to perform activity classification. We also provide a method to obtain imputation-aware activity prediction sets to handle uncertainty in data when using imputation. Experiments on three HAR datasets show that CIM achieves accuracy within 10% of a baseline without missing data for one missing sensor when providing single activity labels. The accuracy gap drops to less than 1% with imputation-aware classification. Measurements on a low-power processor show that CIM achieves close to 100% energy savings compared to state-of-the-art generative approaches.


  • Open Access

    Reliable Machine Learning for Wearable Activity Monitoring

    by Dina Hussein, Taha Belkhouja, Ganapati Bhat, Janardhan Rao Doppa

    Wearable devices are becoming popular for health and activity monitoring. The machine learning (ML) models for these applications are trained by collecting data in a laboratory with precise control of experimental settings. However, during real-world deployment/usage, the experimental settings (e.g., sensor position or sampling rate) may deviate from those used during training. This discrepancy can degrade the accuracy and effectiveness of the health monitoring applications. Therefore, there is a great need to develop reliable ML approaches that provide high accuracy for real-world deployment. In this paper, we propose a novel statistical optimization approach referred as StatOpt that automatically accounts for the real-world disturbances in sensing data to improve the reliability of ML models for wearable devices. We theoretically derive the upper bounds on sensor data disturbance for StatOpt to produce a ML model with reliability certificates. We validate StatOpt on two publicly available datasets for human activity recognition. Our results show that compared to standard ML algorithms, the reliable ML classifiers enabled by the StatOpt approach improve the accuracy up to 50% in real-world settings with zero overhead, while baseline approaches incur significant overhead and fail to achieve comparable accuracy.