| 1. |
- Deng, Weipeng, et al.
(author)
-
Energy-Efficient Monitoring of Potential Side Effects from COVID-19 Vaccines
- 2022
-
In: Proceedings. - : IEEE. - 9781665454179 - 9781665454186 ; , s. 222-227
-
Conference paper (peer-reviewed)abstract
- COVID-19 has affected the world for almost two years causing lots of damages and losses of lives. With the development of sensing technology and digital health, research studies suggest to use wearable devices for monitoring COVID-19 symptoms or analyzing people’s behaviour change. As COVID-19 vaccines are getting widely available, their side effects have raised public concerns, though have not yet been thoroughly studied due to the short deployment time. As far as we know, this work is the first study to use wearable devices and mobile app to collect physiological data to explore potential side effects to human bodies from COVID-19 vaccinations. We designed and developed a mobile sensing system, which can monitor changes of physiological indicators through wearable devices, collect self-reported data from the users and proposed a green data transmission mechanism which can reduce the communication overheads. Pilot study has been conducted to evaluate the feasibility of our system. Preliminary results show that increased resting heart rate (RHR) and changes on average heart rate (HR) are observed in some participants after COVID-19 vaccinations. This study opens up the opportunity to collect larger amount of data and further investigate potential side effects from COVID-19 vaccinations.
|
|
| 2. |
|
|
| 3. |
- Jiang, Zhihan, et al.
(author)
-
Leveraging Machine Learning for Disease Diagnoses based on Wearable Devices : A Survey
- 2023
-
In: IEEE Internet of Things Journal. - : Institute of Electrical and Electronics Engineers (IEEE). - 2327-4662. ; 10:24, s. 21959-21981
-
Journal article (peer-reviewed)abstract
- Many countries around the world are facing a shortage of healthcare resources, especially during the post-epidemic era, leading to a dramatic increase in the need for self-detection and self-management of diseases. The popularity of smart wearable devices, such as smartwatches, and the development of machine learning bring new opportunities for the early detection and management of various prevalent diseases, such as cardiovascular diseases, Parkinson’s disease, and diabetes. In this survey, we comprehensively review the articles related to specific diseases or health issues based on small wearable devices and machine learning. More specifically, we first present an overview of the articles selected and classify them according to their targeted diseases. Then, we summarize their objectives, wearable device and sensor data, machine learning techniques, and wearing locations. Based on the literature review, we discuss the challenges and propose future directions from the perspectives of privacy concerns, security concerns, transmission latency and reliability, energy consumption, multi-modality, multi-sensor, multi-devices, evaluation metrics, explainability, generalization and personalization, social influence, and human factors, aiming to inspire researchers in this field.
|
|
| 4. |
- Kaivonen, Sami, et al.
(author)
-
Real-time air pollution monitoring with sensors on city bus
- 2020
-
In: Digital Communications and Networks. - : KeAi. - 2468-5925 .- 2352-8648. ; 6:1, s. 23-30
-
Journal article (peer-reviewed)abstract
- This paper presents an experimental study on real-time air pollution monitoring using wireless sensors on public transport vehicles. The study is part of the GreenIoT project in Sweden, which utilizes Internet-of-Things to measure air pollution level in the city center of Uppsala. Through deploying low-cost wireless sensors, it is possible to obtain more fine-grained and real-time air pollution levels at different locations. The sensors on public transport vehicles complement the readings from stationary sensors and the only ground level monitoring station in Uppsala. The paper describes the deployment of wireless sensors on Uppsala buses and the integration of the mobile sensor network with the GreenIoT testbed. Extensive experiments have been conducted to evaluate the communication quality and data quality of the system.
|
|
| 5. |
- Li, Shenghui, 1994-, et al.
(author)
-
An Experimental Study of Byzantine-Robust Aggregation Schemes in Federated Learning
- 2023
-
In: IEEE Transactions on Big Data. - : Institute of Electrical and Electronics Engineers (IEEE). - 2332-7790 .- 2372-2096.
-
Journal article (peer-reviewed)abstract
- Byzantine-robust federated learning aims at mitigating Byzantine failures during the federated training process, where malicious participants (known as Byzantine clients) may upload arbitrary local updates to the central server in order to degrade the performance of the global model. In recent years, several robust aggregation schemes have been proposed to defend against malicious updates from Byzantine clients and improve the robustness of federated learning. These solutions were claimed to be Byzantine-robust, under certain assumptions. Other than that, new attack strategies are emerging, striving to circumvent the defense schemes. However, there is a lack of systematical comparison and empirical study thereof. In this paper, we conduct an experimental study of Byzantine-robust aggregation schemes under different attacks using two popular algorithms in federated learning, FedSGD and FedAvg . We first survey existing Byzantine attack strategies, as well as Byzantine-robust aggregation schemes that aim to defend against Byzantine attacks. We also propose a new scheme, ClippedClustering, to enhance the robustness of a clustering-based scheme by automatically clipping the updates. Then we provide an experimental evaluation of eight aggregation schemes in the scenario of five different Byzantine attacks. Our experimental results show that these aggregation schemes sustain relatively high accuracy in some cases, but they are not effective in all cases. In particular, our proposed ClippedClustering successfully defends against most attacks under independent and identically distributed (IID) local datasets. However, when the local datasets are Non-IID, the performance of all the aggregation schemes significantly decreases. With Non-IID data, some of these aggregation schemes fail even in the complete absence of Byzantine clients. Based on our experimental study, we conclude that the robustness of all the aggregation schemes is limited, highlighting the need for new defense strategies, in particular for Non-IID datasets.
|
|
| 6. |
- Li, Shenghui, 1994-, et al.
(author)
-
Auto-Weighted Robust Federated Learning with Corrupted Data Sources
- 2022
-
In: ACM Transactions on Intelligent Systems and Technology. - : Association for Computing Machinery. - 2157-6904 .- 2157-6912. ; 13:5
-
Journal article (peer-reviewed)abstract
- Federated learning provides a communication-efficient and privacy-preserving training process by enabling learning statistical models with massive participants without accessing their local data. Standard federated learning techniques that naively minimize an average loss function are vulnerable to data corruptions from outliers, systematic mislabeling, or even adversaries. In this article, we address this challenge by proposing Auto-weighted Robust Federated Learning (ARFL), a novel approach that jointly learns the global model and the weights of local updates to provide robustness against corrupted data sources. We prove a learning bound on the expected loss with respect to the predictor and the weights of clients, which guides the definition of the objective for robust federated learning. We present an objective that minimizes the weighted sum of empirical risk of clients with a regularization term, where the weights can be allocated by comparing the empirical risk of each client with the average empirical risk of the best ( p ) clients. This method can downweight the clients with significantly higher losses, thereby lowering their contributions to the global model. We show that this approach achieves robustness when the data of corrupted clients is distributed differently from the benign ones. To optimize the objective function, we propose a communication-efficient algorithm based on the blockwise minimization paradigm. We conduct extensive experiments on multiple benchmark datasets, including CIFAR-10, FEMNIST, and Shakespeare, considering different neural network models. The results show that our solution is robust against different scenarios, including label shuffling, label flipping, and noisy features, and outperforms the state-of-the-art methods in most scenarios.
|
|
| 7. |
- Li, Shenghui, 1994-, et al.
(author)
-
Blades : A Unified Benchmark Suite for Byzantine Attacks and Defenses in Federated Learning
- 2024
-
Conference paper (peer-reviewed)abstract
- Federated learning (FL) facilitates distributed training across different IoT and edge devices, safeguarding the privacy of their data. The inherent distributed structure of FL introduces vulnerabilities, especially from adversarial devices aiming to skew local updates to their advantage. Despite the plethora of research focusing on Byzantine-resilient FL, the academic community has yet to establish a comprehensive benchmark suite, pivotal for impartial assessment and comparison of different techniques. This paper presents Blades, a scalable, extensible, and easily configurable benchmark suite that supports researchers and developers in efficiently implementing and validating novel strategies against baseline algorithms in Byzantine-resilient FL. Blades contains built-in implementations of representative attack and defense strategies and offers a user-friendly interface that seamlessly integrates new ideas. Using Blades, we re-evaluate representative attacks and defenses on wide-ranging experimental configurations (approximately 1,500 trials in total). Through our extensive experiments, we gained new insights into FL robustness and highlighted previously overlooked limitations due to the absence of thorough evaluations and comparisons of baselines under various attack settings. We maintain the source code and documents at https://github.com/lishenghui/blades.
|
|
| 8. |
- Li, Shenghui, 1994-, et al.
(author)
-
Byzantine-Robust Aggregation in Federated Learning Empowered Industrial IoT
- 2023
-
In: IEEE Transactions on Industrial Informatics. - : Institute of Electrical and Electronics Engineers (IEEE). - 1551-3203 .- 1941-0050. ; 19:2, s. 1165-
-
Journal article (peer-reviewed)abstract
- Federated Learning (FL) is a promising paradigm to empower on-device intelligence in Industrial Internet of Things(IIoT) due to its capability of training machine learning models across multiple IIoT devices, while preserving the privacy of their local data. However, the distributed architecture of FL relies on aggregating the parameter list from the remote devices, which poses potential security risks caused by malicious devices. In this paper, we propose a flexible and robust aggregation rule, called Auto-weighted Geometric Median (AutoGM), and analyze the robustness against outliers in the inputs. To obtain the value of AutoGM, we design an algorithm based on alternating optimization strategy. Using AutoGM as aggregation rule, we propose two robust FL solutions, AutoGM_FL and AutoGM_PFL. AutoGM_FL learns a shared global model using the standard FL paradigm, and AutoGM_PFL learns a personalized model for each device. We conduct extensive experiments on the FEMNIST and Bosch IIoT datasets. The experimental results show that our solutions are robust against both model poisoning and data poisoning attacks. In particular, our solutions sustain high performance even when 30% of the nodes perform model or 50% of the nodes perform data poisoning attacks.
|
|
| 9. |
- Liu, Xiuming, et al.
(author)
-
Approximate Gaussian Process Regression and Performance Analysis Using Composite Likelihood
- 2020
-
In: 30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020, Espoo, Finland, September 21-24, 2020. - : IEEE. - 9781728166629 ; , s. 1-6
-
Conference paper (peer-reviewed)abstract
- Nonparametric regression using Gaussian Process (GP) models is a powerful but computationally demanding method. While various approximation methods have been developed to mitigate its computation complexity, few works have addressed the quality of the resulting approximations of the target posterior. In this paper we start from a general belief updating framework that can generate various approximations. We show that applying using composite likelihoods yields computationally scalable approximations for both GP learning and prediction. We then analyze the quality of the approximation in terms of averaged prediction errors as well as Kullback-Leibler (KL) divergences.
|
|
| 10. |
- Liu, Xiuming, et al.
(author)
-
Scalable Belief Updating for Urban Air Quality Modeling and Prediction
- 2021
-
In: ACM/IMS Transactions on Data Science. - : Association for Computing Machinery (ACM). - 2577-3224 .- 2691-1922. ; 2:1, s. 1-19
-
Journal article (peer-reviewed)abstract
- Air pollution is one of the major concerns in global urbanization. Data science can help to understand the dynamics of air pollution and build reliable statistical models to forecast air pollution levels. To achieve these goals, one needs to learn the statistical models which can capture the dynamics from the historical data and predict air pollution in the future. Furthermore, the large size and heterogeneity of today’s big urban data pose significant challenges on the scalability and flexibility of the statistical models. In this work, we present a scalable belief updating framework that is able to produce reliable predictions, using over millions of historical hourly air pollutant and meteorology records. We also present a non-parametric approach to learn the statistical model which reveals interesting periodical dynamics and correlations of the dataset. Based on the scalable belief update framework and the non-parametric model learning approach, we propose an iterative update algorithm to accelerate Gaussian process, which is notorious for its prohibitive computation with large input data. Finally, we demonstrate how to integrate information from heterogeneous data by regarding the beliefs produced by other models as the informative prior. Numerical examples and experimental results are presented to validate the proposed method.
|
|
| 11. |
- Liu, Xiuming, et al.
(author)
-
Secure Information Fusion using Local Posterior for Distributed Cyber-Physical Systems
- 2020
-
In: IEEE Transactions on Mobile Computing. - : IEEE. - 1536-1233 .- 1558-0660. ; 20:5, s. 2041-2054
-
Journal article (peer-reviewed)abstract
- In modern distributed cyber-physical systems (CPS), information fusion often plays a key role in automate and self-adaptive decision making process. However, given the heterogeneous and distributed nature of modern CPSs, it is a great challenge to operate CPSs with the compromised data integrity and unreliable communication links. In this paper, we study the distributed state estimation problem under the false data injection attack (FDIA) with probabilistic communication networks. We propose an integrated "detection + fusion" solution, which is based on the Kullback-Leibler divergences (KLD) between local posteriors and therefore does not require the exchange of raw sensor data. For the FDIA detection step, the KLDs are used to cluster nodes in the probability space and to partition the space into secure and insecure subspaces. By approximating the distribution of the KLDs with a general chi(2) distribution and calculating its tail probability, we provide an analysis of the detection error rate. For the information fusion step, we discuss the potential risk of double counting the shared prior information in the KLD-based consensus formulation method. We show that if the local posteriors are updated from the shared prior, the increased number of neighbouring nodes will lead to the diminished information gain. To overcome this problem, we propose a near-optimal distributed information fusion solution with properly weighted prior and data likelihood. Finally, we present simulation results for the integrated solution. We discuss the impact of network connectivity on the empirical detection error rate and the accuracy of state estimation.
|
|
| 12. |
- Liu, Xiuming
(author)
-
Statistical Data Analysis for Internet-of-Things : Scalability, Reliability, and Robustness
- 2020
-
Doctoral thesis (other academic/artistic)abstract
- Internet-of-Things is a set of sensing, communication, and computation technologies to connect physical objects, such as wearable devices, vehicles, and buildings. From those connected “Things”, a large amount of data is generated. Data analysis plays a central role in the automated and intelligent decision-making process to manage and optimize IoT systems. In this thesis, we focus on tackling the challenges of analyzing large, incomplete, and corrupt IoT data. This thesis consists of three topics. In the first topic, we study scalable GP regression for big IoT data. We propose a novel scalable GP model for urban air quality modeling and prediction. Comparing to the existing scalable GP models, the proposed scalable GP model enables tractable analysis of approximation errors. The second topic is to handle the missing data problem. In the case of missing labels in training data, we investigate different missing data mechanisms. We propose a reliable semi-supervised learning approach, which provides accurate predictive error probability. In the case of missing features in testing data, we design a robust predictor. The predictor significantly reduces the prediction error caused by rare values of missing features, while incurring only a small loss on the overall performance. The third topic is information fusion for IoT systems under false data injection attacks. We propose a robust and distributed information fusion method. This proposed information fusion method only requires exchanging the latest local posterior distributions, instead of synchronizing the full historical measurements. Furthermore, we design a false data detector based on the clustering of local posterior distributions. The distributed information fusion method and false data detector enable secure state estimation for mobile IoT networks with probabilistic communication links. Altogether, this thesis is a step to scalable, reliable, and robust IoT data analysis.
|
|
| 13. |
|
|
| 14. |
|
|
| 15. |
- Pitsillos, Tryfonas, et al.
(author)
-
Association Between Objectively Assessed Sleep and Depressive Symptoms During Pregnancy and Post-partum
- 2022
-
In: Frontiers in Global Women's Health. - : Frontiers Media S.A.. - 2673-5059. ; 2
-
Journal article (peer-reviewed)abstract
- Introduction: Sleep problems are common in pregnancy but many studies have relied only on self-reported sleep measures. We studied the association between objectively measured sleep and peripartum depressive symptoms in pregnant women.Material and Methods: Sleep was assessed using Actiwatch accelerometers in a sample of 163 pregnant women in the late first (weeks 11-15) or early second trimester (weeks 16-19). Depressive symptoms were assessed in gestational weeks 17, 32 and at 6 weeks post-partum using the Edinburgh Postnatal Depression Scale (EPDS). Multiple linear regression and logistic regression analyses, adjusting for age, BMI, pre-pregnancy smoking, ongoing mental health problems, trimester and season of sleep assessment were carried out to test the association between sleep and depression. Sleep was measured by total sleep time and sleep efficiency, whereas depression was indicated by depressive symptoms and depression caseness. Results are presented as unstandardized beta (B) coefficients or adjusted odds ratios (AOR) and 95% confidence intervals (CI).Results: Total sleep time ranged from 3 to 9 h (mean 7.1, SD 0.9) and average sleep efficiency was 83% (SD 6.0). Women with the shortest total sleep time, i.e., in the lowest quartile (<6.66 h), reported higher depressive symptoms during pregnancy (week 17, B = 2.13, 95% CI 0.30-3.96; week 32, B = 1.70, 95% CI 0.03-3.37) but not post-partum. Their probability to screen positive for depression in gestational week 17 was increased more than 3-fold (AOR = 3.46, 95% CI 1.07-11.51) but unchanged with regards to gestational week 32 or 6 weeks post-partum. Sleep efficiency was not associated with depressive symptoms at any stage of pregnancy or post-partum.Discussion: In one of the few studies to use objective sleep measures to date, mental health of pregnant women appeared to be affected by shortened sleep, with total sleep time being negatively associated with depressive symptoms in the early second and third trimester. This finding highlights the relevance of identifying and treating sleep impairments in pregnant women early during antenatal care to reduce the risk of concomitant depression.
|
|
| 16. |
- van Zoest, Vera, et al.
(author)
-
Data Quality Evaluation, Outlier Detection and Missing Data Imputation Methods for IoT in Smart Cities
- 2021
-
In: Machine Intelligence and Data Analytics for Sustainable Future Smart Cities. - Cham : Springer. ; , s. 1-18
-
Book chapter (peer-reviewed)abstract
- Low-cost IoT devices allow data collection in smart cities at a high spatio-temporal resolution. Data quality evaluation is needed to investigate the pre-processing steps required to use these data. Besides data pre-processing, outlier detection techniques are required to detect anomalies in the spatio-temporal IoT dataset. We distinguish between erroneous outliers and events based on spatio-temporal autocorrelation patterns, as well as correlations with other dynamic processes in the environment. We consider missing data imputation to fill gaps caused by sensor failures, maintenance, pre-processing and outlier detection. In this study, we use the temporal covariance structure within the data to impute missing data. We apply the methods for outlier detection and missing data imputation to an IoT testbed for air quality monitoring in the city of Eindhoven, the Netherlands. The methods can be applied in a more general sense to other continuous environmental variables which show a similarly strong spatio-temporal autocorrelation structure.
|
|
| 17. |
- van Zoest, Vera, et al.
(author)
-
Demand charges and user flexibility : Exploring differences in electricity consumer types and load patterns within the Swedish commercial sector
- 2021
-
In: Applied Energy. - : Elsevier. - 0306-2619 .- 1872-9118. ; 302
-
Journal article (peer-reviewed)abstract
- Demand-based charges have been employed as a tool intended to reduce electricity users’ maximum demand but there is a lack of consensus regarding their efficacy. One reason for this may be the diversity in the flexibility potential of different types of users. This study explores the flexibility potential of different types of electricity consumers in the small to medium-sized commercial sector (35-63A) in response to a compulsory demand charge. The objective is to characterize varying levels of flexibility with respect to different types of commercial users with different load patterns. A multivariate clustering technique was used to group commercial users with comparable load patterns based on a year of hourly data before the tariff change was introduced. This method was used to: (1) match users from the intervention area and reference area with similar load patterns, without losing any user data, and (2) compare how users with different load patterns react differently to the tariff change. We found clear distinctions in the types of commercial users in each cluster and their response to the tariff, demonstrating the extent to which demand flexibility may be dependent on the nature of an organization’s activities and its respective load patterns. The highest demand flexibility was found in clusters which had a large share of users in the IT sector, commerce and public administration. The lowest demand flexibility was found in the real estate and education sectors. Future research should further investigate these variations and explore the possibilities of tailoring interventions to the specific types of users.
|
|
| 18. |
|
|
| 19. |
|
|
| 20. |
- Wen, Quansi, et al.
(author)
-
Modeling Human Activity With Seasonality Bursty Dynamics
- 2020
-
In: IEEE Transactions on Industrial Informatics. - : Institute of Electrical and Electronics Engineers (IEEE). - 1551-3203 .- 1941-0050. ; 16:2, s. 1130-1139
-
Journal article (peer-reviewed)abstract
- The public's purchase incentive increases dramatically during the holiday season and subsequently returns to normal levels. This seasonality is common in various scenarios and highlights the following questions: how does the public's purchase incentive fluctuate over the course of a year? Which factors are conducive to this seasonal behavior and how can they be modeled? In this paper, we propose a model that explicitly integrates temporal point process theory with the construction of a networked community, to describe the dynamics of collective action propagation with seasonal fluctuation. Furthermore, a database is constructed of sales records for 21 video game consoles and 13 237 video games in France, Germany, Japan, the U.K., the USA, and worldwide from 1989 to 2018. Experimental results suggest that peak desire always appears in the holiday season about one week before Christmas and is about four times higher than consumption desire in a normal period in all areas.
|
|
| 21. |
- Zhu, Chunsheng, et al.
(author)
-
Towards Pricing for Sensor-Cloud
- 2020
-
In: IEEE Transactions on Cloud Computing. - 2168-7161. ; 8:4, s. 1018-1029
-
Journal article (peer-reviewed)abstract
- Motivated by complementing the ubiquitous wireless sensor networks (WSNs) and powerful cloud computing (CC), a lot of attention from both industry and academia has been drawn to Sensor-Cloud (SC). However, SC pricing is barely investigated. Towards pricing for SC, this paper 1) introduces five SC Pricing Models (SCPMs) first. Specifically, to charge a SC user, each SCPM considers one of the following factors respectively: i) the lease period of the SC user; ii) the required working time of SC; iii) the SC resources utilized by the SC user; iv) the volume of sensory data obtained by the SC user; v) the SC path that transmits sensory data from the WSN to the SC user. Further, this paper 2) performs analysis to discuss and exhibit the characteristics of the proposed SCPMs. With that, this paper 3) presents the case studies regarding the application of SCPMs. Eventually, this paper 4) conducts a review about the user behavior study. This paper aims to serve as a very favorable guidance for future research about pricing in SC.
|
|
