A spatiotemporal data compression approach with low transmission cost and high data fidelity for an air quality monitoring system

Chen, Hsing‐Chung; Putra, Karisma Trinanda; Tseng, Shian‐Shyong; Tu, Yu–Kang; Lin, Jerry Chun‐Wei

doi:10.1016/j.future.2020.02.032

Cited by 15 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is interesting to note that the DCT-based FCL scheme provides more compact data generation than the DWT-based FCL scheme. As described in [ 25 , 26 ], the DCT performs a higher compression rate rather than other techniques but, sacrifices a slight error rate. However, when faced with federated learning problems, both CS techniques (i.e., DCT and DWT) produce nearly identical learning features.…”

Section: Discussionmentioning

confidence: 99%

“…The classical transform theorems (i.e., lossy compression) include Fourier transform, Hadamard transform, discrete cosine transform, and discrete wavelet transform are proven to be used to reduce communication overhead. Lossy compression can reduce data size significantly with a small error rate [ 25 , 26 ]. In some previous applications, the compression often shows small data changes even, quite sharp deformations appear in a small data area.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Federated Compressed Learning Edge Computing Framework with Ensuring Data Privacy for PM2.5 Prediction in Smart City Sensing Applications

Putra

Chen

Prayitno

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

The sparse data in PM2.5 air quality monitoring systems is frequently happened on large-scale smart city sensing applications, which is collected via massive sensors. Moreover, it could be affected by inefficient node deployment, insufficient communication, and fragmented records, which is the main challenge of the high-resolution prediction system. In addition, data privacy in the existing centralized air quality prediction system cannot be ensured because the data which are mined from end sensory nodes constantly exposed to the network. Therefore, this paper proposes a novel edge computing framework, named Federated Compressed Learning (FCL), which provides efficient data generation while ensuring data privacy for PM2.5 predictions in the application of smart city sensing. The proposed scheme inherits the basic ideas of the compression technique, regional joint learning, and considers a secure data exchange. Thus, it could reduce the data quantity while preserving data privacy. This study would like to develop a green energy-based wireless sensing network system by using FCL edge computing framework. It is also one of key technologies of software and hardware co-design for reconfigurable and customized sensing devices application. Consequently, the prototypes are developed in order to validate the performances of the proposed framework. The results show that the data consumption is reduced by more than 95% with an error rate below 5%. Finally, the prediction results based on the FCL will generate slightly lower accuracy compared with centralized training. However, the data could be heavily compacted and securely transmitted in WSNs.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Federated Compressed Learning Edge Computing Framework with Ensuring Data Privacy for PM2.5 Prediction in Smart City Sensing Applications

Putra

Chen

Prayitno

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…A spatiotemporal classification model can be used to study sequential data because it can extract time-series patterns in spatiotemporal datasets, such as plantar pressure images. These spatiotemporal datasets could be analyzed accurately by using the deep spatiotemporal classification model [ 22 ] and spatiotemporal data analysis [ 54 ]. Third, the plantar pressure image generated using the insole-type F-scan system measurement device is not very detailed in terms of resolution and measurement in this study.…”

Section: Discussionmentioning

confidence: 99%

Estimation of Various Walking Intensities Based on Wearable Plantar Pressure Sensors Using Artificial Neural Networks

Chen

Sunardi

Liau

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Walking has been demonstrated to improve health in people with diabetes and peripheral arterial disease. However, continuous walking can produce repeated stress on the plantar foot and cause a high risk of foot ulcers. In addition, a higher walking intensity (i.e., including different speeds and durations) will increase the risk. Therefore, quantifying the walking intensity is essential for rehabilitation interventions to indicate suitable walking exercise. This study proposed a machine learning model to classify the walking speed and duration using plantar region pressure images. A wearable plantar pressure measurement system was used to measure plantar pressures during walking. An Artificial Neural Network (ANN) was adopted to develop a model for walking intensity classification using different plantar region pressure images, including the first toe (T1), the first metatarsal head (M1), the second metatarsal head (M2), and the heel (HL). The classification consisted of three walking speeds (i.e., slow at 0.8 m/s, moderate at 1.6 m/s, and fast at 2.4 m/s) and two walking durations (i.e., 10 min and 20 min). Of the 12 participants, 10 participants (720 images) were randomly selected to train the classification model, and 2 participants (144 images) were utilized to evaluate the model performance. Experimental evaluation indicated that the ANN model effectively classified different walking speeds and durations based on the plantar region pressure images. Each plantar region pressure image (i.e., T1, M1, M2, and HL) generates different accuracies of the classification model. Higher performance was achieved when classifying walking speeds (0.8 m/s, 1.6 m/s, and 2.4 m/s) and 10 min walking duration in the T1 region, evidenced by an F1-score of 0.94. The dataset T1 could be an essential variable in machine learning to classify the walking intensity at different speeds and durations.

show abstract

“…Besides the obvious potential impact of IoT technologies to the environment, IoT products could on the other side be used for environmental protection. The design and concept of a systematic framework for the massive deployment of IoT-based PM (Particulate Matter) sensing devices was elaborated in ( Chen et al., 2020c ). The proposed framework was applied for the monitoring of air quality.…”

Section: Iot Technologies In Sustainable Energy and Environmentmentioning

confidence: 99%

Internet of Things (IoT): Opportunities, issues and challenges towards a smart and sustainable future

Nižetić

Šolić

López-de-Ipiña

et al. 2020

Journal of Cleaner Production

576

165

View full text Add to dashboard Cite

The rapid development and implementation of smart and IoT (Internet of Things) based technologies have allowed for various possibilities in technological advancements for different aspects of life. The main goal of IoT technologies is to simplify processes in different fields, to ensure a better efficiency of systems (technologies or specific processes) and finally to improve life quality. Sustainability has become a key issue for population where the dynamic development of IoT technologies is bringing different useful benefits, but this fast development must be carefully monitored and evaluated from an environmental point of view to limit the presence of harmful impacts and ensure the smart utilization of limited global resources. Significant research efforts are needed in the previous sense to carefully investigate the pros and cons of IoT technologies. This review editorial is partially directed on the research contributions presented at the 4th International Conference on Smart and Sustainable Technologies held in Split and Bol, Croatia, in 2019 (SpliTech 2019) as well as on recent findings from literature. The SpliTech2019 conference was a valuable event that successfully linked different engineering professions, industrial experts and finally researchers from academia. The focus of the conference was directed towards key conference tracks such as Smart City, Energy/Environment, e-Health and Engineering Modelling. The research presented and discussed at the SpliTech2019 conference helped to understand the complex and intertwined effects of IoT technologies on societies and their potential effects on sustainability in general. Various application areas of IoT technologies were discussed as well as the progress made. Four main topical areas were discussed in the herein editorial, i.e. latest advancements in the further fields: (i) IoT technologies in Sustainable Energy and Environment, (ii) IoT enabled Smart City, (iii) E-health – Ambient assisted living systems (iv) IoT technologies in Transportation and Low Carbon Products. The main outcomes of the review introductory article contributed to the better understanding of current technological progress in IoT application areas as well as the environmental implications linked with the increased application of IoT products.

show abstract

A spatiotemporal data compression approach with low transmission cost and high data fidelity for an air quality monitoring system

Cited by 15 publications

References 28 publications

Federated Compressed Learning Edge Computing Framework with Ensuring Data Privacy for PM2.5 Prediction in Smart City Sensing Applications

Federated Compressed Learning Edge Computing Framework with Ensuring Data Privacy for PM2.5 Prediction in Smart City Sensing Applications

Estimation of Various Walking Intensities Based on Wearable Plantar Pressure Sensors Using Artificial Neural Networks

Internet of Things (IoT): Opportunities, issues and challenges towards a smart and sustainable future

Contact Info

Product

Resources

About