FPGA-Accelerated Time Series Mining on Low-Power IoT Devices

Kang, Seongyoung; Moon, Jinyeong; Jun, Sang-Woo

doi:10.1109/asap49362.2020.00015

Cited by 12 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While integrating FPGAs onto the IoT is far from a trivial task, FPGAs have a variety of uses and implementations as an IoT device [14][15][16][17][18][19]. IoT ready FPGAs are currently being utilized for online methods digital image processing, smart grid energy management, managing complex timing systems, broadcasting video recording solutions, data encryption, medical diagnoses and monitoring, and storage system solutions [14].…”

Section: Fpga Iot Integration Methods and Applicationsmentioning

confidence: 99%

“…With the combined power of parallel processing provided by the FPGA along with Internet access, researchers are able to tackle an incredible amount of issues in the modern era. For example, Kang et al [15] utilize an IoT-capable FPGA for transmitting and mining data from an external server. The FPGA gives the ability to process the data extracted from the server with an improved collection rate of over 200% and an increase in energy efficiency of 15% [15].…”

Section: Fpga Iot Integration Methods and Applicationsmentioning

confidence: 99%

“…For example, Kang et al [15] utilize an IoT-capable FPGA for transmitting and mining data from an external server. The FPGA gives the ability to process the data extracted from the server with an improved collection rate of over 200% and an increase in energy efficiency of 15% [15].…”

Section: Fpga Iot Integration Methods and Applicationsmentioning

confidence: 99%

See 2 more Smart Citations

FPGA Remote Laboratory Using IoT Approaches

Magyari

Chen

2021

Electronics

View full text Add to dashboard Cite

Field-Programmable Gate Arrays (FPGAs) are relatively high-end devices that are not easily shared between multiple users. In this work, we achieved a remotely accessible FPGA framework using accessible Internet of Things (IoT) approaches. We sought to develop a method for students to receive the same level of educational quality in a remote environment that they would receive in a typical, in-person course structure for a university-level digital design course. Keeping cost in mind, we are able to combine the functionality of an entry-level FPGA and a Raspberry Pi Zero to provide IoT access for laboratory work. Previous works in this field allow only one user to access an FPGA at a time, which requires students to schedule time slots. Our design is unique in that it gives multiple users the ability to interact simultaneously with one individual top-level design on an FPGA. This novel design has the benefit for classroom presentations, collaboration and debugging, and eliminates the need for restricting student access to a time slot for FPGA access. Further, our hardware wrapper is lightweight, utilizing less than 1% of tested FPGA chips, allowing it to be integrated with resource-heavy designs. The application is meant to scale with large designs; there is no difference between how many users can interact with the remote design, regardless of the complexity of the design. Further, the number of users who can interact with a single project is limited only by the bandwidth restrictions imposed by Google Fire Base, which is far beyond any practical number of users for simultaneous access.

show abstract

Section: Fpga Iot Integration Methods and Applicationsmentioning

confidence: 99%

Section: Fpga Iot Integration Methods and Applicationsmentioning

confidence: 99%

See 1 more Smart Citation

FPGA Remote Laboratory Using IoT Approaches

Magyari

Chen

2021

Electronics

View full text Add to dashboard Cite

show abstract

“…if the length of the subsequence is not a multiple of , then the subsequence is complemented by dummy zero elements. We denote the number of dummy elements by pad =  -(n mod ), then the aligned subsequence 𝑇 𝑥,𝑚 is defined by (12):…”

Section: Data Compositionmentioning

confidence: 99%

“…A parallel time series algorithm for searching similar sub-sequences (Firas Mahmood Saeed) 1653 core system [11]. As well as, parallel algorithms were proposed for finding similar subsequences for fieldprogrammable gate array (FPGA) [12], multi-core of the graphics processing unit (GPU) architectures [13],…”

Section: Introductionmentioning

confidence: 99%

A parallel time series algorithm for searching similar sub-sequences

Saeed

Ali

Al-Neama

2022

IJEECS

View full text Add to dashboard Cite

<p><span>Dynamic time warping (DTW) is an important metric for measuring similarity for most time series applications. The computations of DTW cost too much especially with the gigantic of sequence databases and lead to an urgent need for accelerating these computations. However, the multi-core cluster systems, which are available now, with their scalability and performance/cost ratio, meet the need for more powerful and efficient performance. This paper proposes a highly efficient parallel vectorized algorithm with high performance for computing DTW, addressed to multi-core clusters using the Intel quad-core Xeon co-processors. It deduces an efficient architecture. Implementations employ the potential of both message passing interface (MPI) and OpenMP libraries. The implementation is based on the OpenMP parallel programming technology and offloads execution mode, where part of the code sub-sequences on the processor side, which are uploaded to the co-processor for the DTW computations. The results of experiments confirm the effectiveness of the algorithm.</span></p>

show abstract

Myrmec: FPGA-Accelerated SmartNIC for Cost and Power Efficient IoT Sensor Networks

Chen,

Jun

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

FPGA-Accelerated Time Series Mining on Low-Power IoT Devices

Cited by 12 publications

References 14 publications

FPGA Remote Laboratory Using IoT Approaches

FPGA Remote Laboratory Using IoT Approaches

A parallel time series algorithm for searching similar sub-sequences

Myrmec: FPGA-Accelerated SmartNIC for Cost and Power Efficient IoT Sensor Networks

Contact Info

Product

Resources

About