A Review of Algorithm &amp; Hardware Design for AI-Based Biomedical Applications

Wei, Ying; Zhou, Jun; Wang, Yin; Liu, Yinggang; Liu, Qingsong; Luo, Jiansheng; Wang, Chao; Ren, Fengbo; Huang, Li

doi:10.1109/tbcas.2020.2974154

Cited by 93 publications

(36 citation statements)

References 96 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…An intelligence system atau sebuah sisem cerdas merupakan idaman bagi manusia di mana sistem tersebut dapat menganalisa permasalahan yang ada (perception) dan memberikan feedback secara natural (decision making). Penggunaan sistem cerdas saat ini meliputi banyak sektor seperti transportasi [1], ekonomi [2], pelayanan umum [3], pendidikan [4] hingga dunia medis [5].…”

Section: Pendahuluanunclassified

Tahapan Desain dan Implementasi Model Machine Learning untuk Sistem Tertanam

Rizal¹

2020

ULTIMA Computing

View full text Add to dashboard Cite

machine learning and edge computing currently becomes popular technology used in any discipline. Flexibility and adapt to the problem are the main advantages of its technology. In this paper, we explain step-by-step way to make a lightweight machine learning model especially intended for embedded system application. We use open source machine learning tool called as Weka to design the model. Moreover, we performed a simple stress recognition experiment to make our own dataset for evaluation. We evaluate algorithm complexity and accuracy for different well-known classifier such as support vector machine, simple logistic and hoeffding tree.

show abstract

Section: Pendahuluanunclassified

Tahapan Desain dan Implementasi Model Machine Learning untuk Sistem Tertanam

Rizal¹

2020

ULTIMA Computing

View full text Add to dashboard Cite

show abstract

“…It provided a significant increase in the power efficiency of the overall system due to a decrease in radio utilization, emphasizing the need to maximize local processing. Generic hardware accelerators discussed in [8,10,11], target common signal processing techniques predominantly used in biomedical applications. This ensures the use of accelerators in multiple varied algorithms and provides an energy-efficient solution with the flexibility to map a large set of biomedical applications.…”

Section: Introductionmentioning

confidence: 99%

A Low gate count reconfigurable architecture for biomedical signal processing applications

2021

View full text Add to dashboard Cite

A new reconfigurable architecture for biomedical applications is presented in this paper. The architecture targets frequently encountered functions in biomedical signal processing algorithms thereby replacing multiple dedicated accelerators and reports low gate count. An optimized implementation is achieved by mapping methodologies to functions and limiting the required memory leading directly to an overall minimization of gate count. The proposed architecture has a simple configuration scheme with special provision for handling feedback. The effectiveness of the architecture is demonstrated on an FPGA to show implementation schemes for multiple DSP functions. The architecture has gate count of $$\approx$$ ≈ 25k and an operating frequency of 46.9 MHz.

show abstract

“…In this situation it seems to be very important to develop new numerical approaches well fitted to a powerful contemporary hardware. Our model operates as a neural network that can be run either using various network software systems available today, such as TensorFlow [13] and PyTorch [30], or it can be uploaded to a dedicated computer chip called AI accelerator (AI stands for artificial intelligence) [20,21].…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network as a Universal Model of Nonlinear Dynamical Systems

Kuptsov¹,

Kuptsova²,

Stankevich³

2021

Nelin. Dinam.

View full text Add to dashboard Cite

We suggest a universal map capable of recovering the behavior of a wide range of dynamical systems given by ODEs. The map is built as an artificial neural network whose weights encode a modeled system. We assume that ODEs are known and prepare training datasets using the equations directly without computing numerical time series. Parameter variations are taken into account in the course of training so that the network model captures bifurcation scenarios of the modeled system. The theoretical benefit from this approach is that the universal model admits applying common mathematical methods without needing to develop a unique theory for each particular dynamical equations. From the practical point of view the developed method can be considered as an alternative numerical method for solving dynamical ODEs suitable for running on contemporary neural network specific hardware. We consider the Lorenz system, the Rössler system and also the Hindmarch – Rose model. For these three examples the network model is created and its dynamics is compared with ordinary numerical solutions. A high similarity is observed for visual images of attractors, power spectra, bifurcation diagrams and Lyapunov exponents.

show abstract

A Review of Algorithm & Hardware Design for AI-Based Biomedical Applications

Cited by 93 publications

References 96 publications

Tahapan Desain dan Implementasi Model Machine Learning untuk Sistem Tertanam

Tahapan Desain dan Implementasi Model Machine Learning untuk Sistem Tertanam

A Low gate count reconfigurable architecture for biomedical signal processing applications

Artificial Neural Network as a Universal Model of Nonlinear Dynamical Systems

Contact Info

Product

Resources

About