Design of RNS Reverse Converters with Constant Shifting to Residue Datapath Channels

Patronik, Piotr; Piestrak, Stanisław J.

doi:10.1007/s11265-017-1238-6

Cited by 6 publications

(12 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many image-based machine learning studies made use of MRI scans to extract and select features from brain tissue properties. Such properties include volumetric information, geometric (shapebased) measures, diffusion parameters, fractional anisotropy (FA), and activation patterns [3], [54]- [58], [68]. For EEG based machine learning studies, features relating to brain electrical signals or eye movement patterns have been extracted using various techniques, for example discrete wavelet transform [51], [52].…”

Section: Feature Extraction and Selectionmentioning

confidence: 99%

Advance Machine Learning Methods for Dyslexia Biomarker Detection: A Review of Implementation Details and Challenges

et al. 2021

View full text Add to dashboard Cite

Dyslexia is a neurological disorder that is characterized by imprecise comprehension of words and generally poor reading performance. It affects a significant population of school-age children, with more occurrences in males, thus, putting them at risk of poor academic performance and low selfesteem for a lifetime. The long-term hope is to have a dyslexia diagnostic method that is informed by neural-biomarkers. In this regard, large numbers of machine learning methods and, more recently, deep learning methods have been implemented across various types of dataset with the above-chance classification accuracy. However, attainment of clinical acceptability of these state-of-the-art methods is bedeviled by certain challenges including lack of biologically-interpretable biomarkers, privacy of dataset and classifiers, hyper-parameter selection/optimization, and overfitting problem among others. This review paper critically analyzes recent machine learning methods for detecting dyslexia and its biomarkers and discusses challenges that require proper attentions from the users of deep learning methods in order to enable them to attain clinically relevance and acceptable level. The review is conducted within the premise of implementation and experimental outcomes for each of the 22 selected articles using the Preferred Reporting Items for Systematic review and Meta-Analyses (PRISMA) protocol, with a view to outlining some critical challenges for achieving high accuracy and reliability of the state-of-the-art machine learning methods. As an evidence-based protocol for reporting in systematic reviews and meta-analyses, PRISMA helps to ensure clarity and transparency of this paper by showing a four-phase flow diagram of the selection process for articles used in this review. It is therefore envisaged that higher classification performance of clinical relevance can be achieved using deep learning models for dyslexia and its biomarkers by addressing identified potential challenges.

show abstract

Section: Feature Extraction and Selectionmentioning

confidence: 99%

Advance Machine Learning Methods for Dyslexia Biomarker Detection: A Review of Implementation Details and Challenges

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In [7] proposed novel end-around carry units (EAC) to optimize the complication in modular addition to solve the performance trade-off that exists in any RNS FIR filter design with an increased number of FIR taps. In [8] used constant shifting accumulation to mitigate the path delay limitations that exist in the reverse conversion process of RNS arithmetic.…”

Section: Introductionmentioning

confidence: 99%

An Efficient FIR Filter Design using DA based Speculative Residue and Reverse Computation RNS system

2020

IJETER

View full text Add to dashboard Cite

Finite impulse response (FIR) filter is prominently used in many digital signal processing (DSP) systems for various applications. In this paper, we present high-performance RNS based finite impulse response (FIR) filters design for ECG signal classification. In general, the residue number system (RNS) gives significant metrics over FIR implementation with its inherent parallelism and data partitioning mechanism. But increased bit width cause considerable performance trade-off due to its residue computation and the reverse conversion. In this paper optimized Residue Number System (RNS) arithmetic is proposed which includes distributed arithmetic based residue computation during RNS multiplication followed by speculative delay optimized reverse computation to mitigate the FIR filter trade-off characteristics with filter length. The proposed RNS design utilizes built-in block RAMs available in FPGA devices to accomplish the reverse conversion process. A distinctive feature of our FIR filter implementation with core optimized RNS is to minimize hardware complexity overhead with the improved operating speed. Initially fetal ECG signal detection is carried out to validate the functionality of FIR filter core and FPGA hardware synthesis is carried out for various input word size and FIR length. From the experimental, it is proved that the trade-off exists in conventional RNS FIR over filter length is narrow down along with considerable complexity reduction with our proposed optimized RNS system

show abstract

“…Generally, the basic processes such as addition, subtraction, division that can be done by using different types of binary adders in any digital based processors and control systems [1]. The adder performance which is used in the device is only measured the high speed and accuracy of a processor or system.…”

Section: Introductionmentioning

confidence: 99%

Design and Analysis of 32-bit Parallel Prefix Adders for Low Power VLSI Applications

Daphni¹,

Grace²

2019

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

The basic processes like addition, subtraction can be done using various types of binary adders with dissimilar addition times (delay), area and power consumption in any digital processing applications. To minimize the Power Delay Product (PDP) of Digital Signal Processing (DSP) processors is necessary for high performance in Very Large Scale Integration (VLSI) applications. In this paper, a 32-bit various Parallel Prefix adders design is proposed and compared the performance results on the aspects of area, delay and power. Implementation (Simulation and Synthesis) results really achieve significant improvement in power and power-delay product when compared with the previous bit adders which is used in processors. To reduce the power, here apply the energy recovery logic like power gating technique for all three adders. All the simulations and synthesis results can be noted using Xilinx ISE 14.2i tool.

show abstract

Design of RNS Reverse Converters with Constant Shifting to Residue Datapath Channels

Cited by 6 publications

References 40 publications

Advance Machine Learning Methods for Dyslexia Biomarker Detection: A Review of Implementation Details and Challenges

Advance Machine Learning Methods for Dyslexia Biomarker Detection: A Review of Implementation Details and Challenges

An Efficient FIR Filter Design using DA based Speculative Residue and Reverse Computation RNS system

Design and Analysis of 32-bit Parallel Prefix Adders for Low Power VLSI Applications

Contact Info

Product

Resources

About