Conference PaperPDF Available

Towards Low-Cost, Real-Time, Distributed Signal and Data Processing for Artificial Intelligence Applications at Edges of Large Industrial and Internet Networks

Authors:
Emmanuel Oyekanlu at Drexel University
Emmanuel Oyekanlu
Kevin Scoles
Kevin Scoles
Kevin Scoles
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Download full-text PDF
Read full-text
Download citation

Abstract

Digital Signal Processors (DSP) are vital system components in industrial Artificial Intelligence (AI) applications. In this paper, FIR filters that could be used for industrial AI applications are designed from the Spline Biorthogonal 1.5 (SB1.5) mother wavelet using a real-time, low-cost, generic industrial IoT (IIoT) hardware: the C28x DSP and low-level, Embedded C, system software. Our contribution in this paper is the first reported application of the C28x for SB1.5 wavelet construction. The significance of this approach is to be able to repurpose low-cost, readily available hardware for distributed AI applications. Our approach is different from the state of the art, in which specialized hardware are always manufactured for implementing AI applications at large network edges. Our approach supports low-cost and fast single-stage FIR implementation suitable for use in real-time, distributed AI application at network edges, since in our case, successive recursion of FIR filters leading to a full implementation of Pyramid Algorithm is not implemented. The designed FIR filter is evaluated and found capable of both low-pass and high pass filtering operations. Results of this paper indicate that the C28x real-time DSP, which exists in many IoT devices, could have improved scalability by being deployed for other important AI and IoT network edge analytic applications, different from its present uses.
Content uploaded by Emmanuel Oyekanlu
Author content
All content in this area was uploaded by Emmanuel Oyekanlu on Mar 14, 2019
Content may be subject to copyright.
Towards Low-Cost, Real-Time, Distributed Signal and Data Processing for Artificial Intelligence
Applications at Edges of Large Industrial and Internet Networks
Emmanuel Oyekanlu
Electrical and Computer Engr. Department,
Drexel University, Philadelphia,
Pennsylvania, USA.
eao48@drexel.edu
Kevin Scoles
Electrical and Computer Engr. Department
Drexel University, Philadelphia
Pennsylvania, USA
Abstract—
Digital Signal Processors (DSP) are vital system
components in industrial Artificial Intelligence (AI) applications. In
this paper, FIR filters that could be used for industrial AI applications
are designed from the Spline Biorthogonal 1.5 (SB1.5) mother wavelet
using a real-time, low-cost, generic industrial IoT (IIoT) hardware: the
C28x DSP
and low-level, Embedded C, system software. Our
contribution in this paper is the first reported application of the C28x
for SB1.5 wavelet construction. The significance of this approach is to
be able to repurpose low-cost, readily available hardware for
distributed AI applications. Our approach is different from the state of
the art, in which specialized hardware are
always manufactured for
implementing AI applications at large network edges. Our approach
supports low-cost and fast single-stage FIR implementation suitable for
use in real-time, distributed AI application at network edges, since in
our case, successive recursion of FIR filters leading to a full
implementation of Pyramid Algorithm is not implemented. The
designed FIR filter is evaluated and found capable of both low-
pass
and
high pass filtering operations. Results of this paper indicate that the
C28x real-time DSP, which exists in many IoT devices, could have
improved scalability by being deployed for other important AI and IoT
network edge analytic applications, different from its present uses.
Keywords- embedded systems, real-time, AI, FIR filter, wavelet
I. INTRODUCTION
DSPs are used extensively in AI applications. Real-time
DSPs are useful in preprocessing data and signals, in filtering
applications, in signal denoising and in feature extraction
applications for AI systems [1], [2]. In the past few decades,
wavelet transform methods, fully implemented on DSPs have
been used as integral part of several AI preprocessing steps
such as in image compression, computer vision and
audiovisual applications especially in the cloud layer of
Internet of Things (IoT) systems. The Mallat’s Pyramid
algorithm, a fast implementation of the Discrete Wavelet
Transform which involves successive recursion of FIR filters
with increasing resolution is often used in most wavelet-based
AI applications [3]. An illustration of Pyramid algorithm for a
two-step recursion is shown in Fig. 1. However, most edge
computing IoT devices always have low computing po
wer
with small memory, and as a result, the amount of analytics
works they can accomplish is often minimal. Hence most AI
algorithms due to their needs for excessive computing power
are often deployed in IoT clouds [4]. To deploy more AI
applications to the edge and fog layers of IIoT systems, our
contribution in this paper is to facilitate distributed computing
approach by which FIR filters, useful for pre-processing
applications in AI can be designed at the
edge and fog layer of
IIoT systems using generic, widely available IoT DSPs.
Towards this end, similar to the approach used in [3], we have
used the widely available C28x DSP, manufactured by Texas
Instruments (TI), and deployed in estimated billions of edge
computing devices [5],
to construct the SB1.5 mother wavelet
using low-level Embedded C programming language.
Embedded C is suitable for computing applications for edge
devices that have low computing power [6]. An advanced
signal processing method involving construction of sine wave,
then signal clipping, sequencing and concatenation as shown
in Fig. 2 is used to construct the SB1.5 in TI’s real-time Code
Composer Studio (CCS) programming environment.
Different from the approach used in [3]
however, as shown in
Fig. 1, we have not implement the full Pyramid algorithm.
Block diagram showing our contribution in this paper is
shown in Fig. 3. After constructing the SB1.5 wavelet,
samples of the SB1.5 wavelet are then exported to Matlab, and
used to construct FIR filters, useful for AI preprocessing
applications. The main reason for selecting the SB1.5 wavelet
for our design in this paper is that, it is a biorthogonal and
symmetric wavelet, which gives it the desirable property of
being a linear phase wavelet [7]. Hence, FIR filter that results
from the SB1.5 wavelet will be linear phase. Phase linearity is
an excellent property for filters deployed in many applications
in AI including data compression and modulation, computer
vision, image processing and in AI robot vision and target
tracking applications [8]. Section II of the paper shows our
Clipped signal
Sequencer
=
Fig. 2 Schematic of the Spline Biorthogonal 1.5
wavelet design for the C28x DSP
C
1
(k)
C
0
(k)
d
0
(k)
x(n)
h(n)
w(n)
h(n)
w(n)
Conventional full Mallat’s Pyramid Algor ithm (DWT) filter bank for J = 2 octaves
Fig. 1. Comparison of our SB1.5 wavelet-based FIR filter for AI
application discussed in this paper compared to full Pyramid algorithm
166
2018 IEEE First International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)
978-1-5386-9555-5/18/$31.00 ©2018 IEEE
DOI 10.1109/AIKE.2018.00037
results and the design of FIR filter for AI applications. Section
III is conclusion of the paper.
II. DESIGN OF FIR FILTERS BASED ON THE SPLINE
BIORTHOGONAL 1.5 WAVELET AND C28XIOT DSP FOR
ARTIFIC IAL INTELLIGENCE A
PPLICATIONS
A generic IIoT edge device, the TMS320C2000 C28x
powerline communication (PLC) modem is used to show our
distributed computing approach used in this paper. The C28x
PLC modem is attached to a PC running CCS. The advanced
signal processing method described in Fig. 2 is used to
construct the SB1.5 wavelet using Embedded C and the result
is shown in Fig. 4. This is used to signify the distributed edge
computing for AI application at the edge of the IIoT network.
To show distributed edge computing at the IIoT fog layer,
125
samples of the SB1.5 wavelet is exported to Matlab using
Excel.csv file. The exported wavelet samples are then used to
construct low-pass (LP) and high pass (HP) filters of order 20
suitable for use in AI preprocessing applications. Matlab ‘fir1’
(FIR filter) toolbox is used at this layer since it is assumed that
fog layer devices can run more compute intensive applications
such as Matlab. Kaiser widow is used. A Kaiser window
allows better control over passband and stopband ripples
when compared to other window types. The designed LP and
HP FIR filters using SB1.5 wavelet samples are obtained and
plotted in Fig. 5. Results shows that the filters have the desired
linear phases with LP and HP characteristics. To evaluate the
performances of the designed FIR filters, sine waves of 150
Hz, 600 Hz, 2.8 kHz and 3.4 kHz respectively are generated
and passed through the filters using their fast Fourier
transforms (FFTs). Results for LP and HP FIR filters are
shown in Fig. 6. The FIR LP performs by filtering out the
higher frequency 2.8 kHz and 3.4 kHz signals and allows
lower frequency signals. Similarly, the HP FIR filter performs
by filtering out the lower frequency 150 Hz and 600 Hz
signals and allows the high frequency signals.
III. CONCLUSION
In this paper, a distributed computing approach that will
enable generic, low-cost, low-memory, DSPs to participate in
distributed computing for AI applications at edges of large
scale IoT networks is discussed. Real-time C28x DSP is used
with Embedded C to design the SB1.5 wavelet at the edge
layer and Matlab is used at the fog layer of IIoT system to
construct FIR filter suitable for AI applications out of the
constructed SB1.5 wavelet. Future work will include complete
design of the both wavelet and filter at the edge layer for AI
applications.
REFERENCES
[1] J. Szalai, F. Mozes, “Intelligent Digital Signal and Feature Extraction
Methods”, Springer Int’l Publishing, 2016
[2] R. Oshana, “DSP Software Development Techniques for Embedded
and Real-Time Systems”, Elsevier, 2006
[3]
Y. Guo et’al, “VLSI Implementation of Fast Discrete Wavelet
Transform Algorith with Reduced Complexity”, IEEE, 2001.
[4] B. Dickson, “How Do You Bring Artificial Intelligence form the Cloud
to the Edge?”, online, available,
www.thenextweb.com/contributors/2017/08/21
[5] Texas Instruments, “Digital Control Developer Forum – Digital
Control Systems Group”, Texas Instruments, 2000
[6] M. J. Pont, “Embedded C”, Addison Wesley, 2002.
[7]
Wavelet Browser, “Wavelet Biorthogonal 1.5”, online, available,
http://wavelets.pybytes.com/wavelet/bior1.5/ March 2018
[8] H. Kennedy, “Multidimensional Digital Smoothing Filters for Target
Detection”, Journal of Sig. Proc., vol. 114, Sept. 2015
Edge Layer Computing for Artificial
Intelligence in large networks:
Distributed Task at Edge Layer:SB1.5
Mother Wavelet construction using
low-level machine language due to
computing resource constraint at
network edges
Fog Layer Computing for Artificial
Intelligence in large networks:
Distributed Task at Fog Layer:Adaptive
Pyramid Algorithm by generating only
FIR filter from constructed wavelet.
Filtering for AI applications. More
computing resource exist at this layer
Cloud Layer Computing for Artificial
Intelligence in large networks:
Distributed Task at Cloud Layer:
Complete Pyramid Algorithm
implementation: Full multi-resolution
analysis (MRA), not implemented in
this paper.
Fig. 3 Block diagram showing the design of the AI preprocessing FIR filter at the edge and fog layer of IIoT system discussed in this paper
Fig. 5. High Pass (left) and Low Pass (right) C28x DSP Spline
Biorthogonal 1.5 wavelet-based FIR filter showing linear phase
Fig. 6. Designed FIR filters work by allowing only high (HPF) and
low (LPF) frequency signals
DAC Voltage Amplitude
Fig. 4. Spline Biorthogonal wavelet constructed for AI applications using
low-level Embedded C for C28x real-time DSP at the edge of large scale
(SG) network
167
... Modern artificial intelligence (AI) techniques have recently been used effectively to improve solutions in multiple application fields, to name a few: the medical field, industrial field, automotive, and so on [1][2][3]. ...
... Recently, AI-based approaches have also been applied in applications in the field of large-scale distribution [1,2]. Specifically, the scientific community is currently investigating the development of intelligent solutions capable of making the management of large-scale food supermarkets easier, providing an effective out-of-stock issue, customer sentiment monitoring, etc. [1,2]. ...
... Recently, AI-based approaches have also been applied in applications in the field of large-scale distribution [1,2]. Specifically, the scientific community is currently investigating the development of intelligent solutions capable of making the management of large-scale food supermarkets easier, providing an effective out-of-stock issue, customer sentiment monitoring, etc. [1,2]. Through the use of modern approaches based on AI or an AI-cloud, the modern advanced solutions for the management of large-scale distribution offer a high level of customization of business processes to create an "intelligent agent" capable of increasing profits, reducing inefficiencies and optimizing warehouse stock [2][3][4]. ...
GAIA: Great-Distribution Artificial Intelligence-Based Algorithm for Advanced Large-Scale Commercial Store Management
Article
Full-text available
  • May 2022
Today, the intelligent management of market stores in the large distribution field represents one of the most difficult tasks to address, considering the various problems to be managed. Specifically, from the classic issues of managing out-of-stock to the reconstruction of customer sentiment and the optimal management of shelves, scientific research has placed considerable effort on producing robust and efficient solutions to the aforementioned problems. In this context, modern deep learning techniques have allowed for the development of intelligent and adaptive systems capable of automating and significantly improving the management of a large-scale distribution market. Specifically, the authors have designed and implemented an innovative full pipeline that integrates modern deep learning technologies. More in detail, an innovative pipeline embedding a visual AI-based engine for customer sentiment assessment merged with a deep framework for stock management and market store cashflow monitoring is proposed. The innovative proposed system has been tested and validated in a large-scale distribution supermarket, confirming the effectiveness of the proposed solution. Specifically, in the performed testing sessions, the designed pipeline was able to show ad hoc visual customer sentiment assessment with an accuracy of 95% as well as intelligent stock monitoring with an accuracy of 93% in cross validation.
View
... The current digital transformation of industrial production has increased the need for processing data for several purposes, improved quality control [1], optimized production process control [2] and more detailed digital twins [3] representing the most common. Life cycles of industrial machinery are typically in the range of decades so that retrofitting and up-cycling have to be addressed [4]. In this paper, a case study is presented which demonstrates the viability of a low-cost setup monitoring industrial punching processes to improve resource planning and scheduling by process data. ...
... The results for different training sets and the introduced parameters are shown in Table III. As the results only slightly differ between validation and test set, Figure 3 shows the accuracy, sensitivity and precision for the validation set ordered by the training sets (1)(2)(3)(4) and divided between limited and full. ...
Mel Spectrogram Analysis for Punching Machine Operating State Classification with CNNs
Conference Paper
  • Sep 2021
Data driven analysis and optimization of production processes has become a pivotal instrument to use enterprise resources more efficiently and to improve product quality. However, availability and quality requirements still limit the prevalence of big data and learning techniques in industrial applications. Therefore, retrofitting sensors to brownfield systems has been suggested as a solution to acquire relevant real-time process data. In this paper, a low-cost retrofit approach to analyze the operating state of manually operated punching machines based on sound analysis is presented. The machine operating states provide additional information about the metal forming process, required for the enterprise resource planning (ERP) system to optimally schedule orders in prefabrication and plan available resources. As an analysis tool, a transfer learning approach with a convolutional neural network was used to assess data accuracy and prediction results. The input data consists of Mel Spectrogram images acquired by sound sensors retrofitted to the punching machines. The experiments show that the adapted EfficentNet-B0 achieves an accuracy, sensitivity, and precision of approximately 98 % on unseen data in real environment thus demonstrating the applicability of the implemented system.
View
IoT Video Delivery Optimization Through Machine Learning-Based Frame Resolution Adjustment
Article
  • May 2024
Providing acceptable video quality in the Internet of Things (IoT) implementation poses a significant challenge, mainly when the application is performed on low-cost and low-power devices. This research focuses on developing a frame resolution adjustment system that maintains the frame rate value of video delivery in wireless IoT environments with resource-constrained devices. Consistent frame rates prevent motion lag and data loss, improving user experience. The system works by predicting the upcoming throughput values using machine learning methods to adjust the sensing parameter, which is the resolution of the video frame to be captured by camera nodes. Hence, the proposed system is equipped with a file size estimator to estimate the size of the next video frame and then adjust the resolution in accordance with the throughput prediction. In this research, we conducted extensive experiments to evaluate the accuracy of the file size estimator and the throughput prediction. The experiment generated a dataset to evaluate throughput prediction and file size estimator model. The evaluation results for the file size estimator showed a Mean Absolute Percentage Error (MAPE) of 6.73% in the experiment using 317 frames with video resolutions between 72p and 720p. Experiments were also conducted to compare several machine learning methods for predicting throughput values. Compared to Long Short-Term Memory (LSTM) and Autoregressive Integrated Moving Average (ARIMA), Simple Exponential Smoothing (SES) outperforms the others with the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) values. Building upon these findings, we implemented the frame resolution adjustment system using SES as the method for predicting the upcoming throughput values. Finally, we demonstrated that the proposed system can maintain the frame rate according to the threshold set by the system while the resolution is being maximized, thereby addressing the challenges of maintaining video quality in resource-constrained IoT environments.
View
View
Data Engineering for the Factory of the Future: From Factory Floor to the Cloud – Part 1: Performance Evaluation of State-of-the-Art Data Formats for Time Series Applications
Chapter
  • Jan 2023
In this chapter, the benefits that can be derived by using different existing data formats for industrial IoT (IIoT) and factory of the future (FoF) applications are analyzed. For factory floor automation, in-depth performance evaluation in terms of storage memory footprint and usage advantages and disadvantages are provided for various traditional and state-of-the-art data formats including: YAML, Feather, JSON, XML, Parquet, CSV, TXT, and Msgpack. Benefits or otherwise of using these data formats for cloud based FoF applications including for setting up robust Delta Lakes having very reactive bronze, silver, and gold data tables are also discussed. Based on extensive literature survey, this chapter provides the most comprehensive data storage performance evaluation of different data formats when IIoT and FoF applications are considered. The companion chapter, Part II, provides an extensive Pythonlibraries and examples that are useful for converting data from one format to another.
View
Data Engineering for the Factory of the Future, Multimedia Applications and Cyber-Physical Systems: Part 2 – Algorithms and Python-Based Software Development for Time-Series Data Format Conversion
Chapter
  • Jan 2023
This chapter is the companion chapter to “Part 1: State-of-the-Art Time-Series Data Formats Performance Evaluation.” In this chapter, algorithms for converting data from one format to other formats are presented. To implement the algorithms, existing open-source Python libraries are used extensively, and where needed, new Python routines for converting data formats are developed. It is envisaged that the algorithms and Python libraries and routines that are freely provided in this chapter will be useful for data engineers, data scientists, and for industrial IoT, cyber-physical systems (CPS), multimedia, and big data practitioners who are on the quest to use different types of data formats that are compatible with memory-constrained factory floor IoT devices. It will also be useful for Delta Lake and big data engineers, who are on the quest for delivering robust bronze, silver, and gold data lakes in the cloud.
View
Regeneration of discrete signals missing samples in the internet of things applications at digital information transmitting via infocommunication channels
Article
  • Jan 2021
The paper discusses a method for recovering missing samples of an analog signal during transmission over communication channels in applications of the Internet of Things. The aim of the work is to obtain a mathematical description of the procedure for restoring the values of the signal samples from the output of the analog sensor on the receiving side, which were not transmitted in order to reduce the load on data transmission channels. The procedure is based on the well-known principles of adaptive signal processing, based on the dynamic determination of the parameters of digital filters based on the assessment of the least-mean-square (LMS) deviation of the signal passing through the filter from a reference signal obtained in one way or another. A feature of the proposed method is the solution of the inverse problem of restoring the samples of the original signal with the known parameters of the filter and the reference signal. In this work, the problem of skipping and restoring samples of a discrete signal is formulated, an expression is obtained for the objective function of the method for restoring missing discrete samples, as well as an expression for iterative restoration by Newton's method of the values of the samples of the original analog signal on the receiving side, which were not transmitted via the data transmission channel. The conditions for the applicability of the method are established, which consist in the a priori known parameters of the reference signal and the digital filter, which are determined in advance from the known characteristics of the original signal. Filtration and transmission of electrocardiogram signals through communication channels, for which an electrocardiogram can be obtained as a reference form, as the norm for healthy patients, is considered as a problem for the solution of which the proposed method is applicable. The practical significance of the proposed method lies in the organization of distributed computing for IoT systems, for which it is critically important to ensure energy savings of an autonomous power source for sensors and reduce the load on data transmission channels.
View
A Journey of Artificial Intelligence and Its Evolution to Edge Intelligence
Chapter
  • Feb 2022
The progressions in the innovations and the expansion in the computerized scaling down are making gadgets become more intelligent. The development of Internet of Things (IoT) and the cloud platform have made things stunningly better. Moving all information to the cloud for handling has steadily neglected to meet the continuous prerequisite of IoT benefits because of high network traffic and delay. The restrictions in cloud platform in resource allocation, service providing, and delay in transmission prompt us to move from cloud to edge. Edge computing (EC) moves the computation part from the cloud to the edge nodes (ENs). This will considerably improve the quality of service (QoS) of the IoT programs that demand less latency. With the forward leaps in deep learning, recent research has seen a blasting of artificial intelligence (AI) applications in various fields like suggestion systems, decision systems, and surveillance systems. The rise of the artificial intelligence in the edge computing has ended up being main focus as it boosts up the speed and number of the IOT applications. Edge computing that pushes processing and services from the network center to the network edge, widely accepted as a productive solution. The outcome is edge AI, or edge knowledge (EI) is starting to get a huge measure of interest. The research on edge intelligence is only in the starting stage. We do a comprehensive survey of the recent research efforts on evolution of EI, the security challenges encountered by distributed ENs as they are more defenseless against attacks for shortened computing equipment and storage. The incredible learning capacity of AI empowers the framework to recognize malignant assaults more precisely and effectively.KeywordsArtificial intelligenceEdge nodesEdge computingIoT
View
Design of a Secure Blockchain-Based Toll-Tax Collection System
Chapter
  • Feb 2022
The most advanced application of the Electronic Toll Collection (ETC) system is to collect the Toll-Tax Amount (TA) without slowing down a vehicle’s speed at the toll plazas of the national highways. A few existing ETC systems suffer from various unexpected activities such as data security, transparency of the stored data, the privacy of users, and data immutability as these systems perform in a centralized platform. Blockchain is a secure technology for its nascent features such as decentralization, transparency, and data security. In this paper, a Blockchain-based Automated Toll-Tax Collection System (BATCS) has been proposed. The proposed system can collect an appropriate TA without stopping the vehicle while it passes the toll plaza. While vehicles cross the toll plaza, the predefined amount of tax will be deducted automatically from the bank account. The smart contract can authenticate the vehicle data and collect TA automatically at toll plazas. This research work provides Security, Trust, Transparency, and Privacy (STTP) in the field of the ETC system. The significant benefits of the BATCS concerning the RFID-based system are less fuel consumption and more time-saving for a vehicle. It also provides the zero-waiting time in the queuing line of the toll plazas.KeywordsAutomated toll-tax collection systemBlockchain applicationDecentralized electronic toll collection systemIntelligent internet of vehicular thingsSmart contracts
View
ICICOS: Industrial Cyber Intelligent Control Operating System for Cloud and Edge Computing
Conference Paper
  • Aug 2021
We introduce ICICOS, a specific cloud and edge computing platform that provides industrial automation and artificial intelligence services. This platform is based on IEC61131-3 programming standard that used to replace traditional Programmable Logic Controller (PLC). As is known to all, PLC has been playing an important role during the years of industrial automation revolution, we call it the Third Industrial Revolution. But the limited computing power of this device is not able to support artificial intelligence well, which cannot support deep learning algorithms. While different variations and implementations of controllers have been created over the last decade, ICICOS focuses on virtualization technology of industrial automation. It brings many benefits, including: the standardized electrical programming language brings a lot of users; the backup redundancy of virtual technology enhances the stability of the system; the concentration of computing power makes it competent for reasoning and learning of artificial intelligence.
View
Multidimensional Digital Smoothing Filters for Target Detection
Article
Full-text available
  • Sep 2015
  • SIGNAL PROCESS
Recursive, causal and non-causal, multidimensional digital filters, with infinite impulse responses and maximally flat magnitude and delay responses in the low-frequency region, are designed to negate correlated clutter and interference in the background and to accumulate power due to dim targets in the foreground of a surveillance sensor. Expressions relating mean impulse-response duration, frequency selectivity and group delay, to low-order linear-difference-equation coefficients are derived using discrete Laguerre polynomials and discounted least-squares regression, then verified through simulation.
View
VLSI implementation of Mallat's fast discrete wavelet transform algorithm with reduced complexity
Conference Paper
Full-text available
  • Feb 2001
This paper proposes a novel VLSI architecture to compute the DWT (discrete wavelet transform) coefficients using Mallat's algorithm with reduced complexity. We studied the commonality embedded in the mirror low-pass and high-pass filters of the algorithm and use a PLA as an address generator (PAG) to load the data for cascaded FIR computation. By using an embedded downsampling process in the control signal design, we reduced the complexity by saving storage and computation. The prototyping design is implemented and fabricated using the AMI 1.5 micron CMOS process through the MOSIS service
View
Intelligent Digital Signal Processing and Feature Extraction Methods
Chapter
  • May 2016
Intelligent systems comprise a large variety of applications, including ones based on signal processing. This field benefits from considerable popularity, especially with recent advances in artificial intelligence, improving existing processing methods and providing robust and scalable solutions to existing and new problems. This chapter builds on well-known signal processing techniques, such as the short-time Fourier and wavelet transform, and introduces the concept of instantaneous frequency along with implementation details. Applications featuring the presented methods are discussed in an attempt to show how intelligent systems and signal processing can work together. Examples that highlight the cooperation between signal analysis and fuzzy c-means clustering, neural networks and support vector machines are being presented.
View
DSP Software Development Techniques for Embedded and Real-Time Systems
Article
  • Jan 2006
Developing embedded and real-time DSP applications is a complex and often daunting process, influenced by a wide range of parameters and issues. This introduction to DSP software development for embedded and real-time systems guides engineers and software developers through the complicated world of embedded DSP by clearly explaining how to use digital signal processors efficiently. Robert Oshana, a highly regarded expert with decades of experience in the management and development of real-time embedded systems, covers design principles from processor architectures and basic theory to the selection of appropriate languages and algorithms. In this book, you will find practical guidelines, diagrammed techniques, tool descriptions, and code templates for developing and optimizing DSP software and firmware. Integration and testing of DSP systems are covered, in addition to thorough discussions of: Multicore SoC architecture DSP software designs, Power optimization techniques, Hard real-time vs. soft real-time systems, Debugging DSP systems, Cache optimization tips, Future trends in Embedded DSP, A case study of Software Performance Engineering, And more! Book jacket.
View
How Do You Bring Artificial Intelligence form the Cloud to the Edge?
  • B Dickson
B. Dickson, "How Do You Bring Artificial Intelligence form the Cloud to the Edge?", online, available, www.thenextweb.com/contributors/2017/08/21
  • Mar 2018
  • Wavelet Browser
Wavelet Browser, "Wavelet Biorthogonal 1.5", online, available, http://wavelets.pybytes.com/wavelet/bior1.5/ March 2018