Al-based Parkinson’s Disease Diagnosis with Word Level Speech Data using Advanced Signal Processing Techniques

This chapter describes some recent advances in signal processing as applied to NDT problems. This is an area that has made progress for over twenty years and its importance is gaining attention gradually, especially since the new advanced techniques in signal processing and pattern recognition.

The current research shows tremendous improvements in the business marketing processes because some problems are long‐term bond yields and macroeconomic data handling at a minimum level. Any industry can revolutionize business marketing processes if it takes a specific business marketing model to eliminate such deficiencies, examines the various elements that occur in them, and finds out how to fix them. As a result, some factors have to be controlled for in this research. Innovations and advancements in signal processing techniques on business processes occur spontaneously in business processes that are managed like this. In the below‐mentioned business improvement success factors, score, learning best, future creation, people involvement, goals setting, plan and develop is the most essential factor. The elimination of these factors causes some disruption in business marketing processes. These gaps cause problems in the field of science and technology‐based business marketing. The problem caused by these factors is the excess usage of two‐wheeler, which generates more vehicular crises. The smart helmet business is the only solution to this automotive crisis. But because some of the above problems occur to this business process marketing. Considering that some sensors to make smart helmets will develop the business in the name of this imperative, considering the factors of production are land, labour, capital, and entrepreneurship as the centre, this research introduces signal processing technology to make a helmet. The signal processing‐based helmet proposed here is constructive for business. This research suggests a smart helmet business with signal‐processing technology. This study highlights how adopting the smart helmet product might improve corporate marketing procedures. According to the results of our research, when people use this smart helmet product, depending on how well they can use it, that specific business rises to the top and falls to the bottom. These business marketing methods operate at a greater level and are profitable whenever their capacity rises. The effectiveness of this smart helmet declines as accidents increase and corporate marketing procedures degrade. Since our production now depends on whether the intelligent helmets are beneficial or harmful and destructive. The analytical technique described below can be used to find them.

Characteristic movements of human body parts ranging from eye twitches to limbs jerky movements have been used for decades by physicians as clinical indicators of certain neurological disorders. Through a multidisciplinary research approach, our team, composed of medical experts, signal-processing specialists, wireless sensing experts, and computer scientists, aims at developing a sophisticated framework for automatic characterization of certain clinical conditions via identification of a proposed unique sequence (a signature pattern) of limb movements in relation to other body parts. We argue that a set of movement data collected from human subjects via strategically located movement sensors fused with other supporting data, such as gyroscopic movements and relative locations of sensors, can be processed by advanced intelligent signal processing techniques. Using medical expert systems fed with knowledge provided by the contributing medical experts this can be used to characterize and classify typical and atypical human movements. The collected data is then processed using machine learning algorithms which is trained to automatically detect and characterize a set of movement disorders and classify them into specific clinical diagnosis such as specific types of seizures. In particular, our work ambitiously aims at developing a prototype proof-of-concept seizure remote monitoring and detection system. This would demonstrate the applicability of our developed methodology in real-life scenarios, using commercial of-the-shelf wireless sensing platforms coupled to our intelligent expert-based signal-processing platform. We believe that the outcomes of this applied research will pave the roads for new methods in clinical diagnosis of various neurological diseases and monitoring progress and outcome of treatment that will, in turn, reduce human suffering and medical costs. Further, when coupled with our wireless technology and positioning methods, DC-MOVE can initiate or trigger an alerting response that could be life-saving.

Previous studies have indicated heart sounds contain information for the detection of partially occluded coronary arteries. In this study, recordings of diastolic heart sound segments were analyzed by using three advanced signal processing techniques; the Autoregressive (AR), the Autoregressive Moving Average (ARMA), and the Minimum-Norm (Eigenvector) methods. In order to enhance the diastolic heart sounds and eliminate background noise, the Adaptive Line Enhancer (ALE) method was used as a preprocessor. These advanced signal processing techniques were used to estimate the model parameters. The poles of the AR, ARMA and Minimum-Norm methods were used to diagnose patients as diseased or normal-Results showed that normal and abnormal records were correctly identified in 32 of 38 (36 patient) cases.

: Acoustic signal processing has long been the domain of electrical and mechanical engineers, physicists, and mathematicians. However, more and more biologists and psychologists are starting to use advanced signal processing techniques and analyses, especially with the influx of the many signal processing programs now available. What is lacking for many of these new users is an understanding of the theoretical underpinnings of different techniques. This has happened because the learning curve can be rather steep, especially for those in the biological and psychological sciences, and the theoretical constructs are often ignored or deemed too difficult to comprehend. This also applies to many students and beginning researchers with a physical science background, since various ideas and methodologies are scattered across different texts and manuscripts. The goal of this project is to write a book on animal bioacoustics that brings together ideas, concepts and methods that are often found in diverse texts and manuscripts. We will approach basic principles from the perspective of processing and analyzing acoustic signals emitted by animals. The book will be aimed at advanced undergraduates and beginning graduate students people with some background in sound analysis who come from a background in either an animal communication or signal processing. Our goal will be to make a practical guide by which people can understand and use the tools we have, rather than an theoretical exposition of the frontiers of our field. Such a book that is written with animal bioacousticians in mind is strongly needed in order for the field to grow in a good way. By making bioacoustic signal processing techniques available to a wider audience, we aim to advance the understanding and utility of marine bioacoustics.

Over the last decade, Computer-Aided Diagnosis (CAD) systems have been provided significant research focus by researchers. CAD systems have been developed in order to minimise visual errors, to compensate manual interpretation, and to help medical staff to take decisions swiftly. These systems have been considered as powerful tools for a reliable, automatic, and low-cost monitoring and diagnosis. CAD systems are based on analysis and classification of several physiological signals for detecting and assessing different diseases related to the corresponding organ. The implementation of these systems requires the application of several advanced signal processing techniques. Specifically, in cardiology, CAD systems have achieved promising results in providing an accurate and rapid detection of cardiovascular diseases (CVDs). Particularly, the number of works on signal processing field for impedance cardiography (ICG) signals starts to grow slowly in recent years. This paper presents a review study of signal processing techniques applied to the ICG signal for the denoising, the analysis, the classification and the characterisation purposes. This review is intended to provide researchers with a broad overview of the currently used signal processing techniques for ICG signal analysis, as well as to improve future research by applying other recent advanced methods.

The accurate diagnosis of cardiovascular conditions relies heavily on Electrocardiogram (ECG) signals, yet persistent interference challenges, including baseline wander, powerline interference, and muscle artifacts, compromise clinical accuracy. This study comprehensively explores cutting-edge preprocessing techniques aimed at addressing multifaceted challenges in ECG signal processing. Investigating noise removal, baseline correction, feature extraction, arrhythmia detection, and heart rate variability (HRV) analysis, we synthesize insights from recent research to provide a thorough understanding of current state-of-the-art methodologies. Each facet plays a crucial role in enhancing the reliability of ECG signals for accurate cardiovascular diagnoses. In a landscape where clinical accuracy is paramount, this review critically assesses advancements in signal processing techniques, shedding light on innovative strategies and potential breakthroughs.

Recent advancements in signal processing techniques have enabled non-invasive Brain-Computer Interfaces (BCIs) to control assistive devices, like robotic arms, directly with users' EEG signals. However, the applications of these systems are currently limited by the low signal-to-noise ratio and spatial resolution of EEG from which brain intention is decoded. In this study, we propose a motor-imagery (MI) paradigm, inspired by the mechanisms of a computer mouse, that adds an additional "click" signal to an established 2D movement BCI paradigm. The additional output signal increases the degrees of freedom of the BCI system and may enable more complex tasks. We evaluated this paradigm using deep learning (DL) based signal processing on both healthy subjects and stroke-survivors in online BCI tasks derived from two potential applications: clicking on virtual targets and moving physical objects with a robotic arm in a continuous reach-and-grasp task. The results show that subjects were able to control both movement and clicking simultaneously to grab, move, and place up to an average of 7 cups in a 5-minute run using the robotic arm. The proposed paradigm provides an additional degree of freedom to EEG BCIs, and improves upon existing systems by enabling continuous control of reach-and-grasp tasks instead of selecting from a discrete list of predetermined actions. The tasks studied in these experiments show BCIs may be used to control computer cursors or robotic arms for complex real-world or clinical applications in the near future, potentially improving the lives of both healthy individuals and motor-impaired patients.

Psychological analysis related to voluntary reciprocal trust games were obtained using functional magnetic resonance imaging (fMRI) hyperscanning for 44 pairs of strangers throughout 36 trust games (TG) and 16 control games (CG). Hidden Markov models (HMMs) are proposed to train and classify the fMRI data acquired from these brain regions and extract the essential features of the initial decision of the first player to trust or not trust the second player. These results are evaluated using the different versions of the multifold cross-validation technique and compared to other speech data and other advanced signal processing techniques including linear classification, support vector machines (SVMs), and HMMs. With above 80% classification accuracy for HMM as compared to no more than 66% classification accuracy of a linear classifier and SVM, the corresponding experimental results demonstrate that the HMMs can be adopted as an outstanding paradigm to predict the psychological financial (trust/non-trust) activities reflected by the neural responses recorded using fMRI. Additionally, extracting the specific decision period and clustering the continuous time series proved to increase the classification accuracy by almost 20%.

In this paper, a set of multi-channel sEMG was given to examine the coordination between quadriceps and hamstring. To extract valuable muscle information and also describe muscles’ activities from noisy multi-channel sEMG, advanced signal processing techniques are required to cancel additive noise, remove artifacts and reduce crosstalkes among electrodes. In the last two decades, Independent Component Analysis (ICA) techniques have been successfully used to remove crosstalkes among electrodes. Besides that, ICA are multi-channel adaptive signal processing techniques and do not require any prior information of the signal. In our study, ICA is used to eliminate the crosstalks among the electrodes. To improve the performance of our system, spectral descriptors were also used to describe muscle activities. Many experiments and various simulations have been conducted. Our experimental results showed that ICA can remove the cross-talks and further improve the signal quality while three different spectral descriptors which are energy, MPF and VMF can work together to describe a muscle activity effectively.KeywordsMulti-channel sEMGICASpectral Curve DescriptorQuadricepsHamstring

Round timbers are extensively used as utility poles in Australia for electricity distribution and communication. Lack of information on their conditions results in great difficulties on asset management for industries. Despite the development of various non-destructive testing (NDT) techniques for evaluating the condition of piles, few NDTs are reported for applications on timber poles. This paper addresses challenges and issues on development of NDTs for condition assessment and embedded length of timber poles. For this paper, it is mainly focusing on determining the embedded length of the pole considering loss of the sufficient embedment length is a main factor compromising capacity and safety of timber poles. Since it is impractical for generating longitudinal waves by impacting from the top of poles, utilising flexural wave from side impact on poles becomes attractive. However, the flexural wave is known by its highly dispersive nature. In this paper, one dimensional wave theory, guided wave theory and advanced signal processing techniques have been introduced in order to provide a solution for the problem. Two signal processing techniques, namely short kernel method and continuous wavelet transform, have been investigated for processing flexural wave signals to evaluate wave velocity and embedment length of timber poles in service.

In this paper, demagnetization detection in permanent magnet generators is analyzed using advanced signal processing techniques. The merits of these methods are thoroughly compared against the commonly adopted short-time Fourier transform analysis. Moreover, traditional signal processing techniques may not be suitable for fault detection when the machine operates at variable speed. Under such condition, interference between the fundamental frequency of the machine and the fault harmonic can lead to false alarms. Simulation results demonstrate effective performance and feasibility of the proposed methods for demagnetization detection of permanent generators operating under non-stationary conditions.

This paper investigates the feasibility of the distance measuring equipment (DME)-based alternative position, navigation, and timing architecture using the recent advances on DME/N (normal) signal processing techniques; an improved DME/N pulse waveform and learning-based multipath mitigation algorithm. This paper evaluates the achievable DME range accuracy by using the advanced signal processing techniques, and provides the analysis on the required augmentation of ground DME stations in a selected test region in contiguous United States.

<p>Street trees are widely recognised to be an essential asset for the urban environment, as they bring several environmental, social and economic benefits [1]. However, the conflicting coexistence of tree root systems with the built environment, and especially with road infrastructures, is often cause of extensive damage, such as the uplifting and cracking of sidewalks and curbs, which could seriously compromise the safety of pedestrians, cyclists and drivers.</p><p>In this context, Ground Penetrating Radar (GPR) has long been proven to be an effective non-destructive testing (NDT) method for the evaluation and monitoring of road pavements. The effectiveness of this tool lies not only in its ease of use and cost-effectiveness, but also in the proven reliability of the results provided. Besides, recent studies have explored the capability of GPR in detecting and mapping tree roots [2]. Algorithms for the reconstruction of the tree root systems have been developed, and the spatial variations of root mass density have been also investigated [3].</p><p>The aim of this study is, therefore, to investigate the GPR potential in mapping the architecture of root systems in street trees. In particular, this research aims to improve upon the existing methods for detection of roots, focusing on the identification of the road pavement layers. In this way, different advanced signal processing techniques can be applied at specific sections, in order to remove reflections from the pavement layers without affecting root detection. This allows, therefore, to reduce false alarms when investigating trees with root systems developing underneath road pavements.</p><p>In this regard, data from trees of different species have been acquired and processed, using different antenna systems and survey methodologies, in an effort to investigate the impact of these parameters on the GPR overall performance.</p><p> </p><p><strong>Acknowledgements</strong></p><p>The authors would like to express their sincere thanks and gratitude to the following trusts, charities, organisations and individuals for their generosity in supporting this project: Lord Faringdon Charitable Trust, The Schroder Foundation, Cazenove Charitable Trust, Ernest Cook Trust, Sir Henry Keswick, Ian Bond, P. F. Charitable Trust, Prospect Investment Management Limited, The Adrian Swire Charitable Trust, The John Swire 1989 Charitable Trust, The Sackler Trust, The Tanlaw Foundation, and The Wyfold Charitable Trust. This paper is dedicated to the memory of our colleague and friend Jonathan West, one of the original supporters of this research project.</p><p> </p><p><strong>References</strong></p><p>[1] J. Mullaney, T. Lucke, S. J. Trueman, 2015. “A review of benefits and challenges in growing street trees in paved urban environments,” Landscape and Urban Planning, 134, 157-166.</p><p>[2] A. M. Alani, L. Lantini, 2019. “Recent advances in tree root mapping and assessment using non-destructive testing methods: a focus on ground penetrating radar,” Surveys in Geophysics, 1-42.</p><p>[3] L. Lantini, F. Tosti, Giannakis, I., Egyir, D., A. Benedetto, A. M. Alani, 2019. “A Novel Processing Framework for Tree Root Mapping and Density Estimation using Ground Penetrating Radar,” In 10th International Workshop on Advanced Ground Penetrating Radar, EAGE.</p>

In this tutorial paper, we systematically present the fundamental operating principles and analytical details of the discrete Fourier transform based signal processing techniques for the TDM MIMO FMCW millimeter-wave (mmWave) automotive radars. The mmWave radars provide a key sensing capability to support safety features of the conventional and autonomous vehicles. Automotive radar sensors are used to detect presence and location of the objects of interest to derive comprehensive and accurate knowledge of road conditions and surrounding environments. Automotive radars are subjected to an increasing demand to provide high-resolution measurements in the range-Doppler-azimuth-elevation domains. Therefore, the current state-of-the-art automotive radars commonly employ MIMO technologies, resulting in a large block of multidimensional data to process in real time through a long chain of signal processing algorithms. Detailed coverage on the fundamental radar signal processing techniques are scattered in a large body of literature for classical radar systems. Currently, there is no tutorial available that covers the technical details of the latest TDM MIMO FMCW radar technology, making it extremely hard for new researchers in the field of automotive mmWave radars. This paper contains sufficient technical details to serve as a tutorial. It can help lay a solid analytical foundation to facilitate exploration and development of advanced radar signal processing techniques for automotive applications. The algorithmic details and analytical results presented in this paper can be readily applied to both real-time implementation and post-processing. Simulation and experimental results are presented in this paper to validate analytical derivations and to demonstrate the capabilities of the TDM MIMO radar sensor in practical implementations.