Real-time Experiments Research Articles

LiDAR-based estimation of bounding box coordinates using Gaussian process regression and particle swarm optimization

Camera-based object tracking systems in a given closed environment lack privacy and confidentiality. In this study, light detection and ranging (LiDAR) was applied to track objects similar to the camera tracking in a closed environment, guaranteeing privacy and confidentiality. The primary objective was to demonstrate the efficacy of the proposed technique through carefully designed experiments conducted using two scenarios. In Scenario I, the study illustrates the capability of the proposed technique to detect the locations of multiple objects positioned on a flat surface, achieved by analyzing LiDAR data collected from several locations within the closed environment. Scenario II demonstrates the effectiveness of the proposed technique in detecting multiple objects using LiDAR data obtained from a single, fixed location. Real-time experiments are conducted with human subjects navigating predefined paths. Three individuals move within an environment, while LiDAR, fixed at the center, dynamically tracks and identifies their locations at multiple instances. Results demonstrate that a single, strategically positioned LiDAR can adeptly detect objects in motion around it. Furthermore, this study provides a comparison of various regression techniques for predicting bounding box coordinates. Gaussian process regression (GPR), combined with particle swarm optimization (PSO) for prediction, achieves the lowest prediction mean square error of all the regression techniques examined at 0.01. Hyperparameter tuning of GPR using PSO significantly minimizes the regression error. Results of the experiment pave the way for its extension to various real-time applications such as crowd management in malls, surveillance systems, and various Internet of Things scenarios.

A methodology for setting-up a low-cost quadrotor experimental platform

Quadrotor vehicles are captivating devices that serve as valuable platforms for testing and developing nonlinear control algorithms due to the pronounced nonlinearities in their dynamics models. Additionally, these platforms are employed for a range of functions, spanning from entertainment to industrial applications. In engineering practice, it is imperative to develop a controller for a quadrotor to fulfill a desired task. Nevertheless, we must perform real-time experiments to assess the controller’s performance effectively. Regardless, this task is challenging due to hardware and software limitations hindering the setup of the experimental platform and deployment of the controller. Therefore, it is essential to have a functional experimental platform for validating the performance of different control methodologies. With this objective in mind, this manuscript develops a step-by-step procedure for setting up a low-cost quadrotor testbed. To better understand the process, tutorial videos were generated to walk the reader through the steps required to implement a given controller successfully. Furthermore, an academic example employing a new Observer-based Proportional Integral Derivative controller is applied to demonstrate the effectiveness of the proposed methodology. The experimental results verify the novel method’s efficiency despite the inherent hardware and software limitations or the influence effect of the inevitable endogenous and exogenous perturbations.

CUSTOMER EXPERIENCE MANAGEMENT: THE KEY TO THE SUSTAINABLE DEVELOPMENT OF ORGANIZATION

The article explores the importance of customized customer interaction management for personalizing their experience in real time through understanding their needs and using reflective innovative tools, in particular, a manifestation of cognitive marketing – neuromarketing. The key stages of effective customer experience management are highlighted, including understanding customer needs, providing a consistent experience, using technology and continuous improvement based on feedback, and customer experience management tools such as CRM systems, experience evaluation and the use of social media as a platform for the influence of a brand that takes on the role of a full-fledged influencer. The article also discusses the difference between conducting marketing research from the point of view of traditional marketing and cognitive marketing. The main aspects of comparison were communication, attention, persuasion, repetition (reminder) and self-report. Data have been presented regarding the increase in willingness to purchase goods under the influence of neuromarketing technologies.

Targeting motor cortex high-excitability states defined by functional connectivity with real-time EEG–TMS

We tested previous post-hoc findings indicating a relationship between functional connectivity (FC) in the motor network and corticospinal excitability (CsE), in a real-time EEG-TMS experiment in healthy participants.We hypothesized that high FC between left and right motor cortex predicts high CsE.FC was quantified in real-time by single-trial phase-locking value (stPLV), and TMS single pulses were delivered based on the current FC. CsE was indexed by motor-evoked potential (MEP) amplitude in a hand muscle. Possible confounding factors (pre-stimulus μ-power and phase, interstimulus interval) were evaluated post hoc.MEPs were significantly larger during high FC compared to low FC. Post hoc analysis revealed that the FC condition showed a significant interaction with μ-power in the stimulated hemisphere. Further, inter-stimulus interval (ISI) interacted with high vs. low FC conditions. In summary, FC was confirmed to be predictive of CsE, but should not be considered in isolation from μ-power and ISI. Moreover, FC was complementary to μ-phase in predicting CsE. Motor network FC is another marker of real-time accessible CsE beyond previously established markers, in particular phase and power of the μ rhythm, and may help define a more robust composite biomarker of high/low excitability states of human motor cortex.

Discovery of the toxicity-related quality markers and mechanisms of Zhi-Zi-Hou-Po decoction based on Chinmedomics combined with differentially absorbed components and network pharmacology

Ethnopharmacological relevanceZhi-Zi-Hou-Po decoction (ZZHPD), as a representative traditional Chinese medicine (TCM) formula for the treatment of depression, has frequently triggered hepatorenal toxicity in recent years. However, its toxic effect, material basis, and underlying mechanisms have not been fully elucidated. Aim of the studyTo explore the hepatorenal toxicity-material basis-quality markers (Q-markers) and multiple mechanisms of ZZHPD. Materials and methodsZZHPD-induced rat model of toxicity was evaluated by behavioral indicators, biochemical parameters, and histopathological sections. Then, UHPLC-Q-Exactive Orbitrap-MS combined with multivariate data analysis was utilized to identify the endogenous differential metabolites and the prototype components of ZZHPD in the plasma. A comprehensive strategy integrating in-house library, diagnostic ions, Compound Discover software, and network databases was constructed to identify the chemical constituents of ZZHPD. Additionally, the differentially absorbed components of ZZHPD were screened out based on the spectrum-effect relationship (toxic state and normal state), feature extraction of exogenous components, and variable influence on projection (VIP). Further, Chinmedomics and network pharmacology oriented by differentially absorbed components were performed to predict toxicity-related Q-markers and core targets, as well as relevant pathways. Finally, the binding ability between components and targets was predicted using molecular docking, and the mRNA expression of core target genes was determined by real-time qPCR experiment. ResultsZZHPD exerted significant hepatotoxicity and nephrotoxicity in rats accompanied by body weight loss, abnormal biochemical indicators, and pathologic characteristics with mild inflammation and cell damage. The results of plasma metabolomics indicated that 22 differential metabolites interfered by ZZHPD mainly involved in primary bile acid biosynthesis, arginine and proline metabolism, phenylalanine metabolism and biosynthesis, sphingolipid metabolism, pyrimidine and purine metabolism. Firstly, 106 chemical substances of ZZHPD were identified, 44 of them were absorbed into the blood, mainly including 7 iridoid glycosides, 15 flavonoids, 5 lignans, and others. Then, the correlation analysis results suggested that 12 of 19 differentially absorbed constituents were highly correlated with 22 differential metabolites and recognized as potential Q-markers. Finally, 9 toxicity-related Q-markers were predicted and confirmed with better binding ability to 5 core targets (PTGS2, CASP3, TNF, PPARG, HMOX1), including 3 flavonoids (naringin, hesperidin, and neohesperidin), 2 iridoid glycosides (geniposide and genipin-1-β-D-gentiobioside), 2 lignans (honokiol and magnolol), organic acid (chlorogenic acid), and crocin (crocetin). The real-time qPCR results showed that the mRNA levels of CASP3, TNF-α, and PPARG significantly increased in the damaged liver. Combining metabolomics and network pharmacology results, the multiple mechanisms of toxicity might involve in oxidative damage, inflammation, and apoptosis pathways. ConclusionTaken together, the toxicity-related Q-markers of ZZHPD screened for the first time in this work were reliable, and the holistic intervention for hepatorenal toxicity further revealed the multi-component, multi-target, and multi-pathway features in TCM. The integrated approach provides a novel perspective for the discovery of toxicity/efficacy-related substances and mechanistic studies in TCM.

Mathematical modeling and application of IL-1β/TNF signaling pathway in regulating chondrocyte apoptosis.

Introduction: Mathematical model can be used to model complex biological processes, and have shown potential in describing apoptosis in chondrocytes. Method: In order to investigate the regulatory mechanisms of TNF signaling pathway in regulating chondrocyte apoptosis, a fractional-order differential equation model is proposed to describe the dynamic behavior and mutual interaction of apoptosis-related genes under the activation of TNF signaling pathway. Compared with the traditional molecular biology techniques, the proposed mathematical modeling has advantages to providing a more comprehensive understanding of the regulatory mechanisms of TNF signaling pathway in chondrocyte apoptosis. Result: In this paper, differentially expressed genes induced by IL-1β in human chondrocyte apoptosis are screened using high-throughput sequencing. It is found that they were significantly enriched in the TNF signaling pathway. Therefore, a mathematical model of the TNF signaling pathway is built. Using real-time PCR experiments, mRNA data is measured and used to identify the model parameters, as well as the correlation coefficient. Finally, the sensitivity of the model parameters is discussed by using numerical simulation methods, which can be used to predict the effects of different interventions and explore the optimal intervention strategies for regulating chondrocyte apoptosis. Discussion: Therefore, fractional-order differential equation modeling plays an important role in understanding the regulatory mechanisms of TNF signaling pathway in chondrocyte apoptosis and its potential clinical applications.

High speed 60 Gbps RGB laser based-FSOC link by incorporating hybrid PDM-MIMO scheme for indoor applications

Abstract Visible Light Communication (VLC) systems enhanced by red, green and blue (RGB) lasers are at the forefront of indoor technology, offering dynamic lighting, high-speed data transfer, and energy efficiency. This innovative combination not only revolutionizes connectivity and illumination but also ensures privacy and security, making it a game-changer for smart homes, offices, and various indoor applications. In our research, we introduce a polarization division multiplexing and Multiple Input Multiple Output based (PDM-MIMO) system that carries 60 Gbps of data over a transmission range of 500 m in free space Channels. The utilization of the cost-effective on-off key (OOK) modulation format is attributed to its affordability in our transmission scheme. For parallel data transmission, three laser diodes in RGB were utilized. To enhance both the transmission range and reduce the Bit Error Rate (BER), MIMO scheme is employed. Our study presents simulation outcomes, conducted using OptiSystemTM software, that focus on evaluating the bit error rates for the proposed PDM-MIMO link. Our findings demonstrate successful 60 Gbps data transmission over 350 m in FSO with an acceptable BER, reinforced by clear eye diagrams. Introducing MIMO expands the range to 500 m while improving BER, paving the way for real-time experimentation and research advancement.

Analyzing the challenges faced by recently qualified nurses in radiation therapy nursing at Japan’s National University Hospitals: Uncovering the determinants of difficulty

ObjectiveNewly graduated nurses embarking on careers in radiation therapy nursing at Japan’s National University Hospitals face a spectrum of challenges, many of which have received limited attention in existing literature. This study aimed to uncover the primary difficulties encountered by these nurses, with a specific focus on their implications for training and systematic education. MethodsEmploying a survey involving nurses from five prestigious medical institutions in Japan, we explored the real-time experiences and challenges within radiation therapy nursing. Our investigation concentrated on adverse events and the requisite knowledge for effective symptom management. The results illuminated a notable divergence in experiences among nurses, with particular challenges emerging in the treatment of head and neck cancers, especially when combined with chemotherapy. The data emphasized the pivotal role of certified nurses in offering support and knowledge transfer in complex cases, underscoring the importance of peer support and consultations. ResultsThe findings underscored a significant variance in experiences among nurses, with specific difficulties encountered in the management of head and neck cancers, particularly in conjunction with chemotherapy. The data highlighted the essential role of certified nurses in providing support and knowledge dissemination in challenging scenarios, underscoring the significance of peer support and consultations. ConclusionsThis study provides an overview of the landscape, highlighting the critical role of peer consultation and the need for advancements in the educational framework for radiation therapy nurses.

USER PERCEPTIONS BASED LEVEL OF SERVICE FOR UNCONTROLLED MID-BLOCK CROSSINGS USING TRAFFIC SURVEYS AND ITS REGRESSION ANALYSIS

The exponential growth of urban populations has led to a substantial increase in traffic on urban roads, prompting extensive research into optimizing road networks for vehicular traffic. However, there has been a noticeable lack of attention given to the safety and well-being of pedestrians. One particularly perilous scenario for pedestrians occurs at mid-block crossing locations where well-designed crosswalks are absent. In such areas, pedestrians are forced to identify safe crossing points, often with limited safety measures in place. Ensuring the safety, convenience, comfort, and minimal delay for pedestrians in these situations is imperative. To address this gap, a comprehensive evaluation of the quality of service at mid-block crosswalks is necessary. This research study focused on assessing the quality of service at non-signalized mid-block pedestrian crossings from the perspective of consumers. The analysis employed regression techniques and gathered data from four distinct mid-block crossing locations in different areas of Visakhapatnam. Data collection involved video image surveillance to obtain data on pedestrian quantities, volume-based characteristics, walking speeds, capacity, and gap sizes, complemented by questionnaires to capture real-time experiences and opinions of pedestrians. The questionnaire encompassed various variables affecting crossing quality, including demographic information and pedestrian perceptions of safety and comfort. Pedestrians rated these attributes on a scale of one to six, with their scores serving as variables for subsequent analysis. This approach seeks to ensure that pedestrians have the safest, most comfortable, and efficient means to cross the street while minimizing potential delays. Keywords:Pedestrian safety,Mid-block crossing,Quality of service,Urban road traffic,Crosswalk design, Consumer perspective,Data collection, ,Questionnaires,Perception,Safety measures,Comfort, Demographic information,,Efficiency,Delay mitigation,Regression analysis,Vehicular traffic optimization,Urbanization impact.

From PID to Set Point Weighted PID: A Teaching DC-DC Buck Converter Platform

This article presents a lowcost educational platform based on a DC-DC Buck Converter to implement real-time control laws for engineering students. The motivation for this work arises from what happened during the COVID-19 pandemic when students did not have access to laboratory equipment and instruments necessary for their academic development. Particularly in the subjects of electrical circuits, electronics, and control, there has been a significant drop in the development of projects. This work shows the Buck converter's modeling and design to build and program different control laws like the Proportional Integral Derivative and the Setpoint weighted PID. Real-time experiments show the performance of the DC-DC Buck converter. The control algorithms are implemented using the MatLab / Simulink programming platform under the Waijung real-time control environment and an STM32704 data acquisition card.

Real-Time Implementation of an Online Controller for the Walking of the NAO Robot

Practical problems for the implementation of a real-time controller for gaits subject to disturbances on the NAO robot are shown in this paper. Moreover, how to deal with them and carry out real-time practical stable walkings is explained. The robot is modeled with the Linear Inverted Pendulum (LIP) model, which is a simplified model that concentrates the mass of the robot in a single point and constrains the height of the Center of Mass to a straight line. The controller in charge of keeping a stable gait is the Model Predictive Controller (MPC). The MPC is perhaps the most used controller in legged robots due to its optimization over a time horizon and to the possibility of including constraints in the optimization problem. Furthermore, important notes about the implementation of real-time experiments with the NAO robot are discussed in this work. This work gives the first steps to achieve a real-time control using the Essential Model.

CRTC2 activates the epithelial–mesenchymal transition of diabetic kidney disease through the CREB-Smad2/3 pathway

BackgroundEpithelial–mesenchymal transition (EMT) plays a key role in tubulointerstitial fibrosis, which is a hallmark of diabetic kidney disease (DKD). Our previous studies showed that CRTC2 can simultaneously regulate glucose metabolism and lipid metabolism. However, it is still unclear whether CRTC2 participates in the EMT process in DKD.MethodsWe used protein‒protein network (PPI) analysis to identify genes that were differentially expressed during DKD and EMT. Then, we constructed a diabetic mouse model by administering STZ plus a high-fat diet, and we used HK-2 cells that were verified to confirm the bioinformatics research results. The effects that were exerted by CRTC2 on epithelial-mesenchymal transition in diabetic kidney disease through the CREB-Smad2/3 signaling pathway were investigated in vivo and in vitro by real-time PCR, WB, IHC and double luciferase reporter gene experiments.ResultsFirst, bioinformatics research showed that CRTC2 may promote EMT in diabetic renal tubules through the CREB-Smad2/3 signaling pathway. Furthermore, the Western blotting and real-time PCR results showed that CRTC2 overexpression reduced the expression of E-cadherin in HK-2 cells. The CRTC2 and α-SMA levels were increased in STZ-treated mouse kidneys, and the E-cadherin level was reduced. The luciferase activity of α-SMA, which is the key protein in EMT, was sharply increased in response to the overexpression of CRTC2 and decreased after the silencing of CREB and Smad2/3. However, the expression of E-cadherin showed the opposite trends. In the real-time PCR experiment, the mRNA expression of α-SMA increased significantly when CRTC2 was overexpressed but partially decreased when CREB and Smad2/3 were silenced. However, E-cadherin expression showed the opposite result.ConclusionThis study demonstrated that CRTC2 activates the EMT process via the CREB-Smad2/3 signaling pathway in diabetic renal tubules.

Deciphering Potential Molecular Signatures to Differentiate Acute Myeloid Leukemia (AML) with BCR::ABL1 from Chronic Myeloid Leukemia (CML) in Blast Crisis.

Acute myeloid leukemia (AML) with BCR::ABL1 has recently been recognized as a distinct subtype in international classifications. Distinguishing it from myeloid blast crisis chronic myeloid leukemia (BC-CML) without evidence of a chronic phase (CP), remains challenging. We aimed to better characterize this entity by integrating clonal architecture analysis, mutational landscape assessment, and gene expression profiling. We analyzed a large retrospective cohort study including CML and AML patients. Two AML patients harboring a BCR::ABL1 fusion were included in the study. We identified BCR::ABL1 fusion as a primary event in one patient and a secondary one in the other. AML-specific variants were identified in both. Real-time RT-PCR experiments demonstrated that CD25 mRNA is overexpressed in advanced-phase CML compared to AML. Unsupervised principal component analysis showed that AML harboring a BCR::ABL1 fusion was clustered within AML. An AML vs. myeloid BC-CML differential expression signature was highlighted, and while ID4 (inhibitor of DNA binding 4) mRNA appears undetectable in most myeloid BC-CML samples, low levels are detected in AML samples. Therefore, CD25 and ID4 mRNA expression might differentiate AML with BCR::ABL1 from BC-CML and assign it to the AML group. A method for identifying this new WHO entity is then proposed. Finally, the hypothesis of AML with BCR::ABL1 arising from driver mutations on a BCR::ABL1 background behaving as a clonal hematopoiesis mutation is discussed. Validation of our data in larger cohorts and basic research are needed to better understand the molecular and cellular aspects of AML with a BCR::ABL1 entity.

Saturated formation containment control for a heterogeneous multi-agent system with unknown perturbations

This work addresses formation containment control for a heterogeneous multi-agent system composed of first-order (FO) and second-order (SO) agents that can be either leader or follower agents. It is assumed that unknown but bounded disturbances perturb its dynamical model. An error-based version of a generalized proportional–integral observer (GPIO) is proposed to estimate these perturbations, and saturation functions, based on position measurement and estimated velocity errors, are designed to achieve the control objective. Specifically, it is shown that the leader agents converge to a desired geometric pattern following a desired trajectory simultaneously. Furthermore, the follower agents converge to the convex hull spanned by the leaders. The result applies to a group of robots in which a directed spanning tree gives the communication topology among the leaders with a root in the main leader. At the same time, each follower receives information from at least one leader agent, and the communication is directed. Real-time experiments and a comparison with a robust control technique exhibit the excellent performance of the proposed GPIO and control strategy in achieving formation containment control.

Hand-Breathe: Noncontact Monitoring of Breathing Abnormalities From Hand Palm

In post-covid19 world, radio frequency (RF)-based non-contact methods, e.g., software-defined radios (SDR)-based methods have emerged as promising candidates for intelligent remote sensing of human vitals, and could help in containment of contagious viruses like covid19. To this end, this work utilizes the universal software radio peripherals (USRP)-based SDRs along with classical machine learning (ML) methods to design a non-contact method to monitor different breathing abnormalities. Under our proposed method, a subject rests his/her hand on a table in between the transmit and receive antennas, while an orthogonal frequency division multiplexing (OFDM) signal passes through the hand. Subsequently, the receiver extracts the channel frequency response (basically, fine-grained wireless channel state information), and feeds it to various ML algorithms which eventually classify between different breathing abnormalities. Among all classifiers, linear SVM classifier resulted in a maximum accuracy of 88.1%. To train the ML classifiers in a supervised manner, data was collected by doing real-time experiments on 4 subjects in a lab environment. For label generation purpose, the breathing of the subjects was classified into three classes: normal, fast, and slow breathing. Furthermore, in addition to our proposed method (where only a hand is exposed to RF signals), we also implemented and tested the state-of-the-art method (where full chest is exposed to RF radiation). The performance comparison of the two methods reveals a trade-off, i.e., the accuracy of our proposed method is slightly inferior but our method results in minimal body exposure to RF radiation, compared to the benchmark method.

A narrowband active noise control system with coarse frequency estimator and spectrum shifter

The frequency of an internal synthetic reference signal that is inconsistent with that of the noise signal is a serious problem in narrowband active noise control (NANC) system. This is called frequency mismatch (FM), which severely deteriorates the performance of the system. To alleviate this problem, a multichannel feedback NANC system with a coarse frequency estimator and spectrum shifter is proposed in this paper. Rough estimations of multiple tones are provided by a coarse frequency estimator based on discrete Fourier transform (DFT) coefficients and fed into the spectrum shifter. Splitting the noise signal into several individual orthogonal reference signals by the spectrum shifter rather than internal generation can avoid FM problem. Because estimated frequency errors can be tolerated in the spectrum shifter but cannot be compensated by signal generators. Compared with existing methodologies, the proposed method relaxes the demand on the precision of the frequency estimator, and reduces the undesired delay in the frequency estimation by using smaller fast Fourier transform (FFT) blocks. Moreover, a computational complexity analysis of the proposed method indicates that the proposed method is advantageous in terms of computational complexity. Extensive simulations and real-time experiments were conducted to verify the superior noise reduction performance and faster convergence speed of the proposed method under different FM situations.

Remote Operation of Marine Robotic Systems and Next-Generation Multi-Purpose Control Rooms

Since 2017, NTNU’s Applied Underwater Robotics Laboratory has been developing an infrastructure for remote marine/subsea operations in Trondheim Fjord. The infrastructure, named the OceanLab subsea node, allows remote experimentation for three groups of assets: seabed infrastructure, surface or subsea vehicles/robots, and assets at remote experimentation sites. To achieve this task, a shoreside control room serves as a hub that enables efficient and diverse communication with assets in the field as well as with remote participants/operators. Remote experimentation has become more popular in recent years due to technological developments and convenience, the COVID-19 pandemic, and travel restrictions that were imposed. This situation has shown us that physical presence at the experimentation site is not necessarily the only option. Sharing of the infrastructure among different experts, which are geographically distributed, but participating in a single, local, real-time experiment, increases the level of expertise available and the efficiency of the operations. This paper also elaborates on the development of a virtual experimentation environment that includes simulators and digital twins of various marine vehicles, infrastructures, and the operational marine environment. By leveraging remote and virtual experimentation technologies, users and experts can achieve relevant results in a shorter time frame and at a reduced cost.

A - 175 EEG Phase Can be Predicted with Similar Accuracy across Cognitive States after Accounting for Power and SNR.

Electroencephalogram (EEG) phase can capture neural oscillation dynamics. Accordingly, EEG phase is a potential target for neurofeedback and brain-computer interfaces (BCIs). However, rigorous tests of the generalizability of real-time EEG phase are needed, requiring accurate phase estimates. We examined how cognitive states affect EEG phase prediction accuracy in the parieto-occipital alpha band. We identified datasets through public repositories. After preprocessing, we used the Educated Temporal Prediction Algorithm (ETP) to predict future peaks. We compared these predictions to the original signal, and defined accuracy from 0 to 100%. Our independent variable was cognitive state (eyes-open rest, eyes-closed rest, task), dependent variable was accuracy, and covariates were EEG instantaneous power and signal-to-noise ratio (SNR). We used a linear mixed-effects model, with random effects for dataset and individual. Across the 11 datasets, we had 543 participants and 1,641,074 predictions. There were no significant accuracy differences among the conditions (p < 1e-5), with a baseline accuracy of 59.07%. Power had an effect on accuracy, with a unit increase leading to a 13.1% increase in accuracy (p < 1e-5). SNR had an effect on accuracy, with an effect size of 0.46% (p < 1e-5), with a significant negative interaction with power with an effect size of -0.51% (p < 1e-5). Our results indicated that we could predict EEG phase accurately across cognitive conditions and datasets, with higher accuracy for high instantaneous band-power and SNR. Accordingly, real-time EEG phase experiments, closed-loop technologies, and BCIs should minimize external unwanted noise while targeting periods of high power, as opposed to manipulating experimental and cognitive conditions.

Speech data collection system for KUI, a Low resourced tribal language

&lt;p&gt;A new generation of speech translation technology is being developed to enable natural cross-language communication. Research efforts must focus on large vocabulary, spontaneous speech, and speaker variances to accommodate the varying demands of speech recognition technologies. These are important issues that need to be resolved for the general application of voice recognition in realistic settings. Most languages with limited resources don’t even have any speech data. Creating speech corpora is extremely difficult and time-consuming. Among all, KUI is regarded as one of the low-resource languages. In this paper, we developed the speech dataset for the KUI language to document and preserve their culture, tradition, and history for future generations. We also discuss the design, data collection procedures, and implementations and outline the different research possibilities using our KUI dataset. This paper mainly describes the GUI and method for the collection of KUI speech more quickly. In this section, the statistics of the people who helped and contributed to the collection of this KUI dataset have been provided. This study details a novel method of gathering data for any speech dataset. Using this process, we collected 60 hours of speech data sampled at 16 kHz by three different devices such as a Zoom recorder, Mobile, and Laptop from 80 different speakers. Each speaker contributed 500 sentences in the KUI language. A GUI application is designed to capture the speeches of numerous speakers in the KUI language. Several guidelines are proposed and used for the collection of the KUI speech dataset. All the guidelines are based on real-time experience gained during the data collection process by our team members.&lt;/p&gt;

Instance-based learning with prototype reduction for real-time proportional myocontrol: a randomized user study demonstrating accuracy-preserving data reduction for prosthetic embedded systems

This work presents the design, implementation and validation of learning techniques based on the kNN scheme for gesture detection in prosthetic control. To cope with high computational demands in instance-based prediction, methods of dataset reduction are evaluated considering real-time determinism to allow for the reliable integration into battery-powered portable devices. The influence of parameterization and varying proportionality schemes is analyzed, utilizing an eight-channel-sEMG armband. Besides offline cross-validation accuracy, success rates in real-time pilot experiments (online target achievement tests) are determined. Based on the assessment of specific dataset reduction techniques’ adequacy for embedded control applications regarding accuracy and timing behaviour, decision surface mapping (DSM) proves itself promising when applying kNN on the reduced set. A randomized, double-blind user study was conducted to evaluate the respective methods (kNN and kNN with DSM-reduction) against ridge regression (RR) and RR with random Fourier features (RR-RFF). The kNN-based methods performed significantly better (p < 0.0005) than the regression techniques. Between DSM-kNN and kNN, there was no statistically significant difference (significance level 0.05). This is remarkable in consideration of only one sample per class in the reduced set, thus yielding a reduction rate of over 99% while preserving success rate. The same behaviour could be confirmed in an extended user study. With k=1, which turned out to be an excellent choice, the runtime complexity of both kNN (in every prediction step) as well as DSM-kNN (in the training phase) becomes linear concerning the number of original samples, favouring dependable wearable prosthesis applications.Graphical abstract