Signal Data Research Articles

Photonic integrated coherent beam combiner based on MMI and the SPGD algorithm.

Atmospheric turbulence severely degrades the optical wavefront of a propagating beam, which greatly reduces the coupling efficiency of free-space optical (FSO) receivers. Among the various methods to mitigate the effects, the use of a multi-channel receiver is more convenient and economical. After passing through the multi-channel receiver, multiple single-mode fibers (SMFs) are output and need to be combined. In this paper, we propose photonic integrated coherent beam combiners based on multimode interference (MMI) and the stochastic parallel gradient descent (SPGD) algorithm, which avoids detecting the light out of each channel and adding the data signal in the electrical domain. First, we propose a 4-channel coherent beam combiner based on a 4×1 MM, and about 21 iterations of the SPGD algorithm are required to enhance the combined optical power to a maximum of 96%. Furthermore, we demonstrate a combination of 16 beams using five 4×1 MMIs, which requires 140 iterations to enhance the combined power to 89%. This study offers theoretical insights to enhance the integration of FSO communication systems.

The strength of the phylogenetic signal in syntactic data

While phonological change has played a central role in assessing linguistic relatedness since the nineteenth century, the usefulness of syntactic change for this purpose has remained debated – despite recent work on the question with a variety of results. In our study, we analyze the phylogenetic signal of syntactic data using state-of-the-art Bayesian algorithms and the SSWL database (Koopman 2012–). With the phylogenetic model, we infer a minimally biased family tree. We find that, generally, the phylogenetic signal in the syntactic dataset is low. The model fails to infer larger-order subgroupings that would be found further back in time. This is in contrast to the clear-cut groupings we can obtain from running this type of model on phonological databases. This raises the question how well these syntactic properties encode phylogenetic information. As it stands, the model fails to provide evidence for strong phylogenetic signal despite the rich dataset and methods.

Supervised learning study on ground classification and state recognition of agricultural robots based on multi-source vibration data fusion

In agricultural environments, recognizing the walking ground and state of tracked mobile robots is a complex and challenging task, influenced by clay conditions and other external environmental disturbances. Therefore, this paper proposes a novel data processing method and efficient classifier. Firstly, the noise signals on the left and right sides of the collected robot are averaged, and a time-wavelet-time domain transformation is performed using the Mallat algorithm to achieve nonlinear enhancement of data features and signal denoising. Secondly, the Gramian Angular Summation Fields (GASF) is introduced to transform sequence data into single-channel images, capturing the periodicity and similarity of time series. Next, the images of three sets of sequences are stacked in the channel dimension in RGB format, thus achieving feature fusion of multi-source data. Finally, a supervised learning classifier named Attention-fused Residual Convolutional Neural Network (ANR-CNN) is proposed. Here, the combination of channel and spatial attention mechanisms captures important features in the feature map in both channel and spatial dimensions. The convolutional residual structure enhances feature transmission, improving the model's classification accuracy. Experimental results demonstrate that the proposed data augmentation method effectively enhances model performance, and the classification accuracy of ANR-CNN reaches 92.35%. This implies accurate recognition of the walking ground and state of tracked mobile robots in agricultural environments.

Conversational agent in HCI a review

Nowadays, AI technology is developing rapidly and slowly covering all areas of life. AI facilitates different parts of our lives and provides us with a lot of help. For example, in learning, students can acquire knowledge more conveniently through AI, and buyers can find suitable goods more conveniently through AI when shopping. At the same time, more and more technology is used in the field of voice agents, which allows humans to enjoy a lot of better services. In this article, we will study to better understand "how to understand human natural language and how the repository of knowledge is built." In the article we build with examples and deep learning models (CNN and RNN) through databases. Through repeated research and analysis, we can find that there are some limitations in this paper, such as the single learning model and the insufficient elaboration of data analysis and signal system technology. But at the same time, we also found a lot of future application prospects that voice agents can develop, it can be applied in many fields, such as finance, medical care, education and so on. For example, in children's education, parents can use voice agents to set time limits and monitor their children's progress. Existing digital interactive storytelling systems have limitations in terms of available storybooks and hand-crafted issues. Voice agents are becoming more popular in everyday scenarios, and more users are adopting devices like Siri and Google Assistant. In the future, conversational agents are expected to play an important role in oral communication with users.

Extrema-Triggered Conversion for Non-Stationary Signal Acquisition in Wireless Sensor Nodes

While wireless sensor node (WSNs) have proliferated with the rise of the Internet of Things (IoT), uniformly sampled analog–digital converters (ADCs) have traditionally reigned paramount in the signal processing pipeline. The large volume of data generated by uniformly sampled ADCs while capturing most real-world signals, which are highly non-stationary and sparse in information content, considerably strains the power budget of WSNs during data transmission. Given the pressing need for intelligent sampling, this work proposes an extrema pulse generator devised to trigger ADCs at significant signal extrema, thereby curbing the volume of data points collected and transmitted, and mitigating transmission power draw. After providing a comprehensive signal-theoretic rationale, we construct and experimentally validate these circuits on a system-on-chip field-programmable analog array in a 350 nm complementary metal-oxide-semiconductor (MOS) process. Operating within a power range of 4.3–12.3 µW (contingent on the input bandwidth requirements), the extrema pulse generator has proven to be capable of effectively sampling both synthetic and natural signals, achieving significant reductions in data volume and signal reconstruction error. Using a nonideality-resilient reconstruction algorithm, that we develop in this work, experimental comparisons between extrema and uniform sampling show that extrema sampling achieves an 18-fold lower normalized root mean square reconstruction error for a quadratic chirp signal, despite requiring 5-fold fewer sample points. Similar improvements in both the reconstruction error and effective sampling rate objectives are found experimentally for an electrocardiogram signal. Using both theoretical and experimental methods, this work demonstrates the potential of extrema-triggered systems for extending Pareto frontiers in modern, resource-constrained sensing scenarios.

Automation and Computerization of (Bio)sensing Systems.

Sensing systems necessitate automation to reduce human effort, increase reproducibility, and enable remote sensing. In this perspective, we highlight different types of sensing systems with elements of automation, which are based on flow injection and sequential injection analysis, microfluidics, robotics, and other prototypes addressing specific real-world problems. Finally, we discuss the role of computer technology in sensing systems. Automated flow injection and sequential injection techniques offer precise and efficient sample handling and dependable outcomes. They enable continuous analysis of numerous samples, boosting throughput, and saving time and resources. They enhance safety by minimizing contact with hazardous chemicals. Microfluidic systems are enhanced by automation to enable precise control of parameters and increase of analysis speed. Robotic sampling and sample preparation platforms excel in precise execution of intricate, repetitive tasks such as sample handling, dilution, and transfer. These platforms enhance efficiency by multitasking, use minimal sample volumes, and they seamlessly integrate with analytical instruments. Other sensor prototypes utilize mechanical devices and computer technology to address real-world issues, offering efficient, accurate, and economical real-time solutions for analyte identification and quantification in remote areas. Computer technology is crucial in modern sensing systems, enabling data acquisition, signal processing, real-time analysis, and data storage. Machine learning and artificial intelligence enhance predictions from the sensor data, supporting the Internet of Things with efficient data management.

Design and Implementation of Mobile Application for CNN-Based EEG Identification of Autism Spectrum Disorder

Autism spectrum disorder (ASD) is a disorder of the nervous system from birth and during infancy. This disorder affects children's development, making it difficult for nerve function to develop, and causes the child concerned to have difficulty in fostering social relationships. Early detection of children with ASD is needed so that treatment is fast and on target. Currently, facilities and research on early diagnosis of ASD patients through EEG signals are still very few, requiring much cost and more effort to analyze EEG signals in examinations related to ASD detection cases. This study proposes a mobile phone application that can distinguish people living with ASD and normal data signals based on asynchronous EEG brain signals. This research also produces a preprocessing algorithm and BCI2000 EEG data signal so that it can be automated using Python. This research also produces an output model, namely the Deep Learning Convolutional Neural Network, which is deployed using Python-Flask so that the diagnosis of EEG signals with ASD and normal patients can be used on various platforms through restAPI. This research is also expected to help the community and support the diagnosis of ASD sufferers so that they can be handled appropriately. Data for ASD sufferers and normal data were correctly classified into the appropriate class. Handling this disease requires close and integrated cooperation, so this ASD classification will be very helpful for patients and can make a diagnosis in a faster time, enabling patients to receive targeted treatment and therapy.

An intelligent financial data mining system using a fuzzy clustering multimedia approach

In order to improve the effect of financial data mining, this paper analyzes the financial data mining system combined with fuzzy clustering multimedia tool algorithm, builds an intelligent model to intelligently process financial data, and studies a multi-layer financial data protection structure model. According to the propagation characteristics of the financial data signal at the uniform cutoff and the theoretical knowledge of the electron microscopic motion, this paper analyzes the calculation formulas of the reflected power and the absorbed power of the financial data to the cutoff. Moreover, this paper improves the effect of fuzzy analysis of financial data and builds a financial data mining system based on fuzzy clustering multimedia tool. The simulation study shows that the financial data mining system based on fuzzy clustering multimedia tool proposed in this paper can effectively improve the effect of financial data mining.

Stress appraisal in the workplace and its associations with productivity and mood: Insights from a multimodal machine learning analysis.

Previous studies have primarily focused on predicting stress arousal, encompassing physiological, behavioral, and psychological responses to stressors, while neglecting the examination of stress appraisal. Stress appraisal involves the cognitive evaluation of a situation as stressful or non-stressful, and as a threat/pressure or a challenge/opportunity. In this study, we investigated several research questions related to the association between states of stress appraisal (i.e., boredom, eustress, coexisting eustress-distress, distress) and various factors such as stress levels, mood, productivity, physiological and behavioral responses, as well as the most effective ML algorithms and data signals for predicting stress appraisal. The results support the Yerkes-Dodson law, showing that a moderate stress level is associated with increased productivity and positive mood, while low and high levels of stress are related to decreased productivity and negative mood, with distress overpowering eustress when they coexist. Changes in stress appraisal relative to physiological and behavioral features were examined through the lenses of stress arousal, activity engagement, and performance. An XGBOOST model achieved the best prediction accuracies of stress appraisal, reaching 82.78% when combining physiological and behavioral features and 79.55% using only the physiological dataset. The small accuracy difference of 3% indicates that physiological data alone may be adequate to accurately predict stress appraisal, and the feature importance results identified electrodermal activity, skin temperature, and blood volume pulse as the most useful physiologic features. Implementing these models within work environments can serve as a foundation for designing workplace policies, practices, and stress management strategies that prioritize the promotion of eustress while reducing distress and boredom. Such efforts can foster a supportive work environment to enhance employee well-being and productivity.

DeepRetroMoCo: deep neural network-based retrospective motion correction algorithm for spinal cord functional MRI.

There are distinct challenges in the preprocessing of spinal cord fMRI data, particularly concerning the mitigation of voluntary or involuntary movement artifacts during image acquisition. Despite the notable progress in data processing techniques for movement detection and correction, applying motion correction algorithms developed for the brain cortex to the brainstem and spinal cord remains a challenging endeavor. In this study, we employed a deep learning-based convolutional neural network (CNN) named DeepRetroMoCo, trained using an unsupervised learning algorithm. Our goal was to detect and rectify motion artifacts in axial T2*-weighted spinal cord data. The training dataset consisted of spinal cord fMRI data from 27 participants, comprising 135 runs for training and 81 runs for testing. To evaluate the efficacy of DeepRetroMoCo, we compared its performance against the sct_fmri_moco method implemented in the spinal cord toolbox. We assessed the motion-corrected images using two metrics: the average temporal signal-to-noise ratio (tSNR) and Delta Variation Signal (DVARS) for both raw and motion-corrected data. Notably, the average tSNR in the cervical cord was significantly higher when DeepRetroMoCo was utilized for motion correction, compared to the sct_fmri_moco method. Additionally, the average DVARS values were lower in images corrected by DeepRetroMoCo, indicating a superior reduction in motion artifacts. Moreover, DeepRetroMoCo exhibited a significantly shorter processing time compared to sct_fmri_moco. Our findings strongly support the notion that DeepRetroMoCo represents a substantial improvement in motion correction procedures for fMRI data acquired from the cervical spinal cord. This novel deep learning-based approach showcases enhanced performance, offering a promising solution to address the challenges posed by motion artifacts in spinal cord fMRI data.

A Novel Method to Identify Mild Cognitive Impairment Using Dynamic Spatio-Temporal Graph Neural Network.

Resting-state functional magnetic resonance imaging (rs-fMRI) has been widely used in the identification of mild cognitive impairment (MCI) research, MCI patients are relatively at a higher risk of progression to Alzheimer's disease (AD). However, almost machine learning and deep learning methods are rarely analyzed from the perspective of spatial structure and temporal dimension. In order to make full use of rs-fMRI data, this study constructed a dynamic spatiotemporal graph neural network model, which mainly includes three modules: temporal block, spatial block, and graph pooling block. Our proposed model can extract the BOLD signal of the subject's fMRI data and the spatial structure of functional connections between different brain regions, and improve the decision-making results of the model. In the study of AD, MCI and NC, the classification accuracy reached 83.78% outperforming previously reported, which manifested that our model could effectively learn spatiotemporal, and dynamic spatio-temporal method plays an important role in identifying different groups of subjects. In summary, this paper proposed an end-to-end dynamic spatio-temporal graph neural network model, which uses the information of the temporal dimension and spatial structure in rs-fMRI data, and achieves the improvement of the three classification performance among AD, MCI and NC.

Smart Aggregate‐Based Concrete Stress Monitoring via 1D CNN Deep Learning of Raw Impedance Signals

A 1‐dimensional convolutional neural network (1D CNN) model is developed to process deep learning of raw impedance signals for smart aggregate (SA)‐based concrete stress monitoring. First, the framework of the SA‐based stress monitoring using deep learning of raw impedance signals is described. An impedance measurement model is designed for a SA‐embedded concrete body under compression. A 1D CNN model is developed for deep learning of raw impedance signals corresponding to various stress levels. Three approaches for concrete stress monitoring are designed to deal with data availability, signal noises, and untrained stress levels. Second, a few SA‐embedded concrete cylinders are experimented to measure impedance signals under various stress levels. Finally, the performance of the proposed method is extensively evaluated by investigating the feasibility of the K‐fold cross‐validation to deal with the data availability and the effects of signal noises and untrained data on the accuracy of stress estimation in the SA‐embedded concrete cylinders.

Optimization of lane based signalized intersections through vissim at outer ring road Bengaluru

Signalized intersections are indispensable parts of urban traffic networks. In developing countries, there are many types of vehicles, which causes heterogenous traffic conditions. Lack of lane discipline, varying composition, and a variety of vehicle situations are all possible issues that get worse with time. For such a dynamic traffic situation, microsimulation modeling is appropriate. The traffic flow characteristics of a particular road are frequently used in traffic simulation research on signalized intersections. The methodology outlines a systematic process for optimizing traffic signals using VISSIM software, including data collection, calibration, and signal timing adjustments at the Iblur and Silkboard Junction, Bengaluru, Karnataka, India. Results show significant improvements in key performance metrics after optimizing signal timings, leading to reduced congestion and smoother traffic flow. The study underscores the significance of accurate data collection for developing and validating simulation models. The successful development and validation of a simulation model in VISSIM, along with efforts to enhance intersection performance through signal timing adjustments, have been achieved. Future research directions include expanding calibration efforts, incorporating real-time field data, and exploring adaptive signal control systems.

Roman stone masonry walls: The application of Ground Penetrating Radar to ancient structures

An investigation on estimating Roman stone masonry wall thickness using non-invasive Ground Penetrating Radar (GPR) and Light Detection and Ranging (LiDAR) technology is presented in this paper. Historical building conservation and structural evaluation require correct wall thickness measurements. The methodology encapsulates data collection, signal processing, and interpretation techniques, including the use of local frequency attributes tailored for historical masonry structures. The main perimeter wall at the Circus of Maxentius, Rome, Italy, is used as the case study. The results indicate that GPR is capable of accurately estimating the thickness of Roman stone masonry walls. By conducting a comparative analysis against a wall section with a known thickness, it has been demonstrated that GPR is a dependable and precise method for conducting archaeological and architectural research. This study highlights the potential of using GPR attributes as a non-destructive investigative methodology in the field of heritage preservation. Future research includes extracting and improving further attributes and applying this approach to other historical structures.

Design of non-electrical protection device for 300Mvar-class large-scale phase-regulating units

Abstract This study investigates the role of non-electrical protective devices in forecasting hazards for large 300Mvar class phase shifter units, which face overvoltage and overcurrent stresses under severe faults, distorting their internal magnetic fields. Utilizing migration learning, the research extracts target and auxiliary data to train autoencoders with sparse constraints. A deep learning-based DSAE-BP online recognition network is constructed using a backpropagation neural network. This network predicts potential safety hazards in large-scale phase-regulating units by analyzing data signals from connected sensors. Experimental results show delay time errors of less than 20ms and ripple rates between 1.40%-1.65% across varied current and voltage conditions, demonstrating the device’s accuracy and stability in fault prediction.

Current Transformer Condition Online Monitoring Platform Based on Big Data

Abstract As an important power equipment indispensable to the normal operation of the power grid, the good or bad working condition of the current transformer directly affects the operational efficiency of the whole power grid. In this paper, an online monitoring platform based on big data technology has been developed to monitor the current status of transformers. First of all, for the temperature of the transformer, through the decoupling of the heat generation mode of the transformer, the state monitoring method based on fiber optic temperature measurement technology and optical multiplexing technology is proposed, and the overall scheme of transformer state monitoring is designed. The data signal of the transformer’s status is collected and processed, and a fault state diagnosis model is constructed based on the decision tree algorithm. Finally, according to the data requirements of the current transformer, an online monitoring platform for transformer status has been constructed using big data technology. Through the simulation test, the variation of ratio error of this paper’s monitoring method is less than 0.60%, and the variation of phase error is less than 0.75 percent, which is in line with international requirements. The average loading time of the monitoring platform is between 123.591s~143.911s, the average loading speed is less than 13s, the average throughput is between 241ops/sec ~257ops/sec, and the average latency of the read and upload operations is 24.225ms. The current transformer condition monitoring platform in this paper has good stability, the overall performance is excellent, and it provides a good solution for the research of the current transformer condition monitoring platform provides practical support for the research of current transformer condition monitoring platform.

Pencirian Isyarat Data Muzik yang Terhasil dari Alat Muzik Tradisional Menggunakan Ciri Fraktal

Musical instruments are usually distinguished by their sound produced through human perception which may lead to misinterpretation due to auditory perception bias and other disturbances. Therefore, recognition using music signals is carried out to help characterize signals from different musical instruments. Fractal analysis is a mathematical tool used to study complex and irregular patterns in various systems. In this study, fractal analysis was used to study and analyze musical notes signal data from different instruments. The fractal analysis method used is the box counting method. The traditional musical instruments involved in this study are the seruling, cak lempong, kompang, and gambus. Matlab software was used to analyze the musical data signal. First, the fractal dimension of the music data signal in the form of time domain is calculated. Then, the mean and standard deviation of the fractal dimension values were determined to recognize different musical instruments. Additionally, different image resolutions and box sizes are also used to calculate the fractal dimension of musical instrument from the time domain data. The error of best fit line, E will also be calculated to ensure the reliability of box counting dimensions using leastsquares regression method. The results show that the value of the fractal dimension for all 18 data is between 1.2636 to 1.7543. In terms of musical instrument recognition, the recognition of seruling and kompang using mean fractal dimension is successful. However, this method is less suitable for identification for cak lempong and gambus due to the high standard deviation. By using different image resolutions and box sizes, the accuracy of fractal dimension values will be affected. Increasing these parameters increases the accuracy of the results. The results of the study show that an image with a resolution of 1024 x 1024 pixels and a scaling factor of 9 is suitable to analyze the fractal characteristics of musical instrument data signals by using the box counting method.

Application of IoT network for marine wildlife surveillance

Abstract Every day of the week, wireless communication is almost all around us. The Internet of Things (IoT) is a standard protocol used to describe the rapidly advancing technology in which almost every electronic device is or may be connected to the Internet. These electronic gadgets constantly provide data signals to the gateways, which satellites such as those in Low Earth Orbit may transmit. Because of these networks’ limited resources and the IoT, these transactions must be completed with the least amount of latency and data loss possible. We also analyze the performance implications of implementing RF-based powering for such a network. The techniques presented in this paper may benefit the scientific community and industry in general when it comes to the dynamic distributed parameter allocation methodology for IoT network devices. We will also discuss how research on animals and the natural environment has been impacted by IoT breakthroughs, in particular, animal sensors’ limits and incapacity to broadcast from everywhere. Our analysis illustrates the most effective data transmission technique and establishes the bounds of these restrictions. Furthermore, the physics of the RF channel plays a critical role in the uncertainty of the channel as well as the amount of energy harvested. By employing simulation based on the physics of the RF channel, the article shows the performance of the system considering both the uncertainty of data arrival as well as the variability of the channel. The findings of the simulation show that the devices consume less energy overall as the signal-to-noise ratio rises. Furthermore, a timing factor of 10–15% is shown to be effective in maintaining a constant mean rate and increasing the energy efficiency of the system.

Generation and classification models of ultrasonic signals in aged cast austenitic stainless steel (CASS)

In this study, we attempted to generate new ultrasonic signals from thermally aged CASS specimens using a statistical-based model to augment the experimental data. A variational auto-encoder (VAE) model is adopted to generate the ultrasonic signals. To verify the quality of the generated data (signals), two ML algorithms (k-nearest neighbor and multi-layer perceptron algorithms) were used for classification with newly generated data for training and experimental data for testing. The results showed that new ultrasonic signals could be generated effectively with a small amount of experimental data, with the newly generated data showing features approximating those of the experimental data, indicating high classification accuracy rate for ultrasonic signals from aged CASS specimens. In addition, a sampling method for the generated model is suggested.

Development of a low-cost, compact, wireless, 16 - channel biopotential data acquisition, signal conditioning and arbitrary waveform stimulator.

The health and fitness of the human body rely heavily on physiological parameters. These parameters can be measured using various tools such as ECG, EMG, EEG, EOG, among others, to obtain real-time physiological data. Analysing the bio-signals obtained from these measurements can provide valuable information that can be used to improve health-care in terms of observation, diagnosis, and treatment. In bio-signal pattern recognition applications, more channels provide multiple information simultaneously. Different biosignal acquisition devices are available in the market, most of which are designed for specific signals like ECG, EMG, EEG etc The gain of the amplifiers and frequency of the filters are designed as per the targeted signals; due to which one device cannot be used for other signals. Also, most of the systems are wired system which is not comfortable for animal studies. In this paper, a low-cost, compact, wireless, 16 channel biopotential data acquisition system with integrated electrical stimulator is designed and implemented. There are several novel and flexible design approaches were incorporated in the proposed design like (1) It has user selectable digital filter in each channel based on the signal frequencies like ECG, EMG, EEG, EOG. The same system will be used to acquire different signals simultaneously. (2) It has variable gain with a configurable analog bandpass filter. (3) It can acquire signals from 4 patients simultaneously. (4) The system is capable to acquire signal from both two-electrode as well as three-electrode configurations. (5) It has integrated stimulator with trapezoidal, charge-balanced, biphasic stimulus output with near zero DC level and user selectable pulse duration or frequency of the stimulus. The developed system has the ability to acquire and transmit data wirelessly in real-time at a high transfer rate. To validate the performance of the system, tests were conducted on the acquired signals using a simulator.