Band Noise Research Articles

Noise from various types of heavy trucks and the influence from low-height solid safety barriers

Types of heavy trucks and their characteristics vary greatly, yet noise from these vehicles is often represented by a single heavy truck category for the purpose of predicting highway traffic noise. This paper presents a case study examining heavy truck pass-by events and their associated measured maximum broadband and 1/3-octave band noise levels, sorting the trucks by various attributes to determine if there are meaningful differentiations. The study further examines the measured heavy truck noise in the presence of a roadside solid safety barrier, installed to shield motorists from natural or man-made obstacles, and can also provide some noise reduction to nearby communities. Results with and without the shielding from solid safety barriers are presented.

Research on on-orbit relative radiometric calibration method based on solar diffuse reflector hyperspectral camera

Abstract In the original image data obtained by optical remote sensing satellite sensors, there is stripe noise caused by inconsistent probe response, which will seriously affect the application effect and accuracy of the image. The importance of relative radiometric calibration is that it can eliminate the stripe noise in the image, thus improving the quality and clarity of the image. In this paper, a relative radiometric calibration method based on the data of a solar diffuse reflector downloaded from the satellite is proposed. The relative radiation calibration coefficient is calculated by using the least square method by obtaining the calibration image of the on-board diffuse reflector covering all the detectors. To verify the method proposed in this paper, the on-board relative radiometric calibration experiment is carried out by using the on-orbit hyperspectral camera of a terrestrial ecological carbon monitoring satellite, and the calibration effect of the calibration coefficient on the original image is tested, and the relative radiometric calibration accuracy is quantitatively analyzed. The experimental results show that the calibration coefficient can effectively eliminate the band noise of the original hyperspectral image. From the quantitative evaluation, the signal-to-noise ratio index of the corrected hyperspectral image is greater than 200, and the generalized noise index is better than 3%, which achieves a good calibration effect and meets the requirements of high-quality remote sensing image application. It provides a reliable guarantee for quantitative remote sensing applications during the satellite’s on-orbit operation.

A study on impact of tinnitus masking on psychophysical and tinnitus tuning curve in participants with hearing impairment suffering from severe tinnitus

Background: Tinnitus can be treated by using different pedagogies of management approaches in which tinnitus masking has been acclaimed most evidence-based approach. Psychophysical tuning curve and tinnitus tuning curve explored as least interested procedures in tinnitus research. This noteworthy but nonspecific psychophysical domain may throw a light on need of the present research. Aim of the study was to find out the effect of tinnitus masking on Psychophysical tuning curve and tinnitus tuning curve. Method: A total of 30 native Bengali speaking participants were included in this study, having mean age of 45.9 years and SD was 6.46. All the participants had unilateral subjective tinnitus with Mild to Moderately severe sensorineural hearing loss. Quasi-experimental research design was used. Dual channel audiometer (MAICO MA 53) with supra-aural TDH 39 headphone was used for psychoacoustic measurements of tinnitus (including pitch matching, loudness matching, minimum masking level etc.) and to provide tinnitus masking therapy. MATLAB version 9.5 was used to develop noise to assess PTC and TTC using Sennheiser HD 201 headphone routed through MAICO MA 53 audiometer via stereo jack and cable. Tinnitus masking therapy was carried out for 30 sessions by using regimen of MML +20 dB of masking level for 30 minutes duration for each session with matched pitch. PTC and TTC were measured before and 30 sessions-after tinnitus masking therapy. PTC was measured using 1000 Hz pure tone at 10 dBSLl as reference followed by four narrow band noise with centre frequency of 500 Hz, 1000 Hz, 2000 Hz, 4000 Hz pertaining to 312 Hz band width as developed by MATLAB software. TTC was measured using the same noise with reference to matched tinnitus pitch. All the above-mentioned conditions forced choice procedure was carried out in dBHL frame work. Results: Wilcoxon sign rank test was used at 95% confidence level to check the influence of tinnitus masking therapy on PTC and TTC measures. Significant changes were portrayed at 1000 Hz and 4000 Hz respectively in PTC measure and at 500 Hz, 1000 Hz, 2000 Hz and 4000 Hz respectively in TTC measures. Conclusion: This study preliminarily provides information regarding influence on tinnitus pitch domains which has been psychoacoustically systematically measured as PTC and TTC. These two psychoacoustic signatures may be treated as prognostic biomarker of tinnitus management in future using replicable research using different methodology or using statistical basis of data mining. At that point conclusive remarks may not throw a clear indication based on the results found in this study.

Temporary Hearing Threshold Shift and Testing the Equal-Energy Hypothesis in a Harbor Porpoise (Phocoena phocoena) After Exposure to a Continuous Noise Band at 8 kHz, and a Revised TTS-Onset Function

Temporary Hearing Threshold Shift and Testing the Equal-Energy Hypothesis in a Harbor Porpoise (Phocoena phocoena) After Exposure to a Continuous Noise Band at 8 kHz, and a Revised TTS-Onset Function

Analysis of noise and its characteristics in avalanche photodiode

Avalanche photodiodes (APDs) produce noise during operation, which affects the device performance. However, the previous research on its noise is mainly theoretical analysis and is only reflected as optical noise. Therefore, according to the characteristics of APD material and the mechanism of noise generation, the main noise of the device is analyzed in this paper. First, the test method of noise in APDs is established, including testing of dark noise, optical noise, and multiplication noise in high frequency bands. The main noises in APDs are 1/f noise, thermal noise, shot noise, generation recombination noise, and multiplication shot noise, and shot noise is suppressed by Fermi–Dirac distribution and Coulomb action. Second, the reliability of APDs is evaluated by measuring and analyzing the noise parameters of the device through thermal aging experiments. It is concluded that the defects introduced by thermal aging can be reflected by the change in noise, which is consistent with the results in the literature. This method can comprehensively obtain the noise in APDs, which is helpful to improve the working efficiency, life, and reliability of the device.

Effects of propeller boss cap fins on hydrodynamics and flow noise of a pump-jet propulsor

As an underwater thruster, the pump-jet propulsor (PJP) exhibits low radiation noise but generates significant line spectral noise in the low-frequency band. In this paper, we equipped the PJP hub with two types of propeller boss cap fins (PBCF): one fixed and the other rotating with the rotor. The hybrid large eddy simulation and Reynolds-averaged Navier–Stokes method, along with the Ffowcs Williams-Hawkings (FW-H) equation, are employed to systematically analyze the hydrodynamics, exciting force, flow noise, and flow field of PJPs. The results indicate that the fixed PBCF improves the hydrodynamic performance and reduces the exiting force, raising the rotor's thrust coefficient by 9.22%–14.99%. The fixed PBCF also modifies the characteristics of line spectrum noise but causes an increase in the flow noise. The rotating PBCF increases the rotor's thrust coefficient by 2.03%–3.15%, decreasing both exciting force and line spectrum noise. For instance, at the advance coefficient of 0.8, its sound pressure level at the rotor frequency drops to 49.6%. Additionally, the rotating PBCF increases the pressure of the hub wake and effectively reduces the hub vortices' strengths. This paper provides a theoretical foundation for designing PJPs that enhance concealment and minimize vibrations and noise.

A 0.00179 mm2/Ch Chopper-Stabilized TDMA Neural Recording System With Dynamic EOV Cancellation and Predictive Mixed-Signal Impedance Boosting.

This article presents a digitally-assisted multi-channel neural recording system. The system uses a 16-channel chopper-stabilized Time Division Multiple Access (TDMA) scheme to record multiplexed neural signals into a single shared analog front end (AFE). The choppers reduce the total integrated noise across the modulated spectrum by 2.4 × and 4.3 × in Local Field Potential (LFP) and Action Potential (AP) bands, respectively. In addition, a novel impedance booster based on Sign-Sign least mean squares (LMS) adaptive filter (AF) predicts the input signal and pre-charges the AC-coupling capacitors. The impedance booster module increases the AFE input impedance by a factor of 39 × with a 7.1% increase in area. The proposed system obviates the need for on-chip digital demodulation, filtering, and remodulation normally required to extract Electrode Offset Voltages (EOV) from multiplexed neural signals, thereby achieving 3.6 × and 2.8 × savings in both area and power, respectively, in the EOV filter module. The Sign-Sign LMS AF is reused to determine the system loop gain, which relaxes the feedback DAC accuracy requirements and saves 10.1 × in power compared to conventional oversampled DAC truncation-error ΔΣ-modulator. The proposed SoC is designed and fabricated in 65 nm CMOS, and each channel occupies 0.00179 mm2 of active area. Each channel consumes 5.11 μW of power while achieving 2.19 μVrms and 2.4 μVrms of input referred noise (IRN) over AP and LFP bands. The resulting AP band noise efficiency factor (NEF) is 1.8. The proposed system is verified with acute in-vivo recordings in a Sprague-Dawley rat using parylene C based thin-film platinum nanorod microelectrodes.

Separation of tire tread vibration noise and air pumping noise using frequency band noise data

Separation of tire tread vibration noise and air pumping noise using frequency band noise data

BearingFM: Towards a foundation model for bearing fault diagnosis by domain knowledge and contrastive learning

Monitoring bearing failures in production equipment can effectively prevent finished product quality issues and unplanned factory downtime, thereby reducing supply chain uncertainties and risk. Therefore, monitoring bearing failures in production equipment is important for improving supply chain sustainability. Due to the generalization limitations of neural network models, specific models must be trained for specific tasks. However, in real industrial scenarios, there is a severe lack of labeled samples, making it difficult to deploy fault diagnosis models across massive amounts of equipment in workshops. In order to solve the above issue, this paper proposes a cloud-edge-end collaborative semi-supervised learning framework, which provides multi-level computing power and data support for building a foundation model. A data augmentation method based on the bearing fault mechanism is proposed, which effectively preserves the inherent essential characteristics in vibration signals by normalizing frequency and adding noise in specific frequency bands. A novel contrastive learning model is designed, which narrows the distances between positive samples and widens the distances between negative samples in the high-dimensional space through cross comparisons in the time dimension and knowledge dimension, thereby extracting the most essential characteristics from the unlabeled signals. Multiple sets of experiments conducted on four datasets demonstrate that the proposed approach achieves an approximately 98% fault classification accuracy with only 1.2% labeled samples.

Underwater radiated noise numerical analysis of polar transport vessels under ship-ice-water-air coupling continuous icebreaking based on the S-ALE algorithm

With the gradual opening of the Arctic channel, the underwater radiated noise induced by the ship-ice collision cannot be ignored. However, the underwater radiated noise induced by ship-ice collision is significantly different from that of ships navigating in open water. To explore the response rule of transient underwater radiation noise induced by ship-ice collision, this paper proposes a simplified numerical analysis method of ship-ice collision-induced transient underwater radiated noise in the full frequency band by combining the explicit dynamic method and acoustic analysis method. The ship-ice-water-air coupled collision analysis method based on the S-ALE algorithm is used to simulate and verify the ice load in the process of ship-ice continuous collision at different speeds. Then, the frequency-domain acoustic analysis method is used to predict the transient underwater radiated noise response in the full frequency band under icebreaking excitation and evaluate it by referring to the steady-state underwater radiated noise standard. The results show that the simplified analysis method can effectively predict the transient underwater radiation noise under icebreaking excitation. Under the icebreaking excitation, the radiation shape is irregularly scattered and the radiation direction is concentrated towards the bottom and bow of the ship with the frequency increase. The influence range of transient underwater radiated noise is mainly within 1000 Hz at different speeds, and the variation in the ship's speed affects the amplitude of the sound power level and the smoothness of the periodic response. The synthesized total sound power levels are 172.56 dB (V = 2.0kn), 174.15 dB (V = 2.5kn), 175.70 dB (V = 3.0kn), and 182.49 dB (V = 4.0kn), respectively. According to the comparison with the evaluation standard, it is found that the transient underwater radiation noise induced by ship icebreaking has a greater impact on marine organisms. It should give more detailed requirements within 10–1000 Hz when using relevant standards to evaluate underwater radiated noise induced by polar icebreaking. This paper can provide a reference for the research of underwater radiated noise induced by ship-ice collision and the formulation of relevant standards.

Experimental Investigation on Transmission of Sound in To Metallic Enclosures During Static Firing Tests Of Solid Rocket Motor

Satellite launch vehicle during lift-off generates intense dynamic environment mainly the acoustic noise, which in turn acts on the nearby launch pad systems. Reliable operation of these launch pad ground systems needs to be ensured by safeguarding against these dynamic loads with adequate protection measures. For future launch vehicle programs where the launch turnaround time is a crucial aspect, sensitive systems like ground check-out electronic packages are planned to be placed adjacent to the launch vehicle mounting pedestal on the launch pad to ensure minimal time for preparation. The enclosures housing these electronic packages needs to be configured to minimize the transmission of acoustic levels being imposed from the lift-off induced noise. In the present work, an experimental investigation is carried out on acoustic transmission characteristics of metallic enclosures of different material and thickness during the static firing tests of solid rocket motors. Acoustics generated from the supersonic jet noise has a wide frequency band from 100 to 10,000 Hz with sound power peaking near 1,000 Hz. The electronic components and packages, which are generally vulnerable to the high frequency noise, need to be protected from this lift-off induced acoustics. The enclosures are placed in the far field of this jet noise and the transmission loss measurements are obtained. Variation of transmission loss with material and thickness of the enclosures are studied with specific attention to the internal acoustic modes and the coincidence phenomena. Subsequently, the enclosures treated with acoustic blankets of different thickness are investigated to verify its influence on internal acoustic modes and also the additional reduction in transmission of sound in the dominant frequency band of supersonic jet noise.

Lithological Discrimination of Khyber Range Using Remote Sensing and Machine Learning Algorithms

In this study, the satellite data of ASTER and Landsat 8 OLI were used for the discrimination of lithological units covering the Khyber range. Of the 24 tested band combinations, the most suitable include 632 and 468 of ASTER and 754 and 147 of OLI in the RGB sequence. The data were also tested with two conventional machine learning algorithms (MLAs), namely maximum likelihood classification (MLC) and support vector machine (SVM), for lithological mapping. Principal component analysis (PCA), minimum noise fraction (MNF), band ratios, and color composites in combination with available lithological maps and field data were utilized for training sample collection for the MLC and SVM models to classify the lithological units. The accuracy assessment of SVM and MLC was performed using a confusion matrix, which revealed a higher accuracy of 74.8419% and 72.1217% for ASTER and an accuracy of 58.4833% and 60.0257% for OLI, respectively. The results indicate that ASTER imagery is more suitable for lithological discrimination in the study area due to its high spectral resolution in the VNIR to SWIR range. The experiment revealed that the SVM classification offered the highest overall accuracy of nearly 75% and the kappa coefficient value of 0.7 on ASTER data. This demonstrates the effectiveness of SVM classification in exploring lithological mapping in dry to semi-arid regions.

Newly identified Phonocardiography frequency bands for psychological stress detection with Deep Wavelet Scattering Network

The timely psychological stress detection can improve the quality of human life by preventing stress-induced behavioral and pathological consequences. This paper presents a novel framework that eliminates the need of Electrocardiography (ECG) signals-based referencing of Phonocardiography (PCG) signals for psychological stress detection. This stand-alone PCG-based methodology uses wavelet scattering approach on the data acquired from twenty-eight healthy adult male and female subjects to detect psychological stress. The acquired PCG signals are asynchronously segmented for the analysis using wavelet scattering transform. After the noise bands removal, the optimized segmentation length (L), scattering network parameters namely-invariance scale (J) and quality factor (Q) are utilized for computation of scattering features. These scattering coefficients generated are fed to K-nearest neighbor (KNN) and Extreme Gradient Boosting (XGBoost) classifier and the ten-fold cross validation-based performance metrics obtained are-accuracy 94.30 %, sensitivity 97.96 %, specificity 88.01 % and area under the curve (AUC) 0.9298 using XGBoost classifier for detecting psychological stress. Most importantly, the framework also identified two frequency bands in PCG signals with high discriminatory power for psychological stress detection as 270–290 Hz and 380–390 Hz. The elimination of multi-modal data acquisition and analysis makes this approach cost-efficient and reduces computational complexity.

Asteroid reflectance spectra from Gaia DR3: Near-UV in primitive asteroids

Context. In the context of charge-coupled devices (CCDs), the ultraviolet (UV) region has mostly remained unexplored after the 1990s. Gaia DR3 offers the community a unique opportunity to explore tens of thousands of asteroids in the near-UV as a proxy of the UV absorption. This absorption has been proposed in previous works as a diagnostic of hydration, organics, and space weathering. Aims. In this work, we aim to explore the potential of the NUV as a diagnostic region for primitive asteroids using Gaia DR3. Methods. We used a corrective factor over the blue part of Gaia spectra to erase the solar analog selection effect. We identified an artificial relation between the band noise and slope and applied a signal-to-noise ratio (S/N) threshold for Gaia bands. Meeting the quality standards, we employed a Markov chain Monte Carlo (MCMC) algorithm to compute the albedo threshold, maximizing primitive asteroid inclusion. Utilizing one- and two-dimensional (1D and 2D) projections, along with dimensionality-reduction methods (such as PCA and UMAP), we identified primitive asteroid populations. Results. We uncovered: (a) the first observational evidence linking UV absorption to the 0.7 µm band, tied to hydrated iron-rich phyllosilicates; and (b) a 2D space revealing a split in C-type asteroids based on spectral features, including UV absorption. The computed average depth (3.5 ± 1.0 %) and center (0.70 ± 0.03 µm) of the 0.7 µm absorption band for primitive asteroids observed with Gaia is in agreement with the literature values. Conclusions. In this paper, we shed light on the importance of the UV absorption feature to discriminate among different mineralogies (i.e., iron-rich phyllosilicates vs. iron-poor) or to identify taxonomies that are conflated in the visible (i.e., F-types vs. B-types). We have shown that this is a promising region for diagnostic studies of the composition of primitive asteroids.

Spectral consistency in sound sequence affects perceptual accuracy in discriminating subdivided rhythmic patterns.

Musical compositions are distinguished by their unique rhythmic patterns, determined by subtle differences in how regular beats are subdivided. Precise perception of these subdivisions is essential for discerning nuances in rhythmic patterns. While musical rhythm typically comprises sound elements with a variety of timbres or spectral cues, the impact of such spectral variations on the perception of rhythmic patterns remains unclear. Here, we show that consistency in spectral cues affects perceptual accuracy in discriminating subdivided rhythmic patterns. We conducted online experiments using rhythmic sound sequences consisting of band-passed noise bursts to measure discrimination accuracy. Participants were asked to discriminate between a swing-like rhythm sequence, characterized by a 2:1 interval ratio, and its more or less exaggerated version. This task was also performed under two additional rhythm conditions: inversed-swing rhythm (1:2 ratio) and regular subdivision (1:1 ratio). The center frequency of the band noises was either held constant or alternated between two values. Our results revealed a significant decrease in discrimination accuracy when the center frequency was alternated, irrespective of the rhythm ratio condition. This suggests that rhythm perception is shaped by temporal structure and affected by spectral properties.

Design of a Sigma-Delta Analog-to-Digital Converter Cascade Decimation Filter

As the current mainstream high-precision ADC architecture, sigma-delta ADC is extensively employed in a wide range of domains and applications. This paper presents the design of a highly efficient cascaded digital decimation filter for sigma-delta ADCs, emphasizing the suppression of high folding band noise and the achievement of a flat passband. Additionally, this study addresses the critical balance between filter performance and power consumption. An inserting zero (IZ) filter is incorporated into a cascaded integrator comb (CIC) filter to enhance aliasing suppression. The IZ filter and compensation filter are optimized using the particle swarm optimization (PSO) algorithm to achieve greater noise attenuation and smaller passband ripple. The designed filter achieves a noise attenuation of 93.4 dB in the folding band and exhibits an overall passband ripple of 0.0477 dB within a bandwidth of 20 KHz. To decrease the power consumption in the filter design, polyphase decomposition has been applied. The filter structure is implemented on an FPGA, processing a 5-bit stream from a 64-times oversampling rate and third-order sigma-delta modulator. The signal-to-noise ratio (SNR) of the output signal reaches 91.7 dB. For ASIC design, the filter utilizes 180 nm CMOS technology with a power consumption of 0.217 mW and occupies a layout area of 0.72 mm2. The post-layout simulation result indicates that the SNR remains at 91.7 dB.

Investigating the Utility of a Compact Loudspeaker Array for Audiometric Testing.

This project addressed the uses of a loudspeaker array for audiometric measurements. It sought to evaluate a prototype compact array in terms of the reliability of test results across sound booths. A seven-loudspeaker array was developed to deliver sounds from -60° to +60° on an arc with a radius of 0.5 m. The system was equipped with a head position sensing system to maintain the listener's head near the optimal test position. Three array systems were distributed to each of the two test sites for within-subject assessments of booth equivalence on tests of sound localization, speech reception in noise, and threshold detection. A total of 36 subjects participated, 18 at each test site. Results showed excellent interbooth consistency on tests of sound localization using speech and noise signals, including conditions in which one or both ears were covered with a muff. Booth consistency was also excellent on sound field threshold measurements for detecting quasi-diffuse noise bands. Nonequivalence was observed in some cases of speech-in-noise tests, particularly with a small one-person booth. Acoustic analyses of in situ loudspeaker responses indicated that some of the nonequivalent comparisons on speech-in-noise tests could be traced to the effects of reflections. Overall, the results demonstrate the utility and reliability of a compact array for the assessment of localization ability, speech reception in noise, and sound field thresholds. However, the results indicate that researchers and clinicians should be aware of the reflection effects that can influence the results of sound field tests in which signal and noise levels from separate loudspeakers are critical.

Method of feature extraction of abnormal communication signal in network based on nonlinear technology

Abstract Accurate extraction of abnormal communication signal features in the network is the basis to ensure the completion of network communication. Therefore, a method of feature extraction of abnormal communication signal in network based on nonlinear technology is proposed. In this method, wavelet transform is adopted to decompose the abnormal network communication signals in the high- and low-frequency bands. According to the distribution characteristics of noise and signal in the frequency band, the corresponding parameters are selected for phase space reconstruction and nonlinear dimension reduction of local tangent space mainstream shape recognition algorithm, and the decomposition coefficients of wavelet packet after noise reduction are reconstructed to realize the nonlinear noise reduction of abnormal signal; the denoised abnormal communication signal in network is mapped to the high-dimensional feature space. The principal component is analyzed in accordance with the nonlinear function in the mapped feature space, and the nonlinear function is solved by self-organizing neural network to output the principal component extraction result. According to test results, this method has a significant signal noise reduction effect, results are more than 92% for different abnormal communication signals, and the features of abnormal signals are accurately extracted.

Data Classification and Parameter Estimations with Deep Learning to the Simulated Time-domain High-frequency Gravitational Waves Detections

Abstract High-frequency Gravitational wave (HFGW) detection is a great challenge, as its signal is significantly weak, compared with the relevant background noise in the same frequency band. Therefore, besides designing and running the feasible installation for the experimental weak-signal detection, developing various effective approaches to process the big detected data for extracting the information 1about the GWs is also particularly important. In this paper, we focus on the simulated time-domain detected data of the electromagnetic response of the GWs in high frequency band, typically such as Gigahertzs. Specifically, we develop an effective deep learning method to implement the classification of the simulated detection data, which includes the strong electromagnetic background noise in the same frequency band, for the parameter estimations of the HFGWs. The simulatively detected data is generated by the transverse first-order electromagnetic responses of the HFGWs passing through a high stationary magnetic field biased 
by a high frequency Gaussian beam. We propose a convolutional neural network (CNN) model to implement the classification of the simulated detection data, whose accuracy can reach more than 90%. With these data being served as the positive sample datasets, the physical parameters of the simulatively detected HFGWs can be effectively estimated by matching the sample datasets with the 
noise-free template library one by one. The confidence levels of these extracted parameters can reach to 95% in the corresponding confidence interval. By the multiple data experiments, the effectiveness and reliability of the proposed data processing method is verified. Hopefully, the proposed method could be generalized to the big data processing for the experimental HFGWs detections, in 
future.

New method for optimizing the detection of low-energy soft X-rays (200–300 eV) in a CMOS detector

Complementary metal-oxide semiconductor (CMOS) sensors have been widely used as soft X-ray detectors in several fields owing to their recent developments and unique advantages. The CMOS detector parameters have been extensively studied and evaluated. However, the methods for discriminating signals and dark noise have not been sufficiently studied, particularly for low-energy soft X-rays. Setting a threshold, which is widely used for discrimination, is not suitable for low-energy soft X-rays because of the crossing of the energy bands of dark noise and signals. In this study, we analyzed the charge correlation of the CMOS detector GSENSE2020BSI (G2020BSI) and proposed a new two-dimensional segmentation method to optimize the discrimination of signals according to the charge correlation. The effectiveness of the method used to discriminate low-energy soft X-rays on the G2020BSI detector was qualitatively evaluated. The optimal feature parameters used in the two-dimensional segmentation method were investigated for G2020BSI. However, the two-dimensional segmentation method is insensitive to feature parameters.