Esophageal cancer(EC),a common malignant tumor of the digestive tract,requires early diagnosis and timely treatment to improve patient prognosis.Automated detection of EC using medical imaging has the potential to inc...Esophageal cancer(EC),a common malignant tumor of the digestive tract,requires early diagnosis and timely treatment to improve patient prognosis.Automated detection of EC using medical imaging has the potential to increase screening efficiency and diagnostic accuracy,thereby significantly improving long-term survival rates and the quality of life of patients.Recent advances in deep learning(DL),particularly convolutional neural networks,have demons-trated remarkable performance in medical imaging analysis.These techniques have shown significant progress in the automated identification of malignant tumors,quantitative analysis of lesions,and improvement in diagnostic accuracy and efficiency.This article comprehensively examines the research progress of DL in medical imaging for EC,covering various imaging modalities such as digital pathology,endoscopy,computed tomography,etc.It explores the clinical value and application prospects of DL in EC screening and diagnosis.Additionally,the article addresses several critical challenges that must be overcome for the clinical translation of DL techniques,including constructing high-quality datasets,promoting multimodal feature fusion,and optimizing artificial intelligence-clinical workflow integration.By providing a detailed overview of the current state of DL in EC imaging and highlighting the key challenges and future directions,this article aims to guide future research and facilitate the clinical implementation of DL technologies in EC management,ultimately contributing to better patient outcomes.展开更多
The various bioacoustics signals obtained with auscultation contain complex clinical information that has been traditionally used as biomarkers,however,they are not extensively used in clinical studies owing to their ...The various bioacoustics signals obtained with auscultation contain complex clinical information that has been traditionally used as biomarkers,however,they are not extensively used in clinical studies owing to their spatiotemporal limitations.In this study,we developed a wearable stethoscope for wireless,skinattachable,low-power,continuous,real-time auscultation using a lung-sound-monitoring-patch(LSMP).LSMP can monitor respiratory function through a mobile app and classify normal and adventitious breathing by comparing their unique acoustic characteristics.The human heart and breathing sounds from humans can be distinguished from complex sound signals consisting of a mixture of bioacoustic signals and external noise.The performance of the LSMP sensor was further demonstrated in pediatric patients with asthma and elderly chronic obstructive pulmonary disease(COPD)patients where wheezing sounds were classified at specific frequencies.In addition,we developed a novel method for counting wheezing events based on a two-dimensional convolutional neural network deep-learning model constructed de novo and trained with our augmented fundamental lung-sound data set.We implemented a counting algorithm to identify wheezing events in real-time regardless of the respiratory cycle.The artificial intelligence-based adventitious breathing event counter distinguished>80%of the events(especially wheezing)in long-term clinical applications in patients with COPD.展开更多
It is of great importance to obtain precise trace data,as traces are frequently the sole visible and measurable parameter in most outcrops.The manual recognition and detection of traces on high-resolution three-dimens...It is of great importance to obtain precise trace data,as traces are frequently the sole visible and measurable parameter in most outcrops.The manual recognition and detection of traces on high-resolution three-dimensional(3D)models are relatively straightforward but time-consuming.One potential solution to enhance this process is to use machine learning algorithms to detect the 3D traces.In this study,a unique pixel-wise texture mapper algorithm generates a dense point cloud representation of an outcrop with the precise resolution of the original textured 3D model.A virtual digital image rendering was then employed to capture virtual images of selected regions.This technique helps to overcome limitations caused by the surface morphology of the rock mass,such as restricted access,lighting conditions,and shading effects.After AI-powered trace detection on two-dimensional(2D)images,a 3D data structuring technique was applied to the selected trace pixels.In the 3D data structuring,the trace data were structured through 2D thinning,3D reprojection,clustering,segmentation,and segment linking.Finally,the linked segments were exported as 3D polylines,with each polyline in the output corresponding to a trace.The efficacy of the proposed method was assessed using a 3D model of a real-world case study,which was used to compare the results of artificial intelligence(AI)-aided and human intelligence trace detection.Rosette diagrams,which visualize the distribution of trace orientations,confirmed the high similarity between the automatically and manually generated trace maps.In conclusion,the proposed semi-automatic method was easy to use,fast,and accurate in detecting the dominant jointing system of the rock mass.展开更多
Real-time, automatic, and accurate determination of seismic signals is critical for rapid earthquake reporting and early warning. In this study, we present a correction trigger function（CTF） for automatically detect...Real-time, automatic, and accurate determination of seismic signals is critical for rapid earthquake reporting and early warning. In this study, we present a correction trigger function（CTF） for automatically detecting regional seismic events and a fourth-order statistics algorithm with the Akaike information criterion（AIC） for determining the direct wave phase, based on the differences, or changes, in energy, frequency, and amplitude of the direct P- or S-waves signal and noise. Simulations suggest for that the proposed fourth-order statistics result in high resolution even for weak signal and noise variations at different amplitude, frequency, and polarization characteristics. To improve the precision of establishing the S-waves onset, first a specific segment of P-wave seismograms is selected and the polarization characteristics of the data are obtained. Second, the S-wave seismograms that contained the specific segment of P-wave seismograms are analyzed by S-wave polarization filtering. Finally, the S-wave phase onset times are estimated. The proposed algorithm was used to analyze regional earthquake data from the Shandong Seismic Network. The results suggest that compared with conventional methods, the proposed algorithm greatly decreased false and missed earthquake triggers, and improved the detection precision of direct P- and S-wave phases.展开更多
Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious an...Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious and they are numerous,resulting in low detection accuracy by deep learning models.Therefore,we proposed a new multi-scale fusion crater detection algorithm(MSF-CDA)based on the YOLO11 to improve the accuracy of lunar impact crater detection,especially for small craters with a diameter of<1 km.Using the images taken by the LROC(Lunar Reconnaissance Orbiter Camera)at the Chang’e-4(CE-4)landing area,we constructed three separate datasets for craters with diameters of 0-70 m,70-140 m,and>140 m.We then trained three submodels separately with these three datasets.Additionally,we designed a slicing-amplifying-slicing strategy to enhance the ability to extract features from small craters.To handle redundant predictions,we proposed a new Non-Maximum Suppression with Area Filtering method to fuse the results in overlapping targets within the multi-scale submodels.Finally,our new MSF-CDA method achieved high detection performance,with the Precision,Recall,and F1 score having values of 0.991,0.987,and 0.989,respectively,perfectly addressing the problems induced by the lesser features and sample imbalance of small craters.Our MSF-CDA can provide strong data support for more in-depth study of the geological evolution of the lunar surface and finer geological age estimations.This strategy can also be used to detect other small objects with lesser features and sample imbalance problems.We detected approximately 500,000 impact craters in an area of approximately 214 km2 around the CE-4 landing area.By statistically analyzing the new data,we updated the distribution function of the number and diameter of impact craters.Finally,we identified the most suitable lighting conditions for detecting impact crater targets by analyzing the effect of different lighting conditions on the detection accuracy.展开更多
Although quality assurance and quality control procedures are routinely applied in most air quality networks, outliers can still occur due to instrument malfunctions, the influence of harsh environments and the limita...Although quality assurance and quality control procedures are routinely applied in most air quality networks, outliers can still occur due to instrument malfunctions, the influence of harsh environments and the limitation of measuring methods. Such outliers pose challenges for data-powered applications such as data assimilation, statistical analysis of pollution characteristics and ensemble forecasting. Here, a fully automatic outlier detection method was developed based on the probability of residuals, which are the discrepancies between the observed and the estimated concentration values. The estimation can be conducted using filtering—or regressions when appropriate—to discriminate four types of outliers characterized by temporal and spatial inconsistency, instrument-induced low variances, periodic calibration exceptions, and less PM_(10) than PM_(2.5) in concentration observations, respectively. This probabilistic method was applied to detect all four types of outliers in hourly surface measurements of six pollutants(PM_(2.5), PM_(10),SO_2,NO_2,CO and O_3) from 1436 stations of the China National Environmental Monitoring Network during 2014-16. Among the measurements, 0.65%-5.68% are marked as outliers. with PM_(10) and CO more prone to outliers. Our method successfully identifies a trend of decreasing outliers from 2014 to 2016,which corresponds to known improvements in the quality assurance and quality control procedures of the China National Environmental Monitoring Network. The outliers can have a significant impact on the annual mean concentrations of PM_(2.5),with differences exceeding 10 μg m^(-3) at 66 sites.展开更多
Brain tumors are neoplastic diseases caused by the proliferation of abnormal cells in brain tissues,and their appearance may lead to a series of complex symptoms.However,current methods struggle to capture deeper brai...Brain tumors are neoplastic diseases caused by the proliferation of abnormal cells in brain tissues,and their appearance may lead to a series of complex symptoms.However,current methods struggle to capture deeper brain tumor image feature information due to the variations in brain tumor morphology,size,and complex background,resulting in low detection accuracy,high rate of misdiagnosis and underdiagnosis,and challenges in meeting clinical needs.Therefore,this paper proposes the CMS-YOLO network model for multi-category brain tumor detection,which is based on the You Only Look Once version 10(YOLOv10s)algorithm.This model innovatively integrates the Convolutional Medical UNet extended block(CMUNeXt Block)to design a brand-new CSP Bottleneck with 2 convolutions(C2f)structure,which significantly enhances the ability to extract features of the lesion area.Meanwhile,to address the challenge of complex backgrounds in brain tumor detection,a Multi-Scale Attention Aggregation(MSAA)module is introduced.The module integrates features of lesions at different scales,enabling the model to effectively capture multi-scale contextual information and enhance detection accuracy in complex scenarios.Finally,during the model training process,the Shape-IoU loss function is employed to replace the Complete-IoU(CIoU)loss function for optimizing bounding box regression.This ensures that the predicted bounding boxes generated by the model closely match the actual tumor contours,thereby further enhancing the detection precision.The experimental results show that the improved method achieves 94.80%precision,93.60%recall,96.20%score,and 79.60%on the MRI for Brain Tumor with Bounding Boxes dataset.Compared to the YOLOv10s model,this represents improvements of 1.0%,1.1%,1.0%,and 1.1%,respectively.The method can achieve automatic detection and localization of three distinct categories of brain tumors—glioma,meningioma,and pituitary tumor,which can accurately detect and identify brain tumors,assist doctors in early diagnosis,and promote the development of early treatment.展开更多
Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extract...Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.展开更多
Since the atmospheric correction is a necessary preprocessing step of remote sensing image before detecting green tide, the introduced error directly affects the detection precision. Therefore, the detection method of...Since the atmospheric correction is a necessary preprocessing step of remote sensing image before detecting green tide, the introduced error directly affects the detection precision. Therefore, the detection method of green tide is presented from Landsat TM/ETM plus image which needs not the atmospheric correction. In order to achieve an automatic detection of green tide, a linear relationship（y =0.723 x＋0.504） between detection threshold y and subtraction x（x=λnir–λred） is found from the comparing Landsat TM/ETM plus image with the field surveys.Using this relationship, green tide patches can be detected automatically from Landsat TM/ETM plus image.Considering there is brightness difference between different regions in an image, the image will be divided into a plurality of windows（sub-images） with a same size firstly, and then each window will be detected using an adaptive detection threshold determined according to the discovered linear relationship. It is found that big errors will appear in some windows, such as those covered by clouds seriously. To solve this problem, the moving step k of windows is proposed to be less than the window width n. Using this mechanism, most pixels will be detected[n/k]×[n/k] times except the boundary pixels, then every pixel will be assigned the final class（green tide or sea water） according to majority rule voting strategy. It can be seen from the experiments, the proposed detection method using multi-windows and their adaptive thresholds can detect green tide from Landsat TM/ETM plus image automatically. Meanwhile, it avoids the reliance on the accurate atmospheric correction.展开更多
As a dispersive wave mode produced by lightning strokes, tweek atmospherics provide important hints of lower ionospheric(i.e., D-region) electron density. Based on data accumulation from the WHU ELF/VLF receiver syste...As a dispersive wave mode produced by lightning strokes, tweek atmospherics provide important hints of lower ionospheric(i.e., D-region) electron density. Based on data accumulation from the WHU ELF/VLF receiver system, we develop an automatic detection module in terms of the maximum-entropy-spectral-estimation(MESE) method to identify unambiguous instances of low latitude tweeks.We justify the feasibility of our procedure through a detailed analysis of the data observed at the Suizhou Station(31.57°N, 113.32°E) on17 February 2016. A total of 3961 tweeks were registered by visual inspection;the automatic detection method captured 4342 tweeks, of which 3361 were correct ones, producing a correctness percentage of 77.4%(= 3361/4342) and a false alarm rate of 22.6%(= 981/4342).A Short-Time Fourier Transformation(STFT) was also applied to trace the power spectral profiles of identified tweeks and to evaluate the tweek propagation distance. It is found that the fitting accuracy of the frequency–time curve and the relative difference of propagation distance between the two methods through the slope and through the intercept can be used to further improve the accuracy of automatic tweek identification. We suggest that our automatic tweek detection and analysis method therefore supplies a valuable means to investigate features of low latitude tweek atmospherics and associated ionospheric parameters comprehensively.展开更多
Accurate detection and picking of the P-phase onset time in noisy microseismic data from underground mines remains a big challenge. Reliable P-phase onset time picking is necessary for accurate source location needed ...Accurate detection and picking of the P-phase onset time in noisy microseismic data from underground mines remains a big challenge. Reliable P-phase onset time picking is necessary for accurate source location needed for planning and rescue operations in the event of failures. In this paper, a new technique based on the discrete stationary wavelet transform （DSWT）and higher order statist!cs, is proposed for processing noisy data from underground mines. The objectives of this method are to （1） Improve manual detection and tPicking of P-phase onset; and （ii） provide an automatic means of detecting and picking P-phase onset me accurately. The DSWT is first used to filter the signal over several scales. The manual P-phase onset detection and picking are then obtained by computing the signal energy across selected scales with frequency bands that capture the signal of interest. The automatic P-phase onset, on the other hand, is achieved by using skewness- and kurtosis-based criterion applied to selected scales in a time-frequency domain. The method was tested using synthetic and field data from an underground limestone mine. Results were compared with results obtained by using the short-term to long-term average （STA/LTA） ratio and that by Reference Ge et al. （2009）. The results show that the me!hod provides a more reliable estimate of the P-phase onset arrival than the STA]LTA method when the signal to noise ratio is very low. Also, the results obtained from the field data matched accurately with the results from Reference Ge et al. （2009）.展开更多
The satellite-based automatic identification system (AIS) receiver has to encounter the frequency offset caused by the Doppler effect and the oscillator instability. This paper proposes a non-coherent sequence detecti...The satellite-based automatic identification system (AIS) receiver has to encounter the frequency offset caused by the Doppler effect and the oscillator instability. This paper proposes a non-coherent sequence detection scheme for the satellite-based AIS signal transmitted over the white Gaussian noise channel. Based on the maximum likelihood estimation and a Viterbi decoder, the proposed scheme is capable of tolerating a frequency offset up to 5% of the symbol rate. The complexity of the proposed scheme is reduced by the state-complexity reduction, which is based on per-survivor processing. Simulation results prove that the proposed non-coherent sequence detection scheme has high robustness to frequency offset compared to the relative scheme when messages collision exists.展开更多
In the process of bromine production,because of lag adjustment methods,there are problems of adjusting delay,raw material wastage and low growth rate.By considering the nature of bromine production,with the help of fu...In the process of bromine production,because of lag adjustment methods,there are problems of adjusting delay,raw material wastage and low growth rate.By considering the nature of bromine production,with the help of fuzzy data processing method,computer detection and display technique,we designed an automatic detection instrument for the ratio of chlorine to bromine in oxidized liquid of bromine production.This instrument can be used to detect the different parameters of raw materials adjustment and control in real time,and afford assurance that raw materials will be adjusted in time.This paper briefly introduces the working mechanism,hardware and software design of the instrument.展开更多
On-line chatter detection can avoid unstable cutting through monitoring the machining process.In order to identify chatter in a timely manner,an improved Support Vector Machine(SVM)is developed in this paper,based on ...On-line chatter detection can avoid unstable cutting through monitoring the machining process.In order to identify chatter in a timely manner,an improved Support Vector Machine(SVM)is developed in this paper,based on extracted features.In the SVM model,the penalty factor(e)and the core parameter(g)have important influence on the classification,more than from Kernel Functions(KFs).Hence,first the classification results are conducted using different KFs.Then two methods are presented for exploring the best parameters.The chatter identification results show that the Genetic Algorithm(GA)approach is more suitable for deciding the parameters than the Grid Explore(GE)approach.展开更多
In the designed automatic balancing head, a non contact induction transformer is used to deliver driving energy to solve the problem of current fed and controlling on line. Computer controlled automatic balancing expe...In the designed automatic balancing head, a non contact induction transformer is used to deliver driving energy to solve the problem of current fed and controlling on line. Computer controlled automatic balancing experiments with phase magnitude control tactics were performed on a flexible rotor system. Results of the experiments prove that the energy feeding method and the control tactics are effective in the automatic balancing head for vibration controlling.展开更多
This paper presents an automatic system for failure detection in hydro-power generators. The main idea of this system is to detect failure using current and voltage signals acquired without any type of internal interf...This paper presents an automatic system for failure detection in hydro-power generators. The main idea of this system is to detect failure using current and voltage signals acquired without any type of internal interference in the generator operation. The detected failures could be mechanical or electrical origins, such as: problems in bearings, unwanted vibrations, partial discharges, misalignment, unbalancing, among others. It is possible because the generator acts as a transducer for mechanical problems, and they appear in current and voltage signals. This automatic system based on electric signature analysis has been installed in Itapebi Power Plant generators since 2012. Some results are presented in this paper.展开更多
The valuation relation of potential difference with discharging time in Electrical Discharge Machining (EDM) is analyzed theoretically and tested and verified by experiments designed in this paper and the relation bet...The valuation relation of potential difference with discharging time in Electrical Discharge Machining (EDM) is analyzed theoretically and tested and verified by experiments designed in this paper and the relation between potential difference and spark location is induced and analyzed, and proceed by experiments under the condition of onedimension.展开更多
As an important promising biomarker,high frequency oscillations(HFOs)can be used to track epileptic activity and localize epileptogenic zones.However,visual marking of HFOs from a large amount of intracranial electroe...As an important promising biomarker,high frequency oscillations(HFOs)can be used to track epileptic activity and localize epileptogenic zones.However,visual marking of HFOs from a large amount of intracranial electroencephalogram(iEEG)data requires a great deal of time and effort from researchers,and is also very dependent on visual features and easily influenced by subjective factors.Therefore,we proposed an automatic epileptic HFO detection method based on visual features and non-intuitive multi-domain features.To eliminate the interference of continuous oscillatory activity in detected sporadic short HFO events,the iEEG signals adjacent to the detected events were set as the neighboring environmental range while the number of oscillations and the peak–valley differences were calculated as the environmental reference features.The proposed method was developed as a MatLab-based HFO detector to automatically detect HFOs in multi-channel,long-distance iEEG signals.The performance of our detector was evaluated on iEEG recordings from epileptic mice and patients with intractable epilepsy.More than 90%of the HFO events detected by this method were confirmed by experts,while the average missed-detection rate was<10%.Compared with recent related research,the proposed method achieved a synchronous improvement of sensitivity and specificity,and a balance between low false-alarm rate and high detection rate.Detection results demonstrated that the proposed method performs well in sensitivity,specificity,and precision.As an auxiliary tool,our detector can greatly improve the efficiency of clinical experts in inspecting HFO events during the diagnosis and treatment of epilepsy.展开更多
Epilepsy is a common neurological disorder that occurs at all ages.Epilepsy not only brings physical pain to patients,but also brings a huge burden to the lives of patients and their families.At present,epilepsy detec...Epilepsy is a common neurological disorder that occurs at all ages.Epilepsy not only brings physical pain to patients,but also brings a huge burden to the lives of patients and their families.At present,epilepsy detection is still achieved through the observation of electroencephalography(EEG)by medical staff.However,this process takes a long time and consumes energy,which will create a huge workload to medical staff.Therefore,it is particularly important to realize the automatic detection of epilepsy.This paper introduces,in detail,the overall framework of EEG-based automatic epilepsy identification and the typical methods involved in each step.Aiming at the core modules,that is,signal acquisition analog front end(AFE),feature extraction and classifier selection,method summary and theoretical explanation are carried out.Finally,the future research directions in the field of automatic detection of epilepsy are prospected.展开更多
AIM:To develop an automated model for subfoveal choroidal thickness(SFCT)detection in optical coherence tomography(OCT)images,addressing manual fovea location and choroidal contour challenges.METHODS:Two procedures we...AIM:To develop an automated model for subfoveal choroidal thickness(SFCT)detection in optical coherence tomography(OCT)images,addressing manual fovea location and choroidal contour challenges.METHODS:Two procedures were proposed:defining the fovea and segmenting the choroid.Fovea localization from B-scan OCT image sequence with three-dimensional reconstruction(LocBscan-3D)predicted fovea location using central foveal depression features,and fovea localization from two-dimensional en-face OCT(LocEN-2D)used a mask region-based convolutional neural network(Mask R-CNN)model for optic disc detection,and determined the fovea location based on optic disc relative position.Choroid segmentation also employed Mask R-CNN.RESULTS:For 53 eyes in 28 healthy subjects,LocBscan-3D’s mean difference between manual and predicted fovea locations was 170.0μm,LocEN-2D yielded 675.9μm.LocEN-2D performed better in non-high myopia group(P=0.02).SFCT measurements from Mask R-CNN aligned with manual values.CONCLUSION:Our models accurately predict SFCT in OCT images.LocBscan-3D excels in precise fovea localization even with high myopia.LocEN-2D shows high detection rates but lower accuracy especially in the high myopia group.Combining both models offers a robust SFCT assessment approach,promising efficiency and accuracy for large-scale studies and clinical use.展开更多
基金Supported by Funding for Clinical Trials from the Nanjing Drum Tower Hospital,Affiliated Hospital of Medical School,Nanjing University,No.2021-LCYJ-MS-11.
文摘Esophageal cancer(EC),a common malignant tumor of the digestive tract,requires early diagnosis and timely treatment to improve patient prognosis.Automated detection of EC using medical imaging has the potential to increase screening efficiency and diagnostic accuracy,thereby significantly improving long-term survival rates and the quality of life of patients.Recent advances in deep learning(DL),particularly convolutional neural networks,have demons-trated remarkable performance in medical imaging analysis.These techniques have shown significant progress in the automated identification of malignant tumors,quantitative analysis of lesions,and improvement in diagnostic accuracy and efficiency.This article comprehensively examines the research progress of DL in medical imaging for EC,covering various imaging modalities such as digital pathology,endoscopy,computed tomography,etc.It explores the clinical value and application prospects of DL in EC screening and diagnosis.Additionally,the article addresses several critical challenges that must be overcome for the clinical translation of DL techniques,including constructing high-quality datasets,promoting multimodal feature fusion,and optimizing artificial intelligence-clinical workflow integration.By providing a detailed overview of the current state of DL in EC imaging and highlighting the key challenges and future directions,this article aims to guide future research and facilitate the clinical implementation of DL technologies in EC management,ultimately contributing to better patient outcomes.
基金supported by the Korea Environment Industry&Technology Institute(KEITI)through Digital Infrastructure Building Project for Monitoring,Surveying and Evaluating the Environmental Health program,funded by the Korea Ministry of Environment(MOE)(2021003330008)supported by the KIST Internal program(2E32851)+1 种基金supported by the Korea Health Technology Research and Development(R&D)Project through the Korea Health Industry Development Institute(KHIDI)and Korea Dementia Research Center(KDRC),funded by the Ministry of Health&Welfare and Ministry of Science and ICT,Republic of Korea(HU20C0164)the Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2022R1A6A3A01087298)。
文摘The various bioacoustics signals obtained with auscultation contain complex clinical information that has been traditionally used as biomarkers,however,they are not extensively used in clinical studies owing to their spatiotemporal limitations.In this study,we developed a wearable stethoscope for wireless,skinattachable,low-power,continuous,real-time auscultation using a lung-sound-monitoring-patch(LSMP).LSMP can monitor respiratory function through a mobile app and classify normal and adventitious breathing by comparing their unique acoustic characteristics.The human heart and breathing sounds from humans can be distinguished from complex sound signals consisting of a mixture of bioacoustic signals and external noise.The performance of the LSMP sensor was further demonstrated in pediatric patients with asthma and elderly chronic obstructive pulmonary disease(COPD)patients where wheezing sounds were classified at specific frequencies.In addition,we developed a novel method for counting wheezing events based on a two-dimensional convolutional neural network deep-learning model constructed de novo and trained with our augmented fundamental lung-sound data set.We implemented a counting algorithm to identify wheezing events in real-time regardless of the respiratory cycle.The artificial intelligence-based adventitious breathing event counter distinguished>80%of the events(especially wheezing)in long-term clinical applications in patients with COPD.
基金supported by grants from the Human Resources Development program (Grant No.20204010600250)the Training Program of CCUS for the Green Growth (Grant No.20214000000500)by the Korea Institute of Energy Technology Evaluation and Planning (KETEP)funded by the Ministry of Trade,Industry,and Energy of the Korean Government (MOTIE).
文摘It is of great importance to obtain precise trace data,as traces are frequently the sole visible and measurable parameter in most outcrops.The manual recognition and detection of traces on high-resolution three-dimensional(3D)models are relatively straightforward but time-consuming.One potential solution to enhance this process is to use machine learning algorithms to detect the 3D traces.In this study,a unique pixel-wise texture mapper algorithm generates a dense point cloud representation of an outcrop with the precise resolution of the original textured 3D model.A virtual digital image rendering was then employed to capture virtual images of selected regions.This technique helps to overcome limitations caused by the surface morphology of the rock mass,such as restricted access,lighting conditions,and shading effects.After AI-powered trace detection on two-dimensional(2D)images,a 3D data structuring technique was applied to the selected trace pixels.In the 3D data structuring,the trace data were structured through 2D thinning,3D reprojection,clustering,segmentation,and segment linking.Finally,the linked segments were exported as 3D polylines,with each polyline in the output corresponding to a trace.The efficacy of the proposed method was assessed using a 3D model of a real-world case study,which was used to compare the results of artificial intelligence(AI)-aided and human intelligence trace detection.Rosette diagrams,which visualize the distribution of trace orientations,confirmed the high similarity between the automatically and manually generated trace maps.In conclusion,the proposed semi-automatic method was easy to use,fast,and accurate in detecting the dominant jointing system of the rock mass.
基金supported by the National Science and Technology Project(Grant No.2012BAK19B04)the Spark Program of Earthquake Sciences,China Earthquake Administration(Grant No.XH12029)
文摘Real-time, automatic, and accurate determination of seismic signals is critical for rapid earthquake reporting and early warning. In this study, we present a correction trigger function（CTF） for automatically detecting regional seismic events and a fourth-order statistics algorithm with the Akaike information criterion（AIC） for determining the direct wave phase, based on the differences, or changes, in energy, frequency, and amplitude of the direct P- or S-waves signal and noise. Simulations suggest for that the proposed fourth-order statistics result in high resolution even for weak signal and noise variations at different amplitude, frequency, and polarization characteristics. To improve the precision of establishing the S-waves onset, first a specific segment of P-wave seismograms is selected and the polarization characteristics of the data are obtained. Second, the S-wave seismograms that contained the specific segment of P-wave seismograms are analyzed by S-wave polarization filtering. Finally, the S-wave phase onset times are estimated. The proposed algorithm was used to analyze regional earthquake data from the Shandong Seismic Network. The results suggest that compared with conventional methods, the proposed algorithm greatly decreased false and missed earthquake triggers, and improved the detection precision of direct P- and S-wave phases.
基金the National Key Research and Development Program of China (Grant No.2022YFF0711400)the National Space Science Data Center Youth Open Project (Grant No. NSSDC2302001)
文摘Impact craters are important for understanding the evolution of lunar geologic and surface erosion rates,among other functions.However,the morphological characteristics of these micro impact craters are not obvious and they are numerous,resulting in low detection accuracy by deep learning models.Therefore,we proposed a new multi-scale fusion crater detection algorithm(MSF-CDA)based on the YOLO11 to improve the accuracy of lunar impact crater detection,especially for small craters with a diameter of<1 km.Using the images taken by the LROC(Lunar Reconnaissance Orbiter Camera)at the Chang’e-4(CE-4)landing area,we constructed three separate datasets for craters with diameters of 0-70 m,70-140 m,and>140 m.We then trained three submodels separately with these three datasets.Additionally,we designed a slicing-amplifying-slicing strategy to enhance the ability to extract features from small craters.To handle redundant predictions,we proposed a new Non-Maximum Suppression with Area Filtering method to fuse the results in overlapping targets within the multi-scale submodels.Finally,our new MSF-CDA method achieved high detection performance,with the Precision,Recall,and F1 score having values of 0.991,0.987,and 0.989,respectively,perfectly addressing the problems induced by the lesser features and sample imbalance of small craters.Our MSF-CDA can provide strong data support for more in-depth study of the geological evolution of the lunar surface and finer geological age estimations.This strategy can also be used to detect other small objects with lesser features and sample imbalance problems.We detected approximately 500,000 impact craters in an area of approximately 214 km2 around the CE-4 landing area.By statistically analyzing the new data,we updated the distribution function of the number and diameter of impact craters.Finally,we identified the most suitable lighting conditions for detecting impact crater targets by analyzing the effect of different lighting conditions on the detection accuracy.
基金supported by the National Natural Science Foundation (Grant Nos.91644216 and 41575128)the CAS Information Technology Program (Grant No.XXH13506-302)Guangdong Provincial Science and Technology Development Special Fund (No.2017B020216007)
文摘Although quality assurance and quality control procedures are routinely applied in most air quality networks, outliers can still occur due to instrument malfunctions, the influence of harsh environments and the limitation of measuring methods. Such outliers pose challenges for data-powered applications such as data assimilation, statistical analysis of pollution characteristics and ensemble forecasting. Here, a fully automatic outlier detection method was developed based on the probability of residuals, which are the discrepancies between the observed and the estimated concentration values. The estimation can be conducted using filtering—or regressions when appropriate—to discriminate four types of outliers characterized by temporal and spatial inconsistency, instrument-induced low variances, periodic calibration exceptions, and less PM_(10) than PM_(2.5) in concentration observations, respectively. This probabilistic method was applied to detect all four types of outliers in hourly surface measurements of six pollutants(PM_(2.5), PM_(10),SO_2,NO_2,CO and O_3) from 1436 stations of the China National Environmental Monitoring Network during 2014-16. Among the measurements, 0.65%-5.68% are marked as outliers. with PM_(10) and CO more prone to outliers. Our method successfully identifies a trend of decreasing outliers from 2014 to 2016,which corresponds to known improvements in the quality assurance and quality control procedures of the China National Environmental Monitoring Network. The outliers can have a significant impact on the annual mean concentrations of PM_(2.5),with differences exceeding 10 μg m^(-3) at 66 sites.
基金supported in part by the National Natural Science Foundation of China under Grants 61861007in part by the Guizhou Province Science and Technology Planning Project ZK[2021]303in part by the Guizhou Province Science Technology Support Plan under Grants[2022]264,[2023]096,[2023]412 and[2023]409.
文摘Brain tumors are neoplastic diseases caused by the proliferation of abnormal cells in brain tissues,and their appearance may lead to a series of complex symptoms.However,current methods struggle to capture deeper brain tumor image feature information due to the variations in brain tumor morphology,size,and complex background,resulting in low detection accuracy,high rate of misdiagnosis and underdiagnosis,and challenges in meeting clinical needs.Therefore,this paper proposes the CMS-YOLO network model for multi-category brain tumor detection,which is based on the You Only Look Once version 10(YOLOv10s)algorithm.This model innovatively integrates the Convolutional Medical UNet extended block(CMUNeXt Block)to design a brand-new CSP Bottleneck with 2 convolutions(C2f)structure,which significantly enhances the ability to extract features of the lesion area.Meanwhile,to address the challenge of complex backgrounds in brain tumor detection,a Multi-Scale Attention Aggregation(MSAA)module is introduced.The module integrates features of lesions at different scales,enabling the model to effectively capture multi-scale contextual information and enhance detection accuracy in complex scenarios.Finally,during the model training process,the Shape-IoU loss function is employed to replace the Complete-IoU(CIoU)loss function for optimizing bounding box regression.This ensures that the predicted bounding boxes generated by the model closely match the actual tumor contours,thereby further enhancing the detection precision.The experimental results show that the improved method achieves 94.80%precision,93.60%recall,96.20%score,and 79.60%on the MRI for Brain Tumor with Bounding Boxes dataset.Compared to the YOLOv10s model,this represents improvements of 1.0%,1.1%,1.0%,and 1.1%,respectively.The method can achieve automatic detection and localization of three distinct categories of brain tumors—glioma,meningioma,and pituitary tumor,which can accurately detect and identify brain tumors,assist doctors in early diagnosis,and promote the development of early treatment.
基金supported by the National Natural Science Foundation of China [Nos. 61772452, 61379116]the Scientific and Technological Innovation Programs of Higher Education Institutions in Shanxi [No.2019L0847]the Natural Science Foundation of Hebei Province, China [No. F2015203046]
文摘Faced with the evolving attacks in recommender systems, many detection features have been proposed by human engineering and used in supervised or unsupervised detection methods. However, the detection features extracted by human engineering are usually aimed at some specific types of attacks. To further detect other new types of attacks, the traditional methods have to re-extract detection features with high knowledge cost. To address these limitations, the method for automatic extraction of robust features is proposed and then an Adaboost-based detection method is presented. Firstly, to obtain robust representation with prior knowledge, unlike uniform corruption rate in traditional mLDA(marginalized Linear Denoising Autoencoder), different corruption rates for items are calculated according to the ratings’ distribution. Secondly, the ratings sparsity is used to weight the mapping matrix to extract low-dimensional representation. Moreover, the uniform corruption rate is also set to the next layer in mSLDA(marginalized Stacked Linear Denoising Autoencoder) to extract the stable and robust user features. Finally, under the robust feature space, an Adaboost-based detection method is proposed to alleviate the imbalanced classification problem. Experimental results on the Netflix and Amazon review datasets indicate that the proposed method can effectively detect various attacks.
基金The National Natural Science Foundation of China under contract Nos 41506198 and 41476101the Natural Science Foundation Projects of Shandong Province of China under contract No.ZR2012FZ003the Science and Technology Development Plan of Qingdao City of China under contract No.13-1-4-121-jch
文摘Since the atmospheric correction is a necessary preprocessing step of remote sensing image before detecting green tide, the introduced error directly affects the detection precision. Therefore, the detection method of green tide is presented from Landsat TM/ETM plus image which needs not the atmospheric correction. In order to achieve an automatic detection of green tide, a linear relationship（y =0.723 x＋0.504） between detection threshold y and subtraction x（x=λnir–λred） is found from the comparing Landsat TM/ETM plus image with the field surveys.Using this relationship, green tide patches can be detected automatically from Landsat TM/ETM plus image.Considering there is brightness difference between different regions in an image, the image will be divided into a plurality of windows（sub-images） with a same size firstly, and then each window will be detected using an adaptive detection threshold determined according to the discovered linear relationship. It is found that big errors will appear in some windows, such as those covered by clouds seriously. To solve this problem, the moving step k of windows is proposed to be less than the window width n. Using this mechanism, most pixels will be detected[n/k]×[n/k] times except the boundary pixels, then every pixel will be assigned the final class（green tide or sea water） according to majority rule voting strategy. It can be seen from the experiments, the proposed detection method using multi-windows and their adaptive thresholds can detect green tide from Landsat TM/ETM plus image automatically. Meanwhile, it avoids the reliance on the accurate atmospheric correction.
基金supported by the National Natural Science Foundation of China (Grants Nos. 41674163, 41474141, 41204120, 41304127, 41304130, and 41574160)the Projects funded by China Postdoctoral Science Foundation (Grants Nos. 2013M542051, 2014T70732)+2 种基金the Hubei Province Natural Science Excellent Youth Foundation (2016CFA044)the Project Supported by the Specialized Research Fund for State Key Laboratoriesthe 985 funded project of School of Electronic information, Wuhan University
文摘As a dispersive wave mode produced by lightning strokes, tweek atmospherics provide important hints of lower ionospheric(i.e., D-region) electron density. Based on data accumulation from the WHU ELF/VLF receiver system, we develop an automatic detection module in terms of the maximum-entropy-spectral-estimation(MESE) method to identify unambiguous instances of low latitude tweeks.We justify the feasibility of our procedure through a detailed analysis of the data observed at the Suizhou Station(31.57°N, 113.32°E) on17 February 2016. A total of 3961 tweeks were registered by visual inspection;the automatic detection method captured 4342 tweeks, of which 3361 were correct ones, producing a correctness percentage of 77.4%(= 3361/4342) and a false alarm rate of 22.6%(= 981/4342).A Short-Time Fourier Transformation(STFT) was also applied to trace the power spectral profiles of identified tweeks and to evaluate the tweek propagation distance. It is found that the fitting accuracy of the frequency–time curve and the relative difference of propagation distance between the two methods through the slope and through the intercept can be used to further improve the accuracy of automatic tweek identification. We suggest that our automatic tweek detection and analysis method therefore supplies a valuable means to investigate features of low latitude tweek atmospherics and associated ionospheric parameters comprehensively.
文摘Accurate detection and picking of the P-phase onset time in noisy microseismic data from underground mines remains a big challenge. Reliable P-phase onset time picking is necessary for accurate source location needed for planning and rescue operations in the event of failures. In this paper, a new technique based on the discrete stationary wavelet transform （DSWT）and higher order statist!cs, is proposed for processing noisy data from underground mines. The objectives of this method are to （1） Improve manual detection and tPicking of P-phase onset; and （ii） provide an automatic means of detecting and picking P-phase onset me accurately. The DSWT is first used to filter the signal over several scales. The manual P-phase onset detection and picking are then obtained by computing the signal energy across selected scales with frequency bands that capture the signal of interest. The automatic P-phase onset, on the other hand, is achieved by using skewness- and kurtosis-based criterion applied to selected scales in a time-frequency domain. The method was tested using synthetic and field data from an underground limestone mine. Results were compared with results obtained by using the short-term to long-term average （STA/LTA） ratio and that by Reference Ge et al. （2009）. The results show that the me!hod provides a more reliable estimate of the P-phase onset arrival than the STA]LTA method when the signal to noise ratio is very low. Also, the results obtained from the field data matched accurately with the results from Reference Ge et al. （2009）.
文摘The satellite-based automatic identification system (AIS) receiver has to encounter the frequency offset caused by the Doppler effect and the oscillator instability. This paper proposes a non-coherent sequence detection scheme for the satellite-based AIS signal transmitted over the white Gaussian noise channel. Based on the maximum likelihood estimation and a Viterbi decoder, the proposed scheme is capable of tolerating a frequency offset up to 5% of the symbol rate. The complexity of the proposed scheme is reduced by the state-complexity reduction, which is based on per-survivor processing. Simulation results prove that the proposed non-coherent sequence detection scheme has high robustness to frequency offset compared to the relative scheme when messages collision exists.
文摘In the process of bromine production,because of lag adjustment methods,there are problems of adjusting delay,raw material wastage and low growth rate.By considering the nature of bromine production,with the help of fuzzy data processing method,computer detection and display technique,we designed an automatic detection instrument for the ratio of chlorine to bromine in oxidized liquid of bromine production.This instrument can be used to detect the different parameters of raw materials adjustment and control in real time,and afford assurance that raw materials will be adjusted in time.This paper briefly introduces the working mechanism,hardware and software design of the instrument.
文摘On-line chatter detection can avoid unstable cutting through monitoring the machining process.In order to identify chatter in a timely manner,an improved Support Vector Machine(SVM)is developed in this paper,based on extracted features.In the SVM model,the penalty factor(e)and the core parameter(g)have important influence on the classification,more than from Kernel Functions(KFs).Hence,first the classification results are conducted using different KFs.Then two methods are presented for exploring the best parameters.The chatter identification results show that the Genetic Algorithm(GA)approach is more suitable for deciding the parameters than the Grid Explore(GE)approach.
文摘In the designed automatic balancing head, a non contact induction transformer is used to deliver driving energy to solve the problem of current fed and controlling on line. Computer controlled automatic balancing experiments with phase magnitude control tactics were performed on a flexible rotor system. Results of the experiments prove that the energy feeding method and the control tactics are effective in the automatic balancing head for vibration controlling.
文摘This paper presents an automatic system for failure detection in hydro-power generators. The main idea of this system is to detect failure using current and voltage signals acquired without any type of internal interference in the generator operation. The detected failures could be mechanical or electrical origins, such as: problems in bearings, unwanted vibrations, partial discharges, misalignment, unbalancing, among others. It is possible because the generator acts as a transducer for mechanical problems, and they appear in current and voltage signals. This automatic system based on electric signature analysis has been installed in Itapebi Power Plant generators since 2012. Some results are presented in this paper.
文摘The valuation relation of potential difference with discharging time in Electrical Discharge Machining (EDM) is analyzed theoretically and tested and verified by experiments designed in this paper and the relation between potential difference and spark location is induced and analyzed, and proceed by experiments under the condition of onedimension.
基金This work was supported by the National Natural Science Foundation of China(81630098,81671282,and 61471314).
文摘As an important promising biomarker,high frequency oscillations(HFOs)can be used to track epileptic activity and localize epileptogenic zones.However,visual marking of HFOs from a large amount of intracranial electroencephalogram(iEEG)data requires a great deal of time and effort from researchers,and is also very dependent on visual features and easily influenced by subjective factors.Therefore,we proposed an automatic epileptic HFO detection method based on visual features and non-intuitive multi-domain features.To eliminate the interference of continuous oscillatory activity in detected sporadic short HFO events,the iEEG signals adjacent to the detected events were set as the neighboring environmental range while the number of oscillations and the peak–valley differences were calculated as the environmental reference features.The proposed method was developed as a MatLab-based HFO detector to automatically detect HFOs in multi-channel,long-distance iEEG signals.The performance of our detector was evaluated on iEEG recordings from epileptic mice and patients with intractable epilepsy.More than 90%of the HFO events detected by this method were confirmed by experts,while the average missed-detection rate was<10%.Compared with recent related research,the proposed method achieved a synchronous improvement of sensitivity and specificity,and a balance between low false-alarm rate and high detection rate.Detection results demonstrated that the proposed method performs well in sensitivity,specificity,and precision.As an auxiliary tool,our detector can greatly improve the efficiency of clinical experts in inspecting HFO events during the diagnosis and treatment of epilepsy.
基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences,Grant No.XDA0330000 and Grant No.XDB44000000。
文摘Epilepsy is a common neurological disorder that occurs at all ages.Epilepsy not only brings physical pain to patients,but also brings a huge burden to the lives of patients and their families.At present,epilepsy detection is still achieved through the observation of electroencephalography(EEG)by medical staff.However,this process takes a long time and consumes energy,which will create a huge workload to medical staff.Therefore,it is particularly important to realize the automatic detection of epilepsy.This paper introduces,in detail,the overall framework of EEG-based automatic epilepsy identification and the typical methods involved in each step.Aiming at the core modules,that is,signal acquisition analog front end(AFE),feature extraction and classifier selection,method summary and theoretical explanation are carried out.Finally,the future research directions in the field of automatic detection of epilepsy are prospected.
文摘AIM:To develop an automated model for subfoveal choroidal thickness(SFCT)detection in optical coherence tomography(OCT)images,addressing manual fovea location and choroidal contour challenges.METHODS:Two procedures were proposed:defining the fovea and segmenting the choroid.Fovea localization from B-scan OCT image sequence with three-dimensional reconstruction(LocBscan-3D)predicted fovea location using central foveal depression features,and fovea localization from two-dimensional en-face OCT(LocEN-2D)used a mask region-based convolutional neural network(Mask R-CNN)model for optic disc detection,and determined the fovea location based on optic disc relative position.Choroid segmentation also employed Mask R-CNN.RESULTS:For 53 eyes in 28 healthy subjects,LocBscan-3D’s mean difference between manual and predicted fovea locations was 170.0μm,LocEN-2D yielded 675.9μm.LocEN-2D performed better in non-high myopia group(P=0.02).SFCT measurements from Mask R-CNN aligned with manual values.CONCLUSION:Our models accurately predict SFCT in OCT images.LocBscan-3D excels in precise fovea localization even with high myopia.LocEN-2D shows high detection rates but lower accuracy especially in the high myopia group.Combining both models offers a robust SFCT assessment approach,promising efficiency and accuracy for large-scale studies and clinical use.
