Single Threshold Method Research Articles

Biomarker trajectory for earlier detection of lung cancer

To determine whether an algorithm based on repeated measurements of a panel of four circulating protein biomarkers (4MP) for lung cancer risk assessment results in improved performance over a single time measurement. We conducted data analysis of the 4MP consisting of the precursor form of surfactant protein B, cancer antigen 125, carcinoembryonic antigen, and cytokeratin-19 fragment in pre-diagnostic sera from 2483 ever-smoker participants (389 cases and 2094 randomly selected non-cases) in the Prostate, Lung, Colorectal, Ovarian (PLCO) Study who had at least two sequential blood collections over 6 years. A parametric empirical Bayes (PEB) algorithm, which incorporates participant biomarker history at each time point, was compared to a single-threshold (ST) method. Among ever-smoker participants, the PEB approach yielded an additional 4% improvement in the AUC compared to the ST approach (P-value: 0.009). When considering an ≥10 PY smoking history and at a fixing the specificity corresponding to 1% 6-year lung cancer risk, PEB resulted in significant improvement in the sensitivity (SenPEB:96.3% vs SenST:91.0%; P-value: 6.7e-3). The PEB algorithm identified 17 of the 35 cases that remained ST negative, at an average of 1.26 years before diagnosis. Ten case individuals who were positive based on ST at an average of 1.03 years prior to diagnosis were identified earlier by PEB, at an average of 2.70 years. An algorithm based on repeated measurements of the 4MP improves sensitivity and results in an earlier detection of lung cancer compared to a single-threshold method. This study was supported by NIH Grant Nos. U01CA271888, U01CA194733, U01CA213285, NCI EDRN U01 CA200468, P30CA016672, and U24CA086368; the Cancer Prevention & Research Institute of Texas RP180505 and RP160693; the SPORE P50CA140388; the CCTS TR000371; and the generous philanthropic contributions to The University of Texas MD Anderson Cancer Center Moon Shots Program and the Lyda Hill Foundation.

DEVELOPMENT OF CLOUD DETECTION METHOD FOR CAS500-1 IMAGERY

Abstract. Clouds are typically characterized by high reflectance and low brightness temperature. They are generally classified as noise in optical land monitoring satellites. In particular, the presence of clouds has a decisive effect on the quality of follow-up data, so they must be detected. In this study, pre-processing was applied to effectively detect clouds while minimizing noise using CAS500-1 images with visible and near-infrared bands. First, the RGB color space is converted to the HSV color space. Next, a triangle thresholding method is applied to the value channel, which exhibits the highest correlation with pixel brightness, to extract bright objects. Then, the maximum likelihood method is applied to differentiate between bright objects and cloud candidate objects. Finally, threshold values for cloud detection are automatically determined to create initial cloud maps using the statistical values derived from the cloud candidate objects. We compared the results generated by the single thresholding method to verify the performance of the proposed method. As a result, the proposed method was able to detect clouds more accurately by considering the reflectance characteristics of each image. Moreover, except for cloud objects, the rest of the bright objects (white roofs, concrete roads, sand, etc.) were minimized. Our experiments showed high stability despite the absence of shortwave infrared and thermal infrared bands, which are effective for cloud detection.

Context Recognition Algorithms for Energy-Efficient Freezing-of-Gait Detection in Parkinson's Disease.

Freezing of gait (FoG) is a disabling clinical phenomenon of Parkinson's disease (PD) characterized by the inability to move the feet forward despite the intention to walk. It is one of the most troublesome symptoms of PD, leading to an increased risk of falls and reduced quality of life. The combination of wearable inertial sensors and machine learning (ML) algorithms represents a feasible solution to monitor FoG in real-world scenarios. However, traditional FoG detection algorithms process all data indiscriminately without considering the context of the activity during which FoG occurs. This study aimed to develop a lightweight, context-aware algorithm that can activate FoG detection systems only under certain circumstances, thus reducing the computational burden. Several approaches were implemented, including ML and deep learning (DL) gait recognition methods, as well as a single-threshold method based on acceleration magnitude. To train and evaluate the context algorithms, data from a single inertial sensor were extracted using three different datasets encompassing a total of eighty-one PD patients. Sensitivity and specificity for gait recognition ranged from 0.95 to 0.96 and 0.80 to 0.93, respectively, with the one-dimensional convolutional neural network providing the best results. The threshold approach performed better than ML- and DL-based methods when evaluating the effect of context awareness on FoG detection performance. Overall, context algorithms allow for discarding more than 55% of non-FoG data and less than 4% of FoG episodes. The results indicate that a context classifier can reduce the computational burden of FoG detection algorithms without significantly affecting the FoG detection rate. Thus, implementation of context awareness can present an energy-efficient solution for long-term FoG monitoring in ambulatory and free-living settings.

Zero-Velocity Detection Method Based on Ultrasonic Ranging Assistance

The accumulated error in inertial pedestrian navigation can be transplanted through the zero-velocity correction algorithm, and the zero-velocity detection algorithm at this stage has the problems of single threshold, easy to miss detection and false detection, large calculation amount and large calculation delay. In order to solve these problems, an ultrasonic ranging auxiliary zero-velocity detection method is proposed. The foot spacing is measured in real time by an ultrasonic sensor placed on both feet, and then a time constraint is added to the Generalized Likelihood Ratio (GLRT) method using the time relationship between the shortest foot spacing and the zero-velocity interval. Experiments show that the accuracy of the proposed algorithm is better than that of the single threshold method under different gait states, and the average accuracy is above 95%. And due to the characteristics of high ultrasonic short-distance accuracy and small size, this method has simple calculation and small delay, which has practical application value.

Comparison of Lake Ice Extraction Methods Based on MODIS Images

As an important part of the cryosphere, lake ice is a sensitive indicator of climate change. Remote sensing technology can quickly and accurately monitor the process of its formation and decay, among which Moderate Resolution Imaging Spectroradiometer (MODIS) images are the most widely used data in the remote sensing monitoring of lake ice. The reasonable selection of monitoring methods is of great significance to grasp the dynamic process and response to climate change of lake ice. In this study, five commonly used remote sensing monitoring methods of lake ice based on MODIS MOD09GA data, including the single band threshold method (SBT), reflectance difference threshold method (RDT), normalized difference snow index method (NDSI), modified normalized difference snow index method (MNDSI) and lake ice index method (LII), were selected to compare their accuracies in extracting lake ice extent by combining them with four evaluation metrics of accuracy, precision, recall and mean intersection over union (MIoU). In addition, the ability of the high-precision LII method for extracting long time series lake ice phenology and its applicability to multiple types of lakes were verified. The results showed that compared with the NDSI method, the other four methods more easily distinguished between lake ice and lake water by setting thresholds. The SBT method and the RDT method had better extraction effects in the freezing process and the melting process, respectively. Compared with the NDSI and MNDSI methods, the LII method showed a significant improvement in lake ice extraction over the entire freeze–thaw cycle, with the smallest mean monitoring error of 1.53% for the percentage of lake ice area in different periods. Meanwhile, the LII method can be used to determine long term lake ice phenology dates and had good performance in extracting lake ice for different types of lakes on the Qinghai–Tibet Plateau with the optimal threshold interval of 0.05~0.07, which can be used for lake ice monitoring and long-term phenological studies in this region.

Identification of high-temperature targets in remote sensing based on correspondence analysis

Abstract High temperature targets (temperature above 500 K), are the special on the surface of the earth such as forest fire, prairie fire, oil well torches, heap coking, volcanic eruptions, significantly different from those of normal surfaces at lower temperatures. Identification of high-temperature targets plays an important role in environmental monitoring, disaster warning, and resource investigation. In remote sensing data, high-temperature target pixels and bands are studied. And they are deemed samples and variables, respectively, in multivariate analysis. And classification of samples for identification of high-temperature targets is necessary. To classify samples, feature analysis of spectrum needs to be done first. In feature analysis of spectrum, feature bands that can be used to distinguish samples need to be selected. Correspondence analysis is the method that can project samples and variables into the same factor space in the meantime. It can realize the classification of samples and variables synchronously, and the results can be interpreted by each other. First, the correspondence analysis is conducted on Landsat8/OLI remote sensing imagery to build the relationship between samples and variables. After that the correspondence relationship between identification results of high-temperature targets and feature bands can be built in the physical theory of remote sensing and factors which have indicative significance on fire are confirmed. Finally, the single band threshold method is adopted to realize high temperature target recognition by using factor scores. In the field confirmation, results suggest that the precision of identification of high-temperature targets reaches 92%. And we also get a consistent result with SWIR temperature inversion.

Long short-term memory model – A deep learning approach for medical data with irregularity in cancer predication with tumor markers

BackgroundMachine learning (ML) has emerged as a superior method for the analysis of large datasets. Application of ML is often hindered by incompleteness of the data which is particularly evident when approaching disease screening data due to varied testing regimens across medical institutions. Here we explored the utility of multiple ML algorithms to predict cancer risk when trained using a large but incomplete real-world dataset of tumor marker (TM) values. MethodsTM screening data were collected from a large asymptomatic cohort (n = 163,174) at two independent medical centers. The cohort included 785 individuals who were subsequently diagnosed with cancer. Data included levels of up to eight TMs, but for most subjects, only a subset of the biomarkers were tested. In some instances, TM values were available at multiple time points, but intervals between tests varied widely. The data were used to train and test various machine learning models to evaluate their robustness for predicting cancer risk. Multiple methods for data imputation were explored and models were developed for both single time-point as well as time-series data. ResultsThe ML algorithm, long short-term memory (LSTM), demonstrated superiority over other models for dealing with irregular medical data. A cancer risk prediction tool was trained and validated for a single time-point test of a TM panel including up to four biomarkers (AUROC = 0.831, 95% CI: 0.827–0.835) which outperformed a single threshold method using the same biomarkers. A second model relying on time series data of up to four time-points for 5 TMs had an AUROC of 0.931. ConclusionsA cancer risk prediction tool was developed by training a LSTM model using a large but incomplete real-world dataset of TM values. The LSTM model was best able to handle irregular data compared to other ML models. The use of time-series TM data can further improve the predictive performance of LSTM models even when the intervals between tests vary widely. These risk prediction tools are useful to direct subjects to further screening sooner, resulting in earlier detection of occult tumors.

Application of the MADM Method for the Admission System for Islamic Religious Trustees

The selection process for Islamic tutor and the decision to pass or fail is made by subjective views of the selector. The konvensional process takes a lot of time. It is necessary to have Decision Support System (DSS) to minimize the subjective side of the selectors and streamline the selection process so that effective decision can be obtained. The character of this problem matches the characteristic of Multi Attribute Decision Making (MADM) model. A combination of Simple Addictive Weighting (SAW) and Technique for Others Reference by Similarity to Ideal Solution (TOPSIS) are selected to solve MADM model. SAW used to rank decision while TOPSIS used to calculate level 2 criteria. Based on testing of 30 data samples using Single Detection Threshold method, the system performance accuracy rate is 83,33% and precision rate is 77%. The combination of the two method has been successfully applied and provide accurate and precise recommendations.

Improved Detection Performance of Energy Detection Based Spectrum Sensing in Cognitive Radio Networks

Background: In cognitive radio networks, spectrum sensing plays an important role in identifying the underutilized spectrum bands. Conventional spectrum sensing using energy detection method uses single detection threshold, which degrades the detection performance. Method: Therefore double detection threshold has been proposed for spectrum sensing in the literature to improve the detection performance, but the performance depends on the region between two thresholds termed as confusion state. Hence to improve the overall detection performance new re-sensing scheme has been proposed in this paper by varying the difference between thresholds by an improvement factor K. Results: The proposed method improves the detection performance compared to the single threshold method and double threshold method. Conclusion: Simulation results show that the proposed method operates better than the single threshold energy detection method and improves the detection performance at low signal to noise ratios.

Medical Image Segmentation Of Wbc Using Improved Dual Threshold Method

segmentation of medical images is a critical method for the proper identification and diagnosis of diseases. Because of the distinction between them, the segmentation of the WBCs is an important issue.The automatic diagnosis of multiple white blood cell or leukocyte disorders plays a significant role. The suggested work is an Improved Dual-Threshold approach based on a variation of white blood cell (WBC) segmentation of different color spaces. The improved dual-threshold segmentation method consists of three stages: the pre-processing stage, the segmentation step of the threshold, and the post-procurement phase. For additional handling, two images are obtained: one is a contrast-stretched grey image and the other is an H part image from the altered colour space of YCbCr in the pre-processing step. The three main steps comprising the threshold segmentation are context separation, red blood cell extraction, and the finest threshold selection.The single-threshold method in RGB colour space is involved in the process of separation of Red Blood Cells (RBC), the H channel image is used in the step of background extraction. The Golden Section search method is used for the best threshold selection item. Finally, to eliminate the noise and the unfinished
 WBCs, median filtering and arithmetical morphology are used in the post-processing stage. The image data collection for Acute Lymphoblastic Leukaemia (ALL) is used to test and segment irregular cells from test data using an overall accuracy. Compared to the current segmentation outcome, the implemented segmentation approach shows better precision performance.

Improving the sorting efficiency of maize haploid kernels using an NMR-based method with oil content double thresholds

BackgroundMaize haploid breeding technology can be used to rapidly develop homozygous lines, significantly shorten the breeding cycle and improve breeding efficiency. Rapid and accurate sorting haploid kernels is a prerequisite for the large-scale application of this technology. At present, the automatic haploid sorting based on nuclear magnetic resonance (NMR) using a single threshold method has been realized. However, embryo-aborted (EmA) kernels are usually produced during in vivo haploid induction, and both haploids and EmA kernels have lower oil content and are separated together using a single threshold method based on NMR. This leads to a higher haploid false discrimination rate (FDR) and requires secondary manual sorting to select the haploid kernels from the mixtures, which increases the sorting cost and decreases the haploid sorting efficiency. In order to improve the correct discrimination rate (CDR) in sorting haploids, a method to distinguish EmA kernels is required.ResultsSingle kernel weight and oil content were measured for the diploid, haploid, and EmA kernels derived from three maize hybrids and nine inbred lines by in vivo induction. The results showed that the distribution of oil content showed defined boundaries between the three types of kernels, while the single kernel weight didn't. According to the distribution of oil content in the three types of kernels, a double-threshold method was proposed to distinguish the embryo-aborted kernels, haploid and diploid kernels based on NMR and their oil content. The double thresholds were set based on the minimum oil content of diploid kernels and the maximum content of EmA kernels as the upper and lower boundary values, respectively. The CDR of EmA kernels in different maize materials was > 97.8%, and the average FDR was reduced by 27.9 percent.ConclusionsThe oil content is an appropriate indicator to discriminate diploid, haploid and EmA kernels. An oil content double-threshold method based on NMR was first developed in this study to identify the three types of kernels. This methodology could reduce the FDR of haploids and improve the sorting efficiency of automated sorting system. Thus, this technique represents a potentially efficient method for haploid sorting and provides a reference for the process of automated sorting of haploid kernels with high efficiency using NMR.

Novel slope-based onset detection algorithm for electromyographical signals

Electromyography (EMG) is a technique of acquiring neuromuscular activity of muscle. Onset and offset gives information about activation and deactivation timings of motor units. This paper proposes a novel slope-based algorithm for onset and offset detection. EMG data are collected from different muscle of different subjects using surface EMG electrodes. Data is divided into smaller windows and average instantaneous amplitude (AIA) and slope is calculated for each window. A threshold is decided to avoid baseline noise. Below threshold, maximum and minimum slope is detected as the onset and offset respectively. The results are accurate compared to single threshold and double threshold method. Accuracy increases with computation complexity (arithmetic calculations); if compared with root mean square (RMS)-based algorithm. The only limitation is decrease in accuracy if signal is acquired between two muscle contractions. The proposed slope-based onset detection algorithm can be way out between accuracy and computational complexity.

Novel slope-based onset detection algorithm for electromyographical signals

Electromyography (EMG) is a technique of acquiring neuromuscular activity of muscle. Onset and offset gives information about activation and deactivation timings of motor units. This paper proposes a novel slope-based algorithm for onset and offset detection. EMG data are collected from different muscle of different subjects using surface EMG electrodes. Data is divided into smaller windows and average instantaneous amplitude (AIA) and slope is calculated for each window. A threshold is decided to avoid baseline noise. Below threshold, maximum and minimum slope is detected as the onset and offset respectively. The results are accurate compared to single threshold and double threshold method. Accuracy increases with computation complexity (arithmetic calculations); if compared with root mean square (RMS)-based algorithm. The only limitation is decrease in accuracy if signal is acquired between two muscle contractions. The proposed slope-based onset detection algorithm can be way out between accuracy and computational complexity.

Measuring Bone Volume at Multiple Densities by Micro-computed Tomography.

Bone strength is controlled by both bone mass, and the organization and quality of the bone material. The current standard method for measuring bone mass in mouse and rat studies is micro-computed tomography. This method typically uses a single threshold to identify bone material in the cortical and trabecular regions. However, this single threshold method obscures information about the mineral content of the bone material and depends on normal morphology to separately analyze cortical and trabecular structures. To extend this method to identify bone mass at multiple density levels, we have established a protocol for unbiased selection and application of multiple thresholds using a standard laboratory-based micro-computed tomography instrument. This non-invasive method can be applied to longitudinal studies and archived samples and provides additional information about bone structure and strength.

Savitzky-Golay Filtering and Improved Energy Entropy for Speech Endpoint Detection under Low SNR

Under the condition of low signal-to-noise ratio (SNR) or non-stationary noise, the performance of endpoint detection is poor. Therefore, this paper proposes a speech endpoint detection algorithm for low SNR. In this paper, Savitzky-Golay filtering, improved sub-band energy entropy and constant Q-transform (CQT) are used to extract features, and single parameter double threshold method is used to realize endpoint detection. In this paper, clean speech and noise-92 speech fragments are used to evaluate the algorithm. Experimental results show that the algorithm in this paper can distinguish speech endpoints well. For Gaussian white noise, Factory noise and Volvo noise, the detection accuracy of the improved algorithm is improved by 5.5%, 5.3% and 4.6% respectively. Therefore, the algorithm in this paper can separate the mute and voice in complex environment.

Contrast Enhancement Using Optimum Threshold Selection

In the recent era, a boom was observed in the field of information retrieval from images. Digital images with high contrast are sources of abundant information. The gathered information is useful in the precise detection of an object, event, or anomaly captured in an image scene. Existing systems do uniform distribution of intensities and apply intensity histogram equalization. These improve the characteristics of an image in terms of visual appearance. The problem of over enhancement and the increase in noise level produces undesirable visual artefacts. The use of Otsu's single threshold method in existing systems is inefficient for segmenting an image with multiple objects and complex background. Additionally, these are incapable to improve the yield of the maximum entropy and brightness preservation. The aforementioned limitations motivate us to propose an efficient statistical pipelined approach, the Range Limited Double Threshold Weighted Histogram Equalization (RLDTWHE). This approach is an integration of Otsu's double threshold, dynamic range stretching, weighted distribution, adaptive gamma correction, and homomorphic filtering. It provides optimum contrast enhancement by selecting the best appropriate threshold value for image segmentation. The proposed approach is efficient in the enhancement of low contrast medical MRI images and digital natural scene images. It effectively preserves all essential information recorded in an image. Experimental results prove its efficacy in terms of maximum entropy preservation, brightness preservation, contrast enhancement, and retaining the natural appearance of an image.

Adaptive Double-Threshold Cooperative Spectrum Sensing Algorithm Based on History Energy Detection

Spectrum sensing is one of the key technologies in the field of cognitive radio, which has been widely studied. Among all the sensing methods, energy detection is the most popular because of its simplicity and no requirement of any prior knowledge of the signal. In the case of low signal-to-noise ratio (SNR), the traditional double-threshold energy detection method employs fixed thresholds and there is no detection result when the energy is between high and low thresholds, which leads to poor detection performance such as lower detection probability and longer spectrum sensing time. To address these problems, we proposed an adaptive double-threshold cooperative spectrum sensing algorithm based on history energy detection. In each sensing period, we calculate the weighting coefficient of thresholds according to the SNR of all cognitive nodes; thus, the upper and lower thresholds can be adjusted adaptively. Furthermore, in a single cognitive node, once the current energy is within the high and low thresholds, we utilize the average energy of history sensing times to rejudge. To ensure the real-time performance, if the average history energy is still between two thresholds, the single-threshold method will be used for the end decision. Finally, the fusion center aggregates the detection results of each node and obtains the final cooperative conclusion through “or” criteria. Theoretical analysis and simulation results show that the algorithm proposed in this paper improved detection performance significantly compared with the other four different double-threshold algorithms.

Robust Combined Binarization Method of Non-Uniformly Illuminated Document Images for Alphanumerical Character Recognition.

Image binarization is one of the key operations decreasing the amount of information used in further analysis of image data, significantly influencing the final results. Although in some applications, where well illuminated images may be easily captured, ensuring a high contrast, even a simple global thresholding may be sufficient, there are some more challenging solutions, e.g., based on the analysis of natural images or assuming the presence of some quality degradations, such as in historical document images. Considering the variety of image binarization methods, as well as their different applications and types of images, one cannot expect a single universal thresholding method that would be the best solution for all images. Nevertheless, since one of the most common operations preceded by the binarization is the Optical Character Recognition (OCR), which may also be applied for non-uniformly illuminated images captured by camera sensors mounted in mobile phones, the development of even better binarization methods in view of the maximization of the OCR accuracy is still expected. Therefore, in this paper, the idea of the use of robust combined measures is presented, making it possible to bring together the advantages of various methods, including some recently proposed approaches based on entropy filtering and a multi-layered stack of regions. The experimental results, obtained for a dataset of 176 non-uniformly illuminated document images, referred to as the WEZUT OCR Dataset, confirm the validity and usefulness of the proposed approach, leading to a significant increase of the recognition accuracy.

Fast Unsupervised Edge Detection Using Genetic Programming [Application Notes

Edge detection has been a fundamental and important task in computer vision for many years, but it is still a challenging problem in real-time applications, especially for unsupervised edge detection, where ground truth is not available. Typical fast edge detection approaches, such as the single threshold method, are expensive to achieve in unsupervised edge detection. This study proposes a Genetic Programming (GP) based algorithm to quickly and automatically extract binary edges in an unsupervised manner. We investigate how GP can effectively evolve an edge detector from a single image without ground truth, and whether the evolved edge detector can be directly applied to other unseen/test images. The proposed method is examined and compared with a recent GP method and the Canny method on the Berkeley segmentation dataset. The results show that the proposed GP method has the ability to effectively evolve edge detectors by using only a single image as the whole training set, and significantly outperforms the two methods it is compared to. Furthermore, the binary edges detected by the evolved edge detectors have a good balance between recall and precision.

Characteristics of the impedance variation in clastic rock reservoirs and lithology interpretation method for the threshold volume

Abstract An analysis of the petrophysical characteristics of a reservoir demonstrated that the variations in wave velocity were controlled by sedimentary and diagenetic differences, resulting in regular variations in the acoustic impedance. The sedimentary differences are mainly associated with the grain size, sorting and shale content and lead to a slow horizontal change in the wave impedance of the reservoir; the diagenetic differences are associated with compaction, pressure dissolution and cementation and lead to a rapid vertical change in the wave impedance of the reservoir. The classic single threshold method only resolved the vertical variation in the acoustic impedance. As a result, the threshold volume method is proposed. The results of a case study demonstrate that the proposed method yields a more accurate and reliable interpretation of lithology using acoustic impedance than the single threshold method. In particular, the method effectively solves the uncertainty in the sand interpretation using the plane variation of impedance caused by the deposit.