Threshold Selection Algorithm Research Articles

An online fault detection and diagnosis method of sensors in district heating substations based on long short-term memory network and adaptive threshold selection algorithm

District heating system is an essential energy infrastructure. Due to the harsh working environment, sensors in district heating substations are prone to faults, which will mislead the control strategies of substations. We propose an online fault detection and diagnosis (FDD) method for sensors in substations. The proposed method establishes a Sequence-to-Sequence Prediction Model based on Long Short-Term Memory network with Spatial-Temporal Attention (abbreviated as STALSTM-seq2seq model) for each target sensor. The model can learn normal and evolving data patterns from historical time series of sensors and predict current sensor observation. Then, an adaptive threshold selection algorithm is used to autonomously determine current anomaly threshold based on the prediction error vector of the model. If the prediction error exceeds the anomaly threshold, the sensor malfunctions. Otherwise, the sensor operates normally. Through a comprehensive case study, we demonstrate that the adaptive threshold selection algorithm can fully utilize the forecasting ability of the STALSTM-seq2seq model, and thereby ensure the accuracy of sensor FDD. Overall, the online sensor FDD method achieves an average F1 score of 0.8473. The research shows that the proposed method provides an effective and robust solution to timely and accurately identify sensor faults for district heating substations.

Discrete Wavelet Transformation for the Sensitive Detection of Ultrashort Radiation Pulse with Radiation-induced Acoustics.

Radiation-induced acoustics (RIA) shows promise in advancing radiological imaging and radiotherapy dosimetry methods. However, RIA signals often require extensive averaging to achieve reasonable signal-to-noise ratios, which increases patient radiation exposure and limits real-time applications. Therefore, this paper proposes a discrete wavelet transform (DWT) based filtering approach to denoise the RIA signals and avoid extensive averaging. The algorithm was benchmarked against low-pass filters and tested on various types of RIA sources, including low-energy X-rays, high-energy X-rays, and protons. The proposed method significantly reduced the required averages (1000 times less averaging for low-energy X-ray RIA, 32 times less averaging for high-energy X-ray RIA, and 4 times less averaging for proton RIA) and demonstrated robustness in filtering signals from different sources of radiation. The coif5 wavelet in conjunction with the sqtwolog threshold selection algorithm yielded the best results. The proposed DWT filtering method enables high-quality, automated, and robust filtering of RIA signals, with a performance similar to low-pass filtering, aiding in the clinical translation of radiation-based acoustic imaging for radiology and radiation oncology.

Design and implementation of a parallel OTSU algorithm based on a ternary optical computer

The OTSU method (OTSU) is considered to be the best algorithm for threshold selection in image segmentation. The algorithm is easy to calculate and not affected by image brightness and contrast, so it is widely used in the field of digital image processing. Due to the slow running speed and large storage space of the algorithm on the traditional electronic computer, this research makes use of the advantages of the ternary optical computer (TOC), such as numerous data bits and the reconfigurable processor. Through the analysis of the OTSU algorithm, we find the part of the OTSU algorithm that can be calculated in parallel, and put forward a parallel OTSU algorithm based on TOC. The algorithm first uses a classifier to classify the number of pixels. By reconstructing the MSD adder and multiplier, the inter-class variance under each gray value is calculated in parallel, and the maximum value is selected by comparing the inter-class variance. The corresponding threshold is the best segmentation threshold. By analyzing the clock cycle and data bit resources of the algorithm, and then conducting a comparative analysis and experimental verification, we found that the computational speed of TOC increased by approximately 12% when handling images with the same amount of computation.

Class-Wise Subspace Alignment-Based Unsupervised Adaptive Land Cover Classification in Scene-Level Using Deep Siamese Network.

In this article, an unsupervised domain adaptation strategy has been investigated using a deep Siamese neural network in scene-level land cover classification using remotely sensed images. At the onset, the soft class label and probability scores of each target sample have been obtained using a pretrained model of a deep convolutional neural network. Thereafter, a semiautomatic threshold selection algorithm along with a graph-based approach has been explored to obtain the ``most-confident'' target samples. Furthermore, the deep Siamese network has been incorporated by training the source and ``most-confident'' target samples to generate the classwise cross domain common subspace. To assess the effectiveness of the proposed framework, experiments are carried out using three aerial image datasets. The results are found to be encouraging for the proposed scheme in comparison with the other state-of-art techniques.

An adaptive noise removal method for EEG signals

EEG signals are the response to the electrophysiological activity of brain nerve cells in the cerebral cortex, but the collected EEG signal generally contains noise. In order to effectively remove the noise and retain useful information, after research and analysis, this paper proposes an improved EEG noise-removing algorithm based on the threshold method where wavelet contraction is used. The improved adaptive threshold selection algorithm makes it possible that the threshold changes with the number of layers of decomposed signal, so it can be applied flexibly in practice. The wavelet transform is used to decompose the EEG signal into multiple layers of high- and low-frequency coefficients. Adaptive threshold processing is then applied to the wavelet coefficients in accordance with the various decomposition levels, and the scaled wavelet coefficients are then reconstituted to produce the denoised EEG signal. Using the Root Mean Square Error (RMSE) and Signal Noise Ratio (SNR) as quantitative measures of the denoising effect Through trials, the improved threshold method, hard and soft threshold method, and adaptive threshold method were contrasted. The experimental findings demonstrate that the wavelet shrinkage-based improved threshold approach has a better denoising effect than the other three threshold methods.

Multi-objective Metaheuristics with Intelligent Deep Learning Model for Pancreatic Tumor Diagnosis

Pancreatic tumor is the deadliest disease which needs earlier identification to reduce the mortality rate. With this motivation, this study introduces a Multi-Objective Metaheuristics with Intelligent Deep Learning Model for Pancreatic Tumor Diagnosis (MOM-IDL) model. The proposed MOM-IDL technique encompasses an adaptive Weiner filter based pre-processing technique to enhance the image quality and get rid of the noise. In addition, multi-level thresholding based segmentation using Kapur’s entropy is employed where the threshold values are optimally chosen by the barnacles mating optimizer (BMO). Besides, densely connected network (DenseNet-169) is employed as a feature extractor and fuzzy support vector machine (FSVM) is utilized as a classifier. For improving the classification performance, the BMO technique was implemented for fine-tuning the parameters of the FSVM model. The design of MOBMO algorithm for threshold selection and parameter optimization processes shows the novelty of the work. A wide range of simulations take place on the benchmark dataset and the experimental results highlighted the enhanced performance of the MOM-IDL technique over the recent state of art techniques.

Applying Machine Learning for Threshold Selection in Drought Early Warning System

This study investigates the relationship between the Normalized Difference Vegetation Index (NDVI) and meteorological drought category to identify NDVI thresholds that correspond to varying drought categories. The gridded evaluation was performed across a 34-year period from 1982 to 2016 on a monthly time scale for Grassland and Temperate regions in Australia. To label the drought category for each grid inside the climate zone, we use the Australian Gridded Climate Dataset (AGCD) across a 120-year period from 1900 to 2020 on a monthly scale and calculate percentiles corresponding to drought categories. The drought category classification model takes NDVI data as the input and outputs of drought categories. Then, we propose a threshold selection algorithm to distinguish the NDVI threshold to indicate the boundary between two adjacent drought categories. The performance of the drought category classification model is evaluated using the accuracy metric, and visual interpretation is performed using the heat map. The drought classification model provides a concept to evaluate drought severity, as well as the relationship between NDVI data and drought severity. The results of this study demonstrate the potential application of this concept toward early drought warning systems.

Quantitative optical diagnostics on macroscopic soot onset for ethylene diffusion flames with ethyl ester addition.

A novel quantitative optical diagnostics method for determining the threshold of soot onset in counterflow diffusion flames was proposed and demonstrated. The method was based on the proportional discrimination of trichromatic luminescence and the nonparametric and unsupervised automatic threshold selection algorithm. The macroscopic soot onset threshold in ethylene diffusion flame with three ethyl esters additions could be precisely determined. It was found that the undesirable soot onset phenomenon for ethylene diffusion flames was significantly suppressed with ethyl ester addition. The method proposed here will be useful as a reference for soot diagnostics in other flames.

Automated surface texture analysis via Discrete Cosine Transform and Discrete Wavelet Transform

Surface roughness and texture are critical to the functional performance of engineering components. The ability to analyze roughness and texture effectively and efficiently is much needed to ensure surface quality in many surface generation processes, such as machining, surface mechanical treatment, etc. Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) are two commonly used signal decomposition tools for surface roughness and texture analysis. Both methods require selecting a threshold to decompose a given surface into its three main components: form, waviness, and roughness. However, although DWT and DCT are part of the ISO surface finish standards, there exists no systematic guidance on how to compute these thresholds, and they are often manually selected on case by case basis. This makes utilizing these methods for studying surfaces dependent on the user's judgment and limits their automation potential. Therefore, we present two automatic threshold selection algorithms based on information theory and signal energy. We use machine learning to validate the success of our algorithms both using simulated surfaces as well as digital microscopy images of machined surfaces. Specifically, we generate feature vectors for each surface area or profile and apply supervised classification. Comparing our results with the heuristic threshold selection approach shows good agreement with mean accuracies as high as 95%. We also compare our results with Gaussian filtering (GF), and show that while GF results for areas can yield slightly higher accuracies, our results outperform GF for surface profiles. We further show that our automatic threshold selection has significant advantages in terms of computational time as evidenced by decreasing the number of mode computations by an order of magnitude compared to the heuristic thresholding for DCT.

Intelligent Deep-Learning-Enabled Decision-Making Medical System for Pancreatic Tumor Classification on CT Images.

Decision-making medical systems (DMS) refer to the design of decision techniques in the healthcare sector. They involve a procedure of employing ideas and decisions related to certain processes such as data acquisition, processing, judgment, and conclusion. Pancreatic cancer is a lethal type of cancer, and its prediction is ineffective with current techniques. Automated detection and classification of pancreatic tumors can be provided by the computer-aided diagnosis (CAD) model using radiological images such as computed tomography (CT) and magnetic resonance imaging (MRI). The recently developed machine learning (ML) and deep learning (DL) models can be utilized for the automated and timely detection of pancreatic cancer. In light of this, this article introduces an intelligent deep-learning-enabled decision-making medical system for pancreatic tumor classification (IDLDMS-PTC) using CT images. The major intention of the IDLDMS-PTC technique is to examine the CT images for the existence of pancreatic tumors. The IDLDMS-PTC model derives an emperor penguin optimizer (EPO) with multilevel thresholding (EPO-MLT) technique for pancreatic tumor segmentation. Additionally, the MobileNet model is applied as a feature extractor with optimal auto encoder (AE) for pancreatic tumor classification. In order to optimally adjust the weight and bias values of the AE technique, the multileader optimization (MLO) technique is utilized. The design of the EPO algorithm for optimal threshold selection and the MLO algorithm for parameter tuning shows the novelty. A wide range of simulations was executed on benchmark datasets, and the outcomes reported the promising performance of the IDLDMS-PTC model on the existing methods.

Otsu-Kmeans gravity-based multi-spots center extraction method for microlens array imaging system

We propose an Otsu-Kmeans gravity-based center extraction method for multi-spot images captured by the microlens array imaging system. We develop a 4-connected-region-based region of interest location method to recognize and segment light spot areas. We design an Otsu-Kmeans gravity-based threshold selection algorithm to realize the multi-spot center accurate position. Both numerical and actual experiments are implemented. The effectiveness and feasibility of the proposed method are validated by comparing with the results from the traditional centroid method, the Hough circle method, the Gaussian fitting method, and the Otsu thresholding centroid method. The results show that the proposed method can realize high-precision positioning and can be used for the sub-image segmentation of the microlens array imaging system.

Predicting postoperative recovery in cervical spondylotic myelopathy: construction and interpretation of T2*-weighted radiomic-based extra trees models.

Conventional MRI may not be ideal for predicting cervical spondylotic myelopathy (CSM) prognosis. In this study, we used radiomics in predicting postoperative recovery in CSM. We aimed to develop and validate radiomic feature-based extra trees models. There were 151 patients with CSM who underwent preoperative T2-/ T2*-weighted imaging (WI) and surgery. They were divided into good/poor outcome groups based on the recovery rate. Datasets from multiple scanners were randomised into training and internal validation sets, whilethe dataset from an independent scanner was used for external validation. Radiomic features were extracted from the transverse spinal cord at the maximum compressed level. Threshold selection algorithm, collinearity removal, and tree-based feature selection were applied sequentiallyin the training set to obtain theoptimal radiomic features. The classification of intramedullary increased signal on T2/T2*WI and compression ratio of the spinal cord on T2*WI were selected as the conventional MRI features. Clinical features were age, preoperative mJOA, and symptom duration. Four models were constructed: radiological, radiomic, clinical-radiological, and clinical-radiomic. An AUC significantly > 0.5 was considered meaningful predictive performance based on the DeLong test. The mean decrease in impurity was used to measure feature importance. p < 0.05 was considered statistically significant. On internal and external validations, AUCs of the radiomic and clinical-radiomic models, and radiological and clinical-radiological models ranged from 0.71 to 0.81 (significantly > 0.5) and 0.40 to 0.55, respectively. Wavelet-LL first-order variance was themost important featurein the radiomic model. Radiomic features, especially wavelet-LL first-order variance, contribute to meaningful predictive models for CSM prognosis. • Conventional MRI features may not be ideal in predicting prognosis. • Radiomics provides greater predictive efficiency in the recovery from cervical spondylotic myelopathy.

Causal Structure Learning Algorithm Based on Partial Rank Correlation under Additive Noise Model

ABSTRACT Aiming at the structural learning problem of the additive noise model in causal discovery and the challenge of massive data processing in the era of artificial intelligence, this paper combines partial rank correlation coefficients and proposes two new Bayesian network causal structure learning algorithms: PRCB algorithm based on threshold selection and PRCS algorithm based on hypothesis testing. We mainly made three contributions. First, we proved that the partial rank correlation coefficient can be used as the standard of independence test, and explored the distribution of corresponding statistics. Second, the partial rank correlation coefficient is associated with the correlation, and a causal discovery algorithm PRCB based on partial rank correlation and an improved PRCS algorithm based on hypothesis testing are proposed. Finally, comparing with the existing technology on seven classic Bayesian networks, it proves the superiority of the algorithm in low-dimensional networks; the processing of millions of data on three high-dimensional Bayesian networks verifies the high-efficiency performance of the algorithm in high-dimensional large sample data; the application performance of the algorithm is tested by performing fault prediction on the real power plant equipment measurement point data set. Theoretical analysis and experimental results have proved the superiority of the algorithm.

Concept Drift Detection Delay Index

Data streams may encounter data distribution changes, which can significantly impair the accuracy of models. Concept drift detection tracks data distribution changes and signals when to update models. Many drift detection methods apply thresholds to distinguish between drift or non-drift streams and to claim their method outperforms others with non-aligned drift thresholds. We consider that selecting a proper drift threshold could be more important than developing a new drift detection algorithm, and different drift detection algorithms may end up with very similar performance with aligned drift thresholds. To better understand this process, we propose a novel threshold selection algorithm to align the drift thresholds of a set of algorithms so that they are all at the same sensitivity level. Based on comprehensive experiment evaluations, we observed that several state-of-the-art drift detection algorithms could achieve similar results by aligning their thresholds, providing a novel insight to explain how drift detection algorithms contribute to data stream learning. We noticed that a higher detection sensitivity improves accuracy for data streams with frequent distribution change. The evaluation results are showing that drift thresholds should not be fixed during stream learning. Rather, they should adjust dynamically based on the prevailing conditions of the data stream.

Time-domain extrapolation method for tractor drive shaft loads in stationary operating conditions

The fatigue failure of critical parts of tractors over the whole life cycle has received much attention in recent years. Load extrapolation is a crucial step in load spectrum compilation and can extrapolate the product's life cycle load based on limited load data measurements. The traditional time-domain extrapolation method is limited because it neglects the time interval between the load changes and the load reconstruction within the threshold range. To address this problem, a time-domain extrapolation method for tractor drive shaft load based on the Markov chain Monte Carlo-peak over threshold (MCMC-POT) model is proposed. Firstly, an improved time-domain load reconstruction method based on MCMC that can reproduce the load change interval based on the measured load change characteristics was proposed. Secondly, in the POT model extrapolation process, an improved threshold selection algorithm that is an optimisation of the traditional mean excess function (MEF) method was proposed. This method avoids the errors caused by subjective factors under the premise of ensuring the fitting accuracy. Finally, the dynamic torque spectrum was obtained by extrapolating the tractor drive shaft load data measured under ploughing conditions. Case analysis results showed that the method can obtain extrapolation models with high fitting accuracy. The power spectral density values of the dynamic torque spectrum before and after extrapolation were very consistent with the mean correlation coefficient of 0.909. The spectrum can effectively reproduce the time-frequency characteristics of the load. Furthermore, the precision of the load spectrum is improved. • A time-domain load reconstruction method based on Markov chain Monte Carlo model. • The threshold selection method based on peak over threshold model was improved. • A load extrapolation method that can retain complete time-frequency information. • Tractor transmission shaft testing was implemented under ploughing conditions. • The extrapolated load has the consistent frequency spectrum with the measured.

Automatic threshold selection algorithm to distinguish a tissue chromophore from the background in photoacoustic imaging.

The adaptive matched filter (AMF) is a method widely used in spectral unmixing to classify different tissue chromophores in photoacoustic images. However, a threshold needs to be applied to the AMF detection image to distinguish the desired tissue chromophores from the background. In this study, we propose an automatic threshold selection (ATS) algorithm capable of differentiating a target from the background, based on the features of the AMF detection image. The mean difference between the estimated thickness, using the ATS algorithm, and the known values was 0.17 SD (0.24) mm for the phantom inclusions and -0.05 SD (0.21) mm for the tissue samples of malignant melanoma. The evaluation shows that the thickness and the width of the phantom inclusions and the tumors can be estimated using AMF in an automatic way after applying the ATS algorithm.

Impairment-aware spectrum allocation in elastic optical networks: A dispersion-sensitive approach

The degradation of quality-of-transmission (QoT) due to the dispersion effect is a critical issue in elastic optical networks (EONs). To satisfy the required quality of transmission, a robust modulation level needs to be adopted. Thus, the number of required slots for spectrum allocation is increased. Although dispersion compensation devices reduce the effect of dispersion, they require an additional cost. This paper presents a dispersion-sensitive spectrum allocation approach for EONs to suppress the call blocking in the network. The presented spectrum allocation approach does not use any dispersion compensating device for suppressing the dispersion effect. It allocates shorter lightpath requests from the largest indexed spectrum slot, where the effect of dispersion is higher, and longer lightpath requests from the smallest indexed spectrum slot, where the effect of dispersion is lower. To satisfy the required QoT threshold level for the longer lightpath requests, the presented approach uses a less robust modulation level. Thus, for lightpath establishment, a lower number of spectrum slots are required. In the presented approach, lightpath requests are separated as longer and shorter lightpath requests using either the predetermined-threshold policy or the lightpath threshold selection algorithm. When the traffic condition is not known in advance, the predetermined-threshold policy is not applicable. In that case, the lightpath threshold selection algorithm is used to find the distance threshold value, which provides the lowest blocking probability. Simulation results indicate that the presented dispersion-sensitive spectrum allocation approach outperforms the conventional spectrum allocation scheme in terms of available contiguous aligned slot ratio and blocking probability.

Real-Time Schedulability Analysis and Enhancement of Transiently Powered Processors With NVMs

Recent Internet-of-Things or Wireless Sensor Network devices are often operated with energy harvesters. As there are no energy storages in those devices, power is not consistently provided to the devices at all times. In such transiently powered systems, in order to keep the system reliable without losing any execution contexts, non-volatile memories (NVMs) are typically used for swift backup/restoration of execution contexts. In this article, we perform a real-time schedulability analysis of the transiently powered processors with NVMs. We first quantitatively characterize the charging and discharging behaviors of the energy harvester and extract the compute capability of the system in time interval domain. Then, based on Real-Time Calculus, we determine whether the given multi-task workload is schedulable or not with respect to the earliest deadline first (EDF) or fixed-priority (FP) scheduling policies. In addition, we study how the choice of the threshold voltage parameter affects the schedulability, then propose a feasible threshold selection algorithm to enhance schedulability. We verify the effectiveness of the proposed technique with extensive simulations. Compared to the naive selection method, the proposed technique always shows improvements in schedulability in various workloads.

A novel framework for MR image segmentation and quantification by using MedGA

Background and Objectives: Image segmentation represents one of the most challenging issues in medical image analysis to distinguish among different adjacent tissues in a body part. In this context, appropriate image pre-processing tools can improve the result accuracy achieved by computer-assisted segmentation methods. Taking into consideration images with a bimodal intensity distribution, image binarization can be used to classify the input pictorial data into two classes, given a threshold intensity value. Unfortunately, adaptive thresholding techniques for two-class segmentation work properly only for images characterized by bimodal histograms. We aim at overcoming these limitations and automatically determining a suitable optimal threshold for bimodal Magnetic Resonance (MR) images, by designing an intelligent image analysis framework tailored to effectively assist the physicians during their decision-making tasks.Methods: In this work, we present a novel evolutionary framework for image enhancement, automatic global thresholding, and segmentation, which is here applied to different clinical scenarios involving bimodal MR image analysis: (i) uterine fibroid segmentation in MR guided Focused Ultrasound Surgery, and (ii) brain metastatic cancer segmentation in neuro-radiosurgery therapy. Our framework exploits MedGA as a pre-processing stage. MedGA is an image enhancement method based on Genetic Algorithms that improves the threshold selection, obtained by the efficient Iterative Optimal Threshold Selection algorithm, between the underlying sub-distributions in a nearly bimodal histogram.Results: The results achieved by the proposed evolutionary framework were quantitatively evaluated, showing that the use of MedGA as a pre-processing stage outperforms the conventional image enhancement methods (i.e., histogram equalization, bi-histogram equalization, Gamma transformation, and sigmoid transformation), in terms of both MR image enhancement and segmentation evaluation metrics.Conclusions: Thanks to this framework, MR image segmentation accuracy is considerably increased, allowing for measurement repeatability in clinical workflows. The proposed computational solution could be well-suited for other clinical contexts requiring MR image analysis and segmentation, aiming at providing useful insights for differential diagnosis and prognosis.

Automated compositional importance splitting

In the formal verification of stochastic systems, statistical model checking uses simulation to overcome the state space explosion problem of probabilistic model checking. Yet its runtime explodes when faced with rare events, unless a rare event simulation method like importance splitting is used. The effectiveness of importance splitting hinges on nontrivial model-specific inputs: an importance function with matching splitting thresholds. This prevents its use by non-experts for general classes of models. In this paper, we present an automated method to derive the importance function. It considers both the structure of the model and of the formula characterising the rare event. It is memory-efficient by exploiting the compositional nature of formal models. We experimentally evaluate it in various combinations with two approaches to threshold selection as well as different splitting techniques for steady-state and transient properties. We find that Restart splitting combined with thresholds determined via a new expected success method most reliably succeeds and performs very well for transient properties. It remains competitive in the steady-state case, which is however challenging to all combinations we consider. All methods are implemented in the modes tool of the Modest Toolset and in the Fig rare event simulator. • We provide methods to automatically derive the parameters of importance splitting for rare-event simulation of formal models. • Our methods apply to a broad class of stochastic models, including Markov chains and stochastic automata. • We introduce a compositional method to derive importance functions and a new threshold selection algorithm. • We implement three different importance splitting algorithms from the literature that use these inputs. • We perform an experimental evaluation using the Modest Toolset and the FIG tool.