A multi-level thresholding algorithm for threshold count and values identification based on dynamic programming

Cone beam CT (CBCT) images contain more scatter than a conventional CT image and therefore provide inaccurate Hounsfield units (HUs). Consequently, CBCT images cannot be used directly for radiotherapy dose calculation. The aim of this study is to enable dose calculations to be performed with the use of CBCT images taken during radiotherapy and evaluate the necessity of replanning. A patient with prostate cancer with bilateral metallic prosthetic hip replacements was imaged using both CT and CBCT. The multilevel threshold (MLT) algorithm was used to categorize pixel values in the CBCT images into segments of homogeneous HU. The variation in HU with position in the CBCT images was taken into consideration. This segmentation method relies on the operator dividing the CBCT data into a set of volumes where the variation in the relationship between pixel values and HUs is small. An automated MLT algorithm was developed to reduce the operator time associated with the process. An intensity-modulated radiation therapy plan was generated from CT images of the patient. The plan was then copied to the segmented CBCT (sCBCT) data sets with identical settings, and the doses were recalculated and compared. Gamma evaluation showed that the percentage of points in the rectum with γ < 1 (3%/3 mm) were 98.7% and 97.7% in the sCBCT using MLT and the automated MLT algorithms, respectively. Compared with the planning CT (pCT) plan, the MLT algorithm showed -0.46% dose difference with 8 h operator time while the automated MLT algorithm showed -1.3%, which are both considered to be clinically acceptable, when using collapsed cone algorithm. The segmentation of CBCT images using the method in this study can be used for dose calculation. For a patient with prostate cancer with bilateral hip prostheses and the associated issues with CT imaging, the MLT algorithms achieved a sufficient dose calculation accuracy that is clinically acceptable. The automated MLT algorithm reduced the operator time associated with implementing the MLT algorithm to achieve clinically acceptable accuracy. This saved time makes the automated MLT algorithm superior and easier to implement in the clinical setting. The MLT algorithm has been extended to the complex example of a patient with bilateral hip prostheses, which with the introduction of automation is feasible for use in adaptive radiotherapy, as an alternative to obtaining a new pCT and reoutlining the structures.

Multilevel minimum cross entropy thresholding: A comparative study

The proliferation of electric vehicles (EVs) brings environmental benefits and technical challenges to power grids. An identification algorithm which can accurately extract individual EV charging profiles out of widely available smart meter measurements has attracted great interests. This paper proposes a non-intrusive identification framework for EV charging profile extraction, which is driven by deep generative models (DGM). First, the proposed DGM is designed as a representation layer embedded into the Markov process and used to model the joint probability distribution of available time-series data. A novel contribution is to approximate posterior distributions by neural networks whose parameters are obtained by variational inference and supervised learning. Second, the EV charging status is inferred from the DGM via dynamic programming. Lastly, the desired EV charging profile can be reconstructed by the rated power of EV models and inferred status. Compared with the benchmark Hidden Markov Models, the proposed framework can better handle noise in data with less computational complexity and better overall accuracy performances with smaller recall. The proposed framework is validated by numerical experiments on the Pecan Street dataset.

ObjectiveThe development of magnetic resonance (MR) imaging systems has been extended for the entire radiotherapy process. However, MR images provide voxel values that are not directly related to electron densities, thus MR images cannot be used directly for dose calculation. The aim of this study is to investigate the feasibility of dose calculations to be performed on MR images and evaluate the necessity of re-planning.MethodsA prostate cancer patient was imaged using both MR and computed tomography (CT). The multilevel threshold (MLT) algorithm was used to categorise voxel values in the MR images into three segments (air, water and bone) with homogeneous Hounsfield units (HU). An intensity-modulated radiation therapy plan was generated from CT images of the patient. The plan was then copied to the segmented MR datasets and the doses were recalculated using pencil beam (PB) and collapsed cone (CC) algorithms and Monte Carlo (MC) modelling.ResultsγEvaluation showed that the percentage of points in regions of interest withγ&lt;1 (3%/3 mm) were more than 94% in the segmented MR. Compared with the planning CT plan, the segmented MR plan resulted in a dose difference of –0·3, 0·8 and –1·3% when using PB, CC and MC algorithms, respectively.ConclusionThe segmentation and conversion of MR images into HU data using the MLT algorithm, used in this feasibility study, can be used for dose calculation. This method can be used as a dosimetric assessment tool and can be easily implemented in the clinic.

In this paper, an improved version of the moth-flame optimization (MFO) algorithm for image segmentation is proposed to effectively enhance the optimal multilevel thresholding of satellite images. Multilevel thresholding is one of the most widely used methods for image segmentation, as it has efficient processing ability and easy implementation. However, as the number of threshold values increase, it consequently becomes computationally expensive. To overcome this problem, the nature-inspired meta-heuristic named multilevel thresholding moth-flame optimization algorithm (MTMFO) for multilevel thresholding was developed. The improved method proposed herein was tested on various satellite images tested against five different existing methods: the genetic algorithm (GA), the differential evolution (DE) algorithm, the artificial bee colony (ABC) algorithm, the particle swarm optimization (PSO) algorithm, and the moth-flame optimization (MFO) algorithm for solving multilevel satellite image thresholding problems. Experimental results indicate that the MTMFO more effectively and accurately identifies the optimal threshold values with respect to the other state-of-the-art optimization algorithms.

Technology mapping for macroblocks is a problem of implementing subcircuits in a Boolean circuit with predesigned IP blocks, like multiplexers and arithmetic circuits. In this paper, we propose algorithms for identifying some special kinds of macroblocks in an arbitrary Boolean circuit using dynamic programming and structural approach. Our algorithms can identify n-input standard gates (and-gates, or-gates, xor-gates, nand-gates, nor-gates and xnor-gates) with a large input size n. Also multiplexers and multiplexer buses can be identified using our algorithms.Proposed algorithms were implemented in a C++ programming language. It can identify and substitute specified macroblocks into a Boolean circuit represented in Verilog HDL format. Algorithms were tested on benchmarks from ICCAD- 2013 contest, where similar problem was introduced, and ISCAS- 85 benchmarks were also used to test our algorithms.

The Viterbi algorithm is one of the most used dynamic programming algorithms for protein comparison and identification, based on hidden markov Models (HMMs). Most of the works in the literature focus on the implementation of hardware accelerators that act as a prefilter stage in the comparison process. This stage discards poorly aligned sequences with a low similarity score and forwards sequences with good similarity scores to software, where they are reprocessed to generate the sequence alignment. In order to reduce the software reprocessing time, this work proposes a hardware accelerator for the Viterbi algorithm which includes the concept of divergence, in which the region of interest of the dynamic programming matrices is delimited. We obtained gains of up to 182x when compared to unaccelerated software. The performance measurement methodology adopted in this work takes into account not only the acceleration achieved by the hardware but also the reprocessing software stage required to generate the alignment.

Pattern Discovery in Genomic Coding Sequences Based on Protein Motifs

Multilevel minimum cross entropy threshold selection based on the firefly algorithm

Multi-level image thresholding is a popular approach for image segmentation where the image is divided into several non-overlapping regions based on the image histogram. Conventional algorithms for multi-level image thresholding are time-consuming. This is in particular so when the number of thresholds increases due to the curse of dimensionality where the search space expands exponentially as the number of parameters (thresholds) increases. One approach to address this problem is to employ population-based metaheuristic algorithms. Since various such optimisation algorithms have been presented in the literature, in this paper, we benchmark the performance of 13 population-based algorithms in the high-dimensional search spaces of the multi-level image thresholding problem. The algorithms we assess include the whale optimisation algorithm (WOA), grey wolf optimiser (GWO), cuckoo optimisation algorithm (COA), biogeography-based optimisation (BBO), teaching-learning-based optimisation (TLBO), gravitational search algorithm (GSA), imperialist competitive algorithm (ICA), cuckoo search (CS), firefly algorithm (FA), bat algorithm (BA), differential evolution (DE), particle swarm optimisation (PSO), and genetic algorithm (GA). We evaluate these on different images with regards to objective function value as well as peak signal-to-noise ratio (PSNR) and also employ a non-parametric statistical test, the Wilcoxon signed rank test, to compare the algorithms and to draw conclusions about their performance for multi-level image thresholding.

Hybrid electric vehicles (HEVs) have an over-actuated system by including two power sources, a battery pack and an internal combustion engine. This feature of HEV is exploited in this paper to simultaneously achieve accurate identification of battery parameters/states. By actively injecting current signals, state of charge, state of health, and other battery parameters can be estimated in a specific sequence to improve the identification performance when compared to the case where all parameters and states are estimated concurrently using the baseline current signals. A dynamic programming strategy is developed to provide the benchmark results about how to balance the conflicting objectives corresponding to identification and system efficiency. The tradeoff between different objectives is presented to optimize the current profile so that the richness of signal can be ensured and the fuel economy can be optimized. In addition, simulation results show that the Root-Mean-Square error of the estimation can be decreased by up to 100% at a cost of less than 2% increase in fuel consumption. With the proposed simultaneous identification and control algorithm, the parameters/states of the battery can be monitored to ensure safe and efficient application of the battery for HEVs.

An efficient adaptive Masi entropy multilevel thresholding algorithm based on dynamic programming

Multilevel image thresholding has attracted plenty of attention in the past decades. Otsu and Kapur’s entropy-based methods are often applied to search the optimal bi-thresholding. These techniques are also suitable for multilevel thresholds. However, it takes a lot of computation to solve the multilevel threshold problem. To address this problem, in this paper, a recently proposed bat algorithm is used to find the appropriate multilevel thresholds, in which Otsu and Kapur’s entropy is regarded as its fitness functions. Evaluation of image segmentation effect is performed using the peak-to-signal ratio (PSNR) and structural similarity (SSIM) index. The experiment results show that Otsu based method is more suitable for multi-level threshold image segmentation.

Multilevel thresholding is a significant technology for image segmentation. Traditional exhaustive search method to solve the optimal multilevel thresholds is time consuming, color images contain more information are even worse. To address this issue, an improved cuckoo search algorithm (ICS) is proposed for color image segmentation in this paper, and a modified fuzzy entropy is used as its objective function. In ICS, two modifications are adopted to improve the standard cuckoo search algorithm. First, an adaptive control parameter mechanism is utilized to enhance the performance of exploration. Second, a hybrid search strategy is used to boost the local search efficiency. To fully demonstrate the superior performance of the ICS, the experiments are conducted on a series of color benchmark test images, and a total of six optimization algorithms are compared with the proposed algorithm. The experimental results show that the presented ICS algorithm outperforms all the other algorithms in term of objective function value, PSNR, FSIM, convergence speed and parametric statistical test. Compared to other algorithms, the ICS algorithm is an effective method for multilevel color image thresholding segmentation.

The measure of cross entropy is a widely used index applied to many areas of computer science. In this article, we proposed a new multilevel thresholding algorithm for image segmentation using the glowworm swarm optimization based on the criterion of minimum cross entropy (MCE). In this paper, a new multilevel MCE thresholding (MCET) algorithm using the glowworm swam optimization (GSO) algorithm is proposed. The proposed image thresholding algorithm is called the GSO-based MCET algorithm. The five different methods including the exhaustive search, the honey bee mating optimization (HBMO), the firefly (FF) algorithm, the artificial bee colony algorithm (ABC) and the particle swarm optimization (PSO) are also implemented for performance comparison. The experimental results demonstrate that the proposed GSO-based MCET algorithm can efficiently search for multiple thresholds that are very close to the optimal ones examined by the exhaustive search method. Compared with the other five thresholding methods, the needs of computation time using the FF-based MCET algorithm is the smallest. Furthermore, the segmentation performance of GSO-based MCET algorithm is better than the PSO-based MCET algorithm, while the results of GSO-based MCET algorithm are not significant different to the other three bio-inspired computing algorithms.