Peiyi Zhu

An accurate multi-cell parameter estimate algorithm with heuristically restrictive ant system

To reliably analyze multi-cell motion in a series of low-contrast image sequences, we present a novel heuristically restrictive ant system, which operates in a non-optimization way, to adaptively estimate multiple parameters of multiple cells. First, the local intensity variation measure on each pixel of image is defined to generate ant colony initial distribution positions, which are further treated as boundary markers to restrict ant searching behavior. Afterwards, to speed up the ant searching process, both location and contour ant decision behaviors are modeled appropriately to acquire cell position and edge estimates on their individual pheromone fields, which are formed by restrictive pheromone deposits but operate independently and in parallel. Finally, the stability of our proposed pheromone control mechanism is proven to guarantee reliable multi-parameter extraction. Experiment results show that our algorithm could automatically and accurately track numerous cells in various scenarios, and it shows considerable robustness against other popular tracking methods. Our algorithm can track multiple cells with the variance in morphology, the difference in dynamics and the changes in number.Our algorithm could give a joint estimate of state and contour of each cell even without birth ant colonies.Our algorithm enjoys a robust tracking performance with high percentage of tracked position when comparing with existing methods.

Modeling analysis of ant system with multiple tasks and its application to spatially adjacent cell state estimate

The problem of multi-cell tracking plays an important role in studying dynamic cell cycle behaviors. In this paper, a novel ant system with multiple tasks is modeled for jointly estimating the number of cells and individual states in cell image sequences. In our ant system, in addition to pure cooperative mechanism used in traditional ant colony optimization algorithm, we model and investigate another two types of ant working modes, namely, dual competitive mode and interactive mode with cooperation and competition to evaluate the tracking performance on spatially adjacent cells. For adjacent ant colonies, dual competitive mode encourages ant colonies with different tasks to work independently, whereas the interactive mode introduces a trade-off between cooperation and competition. In simulations of real cell image sequences, the multi-tasking ant system integrated with interactive mode yielded better tracking results than systems adopting pure cooperation or dual competition alone, both of which cause tracking failures by under-estimating and over-estimating the number of cells, respectively. Furthermore, the results suggest that our algorithm can automatically and accurately track numerous cells in various scenarios, and is competitive with state-of-the-art multi-cell tracking methods.

Modified unsupervised discriminant projection with an electronic nose for the rapid determination of Chinese mitten crab freshness

In this paper, a method to rapidly determine living Chinese mitten crab freshness using an electronic nose (E-nose) and a non-linear data processing technique was studied. E-nose responses to crabs stored at 4 °C were measured. Meanwhile, total volatile basic nitrogen (TVB-N) was examined to provide freshness references for the E-nose analysis. However, traditional classification algorithms are not suitable for E-nose data with non-linear manifold structures; therefore, a modified unsupervised discriminant projection (MUDP) coupled with sample label information was proposed. MUDP can retain the local and global structure and take advantage of the importance of label information and then create a geometric structure optimal linear projection. Data classification experimental results proved that the classification accuracy of K-nearest-neighbor (KNN) combined with the data processed by MUDP was much better than that of other considered methods. Validation experiments indicated that the recognition rates of the proposed algorithm were higher than those of traditional linear algorithms such as PCA and LDA or nonlinear algorithms such as KPCA.

Multi-innovation stochastic gradient method for harmonic modelling of power signals

The harmonic parameter identification and modelling problem for power signals are studied. In order to model power signals, the multi-innovation stochastic gradient (MI-SG) is derived based on the multi-innovation identification theory. The proposed MI-SG algorithm repeatedly uses past innovations by expanding the scalar innovation to the innovation vector and can obtain more accurate parameter estimates than the stochastic gradient algorithm. Finally, the simulation results indicate that the proposed algorithm is effective and has a close estimation accuracy compared with the fast Fourier transform analysis.

A multiCell visual tracking algorithm using multi-task particle swarm optimization for low-contrast image sequences

In terms of the varying number of cell population, shape deformation, collision and uneven movement, a novel method based on multi-task particle swarm optimization (PSO) algorithm without explicit detection module, named MTPSO tracking method, is developed for automatic tracking of biological cells in time-lapse low-contrast microscopy image sequences. For tracking existing cells from the previous frames, a PSO-based tracking module is firstly implemented to give the initial positions of existing cells according to the previous estimated state of each cell, then a PSO-based contour module is proposed to determine the corresponding contour of each cell and finally achieve a precise position tracking by an iterative centroid updating process. For tracking new appearing cells at the current frame, a PSO-based discovery module, followed by the aforementioned PSO-based contour module, is proposed to search for new potential cells through appropriate initialization of particle swarm and searching mechanism. MTPSO tracking method is tested over a number of different real cell image sequences and is shown to provide high accuracy both in position and contour estimate of each cell in various challenging cases. Furthermore, it is more competitive against the state-of-the-art multi-object tracking methods in terms of performance measures such as FAR, FNR, LTR, and LSR.

Multiple cells tracking by firework algorithm

Multiple cells dynamics analysis through fluorescence microscopy imaging requires simultaneously tracking large and time-varying number cells in noisy image sequences. Such process is characterized as a challenging task due to several roadblocks including the severe image noise and clutter, the occlusion of one cell by others, and the weak image contrast. To gain full dynamics of multiple cells, a novel firework explosion searching behavior based tracking algorithm is proposed to tracking multiple cells in fluorescence image sequences in this paper. Each firework (spark) determines the state and then adjusts its following explosion according to cell detection position heuristic information. Simulation results verify the effectiveness of the methods.

Multi-task ant system for multi-object parameter estimation and its application in cell tracking

The multi-task ant system, is first introduced to track multiple objects.Our method can track multiple cells in various challenging scenarios.A novel likelihood function is developed to find the cell potentials.Our algorithm enjoys a robust tracking performance with low FNR and FAR. Inspired by ants stochastic behavior in search for multiple food sources, we propose a cooperating multi-task ant system for tracking multiple synthetic objects as well as multiple real cells in a bio-medical field. In our framework, each ant colony is assumed and assigned to fulfill a given task to estimate the state of an object. Furthermore, two ant levels are used, i.e., ant individual level and ant cooperation level. In the ant individual level, ants within one colony perform independently, and the motion of each individual is probabilistically determined by both its intended motion modes and the likelihood function score. In the ant cooperation level, each ant adjusts individual state within its influence region according to heuristic information of all other ants within the same colony, while the global best template at current iteration is found among all ant colonies and utilized to update ant model probability, influence region, and probability of fulfilling task. Our algorithm is validated by comparing it to the-state-of-art algorithms, and specifically the improved tracking performance in terms of false negative rate (up to 10.0%) and false negative rate (up to 2.1%) is achieved based on the studied three real cell image sequences.

Gradient-Based Iterative Identification for Wiener Nonlinear Dynamic Systems with Moving Average Noises

This paper focuses on the parameter identification problem for Wiener nonlinear dynamic systems with moving average noises. In order to improve the convergence rate, the gradient-based iterative algorithm is presented by replacing the unmeasurable variables with their corresponding iterative estimates, and to compute iteratively the noise estimates based on the obtained parameter estimates. The simulation results show that the proposed algorithm can effectively estimate the parameters of Wiener systems with moving average noises.

Two-stage recursive least squares method for modeling power signals

This paper studies two-stage recursive least squares identification problems for power signals by the decomposition technique. The basic idea is to decompose a power signal model into two submodels and then to identify the parameters of each submodel, respectively. Compared with the recursive least squares algorithm, the dimensions of the involved covariance matrices in each submodel become small and thus the proposed algorithm has a high computational efficiency. Finally, the simulation results indicate that the proposed algorithm is effective.

Two Ant Decision Levels and Its Application to Multi-Cell Tracking

Inspired by ant’s stochastic behavior in searching of multiple food sources, a novel ant system with two ant decision levels are proposed to track multiple cells in biological field. In the ant individual level, ants within the same colony perform independently, and ant decision is determined in probability by both its intended motion model and likelihood function. In the ant cooperation level, each ant adjusts individual state within its influence region, while the global best template at current iteration is found among all ant colonies and further utilized to update ant model probability, influence region, and the probability of fulfilling task. Simulation results demonstrate that our algorithm could automatically track numerous cells and its performance is compared with the multi-Bernoulli filtering method.