Search

Leaf image recognition has been actively researched for plant species identification. However, it remains unclear whether leaf patterns can provide sufficient information for cultivar recognition. This paper reports the first attempt on soybean cultivar recognition by joint leaf patterns. In this paper, we propose a novel multiscale sliding chord matching (MSCM) approach to extract leaf patterns that are distinctive for soybean cultivar identification. A chord is defined to slide along the contour for measuring the synchronised patterns of exterior shape and interior appearance of leaf images. A multiscale sliding chord strategy is developed to extract features in a coarse-to-fine hierarchical order. A joint description that integrates the leaf descriptors from different parts of a soybean plant is proposed for further enhancing the discriminative power of leaf image descriptors. We built a cultivar leaf image database, SoyCultivar200, consisting of 6000 samples from 200 soybean cultivars for performance evaluation. Encouraging experimental results demonstrate the availability of cultivar information in soybean leaves and effectiveness of the proposed MSCM for soybean cultivar identification, which may advance the research in leaf recognition from species to cultivar.

This paper developed a multiobjective Big Data optimization approach based on a hybrid salp swarm algorithm and the differential evolution algorithm. The role of the differential evolution algorithm is to enhance the capability of the feature exploitation of the salp swarm algorithm because the operators of the differential evolution algorithm are used as local search operators. In general, the proposed method contains three stages. In the first stage, the population is generated, and the archive is initialized. The second stage updates the solutions using the hybrid salp swarm algorithm and the differential evolution algorithm, and the final stage determines the nondominated solutions and updates the archive. To assess the performance of the proposed approach, a series of experiments were performed. A set of single-objective and multiobjective problems from the 2015 Big Data optimization competition were tested; the dataset contained data with and without noise. The results of our experiments illustrated that the proposed approach outperformed other approaches, including the baseline nondominated sorting genetic algorithm, on all test problems. Moreover, for single-objective problems, the score value of the proposed method was better than that of the traditional multiobjective salp swarm algorithm. When compared with both algorithms, that is, the adaptive DE algorithm with external archive and the hybrid multiobjective firefly algorithm, its score was the largest. In contrast, for the multiobjective functions, the scores of the proposed algorithm were higher than that of the fireworks algorithm framework.

Image segmentation is among the most important techniques in image processing, and many methods have been developed to perform this task. This paper presents a new multi-objective metaheuristic based on a multi-verse optimization algorithm to segment grayscale images via multi-level thresholding. The proposed approach involves finding an approximate Pareto-optimal set by maximizing the Kapur and Otsu objective functions. Both Kapur’s and Otsu’s methods are highly used for image segmentation performed by means of bi-level and multi-level thresholding. However, each of them has certain characteristics and limitations. Several metaheuristic approaches have been proposed in the literature to separately optimize these objective functions in terms of accuracy, whereas only a few multi-objective approaches have explored the benefits of the joint use of Kapur and Otsu’s methods. However, the computational cost of Kapur and Otsu is high and their accuracy needs to be improved. The proposed method, called Multi-objective Multi-verse Optimization, avoids these limitations. It was tested using 11 natural grayscale images and its performance was compared against three of well-known multi-objective algorithms. The results were analyzed based on two sets of measures, one to assess the performance of the proposed method as a multi-objective algorithm, and the other to evaluate the accuracy of the segmented images. The results showed that the proposed method provides a better approximation to the optimal Pareto Front than the other algorithms in terms of hypervolume and spacing. Moreover, the quality of its segmented image is better than those of the other methods in terms of uniformity measures.

This paper presents an alternative method for cloud task scheduling problem which aims to minimize makespan that required to schedule a number of tasks on different Virtual Machines (VMs). The proposed method is based on the improvement of the Moth Search Algorithm (MSA) using the Differential Evolution (DE). The MSA simulates the behavior of moths to fly towards the source of light in nature through using two concepts, the phototaxis and Levy flights that represent the exploration and exploitation ability respectively. However, the exploitation ability is still needed to be improved, therefore, the DE can be used as local search method. In order to evaluate the performance of the proposed MSDE algorithm, a set of three experimental series are performed. The first experiment aims to compare the traditional MSA and the proposed algorithm to solve a set of twenty global optimization problems. Meanwhile, in second and third experimental series the performance of the proposed algorithm to solve the cloud task scheduling problem is compared against other heuristic and meta-heuristic algorithms for synthetical and real trace data, respectively. The results of the two experimental series show that the proposed algorithm outperformed other algorithms according to the performance measures.

Petrol engine becomes much smaller and has higher compression ratio due to the strict exhaust emission regulations and consumer demand for power performance. Meanwhile, the frequency of super-knock is increasing sharply at low speed of high load working region, which has great damage to engine components. Prediction of super-knock is therefore of great significance to optimize operation conditions and prolong service life. High-performance in-cylinder sensors can provide quality information for super-knock prediction, but at a price that production vehicles cannot afford. An approach that does not require additional engine sensors while having an acceptable accuracy rate is needed. Furthermore, the super-knock events are difficult to capture, making prediction task subjects to sample imbalance. In this research, a deep learning approach using only existing engine sensors was applied to address the challenge. Specifically, a two-stage model was designed: (i) Feature extraction, an LSTM based triplet network is built to extract the differential features between super-knock and normal combustion from the engine working cycles. (ii) Classification, to effectively use the extracted features and metric information from the previous stage, a modified KNN classifier is employed. The effectiveness of the proposed approach, i.e., TLSTM-KNN was evaluated and compared with other state-of-the-art methods on an actual engine-based dataset under different imbalance ratios (IR). The prediction precision and recall of super-knock event reach to 81.67% and 79.01% for the test dataset at IR=10. Even at IR=100, the precision and recall reach to 59.02% and 63.31%. The comparisons suggested that the proposed model provides better prediction performance and robustness capability compared to other traditional prediction models. Finally sensitivity analysis was used to explore the factors influencing super-knock.

This paper proposed a modified version of Spider Monkey Optimization (SMO) algorithm for solving global optimization problems. The traditional SMO consists of seven phases where each phase has its characteristics and tasks to be performed. However, the local leader phase (LLP), that is the second phase of the SMO has the most significant effect on the performance of the algorithm. In which if it does not has good exploration and exploitation capability then the SMO might stick at a local point. Therefore, the proposed modified version of SMO (that called SMONM) used the transformations of the Nelder–Mead (NM) method to improve the ability of LLP. The proposed SMONM algorithm contains the same number of phases of the traditional SMO except the LLP that has modified through using the reflection, expansion, and contraction transformations of the NM. These transformations of NM worked if there is no improvement in the fitness function value after the solution is updating using the original LLP. The performance of the proposed algorithm has compared with other four algorithms namely, original SMO, Artificial Bee Colony optimization, Biography Based Optimization and Particle Swarm Optimization. A set of experimental series is performed to evaluate the performance of the proposed algorithm using 23 standard benchmark functions, 15 composite functions, and three classical engineering problems. The preliminary results show that the modified version of SMO has excellent ability to avoid the limitations of the tradition SMO algorithm, as well as, it provides better results than the other comparative algorithms regarding performance measures.

The routing optimization problem of grain emergency vehicle scheduling with three objectives is studied in this paper. The objectives are: maximizing satisfaction of the needs at the emergency grain demand points, minimizing total cost of grain distribution and minimizing the distribution time. A hybrid algorithm is present to solve the proposed problem based on combining artificial immune and ant colony optimization (ACO) algorithms. This hybrid algorithm calculates the degree of crowding and conducts non-dominated sorting of the population in the ant colony optimization algorithm by applying a Pareto optimization model. A better solution set is quickly generated by making use of the fast global convergence and randomness of the improved immune algorithm together with the distributed search ability and positive feedback of the ACO algorithm. A better solution set obtained as the initial pheromone distribution, is solved further by using ACO until the approximate optimal solution set is obtained. A comparison of the proposed algorithm with several common optimization algorithms on the Solomon benchmark dataset demonstrates that this method obtains better performance in shorter time, and is an efficient way to solve the vehicle routing problem in emergency grain distribution scenarios.

In this paper, we propose a novel low-rank double dictionary learning (LRD2L) method for robust image classification tasks, in which the training and testing samples are both corrupted. Unlike traditional dictionary learning methods, LRD2L simultaneously learns three components from corrupted training data: 1) a low-rank class-specific sub-dictionary for each class to capture the most discriminative class-specific features of each class, 2) a low-rank class-shared dictionary which models the common patterns shared in the data of different classes, and 3) a sparse error term to model the noise in data. Through low-rank class-shared dictionary and noise term, the proposed method can effectively separate the corruptions and noise in training samples from creating low-rank class-specific sub-dictionaries, which are employed for correctly reconstructing and classifying testing images. Comparative experiments are conducted on three public available databases. Experimental results are encouraging, demonstrating the effectiveness of the proposed method and its superiority in performance over the state-of-the-art dictionary learning methods.

A new method to solve global optimization and engineering problems called OBSCA.The proposed method improves the SCA by using opposite-based learning.We apply the OBSCA over mathematical benchmark functions.We test OBSCA in engineering optimization problems.Comparisons support the improvement on the performance of OBCSA. Real life optimization problems require techniques that properly explore the search spaces to obtain the best solutions. In this sense, it is common that traditional optimization algorithms fail in local optimal values. The Sine Cosine Algorithms (SCA) has been recently proposed; it is a global optimization approach based on two trigonometric functions. SCA uses the sine and cosine functions to modify a set of candidate solutions; such operators create a balance between exploration and exploitation of the search space. However, like other similar approaches, SCA tends to be stuck into sub-optimal regions that it is reflected in the computational effort required to find the best values. This situation occurs due that the operators used for exploration do not work well to analyze the search space. This paper presents an improved version of SCA that considers the opposition based learning (OBL) as a mechanism for a better exploration of the search space generating more accurate solutions. OBL is a machine learning strategy commonly used to increase the performance of metaheuristic algorithms. OBL considers the opposite position of a solution in the search space. Based on the objective function value, the OBL selects the best element between the original solution and its opposite position; this task increases the accuracy of the optimization process. The hybridization of concepts from different fields is crucial in intelligent and expert systems; it helps to combine the advantages of algorithms to generate more efficient approaches. The proposed method is an example of this combination; it has been tested over several benchmark functions and engineering problems. Such results support the efficacy of the proposed approach to find the optimal solutions in complex search spaces.

Ultra-fine-grained visual categorization (ultra-FGVC) categorizes objects with more similar patterns between classes than those in fine-grained visual categorization (FGVC), e.g., where the spectrum of granularity significantly moves down from classifying species to classifying cultivars within the same species. It is considered as an open research problem mainly due to the following challenges. First, the inter-class differences among images are much smaller by level of orders (e.g., cultivars in the same species) than those in current FGVC tasks (e.g., species). Second, there is only a few samples per category, which is beyond the ability of most large training data favored convolutional neural network methods. To address these problems, we propose a novel random mask covariance network (MaskCOV), which integrates an auxiliary self-supervised learning module with a powerful in-image data augmentation scheme for the ultra-FGVC. Specifically, we first uniformly partition input images into patches and then augment data by randomly shuffling and masking these patches. On top of that, we introduce an auxiliary self-supervised learning module of predicting the spatial covariance context of these patches to increase discriminability of our network for classification. Very encouraging experimental results of the proposed method in comparison with the state-of-the-art benchmarks demonstrate its superiority and potential of MaskCOV concept, which pushes research boundary forward from the fine-grained to the ultra-fine-grained visual categorization.

Driving performance evaluations can contribute to fleet management and lead to safer and more economical driving conditions for manned or driverless fleet vehicles. One approach to driving performance evaluation involves quantitative mapping or categorical labeling of skill levels and categorizing of driving patterns from extraordinarily mild to the most aggressive. This paper presents a big data system for driving performance evaluations of drivers and trips using a probabilistic framework. The proposed framework combines a feature mixture model for scoring driving performance through defined objective comparison criteria and a latent style mixture model for classifying drivers by the main driving styles they exhibit. To demonstrate the effectiveness of the proposed models, we perform both quantitative and qualitative experiments. The results show that the former produces an interpretable and normal scorecard model, while the latter helps build an improved clustering model that represents enhanced driver behavior.

Person retrieval is an important vision task, aiming at matching the images of the same person under various camera views. The key challenge of person retrieval lies in the large intra-class variations among the person images. Therefore, how to learn discriminative feature representations becomes the core problem. In this paper, we propose a deep part-aware representation learning method for person retrieval. First, an improved triplet loss is introduced such that the global feature representations from the same identity are closely clustered. Meanwhile, a localization branch is proposed to automatically localize those discriminative person-wise parts or regions, only using identity labels in a weakly supervised manner. Via the learning simultaneously guided by the global branch and the localization branch, the proposed method can further improve the performance for person retrieval. Through an extensive set of ablation studies, we verify that the localization branch and the improved triplet loss each contributes to the performance boosts of the proposed method. Our model obtains superior (or comparable) performance compared to state-of-the-art methods for person retrieval on the four public person retrieval datasets. On the CUHK03-labeled dataset, for instance, the performance increases from 73.0% mAP and 77.9% rank-1 accuracy to 80.8% (+7.8%) mAP and 83.9% (+6.0%) rank-1 accuracy.

Walking and running are two distinct movement patterns that characterize pedestrian crossing. While walking is a common behaviour, running is often considered as risky/unsafe. The existing studies about pedestrian crossing speeds usually exclude running. The objectives of this study are 1) to identify whether lanes and crossing stages are influential factors on pedestrian crossing speeds. 2) To describe and model the heterogeneity of pedestrian crossing speeds. 3) To provide knowledge about pedestrian running behaviour. 4) To provide insights for microscopic pedestrian simulation models. The statistical data of crossing speeds in terms of both walking speeds and running speeds from different perspectives: lanes and crossing stages were analyzed. Pedestrian crossing speeds were extracted from videos capturing a non-signalized marked crosswalk. Quantitative analysis in terms of mean, 15th, 50th and 85th percentile speeds for walking and running are calculated and compared. Chi-Square test is conducted as well. In the qualitative aspect, the concept of Pedestrian Crossing Speed Pattern (PCSP), in terms of the number of Speed Pattern Transition Point (SPTP) and the primitives including “Increasing”, “Decreasing” as well as “Flat” were proposed, which can enable the description of the heterogeneity in pedestrian crossing speeds in a more accurate way. Running frequency was also recorded and analyzed.

Difference system of sets (DSS), introduced by Levenshtein, has an interesting connection with the construction of comma-free codes. In this paper, we construct two new families of DSS from the cyclotomic classes of order 12.

Emergency evacuation is an important task while dealing with a sudden accident. Aiming at emergency evacuation in campus, this paper proposed a personalized route planning model for pedestrian–vehicle mixed evacuation. Considering the congestion of pedestrian–vehicle mixed evacuation and the actual factors of students, this model found the optimal user equilibrium close to the system equilibrium. By the help of the Wardrop Equilibrium model, the server calculated the optimized evacuation route planning and guided evacuees by mobile intelligent terminals. Finally this paper applied this model to the evacuation of Wuhan University of Technology. By simulating the process of emergency evacuation, the results showed the feasibility of the algorithm, which proved this model a scientific basis for guiding the real evacuation process.

The automatic congestion detection of campus traffic presents a significant challenge to the traffic congestion research community. Typically, campus road users can be classified into four types including pedestrian, bike, vehicle and motorbike, which enhances the complexity of traffic condition. Thus, existing descriptors of traffic congestion for highway traffic are not valid when describing the traffic congestion in campus. In this paper, we propose a novel descriptor, road occupancy rate, for measuring campus traffic congestion level, which is statistically proved to be the most effective descriptor among other descriptors (including speed of pedestrian, vehicle, motorbike and bike). Two existing models Markov model and back propagation neural network (BPNN) are introduced in this paper to detect the campus traffic congestion combined with the proposed descriptors. And three phases are defined based on three-phase traffic theory to describe the campus traffic congestion levels. Experimental results indicate that the proposed detecting methods are both capable of detecting campus traffic congestion, while the BPNN-based method achieves higher accuracy and more stable performance.

Data set of high quality is the cornerstone of the current data-driven machine learning models, and plays an important role in promoting the development of various application areas. At present, image analysis and processing techniques have intensively involved into the tasks of inheriting and protecting culture resources. However, currently there are few effective image data sets about the traditional Chinese Tibetan culture. In this work, we provided a small data set referred as CYTKv1(Chomo Yarlung Tibet version 1) which includes 1700 + Thangka images (an important and representative carrier of Chinese Tibetan culture), and the main objects in each image are manually labeled and bounding-boxed with semantic words. In addition, we shared a list of tasks of processing and analyzing the Thangkas to enlighten researchers about the challenges and potential applications on this data set. At last, we tested several famous deep learning models for the purpose of validating the annotation task on the new data set and presented the results of them, and finally selected the best one as the baseline for the annotation task.

When contagious diseases hit a city, such as MERS, SARS, and COVID-19, the problem arises as how to assign the limited supermarket resources to urban residential communities for government measures. In this study, in order to solve the assignment problem from supermarket resources to urban residential communities under the situation of the epidemic control, the discrete multi-objective particle swarm algorithm can be improved by introducing some new strategies, and the probability matrix can be used to simulate the many-to-many assignment relationship between residential communities and supermarkets. The ultimate purpose of this research is to achieve an optimal way to balance the two conflicting objectives, i.e. minimization of the cross-infection risk and maximization of the service coverage rate. Also, the optimization considers the accessible distance limit and the service capacity constraints of supermarkets for the feasible scheme. For this aim, we redefine the subtraction operator, add operator and multiply operator to generate the Pareto optimal solutions, and introduce a new study strategy based on the idea of differential evolution in the particle swarm algorithm (PSO-DE). In this work, we take the COVID-19 epidemic outbreak in Wuhan city of China as an example in the experiment. The simulation results are compared with the Genetic Algorithm (GA), Simulated Annealing (SA), Ant Colony Algorithm (ACO) and the Particle Swarm Optimization with Roulette Wheel Selection (PSO-R), and these results have been shown that the algorithm PSO-DE proposed in this work has a better optimization performance in both objectives.

Pedestrian-vehicle conflict is a common and dangerous event which occurs in both urban and rural areas in developing countries. Lane-based evaluation of pedestrian-vehicle conflict is still an open research topic in the traffic safety, urban planning, and city government communities. A lane-based approach for evaluating the post-encroachment time between pedestrians and vehicles was proposed. This study analyzed the lane-based distribution of pedestrian-vehicle conflict using collected video data which recorded the behaviors of vehicles and pedestrians in a non-signalized marked crosswalk in Wuhan, China, and discussed the effect of waiting time on lane-based pedestrian-vehicle conflict as well as the distribution of pedestrian walking speed under different levels of severity of lane-based pedestrian-vehicle conflict. Experimental results showed that shorter waiting times and smaller waiting areas are very strongly related to lane-based conflict, but that walking speed is not a significant factor in lane-based pedestrian-vehicle conflict.

This paper mainly focuses on how to construct concept lattice effectively and efficiently based on improved variable precision rough set. On the basis of preprocessing formal concept, one algorithm that can determine the value range of variable precision parameter β according to the approximate classification quality is proposed. An improved β-upper and lower distribution attribute reduction algorithm is also proposed based on the improved variable precision rough set, the algorithm can be used for attribute reduction on the original data of the concept lattice, and to eliminate the redundant knowledge or noises of the formal context. For the reduced formal context, the paper combines the concept construction algorithm with an improved rule acquisition algorithm seamlessly, and proposes a novel approach of concept lattice construction based on improved variable precision rough set. Finally, a concept lattice generation prototype system is developed, this paper also performs comprehensive experiments, and the effectiveness of the improved algorithm is proved through the experimental results.

Facial landmark detection is a crucial prerequisite for many face analysis applications. Deep learning-based methods currently dominate the approach of addressing the facial landmark detection. However, such works generally introduce a large number of parameters, resulting in high memory cost. In this paper, we aim for a lightweight as well as effective solution to facial landmark detection. To this end, we propose an effective lightweight model, namely Mobile Face Alignment Network (MobileFAN), using a simple backbone MobileNetV2 as the encoder and three deconvolutional layers as the decoder. The proposed MobileFAN, with only 8% of the model size and lower computational cost, achieves superior or equivalent performance compared with state-of-the-art models. Moreover, by transferring the geometric structural information of a face graph from a large complex model to our proposed MobileFAN through feature-aligned distillation and feature-similarity distillation, the performance of MobileFAN is further improved in effectiveness and efficiency for face alignment. Extensive experiment results on three challenging facial landmark estimation benchmarks including COFW, 300W and WFLW show the superiority of our proposed MobileFAN against state-of-the-art methods.

Pedestrian-cyclist interaction is closely relative with traffic safety on campus intersection. The relationships of flow, speed, Level of Service (LOS) with pedestrian-cyclist conflict and interference were studied. Studying pedestrian-cyclist interaction was using collected video data which recorded the behaviours of pedestrians and cyclists at a non-signalized intersection on campus. The pedestrians and cyclists’ flows were recorded by video statistic software, the collected videos were decoded into image frames, their trajectory and distance data were acquired by image processing software, the data was converted into numbers as a VCNXY(Video number, Current frame no, Pedno, Pedx, Pedy) database, then their speeds were computed by Euler's formula. The LOS is classified with three levels under different traffic density and road traffic capacity. Through the analysing of pedestrians and cyclists’ flows and their average speeds at different time, and analysing the relationships with pedestrian-cyclist interaction and their flow, speed, LOS. Results showed that campus’ transportation is much different from city transportation, the proportion of pedestrians and cyclists are much higher, the average speeds of pedestrians and cyclists are lower. Experimental results show that flow, speed and LOS are very strongly related to pedestrian-cyclist interaction.

The phenomenon that pedestrians use smartphones while walking has posed great threat to transportation safety. As ubiquitous computing evolves with increased mobile use ( e.g. smartphones, heads-up displays, wearable devices), safety is becoming increasingly needed, especially in urban environments. However, safety was not a major concern in human-computer interaction (HCI), and owing to the multidisciplinary nature of HCI, it is highly challenging to develop a framework to deal with safety issues. In this paper, we discussed the development of a conceptual framework for evaluating and improving safety for pedestrians using smartphones while walking in safety-critical environments. A preliminary questionnaire based study was conducted to collect smartphone users’ opinions and attitudes towards using smartphones while walking. Some safety-critical details were also collected to address the users’ needs in interaction design. The proposed framework was explored in theoretical, hardware and software levels respectively, which could provide insights for both ergonomists, application designers and researchers.

Define the shape-based features of Flying Apsaras' streamers.Propose a morphological descriptor of incorporating these features for KSVM.Demonstrate the suitability of the descriptor and KSVM for streamer recognition. Recognizing Flying Apsaras' streamers is of great importance in analyzing Chinese cultural background and art forms form the early Chinese dynasties. This analysis is very valuable for cultural protection and heritage. However, few studies have focused on recognition of Flying Apsaras in the Dunhuang Grotto Murals, China, which record elements of Chinese culture in different Chinese dynasties. By introducing a set of feature descriptors for Flying Apsaras' streamers, this paper proposes a morphological streamer feature descriptor to describe the shape-based features (i.e., slenderness, posture ratio, area ratio, and intensity) of Flying Apsaras' streamers. Then, a Kernel Support Vector Machine (KSVM) is implemented to locate and recognize Flying Apsaras' streamers using the proposed feature descriptor. This machine is composed of two important parts: region segmentation of the images in the Dunhuang Grotto Murals, and KSVM-based feature selection for streamer recognition. The implemented KSVM approach incorporating the proposed morphological feature descriptor can classify streamer regions with 89.56% accuracy. Comparing the results of different classifiers and different feature descriptors demonstrates that the proposed morphological feature descriptor is a suitable morphological operator and that the KSVM is a suitable classifier for Flying Apsaras' streamers in the Dunhuang Grotto Murals, China.

Theoretical analyses of algorithms are important to understand their search behaviors and develop more efficient algorithms. Compared with the plethora of works concerning the empirical study of the differential evolution (DE), little theoretical research has been done to investigate the convergence properties of DE so far. This paper focuses on theoretical researches on the convergence of DE and presents a convergent DE algorithm. First of all, it is proved that the classical DE cannot converge to the global optimal set with probability 1 by using the property that it cannot escape from a local optimal set. Inspired by the characteristics of the elitist genetic algorithm, this paper proposed a modified DE to overcome the disadvantage. The proposed algorithm employs two operators that assist it in escaping from a local optimal set and enhance the diversity of the population. And it is then verified that the proposed algorithm is capable of converging to global optima with probability 1. The theoretical research of this paper is undertaken in a finite discrete set, and the analysis tool used is the Markov chain. The numerical experiments are conducted on a deceptive function and a set of benchmark functions. The experimental results support the theoretical analyses on the convergence performances of the classical and modified DE algorithm.

A simulation model based on temporal-spatial conflict and congestion for pedestrian-vehicle mixed evacuation has been investigated. Assuming certain spatial behaviors of individuals during emergency evacuation, a discrete particle swarm optimization with neighborhood learning factor algorithm has been proposed to solve this problem. The proposed algorithm introduces a neighborhood learning factor to simulate the sub-group phenomenon among evacuees and to accelerate the evacuation process. The approach proposed here is compared with methods from the literatures, and simulation results indicate that the proposed algorithm achieves better evacuation efficiency while maintaining lower pedestrian-vehicle conflict levels.

This paper proposes a Ludo game-based strategy to enhance the ability of swarm algorithms to solve numerous global optimization problems. The proposed strategy simulates the rules of playing the game Ludo using two or four players to perform the update process for different swarm intelligent behaviors. The proposed approach is named the Ludo Game-based Swarm Intelligence (LGSI) Algorithm. The LGSI algorithm uses the concepts of two and four players to enhance the exploration and exploitation of the optimization methods. In the proposed LGSI, a player is represented by a swarm algorithm, for example, in the two-player concept; Moth Flame Optimization (MFO) and the Grasshopper Optimization Algorithm (GOA) are selected, while in the four-player version, two other algorithms, the Sine Cosine Algorithm (SCA) and Gray Wolf Optimization (GWO), are added. In the proposed LGSI algorithm, the functional behaviors of all the used algorithms are different; also, there is no similarity among algorithmic behaviors except for convergence towards the global optimum, which is a common interest for all. However, the other algorithms share the same platform with this strategy, so in this case, competitive behavior may not be underestimated. The proposed LGSI algorithm shares positions among all the algorithms used during the search for the optimal solution. The performance of the LGSI algorithm is tested on a set of CEC2005 benchmark problems and engineering problems and is compared with the original versions of the utilized algorithms and a variety of other state-of-the-art algorithms. The experimental results show that the LGSI algorithm can provide promising and competitive results.

Obtaining changeable granules quickly and accurately is one of the important issues in granular computing. The present work proposes a partial order relation and lattice computing to deal with the aforementioned issue. A hyperspherical granular computing classification algorithm (HSGrCCA) is developed in the framework of fuzzy lattices. HSGrCCA computes a fuzzy inclusion relation between two hyperspherical granules using an inclusion measure function based on a linear positive valuation function induced by the radius of a hyperspherical granule. A fuzzy lattice is formed on the hyperspherical granule set by the dilation operator, erosion operator, and partial order relation. HSGrCCA is trained by introducing control parameter ρ of the hyperspherical granule size and then obtains changeable hyperspherical granules. Experimental results on machine learning benchmark data sets show that the proposed algorithm increases the generalization ability.

Evacuation planning is a fundamental requirement to ensure that most people can be evacuated to a safe area when a natural accident or an intentional act happens in a stadium environment. The central challenge in evacuation planning is to determine the optimum evacuation routing to safe areas. We describe the evacuation network within a stadium as a hierarchical directed network. We propose a multi-objective optimization approach to solve the evacuation routing problem on the basis of this hierarchical directed network. This problem involves three objectives that need to be achieved simultaneously, such as minimization of total evacuation time, minimization of total evacuation distance and minimal cumulative congestion degrees in an evacuation process. To solve this problem, we designed a modified ant colony optimization (ACO) algorithm, implemented it in the MATLAB software environment, and tested it using a stadium at the Wuhan Sports Center in China. We demonstrate that the algorithm can solve the problem, and has a better evacuation performance in terms of organizing evacuees’ space–time paths than the ACO algorithm, the k th shortest path algorithm and the second generation of non-dominated sorting genetic algorithm were used to improve the results from the k th shortest path algorithm.