Narrow Results

The rapid expansion of artificial intelligence technologies has enabled machines to comprehend emotional intelligence. Among various indicators, facial expressions serve as an effective medium for understanding emotions. The concept of facial expression recognition (FER) relies heavily on the accurate and robust features available. Initially, the method of three-channel convolutional neural networks (TC-CNN) is adapted to extract facial features. However, only extracting the features is insufficient, the optimization of the extracted features is crucial to determining precise and robust features. This research work focuses on the optimization of the features using the quantum-inspired vortex search algorithm (QVSA). The QVSA integrates the attributes of Q-bits into the vortex search algorithm (VSA), optimizing the features by using the Q-bits to determine the vortex center on the Bloch sphere. The Q-bit attributes also improve the diversity of the features and help to avoid the premature convergence of the VSA. The final recognition of the facial expressions is performed using the deep neural network method of ResNet101v2. The experiments for facial expression recognition are performed on the datasets of RaFD and KDEF, which include different facial positions such as front pose, diagonal pose and profile pose. Performance comparisons demonstrate the effectiveness of the proposed system over state-of-the-art facial expression techniques.

Parameter estimation of chaotic system is an important issue in nonlinear science. The meta-heuristic algorithm is one of the effective estimation approaches, and has received increasing attention. However, few people have noticed the influence of the samples on parameter estimation. In fact, when using meta-heuristic algorithm for parameter estimation, the number of samples will affect the efficiency greatly. In this paper, this problem is investigated. The relationship between sample and step size, and the factors that affect the difficulty of parameter estimation are also considered. Experimental results show that it is more efficient to set the samples to a small number, and the number of estimated parameters is the most important factor affecting the difficulty of parameter estimation. Finally, to improve the precision further, a new hybrid chaotic particle swarm optimization algorithm which combines a special inertia weight with chaotic search is proposed. Results demonstrate that the new hybrid algorithm is more effective than the other four meta-heuristic algorithms.

This work proposes a new powerful meta-heuristic optimization algorithm in education process called Competitive Learning (CLA). The algorithm is benchmarked on 8 well-known test functions, and the results are verified by a comparative study with some meta-heuristic optimization methods including: Imperialist Competitive Algorithm (ICA), Teaching-Learning-Based Optimization (TLBO), Grey Wolf Algorithm (GWO), Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). Analyzing the findings, it is shown that the CLA algorithm is able to provide more accurate results than other well-known meta-heuristic ones. Also, those results applied to famous unimodal and multimodal benchmarks show CLA is efficient in improving accuracy as well as computational speed.

In the image processing application, contrast enhancement is a major step. Conventional contrast enhancement methods such as Histogram Equalization (HE) do not have satisfactory results on many different low contrast images and they also cannot automatically handle different images. These problems result in specifying parameters manually to produce high contrast images. In this paper, an automatic image contrast enhancement on Memetic algorithm (MA) is proposed. In this study, simple exploiter is proposed to improve the current image contrast. The proposed method accomplishes multi goals of preserving brightness, retaining the shape features of the original histogram and controlling excessive enhancement rate, suiting for applications of consumer electronics. Simulation results shows that in terms of visual assessment, peak signal-to-noise (PSNR) and Absolute Mean Brightness Error (AMBE) the proposed method is better than the literature methods. It improves natural looking images specifically in images with high dynamic range and the output images were applicable for products of consumer electronic.

Task scheduling is one of the most difficult problems which is associated with cloud computing. Due to its nature, as it belongs to nondeterministic polynomial time (NP)-hard class of problem. Various heuristic as well as meta-heuristic approaches have been used to find the optimal solution. Task scheduling basically deals with the allocation of the task to the most efficient machine for optimal utilization of the computing resources and results in better makespan. As per literature, various meta-heuristic algorithms like genetic algorithm (GA), particle swarm optimization (PSO), ant colony optimization (ACO) and their other hybrid techniques have been applied. Through this paper, we are presenting a novel meta-heuristic technique — genetic algorithm enabled particle swarm optimization (PSOGA), a hybrid version of PSO and GA algorithm. PSOGA uses the diversification property of PSO and intensification property of the GA. The proposed algorithm shows its supremacy over other techniques which are taken into consideration by presenting less makespan time in majority of the cases which leads up to 22.2% improvement in performance of the system and also establishes that proposed PSOGA algorithm converges faster than the others.

Cloud security in finance is considered as the key importance, taking account of the aspect of critical data stored over cloud spaces within organizations all around the globe. They are chiefly relying on cloud computing to accelerate their business profitability and scale up their business processes with enhanced productivity coming through flexible work environments offered in cloud-run working systems. Hence, there is a prerequisite to contemplate cloud security in the entire financial service sector. Moreover, the main issue challenged by privacy and security is the presence of diverse chances to attack the sensitive data by cloud operators, which leads to double the user’s anxiety on the stored data. For solving this problem, the main intent of this paper is to develop an intelligent privacy preservation approach for data stored in the cloud sector, mainly the financial data. The proposed privacy preservation model involves two main phases: (a) data sanitization and (b) data restoration. In the sanitization process, the sensitive data is hidden, which prevents sensitive information from leaking on the cloud side. Further, the normal as well as the sensitive data is stored in a cloud environment. For the sanitization process, a key should be generated that depends on the new meta-heuristic algorithm called crossover improved-lion algorithm (CI-LA), which is inspired by the lion’s unique social behavior. During data restoration, the same key should be used for effectively restoring the original data. Here, the optimal key generation is done in such a way that the objective model involves the degree of modification, hiding rate, and information preservation rate, which effectively enhance the cyber security performance in the cloud.

In this paper, for the first time the cross-docking concept is considered in a vendor-managed inventory (VMI)-based supply chain. In this supply chain, and based on the economic order quantity (EOQ) model, a vendor prepares and sends several products to retailers. Then, retailers, based upon customers’ order, send products to the cross-dock to be delivered to the customers. Demands of retailers and customers are deterministic and shortage is acceptable as backorder. Presented mathematical model (of integer nonlinear programming type) seeks to minimize the total cost of the supply chain. Thus, a meta-heuristic algorithm (GA) is used to solve the model. In addition, a number of sample problems are analyzed to evaluate the performance of the solving algorithm. Finally, after the conclusion, some suggestions are provided for future researches.

In this paper, we have observed that different types of plants in nature can use their own survival mechanisms to adapt to various living environments. A new population-based vegetation evolution (VEGE) algorithm is proposed to solve optimization problems by interactively simulating the growth and maturity periods of plants. In the growth period, individuals explore their local areas and grow in potential directions, while individuals generate many seed individuals and spread them as widely as possible in the maturity period. The main contribution of our proposed VEGE is to balance exploitation and exploration from a novel perspective, which is to perform these two periods in alternation to switch between two different search capabilities. To evaluate the performance of the proposed VEGE, we compare it with three well-known algorithms in the evolutionary computation community: differential evolution, particle swarm optimization, and enhanced fireworks algorithm — and run them on 28 benchmark functions with 2-dimensions (2D), 10D, and 30D with 30 trial runs. The experimental results show that VEGE is efficient and promising in terms of faster convergence speed and higher accuracy. In addition, we further analyze the effects of the composition of VEGE on performance, and some open topics are also given.