Search

The process of feature mapping is used to represent features on a map with their corresponding properties. The features are displayed visually and their associated information is made available. Various abstraction approaches, including alignment approaches, are introduced to reduce the computational complexity. However, previous works based on standard treatments of feature maps often suffer from the negative effects of noise and background details. To solve this problem, we present a simple and effective implementation approach for Filter Pruning via Attention Consistency (FPAC), which determines a revolutionary filter pruning mechanism. Feature maps that concentrate on a single layer are inconsistent, which can affect the spatial dimension. The feature map with minimum consistency is less significant and is experimentally demonstrated. This study presents a novel layer-wise pruning technique using the Aphid Ant Mutualism (AAM) algorithm, which considers the sensitivity of various convolutional network layers to model inference and sets the optimal pruning ratio. The accuracy of the compressed model is enhanced by eliminating high redundancy through pruning correlated filters. The performance of FPAC is confirmed through the Caltech 256 image dataset. With VGG-16 on the Caltech 256 image dataset, the classification accuracy is enhanced from 93.96 to 94.03%. With ResNet-50 on the Caltech 256 image dataset, 45% FLOPs are achieved with an accuracy loss of only 0.53%. [ABSTRACT FROM AUTHOR]

Cardiovascular diseases (CVD) are the most widely spread diseases all over the world among the common chronic diseases. CVD represents one of the main causes of morbidity and mortality. Therefore, it is vital to accurately detect the existence of heart diseases to help to save the patient life and prescribe a suitable treatment. The current evolution in artificial intelligence plays an important role in helping physicians diagnose different diseases. In the present work, a hybrid framework for the detection of heart diseases using medical voice records is suggested. A framework that consists of four layers, namely "Segmentation" Layer, "Features Extraction" Layer, "Learning and Optimization" Layer, and "Export and Statistics" Layer is proposed. In the first layer, a novel segmentation technique based on the segmentation of variable durations and directions (i.e., forward and backward) is suggested. Using the proposed technique, 11 datasets with 14,416 numerical features are generated. The second layer is responsible for feature extraction. Numerical and graphical features are extracted from the resulting datasets. In the third layer, numerical features are passed to 5 different Machine Learning (ML) algorithms, while graphical features are passed to 8 different Convolutional Neural Networks (CNN) with transfer learning to select the most suitable configurations. Grid Search and Aquila Optimizer (AO) are used to optimize the hyperparameters of ML and CNN configurations, respectively. In the last layer, the output of the proposed hybrid framework is validated using different performance metrics. The best-reported metrics are (1) 100% accuracy using ML algorithms including Extra Tree Classifier (ETC) and Random Forest Classifier (RFC) and (2) 99.17% accuracy using CNN. [ABSTRACT FROM AUTHOR]

Various methods have been proposed to secure access to sensitive information over time, such as many cryptographic methods in use to facilitate secure communications on the internet. But other methods like steganography have been overlooked which may be more suitable in cases where the act of transmission of sensitive information itself should remain a secret. Multiple techniques that are commonly discussed for such scenarios suffer from low capacity and high distortion in the output signal. This research introduces a novel steganographic approach for concealing a confidential portable document format (PDF) document within a host image by employing the hybrid firefly algorithm (HFA) proposed to select the pixel arrangement. This algorithm combines two widely used optimization algorithms to improve their performance. The suggested methodology utilizes the HFA algorithm to conduct a search for optimal pixel placements in the spatial domain. The purpose of this search is to accomplish two main goals: increasing the host image’s capacity and reducing distortion. Moreover, the proposed approach intends to reduce the time required for the embedding procedure. The findings indicate a decrease in image distortion and an accelerated rate of convergence in the search process. The resultant embeddings exhibit robustness against steganalytic assaults, hence rendering the identification of the embedded data, a formidable undertaking. [ABSTRACT FROM AUTHOR]

Swarm-based metaheuristic optimization algorithms have demonstrated outstanding performance on a wide range of optimization problems in both science and industry. Despite their merits, a major limitation of such techniques originates from non-automated parameter tuning and lack of systematic stopping criteria that typically leads to inefficient use of computational resources. In this work, we propose an improved version of grey wolf optimizer (GWO) named adaptive GWO which addresses these issues by adaptive tuning of the exploration/exploitation parameters based on the fitness history of the candidate solutions during the optimization. By controlling the stopping criteria based on the significance of fitness improvement in the optimization, AGWO can automatically converge to a sufficiently good optimum in the shortest time. Moreover, we propose an extended adaptive GWO ( AGWO Δ ) that adjusts the convergence parameters based on a three-point fitness history. In a thorough comparative study, we show that AGWO is a more efficient optimization algorithm than GWO by decreasing the number of iterations required for reaching statistically the same solutions as GWO and outperforming a number of existing GWO variants. [ABSTRACT FROM AUTHOR]

In this study, we apply multilevel thresholding segmentation to color images of plant disease. Given that thresholding segmentation is just an optimization problem, we use Otsu's function as the objective function. To solve this optimization problem, we implement five metaheuristic algorithms, namely artificial bee colony (ABC), cuckoo search (CS), teaching–learning-based optimization (TLBO), teaching–learning-based artificial bee colony (TLABC) and a modified version of TLABC proposed in this work, known as MTLABC. This version is a hybridization between TLABC and Levy flight where the search equations of TLABC are changed according to Levy flight equations; this modification, based on the experimental results, yields a significant improvement in TLABC. Various numbers of thresholding levels are tried to compare the performance of the optimization algorithms at multiple dimensions. The performance is measured according to five measures: the objective function, CPU time, peak noise-to-signal ratio, structural similarity index and color feature similarity. These measures indicate that our proposed algorithm, with the best values of the measures in most images and levels, ranks first. Also, Friedman and Wilcoxon signed-rank tests are used to analyze the results statistically. These two tests prove that our proposed algorithm is significantly different from the other four algorithms. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have evolved as a beneficial machine learning method that has been successfully used in various applications. Currently, DNN is a superior technique of extracting information from massive sets of data in a self-organized method. DNNs have different structures and parameters, which are usually produced for particular applications. Nevertheless, the training procedures of DNNs can be protracted depending on the given application and the size of the training set. Further, determining the most precise and practical structure of a deep learning method in a reasonable time is a possible problem related to this procedure. Meta-heuristics techniques, such as swarm intelligence (SI) and evolutionary computing (EC), represent optimization frames with specific theories and objective functions. These methods are adjustable and have been demonstrated their effectiveness in various applications; hence, they can optimize the DNNs models. This paper presents a comprehensive survey of the recent optimization methods (i.e., SI and EC) employed to enhance DNNs performance on various tasks. This paper also analyzes the importance of optimization methods in generating the optimal hyper-parameters and structures of DNNs in taking into consideration massive-scale data. Finally, several potential directions that still need improvements and open problems in evolutionary DNNs are identified. [ABSTRACT FROM AUTHOR]

This paper proposes a modified version of a well-known optimization technique called Farmland Fertility Optimization algorithm (FFA). The modified FFA (MFFA) is developed in order to improve the performance of conventional FFA. It is mainly based on two stages. Firstly, the Levy flights are used to enhance the local searching capability in the exploitation phase and the global searching capability in the exploration phase. Secondly sine–cosine functions are used to create different solutions which fluctuate outwards or towards the best possible solution. The developed algorithm has been validated using ten benchmark functions and three mechanical engineering benchmark optimization problems. After that, the newly developed algorithm MFFA is used for extracting the effective unknown parameters of Proton Exchange Membrane Fuel Cells (PEMFCs) models. The optimal extraction of these parameters is essential to determine an accurate semi-empirical mathematical model for PEMFC. The sum of squared errors between the experimental data and the corresponding calculated ones is adopted as the objective function. Four different commercial PEMFC stacks are used to validate the effectiveness of the developed algorithm. The results obtained by MFFA are compared with those obtained by the conventional FFA and other well-known optimization techniques. Moreover, a comprehensive statistical analysis is performed to determine the accuracy and efficiency of the developed algorithm. The results prove the reliability and superiority of the developed algorithm compared with the conventional FFA and other state-of-the-art optimizers. [ABSTRACT FROM AUTHOR]

Segmentation is considered as one of the most significant tasks in image processing. It consists of separating the pixels into different segments based on their intensity level according to threshold values. Selecting the optimal threshold value is the key to best quality segmentation. Multilevel thresholding (MT) is an essential approach for image segmentation, and it has become very popular during the past few years, but while increasing the level of thresholds, computational complexity also increases exponentially. In order to overcome this drawback, several metaheuristics-based algorithms have been used for determining the optimal MT levels. Learning enthusiasm-based teaching–learning-based optimization (LebTLBO) is a recently developed efficient, simple-to-implement and computationally inexpensive algorithm. It simulates the behaviors of the teaching and learning process in a classroom and gives the probability of getting the amount of information by the learner (student) from the educator. In this paper, LebTLBO is applied on ten standard test images having a diverse histogram, which are taken from Berkeley Segmentation Dataset 500 (BSDS500) (Martin et al. in a database of human segmented natural images and its application to evaluate segmentation algorithms and measure ecological statistics, 2001) benchmark image set for segmentation. The search capability of the algorithm is combined with Otsu and Kapur's entropy MT objective functions for image segmentation. The proposed approach is compared with the existing state-of-the-art optimization algorithms such as MTEMO, GA, PSO and BF for both Otsu and Kapur's entropy methods. Qualitative experimental outcomes demonstrate that LebTLBO is highly efficient in terms of performance metrics such as PSNR, mean, threshold values, number of iterations taken to converge and image segmentation quality. [ABSTRACT FROM AUTHOR]

Most of today’s mobile robots operate in controlled environments prone to various unpredictable conditions. Programming or reprogramming of such systems is time-consuming and requires significant efforts by number of experts. One of the solutions to this problem is to enable the robot to learn from human teacher through demonstrations or observations. This paper presents novel approach that integrates Learning from Demonstrations methodology and chaotic bioinspired optimization algorithms for reproduction of desired motion trajectories. Demonstrations of the different trajectories to reproduce are gathered by human teacher while teleoperating the mobile robot in working environment. The learning (optimization) goal is to produce such sequence of mobile robot actuator commands that generate minimal error in the final robot pose. Four different chaotic methods are implemented, namely chaotic Bat Algorithm, chaotic Firefly Algorithm, chaotic Accelerated Particle Swarm Optimization and newly developed chaotic Grey Wolf Optimizer (CGWO). In order to determine the best map for CGWO, this algorithm is tested on ten benchmark problems using ten well-known chaotic maps. Simulations compare aforementioned algorithms in reproduction of two complex motion trajectories with different length and shape. Moreover, these tests include variation of population in swarm and demonstration examples. Real-world experiment on a nonholonomic mobile robot in indoor environment proves the applicability of the proposed approach. [ABSTRACT FROM AUTHOR]