Search

Exploring the semantic correspondence of image-text pairs is significant as it bridges vision and language. Most prior works focus on global semantic alignment or local semantic alignment, by developing a fine neural network that facilitates the corresponding alignment but neglects the semantic information and relative position information between image regions, or text words, which will lead to a non-meaningful alignment. To this end, a Heterogeneous Graph Fusion Network (HGFN) is proposed to explore the correlation score of vision-language for improving the accuracy of cross-modal image-text retrieval in this paper. Specifically, we first construct an undirected fully-connected graph based on the semantic or relative position information for each image, as well as a textual graph with neighborhood information of the text. Then, we present a graph fusion module to integrate the features of heterogeneous graphs into a unified hybrid representation, in which the graph convolutional network is utilized to gather neighborhood information to alleviate potentially non-meaningful alignment. In addition, we also propose a novel "Dynamic top- K negative" strategy for the selection of negative examples in the training process. Experimental results demonstrate that HGFN achieves comparable performance with state-of-the-art approaches on the Flickr30K and MSCOCO datasets. • Cross-modal image-text retrieval problems can be treated as graph-graph matching. • A graph fusion module is designed to fuse the visual graph and textual graph. • A novel strategy for selecting negative examples is proposed. • Competitive with state-of-the-art performance on two standard benchmarks. [ABSTRACT FROM AUTHOR]

Block cipher has been one of the most reliable options by which data security is achieved. The strength of block cipher against various attacks is purely dependent on its confusion property, which is gained through the S-Boxes. In recent years, S-Boxes based on chaotic maps have become popular due to their favorable characteristics for cryptography. However, vulnerabilities have been discovered in these constructions, leading to concerns about their reliability. In this research, we first generate dynamic S-Boxes, and then based on the newly generated S-Boxes, a ROI-based medical image encryption scheme is proposed to address the challenges posed by the large size of DICOM images. Rather than encrypting the entire DICOM image, proposed encryption scheme only encrypts the ROI part where the relevant information is present, while leaving the black background unencrypted. This approach reduces the size of the encrypted data and improves the efficiency of the encryption process, while maintaining the privacy and confidentiality of sensitive medical data. The proposed ROI-based medical image encryption scheme is evaluated using standard performance metrics, including encryption speed, image quality tests, correlation-coefficient analysis, randomness of encrypted images, key sensitivity analysis, encryption sensitivity analysis, decryption sensitivity analysis, and resistance against common attacks such as differential and linear attacks. The proposed dynamic S-Box construction technique is evaluated using standard S-Box criteria, which include nonlinearity score, bit independence criterion, strict avalanche criteria, linear approximation probability, and differential approximation probability. Results demonstrate that the proposed technique gains high levels of encryption efficiency and security, making it a fast solution for secure medical image transmission in real-world applications. [ABSTRACT FROM AUTHOR]

Due to the enormous amount of user-generated content being generated on the web, labeling such data is a time-consuming and expensive endeavor. As a result, we have limited annotated data and the vast majority of data are unlabeled. Analysis reveals that extracting (external) knowledge from unlabeled data and integrating it with knowledge extracted from labeled data is a beneficial task for text information processing, in particular text classification. In this paper, we present a hybrid approach for classifying sentiments that employs external knowledge, which is categorized as either general-purpose sentiment knowledge or domain-related knowledge. General-purpose sentiment knowledge is extracted from sentiment lexicons, whereas domain-related knowledge is extracted from unlabeled data from the same or related domains. Similar domains for a given domain are identified based on their similarity score in terms of overlapping features. The proposed approach utilizes both forms of external knowledge and combines them with logistic regression to train an improved classification model. The classification model uses the conventional gradient descent algorithm for optimization, and its convergence analysis indicates that it is convex and converges to the global optimum. The proposed approach is empirically evaluated and compared to three baselines and one state-of-the-art method using standard performance evaluation metrics on a multi-domain sentiment dataset. The experiment results are encouraging, demonstrating that the proposed approach considerably outperforms the baseline approaches and outperforms the state-of-the-art approach by up to 2% in terms of both f-score and accuracy. • A hybrid approach for document-level sentiment classification that makes use of external knowledge. • A domain-specific knowledge extraction approach from unlabeled text documents. • A detailed convergence analysis of the proposed optimization model used in the proposed approach. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel dimensionality reduction term (i.e. TripletPCA and ContrastivePCA) designed to enhance the robustness of pair-based loss functions in metric learning against image corruptions. Notably, our approach achieves this without the need for any data preprocessing steps. Our method can be seamlessly integrated into existing models, such as a block with Plug & Play framework. To the best of our knowledge, our TripletPCA and ContrastivePCA represent the first attempts to incorporate dimensionality reduction directly into pair-based metric learning losses for end-to-end metric learning. By projecting image features into low-dimensional vectors, our proposed loss functions effectively retain the essential components of images while mitigating the impact of corrupted features. Consequently, our metric learning loss function accurately computes feature distances through the projection. Experimental results demonstrate that our dimensionality reduction term can be easily incorporated into various types of existing deep neural networks. This integration leads to a substantial improvement in performance on standard benchmark datasets for corrupted image classification tasks. On several corruption datasets, we achieve an average performance improvement of 10.55% compared to existing baseline methods. Our code is available at https://github.com/Juryun/TDRL. [ABSTRACT FROM AUTHOR]

Visual Attention Networks (VAN) with Large Kernel Attention (LKA) modules have been shown to provide remarkable performance, that surpasses Vision Transformers (ViTs), on a range of vision-based tasks. However, the depth-wise convolutional layer in these LKA modules incurs a quadratic increase in the computational and memory footprints with increasing convolutional kernel size. To mitigate these problems and to enable the use of extremely large convolutional kernels in the attention modules of VAN, we propose a family of Large Separable Kernel Attention modules, termed LSKA. LSKA decomposes the 2D convolutional kernel of the depth-wise convolutional layer into cascaded horizontal and vertical 1-D kernels. In contrast to the standard LKA design, the proposed decomposition enables the direct use of the depth-wise convolutional layer with large kernels in the attention module, without requiring any extra blocks. We demonstrate that the proposed LSKA module in VAN can achieve comparable performance with the standard LKA module and incur lower computational complexity and memory footprints. We also find that the proposed LSKA design biases the VAN more toward the shape of the object than the texture with increasing kernel size. Additionally, we benchmark the robustness of the LKA and LSKA in VAN, ViTs, and the recent ConvNeXt on the five corrupted versions of the ImageNet dataset that are largely unexplored in the previous works. Our extensive experimental results show that the proposed LSKA module in VAN provides a significant reduction in computational complexity and memory footprints with increasing kernel size while outperforming ViTs, ConvNeXt, and providing similar performance compared to the LKA module in VAN on object recognition, object detection, semantic segmentation, and robustness tests. [ABSTRACT FROM AUTHOR]

Multi-dimensional classification (MDC) task can be considered the most inclusive description of all classifications tasks, as it joins multiple class spaces and their multiple class members into a single compound classification problem. The challenges in MDC arise from the possible class dependencies across different class spaces, as well as the imbalance of labels in training datasets due to lack of all possible combinations. In this paper, we propose a straightforward, yet efficient, MDC deep learning classifier, named Deep Self-Organizing Cube (DSOC) that can model dependencies among classes in multiple class spaces, while consolidating its ability to classify rare combinations of labels. DSOC is formed of two n -dimensional components, namely the Hypercube Classifier and the multiple DSOC Neural Networks connected to the hypercube. The multiple neural networks component is responsible for feature selection and segregation of classes, while the Hypercube classifier is responsible for creating the semantics among multiple class spaces and accommodate the model for rare sample classification. DSOC is a multiple-output learning algorithm that successfully classify samples across all class spaces simultaneously. To challenge the proposed DSOC model, we conducted an assessment on seventeen benchmark datasets in the four types of classification tasks, binary, multi-class, multi-label and multi-dimensional. The obtained results were compared to four standard classifiers and eight competitive state-of-the-art approaches reported in literature. The DSOC has achieved superior performance over standard classifiers as well as the state-of-the-art approaches in all the four classification tasks. Moreover, in terms of Exact Match accuracy metrics, DSOC has outperformed all state-of-the-art approaches in 77.8% of the cases, which reflects the superior ability of DSOC to model dependencies and successfully classify rare samples across all dimensions simultaneously. [ABSTRACT FROM AUTHOR]

• Two novel term weighting schemes are proposed for text classification. • The proposed schemes are named as SQRT_TF-IGM imp and TF-IGM imp. • These schemes are derived from standard inverse gravity moment formula. • SQRT_TF-IGM imp method generally outperformed all other schemes. • The performance gains of the SQRT_TF-IGM imp scheme are statistically significant. Text classification is one of the popular high dimensional classification problems where providing better feature vector representations explicitly improve classification performances. Thus, assigning appropriate weights to features or terms are crucial for obtaining effective feature vector representations. The methods used for weighting terms in text classification are called term weighting schemes. Although there exist some term weighting schemes for text classification, they are not fully effective and researchers still focus on proposing new term weighting schemes. In this study, two novel term weighting schemes namely SQRT_TF-IGM imp and TF-IGM imp derived from standard inverse gravity moment formula are proposed to improve weighting behaviors of existing TF-IGM scheme especially for some extreme cases. The performances of proposed schemes are compared with two standard IGM based schemes and five other state-of-the-art term weighting methods on both unbalanced (Reuters-21578) and balanced (20 Mini Newsgroups and 20 Newsgroups) datasets with KNN, SVM, and NN classifiers. Micro-F1 and macro-F1 are used as success measures. The experiments are conducted with various different feature sizes to examine the effects of the feature size on the success of weighting. The experimental results showed that the proposed SQRT_TF-IGM imp method generally outperformed all schemes including both standard TF-IGM and SQRT_TF-IGM schemes. However, the proposed TF-IGM imp scheme also showed mostly better performance than standard TF-IGM. To demonstrate validity of the proposed weighting scheme having maximum performance, t -test is also used and it can be stated that the performance gains obtained by the proposed SQRT_TF-IGM imp weighting scheme compared to standard SQRT_TF-IGM are statistically significant. [ABSTRACT FROM AUTHOR]

The quantity of data generated increases daily, which makes it difficult to process. In the case of supervised learning, labeling training examples may represent an especially tedious and costly task. One of the aims of positive and unlabeled (PU) learning is to train a binary classifier from partially labeled data, representing a strategy for combining supervised and semi-supervised learning and alleviating the cost of labeling data fully. Still, the main strength of PU learning arises when the negative data are not directly available or too diverse. Although the generative approaches have shown promising results in this field, they also bring shortcomings, such as high computational cost, training instability, and inability to generate fully labeled datasets. In the paper, we propose a novel Conditional Generative PU framework (CGenPU) with a built-in auxiliary classifier. We develop a novel loss function to learn the distribution of positive and negative examples, which leads to a unique, desirable equilibrium under a nonparametric assumption. Our CGenPU is evaluated against existing generative approaches using both synthetic and real data. The characteristics of various methods, including ours, are depicted with different toy examples. The results demonstrate the state-of-the-art performance on standard positive and unlabeled learning benchmark datasets. Given only ten labeled CIFAR-10 examples, CGenPU achieves classification accuracy of 84%, while current state-of-the-art D-GAN framework achieves 54%. On top of that, CGenPU is the first single-stage generative framework for PU learning. • CGenPU is capable of conditional generation and binary classification. • Auxiliary PU loss enables the generation of positive and negative data distributions. • The objective has a unique, desirable equilibrium under a non-parametric assumption. • CGenPU shows state-of-the-art results in One-vs-One and One-vs-Rest scenarios. [ABSTRACT FROM AUTHOR]

Service composition can quickly build new value-added composite services by combining existing Web services. However, with the complex and changeable Internet environment, composite services need to effectively understand and manage requirements in a flexible and adaptive manner, and also be able to quickly and proactively provide high-quality services through a series of dynamic evolution models. In response to these challenges, in this study, we propose a service composition evolution method that can adaptively select the appropriate service to improve user satisfaction and service quality. First, we introduce a deep clustering method based on the topic model and auto-encoder, which considers the function description documents and parameter information of the services to reduce the search space of the candidate services. Furthermore, we describe a requirement-oriented context-sensitive task model to integrate functional and non-functional user requirements by connecting the context of Web subtasks. Then, we present a dynamic service matching method with QoS threshold judgement to filter and rank the services. We applied the proposed evolution method to the datasets of real-world Web services and measured the performance using standard measurement metrics. The prototype implementation and results of simulation experiments verified the effectiveness of each part of our method. • A novel service composition evolution method is proposed. • A deep clustering method is presented to implement the service clustering process. • RCT model and various evolutionary types are used to satisfy user requirements. • Simulation experiments on prototype system show the effectiveness. [ABSTRACT FROM AUTHOR]

Existing scene text recognition methods have incorporated text rectification to lessen text irregularity in images for accurate recognition. Previous text rectification methods aim to convert an irregular text image into a regular form, making it easier to be recognized. In this study, we explore text rectification for text recognition and discover the issues: performance degradation of the recognition network and the unreliable situation of text rectification, which are ignored by all previous works. Therefore, we rethink what is causing two issues, and propose a rectification-based text recognition network to mitigate the above issues. The proposed network consists of text rectification and text recognition, and designs a multi-level feature aggregation module to enhance feature learning for character representation. Concretely, we devise a mixed batch training strategy to address the performance degradation of the recognition network, and design a confidence decoding scheme to avoid the unreliable situation of text rectification. Extensive ablation studies verified the positive role of the feature aggregation module in feature learning and the effectiveness of the proposed training strategy and decoding scheme in addressing the issues. Experimental results outperform the state-of-the-art results on public benchmarks. • We explore the limitation and unreliable cases caused by the rectification network. • Mixed batch and confidence decoding are designed for accurate recognition. • We design feature aggregation to exploit multi-level features. • Our method achieves superior performance on standard datasets. [ABSTRACT FROM AUTHOR]

Obesity, termed as excessive body fat, is a major public health problem. Being able to accurately predict body fat percentage provides an opportunity for making appropriate prevention and diagnosis. Although various assessment techniques have been applied for body fat estimation, high-cost tests are required using special equipment, and the performance of standard machine learning models are typically impacted by noise data. In this paper, we propose a novel fuzzy-weighted approach for improving body fat prediction using easily accessed body measurements in a cost-effective manner. Given the noise data problem, we design a novel fuzzy weighted operation by extending the minimum and maximum values for calculating the fuzzy weights to cover more possibilities. The fuzzy weights are incorporated into the error constraints of a relative error support vector machine model to improve its robustness to noise data. In addition, the Whale Optimization Algorithm (WOA) is applied in our proposed model for parameter optimization. Our proposed fuzzy-weighted approach delivers excellent results for body fat prediction by outperforming other well-known machine learning models. Further, the statistical test based on the 20 runs of experiments not only confirms that our proposed model could significantly outperform the models under comparison, but also show the fuzzy weighted operation and WOA are effective to improve the proposed approach. This offers a viable alternative for medical decision makers to make appropriate prevention, early diagnosis, and early treatment of body fat related diseases when high-cost measurement techniques are not available. • A novel fuzzy-weighted approach is proposed for body fat prediction. • The whale optimization algorithm is applied for parameter optimization. • Evaluation metrics indicate the effectiveness of our proposed approach. • Our approach can be a useful tool for medical decision makers. [ABSTRACT FROM AUTHOR]

Ideally, Convolutional Neural Networks (CNNs) should be trained with high quality images with minimum noise and correct ground truth labels. Nonetheless, in many real-world scenarios, such high quality is very hard to obtain, and datasets may be affected by any sort of image degradation and mislabelling issues. This negatively impacts the performance of standard CNNs, both during the training and the inference phase. To address this issue we propose Wise2WipedNet (W2WNet), a new two-module Convolutional Neural Network, where a Wise module exploits Bayesian inference to identify and discard spurious images during the training and a Wiped module takes care of the final classification, while broadcasting information on the prediction confidence at inference time. The goodness of our solution is demonstrated on a number of public benchmarks addressing different image classification tasks, as well as on a real-world case study on histological image analysis. Overall, our experiments demonstrate that W2WNet is able to identify image degradation and mislabelling issues both at training and at inference time, with positive impact on the final classification accuracy. • A novel two-module CNN exploiting Bayesian inference is introduced. • We address image degradation and mislabelling both at training and at inference. • Our method overcomes the deterministic counterpart (standard DenseNet121). • We show results on two public benchmarks and a real-world histological case study. [ABSTRACT FROM AUTHOR]

The relationship between performance and experience is non-linear, thus planning models that seek to manage workforce development through task assignment are difficult to solve. This gets even more complicated when taking into account multi-skilled workers that are capable of performing a variety of tasks. In this paper we develop a competences-based analytical model of the performance of multi-skilled workers undertaking repetitive tasks, taking into account learning and forgetting. A learning curve can be used to estimate improvement when repeating the same operation. Inverse phenomenon is forgetting, which can occur due to interruption in the production process. The Performance Evaluation Algorithm (PEA) was developed for two cases: fixed shift duration and fixed production output. The aim was to build a tool that better describes the capabilities of workers to perform repetitive tasks by binding together hierarchical competences modeled as a weighted digraph together with a learning and forgetting curve model (LFCM) to express individual learning rates. [ABSTRACT FROM AUTHOR]

Nowadays, recruitment processes are increasingly being automated by intelligent systems which provide best candidates for companies' open positions, and vice versa. However, extracting information from the unstructured documents involved in these processes (e.g. resumes, jobs' descriptions) still represents an open challenge because of their high heterogeneity (in the form and style) and the lack of pre-defined standards between different companies and/or countries. In this paper, we address the resume information extraction problem, focusing on documents within the Italian Labor Market. Specifically, we propose an effective and efficient end-to-end framework capable of providing a complete candidate overview including his personal information, skills and work experiences. Specifically, after having extracted the raw data from the resume documents, the system segments them into semantically consistent parts using linguistics patterns. Each segment is further processed with a NER algorithm, based on pre-trained language models, to extract relevant information which an HR specialist could consult in order to assess the suitability of a candidate for a job offer. We collected (and labeled) a new Italian resume dataset and our results prove the effectiveness of the proposed method, especially considering the great advantages our segmentation strategy brings to the NER performance with respect to standard line-based segmentation approaches. In addition, our system achieves promising performance when combined with modern NLP models. • Recruitment process can be improved by techniques extracting information from resumes. • An end-to-end framework has been designed for information extraction from resume. • Relevant information is extracted through a NER task on semantically consistent parts. • Our framework has been evaluated on a real resume dataset, showing promising results. [ABSTRACT FROM AUTHOR]

The particle filter (PF) has been widely studied in the prognostics' field due to its ability to deal with nonlinear and non-stationary systems. However, there is no update of the model parameters during the prediction, preventing PF to work in its traditional way to generate accurate long-term predictions. In order to solve this problem, we put forward an improved PF that is based on a novel health index (HI) similarity matching method. This method is employed to search for similar HIs in the training library and construct an optimal "similar HI" for the system under study. Finally, the obtained HI is consistently fed into the PF to deliver precise state-of-health (SoH) estimates. The effectiveness of the proposed PF was validated on the C-MAPSS datasets as well as data collected from an operational reciprocating compressor. We observed that the new similarity matching method demonstrated excellent performance in finding suitable HIs for failure time prediction. We also observed that the proposed PF framework had a superior prognostics performance over the standard PF. We obtained an averaged predictive accuracy of 96% (C-MAPSS data) and 92% (compressor data) when only the first 10% of the degradation data were used. This work highlights the promise of combining index similarity, Procrustes analysis and PF for complementing existing prognostic methods. • Improves the predictive accuracy and uncertainty level of standard Particle filter. • This method realizes early/incipient fault prognosis. • We put forward a new Spherical-Cosine-distance-based similarity matching method. • We tested the proposed method on both simulation and real-world data. [ABSTRACT FROM AUTHOR]

For an efficient detection of intrusion in the network, the system requires sensitive information. This information contains various features depending upon the network. The selection of useful features and relevant information from the dataset has always been difficult for the user. These features bound the performance of the system and also restrict them in making accurate decisions. This irrelevant feature plays a major role in making confusion between the normal data pattern against the attack data pattern. This article proposes a novel Maximum correlation-based mutual information technique for efficient feature selection (MCMIFS) in a data network. The proposed method is utilized with Kernel Extreme Learning Machine (KELM) based multiclass classifier for effective intrusion detection. The performance of the proposed scheme is evaluated using standard intrusion detection datasets with feature ranging from 42 to 155. The hybrid of MCMIFS with KELM reveals the effectiveness of the proposed scheme by improving the accuracy of detection, i.e., 99.97%, decreasing the FPR, i.e., 0.19, by decreasing the computational complexity. The proposed Intrusion Detection Scheme (IDS) results are analyzed and compared with the other existing techniques. • An optimized MCMIFS based feature selection scheme is proposed. • The proposed MCMIFS is utilized with Kernel ELM for multiclass intrusion detection. • The proposed IDS is tested using standard intrusion detection datasets. • Standard performance metrics i.e. Accuracy, Detection Rate and FPR are utilized. • Proposed technique outperforms the existing ones for all used cases. [ABSTRACT FROM AUTHOR]

Abstract: Many enterprises have recently been pursuing process innovation or improvement to attain their performance goals. To align a business process with enterprise performances, this study proposes a two-stage process analysis for process (re)design that combines the process-based performance measurement framework (PPMF) and business process simulation (BPS). The two-stage analysis consists of macro and micro analyses of business processes. At the early stage of business process analysis (BPA), macro process analysis is conducted to identify the influence of a business process on a target key performance indicator (KPI) or the contribution of a target KPI to other KPIs. If target business processes that need improvement are identified through the macro process analysis and to-be processes are newly designed, micro process analysis using simulation is conducted to predict the performance. The proposed method is validated by application to a real business process within the setting of a large Korean company. By using the proposed, two-stage process analysis, company staff involved in process innovation projects can determine the processes with the greatest influence on enterprise strategy, and can systematically evaluate the performance prediction of the newly designed process. [Copyright &y& Elsevier]

Information technology professionals and administrators are required to cut cost, protect current investments, and meet immediate performance demands without service interruption. Achieving these requirements within tight budgetary constraints, they have to consider the task of how to configure and tune their computer systems. In this work presented here, a novel performance prediction system has been used to provide suitable performance models which can determine application mapping parameters, code execution decisions, and system choices on-the-fly. The method uses heuristics and system performance tools to the diagnosis of bottlenecks and provides the necessary remedies to achieve acceptable computer performance. The work introduces a parameter prioritizing tool to focus on those performance critical parameters. It also demonstrates how to reduce the time when tuning a large system with many tunable parameters. The search space can be reduced by checking the relations among parameters to avoid unnecessary search. [Copyright &y& Elsevier]

Abstract: The development of information technology and internet capabilities over the years has been at an accelerated pace of global intense challenges and competitions of the technologies markets. Therefore, the issue of effectively utilizing valuable information located in databases worldwide, by monitoring the performance of their operations became an important issue in the electronic business environment. Methods to address this issue were employed to quickly identify the Key Performance Indicators (KPI’s) and operational problems and clarify any relationships between them, to allow the overall business objectives to be achieved. In this paper, the Fuzzy Delphi and ranking methods were used to extract the most concerning issues through expert questionnaires. A fuzzy regression model was then constructed and applied to clarify the relationships between the KPI’s and the key management objective, the area of production loss. Therefore, the key factors for future improvements were obtained by tracking the fuzzy regression model. Finally a case study of a semiconductor assembly and testing, through a company in Taiwan, was used to illustrate the proposed framework. The results indicated that this model could be easily implemented to analyze the influence of concerned KPIs on key management objectives. [Copyright &y& Elsevier]

The choice of performance measures is critical to formulating strategies. This paper investigates the relationship among corporate strategies, environmental forces, and the Balanced Scorecard (BSC) performance measures. Corporate strategies are explored within the framework of Miles and Snow''s taxonomy, where they are categorized into prospectors, defenders, analyzers, and reactors. The relative weights for each performance measure are calculated by the use of the Analytic Hierarchy Process. A sample of 219 companies can confirm the link between corporate strategies, environmental forces, and the weights of the BSC performance measures. These weights shift depending on the nature of challenges companies face. In the light of this empirical evidence, a decision support system is proposed to help retrieve the BSC weights of the companies with similar characteristics. In order to measure the proximity between companies, a k-nearest neighbor technique is employed. This system can help find the weights of the performance measures for particular strategies. [Copyright &y& Elsevier]

• Multi-objective non-linear fixed charge transportation problem. • Multiple modes of transportation with fixed capacities. • Solution using three metaheuristic algorithms NSGA-II, SPEA2 and GrEA. • Developed new crossover and mutation operators suitable for multiple modes of transportation. • Comparison of results using four standard performance measures namely, RNI value, HV, Spacing and GS. The main focus of this work is to formulate and solve a Fixed Charge Transportation Problem (FCTP) considering multiple modes of transport with different capacities. The condition for the feasibility is that the total capacity of all the modes of transport at each origin must be at least the total quantity of commodity available at the origin. The problem is modeled as a multi-objective minimization problem with two conflicting objectives: the total transportation cost and the total transportation time. For this purpose, crossover and mutation operators have been designed to make them suitable for the problem. The problem is solved by a modified NSGA-II, obtained by adapting the newly developed genetic operators in the metaheuristic structure of NSGA-II. Five numerical example problems of various sizes are solved using the modified NSGA-II. For a fair comparison of the performance of the modified NSGA-II, the same example problems are solved using two other algorithms: modified SPEA-2 and a modified GrEA, obtained by incorporating the same newly developed crossover and mutation respectively into SPEA-2 and GrEA. The results obtained by the modified NSGA-II, modified SPEA-2 and modified GrEA are compared using four performance metrics: RNI value, HV, Spacing and GS. The modified NSGA-II performs best for all example problems according to the metrics RNI value and GS, and for all the example problems except the example Problem 3 according to the metrics HV and spacing. For the example Problem 3, the modified GrEA yields the best performance with respect to the metrics HV and spacing. The modified SPEA2 performs worst in terms of all the metric values for all the example problems. Finally, some potential future research directions are discussed in the conclusion. [ABSTRACT FROM AUTHOR]

• A modified bat algorithm based on new position selection strategies is proposed. • The modified bat algorithm is hybrized with differantial evolution algorithm. • Exploration and exploitation abilities of the bat algorithm are balanced. • The algorithms are tested on classical benchmark functions and CEC test suites. • Hybrid method improved significantly the performance of the bat algorithm. The bat algorithm (BA) is one of the metaheuristic algorithms that are used to solve optimization problems. The differential evolution (DE) algorithm is also applied to optimization problems and has successful exploitation ability. In this study, an advanced modified BA (MBA) algorithm was initially proposed by making some modifications to improve the exploration and exploitation abilities of the BA. A hybrid system (MBADE), involving the use of the MBA in conjunction with the DE, was then suggested in order to further improve the exploitation potential and provide superior performance in various test problem clusters. The proposed hybrid system uses a common population, and the algorithm to be applied to the individual is selected on the basis of a probability value, which is calculated in accordance with the performance of the algorithms; thus, the probability of applying a successful algorithm is increased. The performance of the proposed method was tested on functions that have frequently been studied, such as classical benchmark functions, small-scale CEC 2005 benchmark functions, large-scale CEC 2010 benchmark functions, and CEC 2011 real-world problems. The obtained results were compared with the results obtained from the standard BA and other findings in the literature and interpreted by means of statistical tests. The developed hybrid system showed superior performance to the standard BA in all test problem sets and produced more acceptable results when compared to the published data for the existing algorithms. In addition, the contribution of the MBA and DE algorithms to the hybrid system was examined. [ABSTRACT FROM AUTHOR]