Vahid Seydi

Bangor University · School of Ocean Sciences

The object segmentation mask’s observation sequence shows the trend of changes in the object’s observable geometric form, and predicting them may assist in solving various difficulties in multi-object tracking and segmentation (MOTS). With this aim, we propose the entangled appearance and motion structures network (EAMSN), which can predict the obj...

Deep learning methods demand enormous amounts of labeled data. Although collecting labeled data is a challenge but it can be accomplished with difficulty. Nevertheless, domain shift or bias may occur due to some conditions. Recollecting data under similar conditions is too expensive or impossible. Domain adaptation is an effective technique to deal...

Community detection in complex networks is an important task for discovering hidden information in network analysis. Neighborhood density between nodes is one of the fundamental indicators of community presence in the network. A community with a high edge density will have correlations between nodes that extend beyond their immediate neighbors, den...

Machine learning covers a large set of algorithms that can be trained to identify patterns in data. Thanks to increases in the amounts of data and computing power available, it has become pervasive across scientific disciplines. We first highlight why machine learning is needed in marine ecology. Then we provide a quick primer on machine learning t...

Due to the growth of using various devices and applications in modern life, the amount of data available is skyrocketing, but labeling all of this data is beyond the reach of data scientists. Thus, it is necessary to categorize data with a small amount of labeled data. In fact, it should be possible to prioritize data for labeling. To achieve this...

Domain adaptation is an attractive approach given the availability of a large amount of labeled data with similar properties but different domains. It is effective in image classification tasks where obtaining sufficient label data is challenging. We propose a novel method, named SELDA, for stacking ensemble learning via extending three domain adap...

Community detection in networks is a useful tool for detecting the behavioral and inclinations of users to a specific topic or title. Weighted, unweighted, directed, and undirected networks can all be used for detecting communities depending on the network structure and content. The proposed model framework for community detection is based on weigh...

Having a lot of labeled data is always a problem in machine learning issues. Even by collecting lots of data hardly, shift in data distribution might emerge because of differences in source and target domains. The shift would make the model to face with problems in test step. Therefore, the necessity of using domain adaptation emerges. There are th...

This paper presents the extraction of the emotional signals from traumatic brain-injured (TBI) patients through the analysis of facial features and implementation of the effective emotion-recognition model through the Pepper robot to assist in the rehabilitation process. The identification of emotional cues from TBI patients is very challenging due...

Dynamic multi-objective optimization algorithms are used as powerful methods for solving many problems worldwide. Diversity, convergence, and adaptation to environment changes are three of the most important factors that dynamic multi-objective optimization algorithms try to improve. These factors are functions of exploration, exploitation, selecti...

Passive acoustic monitoring (PAM) is a common approach to monitor marine mammal populations, for species of dolphins, porpoises and whales that use sound for navigation, feeding and communication. PAM produces large datasets which benefit from the application of machine learning algorithms to automatically detect and classify the vocalisations of t...

In order to estimate the Pareto front, most of the existing evolutionary algorithms apply the discovery of non-dominated solutions in search space, and most algorithms need appropriate diversity. Sometimes the Pareto front is so much thin and several dominated solutions exist beside the Pareto front. This paper proposes a new inverse model-based ev...

The WGMLEARN group was formed to explore the use of machine learning in the marine sci-ences, and work towards increasing knowledge of and competence with relevant methods among marine scientists. The specific objectives were to review methods, applications, and im-plementations, to gather knowledge about them from a wide array of scientists, to ad...

Twitter is one of the most popular and renowned online social networks spreading information which although dependable could lead to spreading improbable and misleading rumors causing irreversible damage to individuals and society. In the present paper, a novel approach for detecting rumor-based conversations of various world events such as real-wo...

Domain adaptation is an attractive approach given the availability of a large amount of labeled data with similar properties but different domains. It is effective in image classification tasks where obtaining sufficient label data is challenging. We propose a novel method, named SELDA, for stacking ensemble learning via extending three domain adap...

The basic idea in the estimation of distribution algorithms is the replacement of heuristic operators with machine learning models such as regression models, clustering models, or classification models. So, recently, the model‐based evolutionary algorithms (MBEAs) have been suggested in three groups: The estimation of distribution algorithms (EDAs)...

With the increasing popularity of the social network Twitter and its use to propagate information, it is of vital importance to detect rumors prior to their dissemination on Twitter. In the present paper, a model to detect rumor conversations is proposed using graph convolutional networks. A reply tree and user graph were extracted for each convers...

Image captioning is a task to make an image description, which needs recognizing the important attributes and also their relationships in the image. This task requires to generate semantically and syntactically correct sentences. Most image captioning models are based on RNN and MLE methods, but we propose a novel model based on GAN networks where...

Digital watermarking is a method for data hiding that ensures the security of multimedia data. The watermark can be a digital image or data stored within digital content. The Shearlet transform, a multi-resolution and multi-directional conversion, can be used for watermarking in digital images. Due to its superior features, this conversion can incr...

Domain adaptation is one of the machine learning approaches, which is very powerful and applicable especially when there is no labeled data on the target domain or there are unequal distributions and different feature spaces between the source and target domains. This paper proposes an unsupervised domain adaptation model, which addresses this prob...

Learning methods are challenged when there is not enough labeled data. It gets worse when the existing learning data have different distributions in different domains. To deal with such situations, deep unsupervised domain adaptation techniques have newly been widely used. This paper surveys such domain adaptation methods that have been used for cl...

Most existing methods of multiobjective estimation of distributed algorithms apply the estimation of distribution of the Pareto‐solution on the decision space during the search and little work has proposed on making a regression‐model for representing the final solution set. Some inverse‐model‐based approaches were reported, such as inversed‐model...

Recommender systems try to discover some latent features of users and items by looking at the available information such as users' history of ratings to items and then use these latent factors to estimate users' interest level in a particular item. Traditional methods such as standard matrix factorisation rely on the ratings that users have submitt...

Recommender systems try to discover some latent features of users and items by looking at the available information such as users' history of ratings to items and then use these latent factors to estimate users' interest level in a particular item. Traditional methods such as standard matrix factorisation rely on the ratings that users have submitt...

Cultural Algorithm is an evolutionary model inspired by the cultural evolution process which employs a basic set of knowledge sources, each related to knowledge observed in various social species. This study presents a modified version of cultural algorithm which benefits from adaptive fuzzy system. The adaptive fuzzy system is implemented as an ex...

This study presents the normative knowledge source for the belief space of cultural algorithm(CA) based on an adaptive Radial Basis Function Neural Network (RBFNN). The use of the RBFNN makes it possible to use the previous upper and lower bounds of the normative knowledge to update them and to extract a logical relationship between the previous pa...

The non-dominate sorting genetic algorithmic-II (NSGA-II) is a relatively recent technique for finding or approximating the Pareto-optimal set for multi-objective optimization problems. In different studies NSGA-II has shown good performance in comparison to other multi-objective evolutionary algorithms (Deb et al., 2002). In this paper an improved...

Use of Multi-Objective Particle Swarm Optimization for designing of planar multilayered electromagnetic absorbers and finding optimal Pareto front is described. The achieved Pareto presents optimal possible trade-offs between thickness and reflection coefficient of absorbers. Particle swarm optimization method in comparison with most of optimizatio...

This paper introduces a new approach for training the adaptive network based fuzzy inference system (ANFIS). The previous works emphasized on gradient base method or least square (LS) based method. In this study we apply one of the swarm intelligent branches, named particle swarm optimization (PSO) with some modification in it to the training of al...

This paper introduces a new hybrid approach for training the adaptive network based fuzzy inference system (ANFIS).This approach based on multi objective optimization mechanism for training parameters in antecedent part. It considers two cost functions as the objectives which are the maximum difference measurements between the real nonlinear system...