Search

Marine ecosystems and their fish habitats are becoming increasingly important due to their integral role in providing a valuable food source and conservation outcomes. Due to their remote and difficult to access nature, marine environments and fish habitats are often monitored using underwater cameras to record videos and images for understanding fish life and ecology, as well as for preserve the environment. There are currently many permanent underwater camera systems deployed at different places around the globe. In addition, there exists numerous studies that use temporary cameras to survey fish habitats. These cameras generate a massive volume of digital data, which cannot be efficiently analysed by current manual processing methods, which involve a human observer. Deep Learning (DL) is a cutting-edge Artificial Intelligence (AI) technology that has demonstrated unprecedented performance in analysing visual data. Despite its application to a myriad of domains, its use in underwater fish habitat monitoring remains under explored. In this paper, we provide a tutorial that covers the key concepts of DL, which help the reader grasp a high-level understanding of how DL works. The tutorial also explains a step-by-step procedure on how DL algorithms should be developed for challenging applications such as underwater fish monitoring. In addition, we provide a comprehensive survey of key deep learning techniques for fish habitat monitoring including classification, counting, localisation, and segmentation. Furthermore, we survey publicly available underwater fish datasets, and compare various DL techniques in the underwater fish monitoring domains. We also discuss some challenges and opportunities in the emerging field of deep learning for fish habitat processing. This paper is written to serve as a tutorial for marine scientists who would like to grasp a high-level understanding of DL, develop it for their applications by following our step-by-step tutorial, and see how it is evolving to facilitate their research efforts. At the same time, it is suitable for computer scientists who would like to survey state-of-the-art DL-based methodologies for fish habitat monitoring. • Marine environments and fish habitats are widely surveyed using underwater cameras. • Deep learning (DL) offers an effective solution for processing underwater videos. • We write a tutorial on the key concepts and steps of DL for underwater monitoring. • We provide a survey of key DL-based visual fish monitoring methods/datasets. • We shed light on challenges/opportunities of DL for underwater fish monitoring. [ABSTRACT FROM AUTHOR]

• The proposed method had fused multi-level information compensation and U-Net. • The module designed for multi-level information compensation and compression. • The method had fused compressed features and correlation features. Recently, Deep Convolutional Neural Networks have demonstrated high-quality reconstruction in image super-resolution procedure. In this paper, we propose improved image super-resolution reconstruction via multi-level information compensation and U-Net network to address the problem that the image super-resolution reconstruction algorithm based on deep neural networks tends to lose feature information in the feature extraction process, resulting in the lack of texture and edge details in the reconstructed image. Firstly, we design the U-net like network for image super-resolution reconstruction, which performs multi-level feature extraction and channel compression for the input features through the down-channel branch. It fuses the compressed features and extracts the correlation features of different channels through the bottom module, and performs multi-level feature extraction and channel recovery for the compressed correlation features through the up-channel branch. The multi-level information compensation model is then designed to compensate for the information lost in the channel compression process and the information that is difficult to recover in the channel recovery process of U-net like network. The experimental results can show that the proposed algorithm achieves a significant improvement in Peak Signal-to-Noise Ratio and Structure Similarity Index and visual effect compared with the state-of-arts algorithms. The average experimental results of PSNR from proposed method had improved by 1.63 dB, 1.53 dB, 0.97 dB and 0.94 dB compared to SRCNN, HAT, DAT and CARN, respectively. [ABSTRACT FROM AUTHOR]

Hardware Trojans (HT) are the most malicious components attacking modern integrated circuits (ICs). Information leakage, incorrect functionality, and overheating are the major effects of HT insertion. Due to the outsourcing of multi-stage digital circuit design and fabrication, HTs can be inserted by rogues at every stage. The types of HTs and insertion methods evolve continuously and their detection becomes more complex. Consequently, designing integrated circuits robust to HT insertion seems efficient. A prerequisite for such a strategy is the evaluation of integrated circuit vulnerability to HT insertion. There are several factors involved in the vulnerability of fabricated integrated circuits such as the distribution of white spaces in the IC layout, the ratio of unutilized routing resources, the amount of activity of the circuit's nodes, the geometrical properties of the circuit's gates, the delay of various paths, and etc. The interrelation of these diverse factors makes IC vulnerability modeling a challenging problem. In this paper, a deep neural network (DNN) based approach is developed to combine all the effective factors in IC vulnerability analysis. Firstly, we generate a comprehensive dataset containing various types and sizes of hardware Trojans inserted into benchmark circuits. The benchmark circuits used in this study are ISCAS 85, ISCAS 89, and ITC 99. Then using the transfer learning concept seven state-of-the-art deep convolutional neural networks are trained and verified using the constructed dataset to classify every integrated circuit into three vulnerability levels (low, moderate, and highly vulnerable classes). Simulation results show that our proposed method achieves almost 95 % accuracy in the most successful case (VGG16). The lowest accuracy belongs to Inception V3 (∼87.65 %) which is much better than the most successful previous studies (72 %). This is mainly because the DNN-based method handles shortcomings (such as incomplete modeling of vulnerability-related factors) in the previous state-of-the-art methods efficiently. [ABSTRACT FROM AUTHOR]

Phishing websites distribute unsolicited content and are frequently used to commit email and internet fraud. Detecting them before any user information is submitted is critical. Several efforts have been made to detect these phishing websites in recent years. Most existing approaches use hand-crafted lexical and statistical features from a website's textual content to train classification models to detect phishing web pages. However, these phishing detection approaches have limitations, including (1) the tediousness of extracting hand-crafted features, which require specialized domain knowledge to determine which features are useful for a particular platform; and (2) the difficulties encountered by models built on hand-crafted features to capture the semantic patterns in words and characters in URL and HTML content. To address these challenges, this paper proposes WebPhish, an end-to-end deep neural network trained using embedded raw URLs and HTML content to detect website phishing attacks. First, the proposed model automatically employs an embedding technique to extract the corresponding characters into homologous dense vectors. Then, the concatenation layer merges the URL and HTML embedding matrices. Following that, Convolutional layers are used to model its semantic dependencies. Extensive experiments were conducted with real-world phishing data, which yielded an accuracy of 98.1%, showing that WebPhish outperforms baseline detection approaches in identifying phishing pages. • WebPhish employs both raw URL and HTML content to detect phishing web pages. • WebPhish uses character-level embeddings to enable the feature vectors to generalize to new data. • Extensive experiments conducted on a real-world dataset yields 98.1% accuracy. • Its application on the airline Twitter dataset shows the proposed model's flexibility. [ABSTRACT FROM AUTHOR]

Domain adaptation provides the possibility of utilizing the knowledge gained from an auxiliary domain to accomplish the task in another related domain. In this paper, a common feature representation of these domains is learned through a new proposed idea to reduce inter-domain differences more precisely which results in higher accuracy for unsupervised domain adaptation. To decrease these divergences, the proposed method finds a subspace that reduces data distribution discrepancy between domains. To achieve this goal, minimization of the divergence of the class conditional probability distributions is considered. By considering class conditional distributions, more discriminative information of data is preserved compared to applying marginal distributions. Also, an explicit parametric distribution of the source and target domains is considered to reduce the discrepancy between the two domains data which results in higher accuracy compared to the other relevant domain adaptation methods. Experimental studies on benchmark image classification tasks confirmed our assumptions and indicated the significant improvement given by the proposed method compared to the other state-of-the-art methods. • Aligning the feature distribution of the source and target domains explicitly. • Introducing a new loss function to impose the common distribution on the features. • Reducing the class conditional probability distribution distance between the domains. [ABSTRACT FROM AUTHOR]

Early fault detection, both in equipment and the products in process, is of paramount importance in industrial processes to ensure the quality of the final product, avoid abnormal operating conditions, expensive repairs, and even production process shutdown. The growing complexity of industrial systems and the increase in the amount of available data have encouraged the development of intelligent systems for automatic fault prediction/detection, mainly based on Industry 4.0 technologies and, particularly, those based on deep learning methodologies. However, the vast majority of proposals and research carried out to date define specific solutions for specific cases, which still requires a high level of expert knowledge for scaling the solutions to industrial environments. Actually, one of the major issues towards the industrialization of deep learning solutions is the determination of the optimal, or near-optimal, hyper-parameters. In this paper, we propose a low-level set-up effort intelligent failure detection system that integrates deep neural networks with a Bayesian Optimization algorithm for self-tuning of the system hyper-parameters. In addition, to facilitate the industrialization of the proposal and its incorporation into current industrial systems, we embedded the proposal in our previously formulated and tested Simulai architecture which allows for containing and interaction with multiple and heterogeneous technological components of manufacturing processes. Finally, our proposal is tested in two real cases of a different nature. The obtained results show a successful performance and demonstrate the easy online integration and interaction in a real production system. • Industrialization of artificial intelligence through a self-adjusting system. • Improvement of the decision-making process in the detection of industrial failures. • Optimization of deep learning for the improvement of industrial health and quality. • Demonstration of the proposal's adaptability to real cases of different natures. [ABSTRACT FROM AUTHOR]

The consequences of fake news and rumors have adversely affected social and political stability worldwide. Many such incidents have been reported, which resulted in mass chaos with the loss of lives and property. In response, many researchers have developed models for the veracity detection of rumors on social media. The recent advances in veracity detection models incorporate the use of Deep Neural Networks (DNN) over statistical and traditional machine learning based models. Current veracity detection approaches leverage powerful DNN models such as Transformer, Adversarial Networks, Graph Convolutional Networks (GCN), Variational Autoencoder (VAE) etc., along with exploiting the intuition of Multi-task learning (MTL) approach. In addition, most of these aforesaid well-known models rely on auxiliary (additional) information to a good extent. Presently, these recent models' dependence on (1) auxiliary information and multiple tasks restrain productivity and incur cost on resources. Moreover, (2) the structural constraints of these models put a limiting effect on model deliverance. These two shortcomings of the recent models result in poor resource utilization and unstructured feature organization of the objective task, resulting in a compromised output of the model. In this paper, we present an efficient Se gregated N on- o verlapping and C ollectively e xhaustive DNN model (SeNoCe) which mitigates the effects of poor utilization of resources and enhances the model performance without the aid of auxiliary information or tasks which incur good manual efforts and costs. SeNoCe is capable of utilizing the fine-granularity of implicit features as attention for task identification. SeNoCe reports a major performance improvement over the state-of-the-art techniques on standard benchmark metrics across two real-world rumor datasets. It records a minimum of 24. 06 − 12. 8 % , 53. 1 − 49. 2 % improvement in terms of Macro F and Accuracy, respectively over the best performing state-of-the-art. • An orthogonality constraint-based feature partitioning approach to classify veracity. • The proposed approach does not rely on any unreliable auxiliary information. • SeNoCe shows promising improvements over the baselines on two real world datasets. [ABSTRACT FROM AUTHOR]

Coronavirus has radically changed the world and our lives in many and various ways. During this crisis, the tourism sector was severely damaged globally, as, within some weeks, popular touristic places worldwide changed from over-tourism to non-tourism destinations. In order to address new challenges in this sector, a novel cloud-based framework is proposed that exploits image labelling through Deep Learning and Neural Network-based Collaborative Filtering models in order to generate personalised recommendations in the context of smart tourism. At the same time, this paper also aims at offering valuable insights regarding Artificial Neural Networks and Matrix Factorisation Neural Networks. Moreover, in this research, the authors demonstrate the architecture/topology of ANN models used to generate predictions regarding tourists' preferences, along with experimental results produced during model evaluation and the configuration that resulted in the highest accuracy in predictions. • A smart tourism framework using deep learning for personalised recommendations. • Combine image labelling and collaborative filtering to realise smart tourism. • Detailed presentation of the utilised Neural Network approaches. • Exploit Matrix Factorisation Neural Network for more accurate models. • Experimental results from different approaches/configurations. [ABSTRACT FROM AUTHOR]

• Automated detection of pain from facial expressions is a challenge in medical care. • A new deep neural network algorithm designed to detection pain intensity effectively. • A new feature extraction algorithm developed to speed up the algorithm. • The new enhanced deep learning algorithm can detect pain in multi level effectively. Automated detection of pain intensity from facial expressions, especially from face images that show a patient's health, remains a significant challenge in the medical diagnostics and health informatics area. Expert systems that prudently analyse facial expression images, utilising an automated machine learning algorithm, can be a promising approach for pain intensity analysis in health domain. Deep neural networks and emerging machine learning techniques have made significant progress in both the feature identification, mapping and the modelling of pain intensity from facial images, with great potential to aid health practitioners in the diagnosis of certain medical conditions. Consequently, there has been significant research within the pain recognition and management area that aim to adopt facial expression datasets into deep learning algorithms to detect the pain intensity in binary classes, and also to identify pain and non-pain faces. However, the volume of research in identifying pain intensity levels in multi-classes remains rather limited. This paper reports on a new enhanced deep neural network framework designed for the effective detection of pain intensity, in four-level thresholds using a facial expression image. To explore the robustness of the proposed algorithms, the UNBC-McMaster Shoulder Pain Archive Database, comprised of human facial images, was first balanced, then used for the training and testing of the classification model, coupled with the fine-tuned VGG-Face pre-trainer as a feature extraction tool. To reduce the dimensionality of the classification model input data and extract most relevant features, Principal Component Analysis was applied, improving its computational efficiency. The pre-screened features, used as model inputs, are then transferred to produce a new enhanced joint hybrid CNN-BiLSTM (EJH-CNN-BiLSTM) deep learning algorithm comprised of convolutional neural networks, that were then linked to the joint bidirectional LSTM, for multi-classification of pain. The resulting EJH-CNN-BiLSTM classification model, tested to estimate four different levels of pain, revealed a good degree of accuracy in terms of different performance evaluation techniques. The results indicated that the enhanced EJH-CNN-BiLSTM classification algorithm was explored as a potential tool for the detection of pain intensity in multi-classes from facial expression images, and therefore, can be adopted as an artificial intelligence tool in the medical diagnostics for automatic pain detection and subsequent pain management of patients. [ABSTRACT FROM AUTHOR]