social media became a fertile soil for various threats, extremism, and radicalization. This challenged policy-makers, researchers and practitioners. Preventing such extreme activities from happening becomes an ultimate priority at local and global scale. This paper introduces a new intertwine between radicalization and natural language processing capable of estimating the risk score of individuals based on their social media activities. The system uses a hybridized ERG22+ and VERA-ER model, which classifies individuals as high or low risk radicalization profile. The developed system was tested and validated on the Video Comments Threat Corpus dataset and Twitter pro-ISIS fanboys datasets where it achieves 95.1% and 64.9% accuracy, respectively.

COVID-19 is a rapidly spreading viral disease and has affected over 100 countries worldwide. The numbers of casualties and cases of infection have escalated particularly in countries with weakened healthcare systems. Recently, reverse transcription-polymerase chain reaction (RT-PCR) is the test of choice for diagnosing COVID-19. However, current evidence suggests that COVID-19 infected patients are mostly stimulated from a lung infection after coming in contact with this virus. Therefore, chest X-ray (i.e., radiography) and chest CT can be a surrogate in some countries where PCR is not readily available. This has forced the scientific community to detect COVID-19 infection from X-ray images and recently proposed machine learning methods offer great promise for fast and accurate detection. Deep learning with convolutional neural networks (CNNs) has been successfully applied to radiological imaging for improving the accuracy of diagnosis. However, the performance remains limited due to the lack of representative X-ray images available in public benchmark datasets. To alleviate this issue, we propose a self-augmentation mechanism for data augmentation in the feature space rather than in the data space using reconstruction independent component analysis (RICA). Specifically, a unified architecture is proposed which contains a deep convolutional neural network (CNN), a feature augmentation mechanism, and a bidirectional LSTM (BiLSTM). The CNN provides the high-level features extracted at the pooling layer where the augmentation mechanism chooses the most relevant features and generates low-dimensional augmented features. Finally, BiLSTM is used to classify the processed sequential information. We conducted experiments on three publicly available databases to show that the proposed approach achieves the state-of-the-art results with accuracy of 97%, 84% and 98%. Explainability analysis has been carried out using feature visualization through PCA projection and t-SNE plots.

The bag-of-words (BoW) model is one of the most popular representation methods for image classification. However, the lack of spatial information, the intra-class diversity, and the inter-class similarity among scene categories impair its performance in the remote-sensing domain. To alleviate these issues, this paper proposes to explore the spatial dependencies between different image regions and introduces patch-based discriminative learning (PBDL) for remote-sensing scene classification. Particularly, the proposed method employs multi-level feature learning based on small, medium, and large neighborhood regions to enhance the discriminative power of image representation. To achieve this, image patches are selected through a fixed-size sliding window and sampling redundancy, a novel concept, is developed to minimize the redundant features while sustaining the relevant features for the model. Apart from multi-level learning, we explicitly impose image pyramids to magnify the visual information of the scene images and optimize their position and scale parameters locally. Motivated by this, a local descriptor is exploited to extract multi-level and multi-scale features that we represent in terms of codewords histogram by performing k-means clustering. Finally, a simple fusion strategy is proposed to balance the contribution of individual features, and the fused features are incorporated into a Bidirectional Long Short-Term Memory (BiLSTM) network for classification. Experimental results on NWPU-RESISC45, AID, UC-Merced, and WHU-RS datasets demonstrate that the proposed approach not only surpasses the conventional bag-of-words approaches but also yields significantly higher classification performance than the existing state-of-the-art deep learning methods used nowadays.

The paper built on First Impression Challenge from Chalearn V2 Workshop on Explainable Computer Vision Multimedia and Job Candidate Screening Competition CVPR17 by focusing solely on Textual Input in contrast to other Challenge’s participants who considered video or audio modalities. Therefore, the paper aims to develop a new deep learning architecture capable of predicting human personality traits and job interview from the video transcripts. Several feature representations that involve statistical and deep learning have contrasted. Our approach achieved the best score when text modality alone were employed, yielding an average of 89% score in human personality traits and 89.10% value for job interview. The research results will help companies and other organization studying human personality to assess a human personality using a minimum textual resources from the job candidates

In the last decade, recognizing and reducing uncertainties in hydrological forecasting has shown renewal interest. However, from a modeler’s perspective, a unified code of practice is always needed to handle the various facets of uncertainty in hydrological forecasting. Pappenberger and Beven, (2006) suggested nine codes of practice for handling uncertainties in hydrological modelling. In this paper, we have revisited those principles and added new insights to yield seven key principles for accounting and reducing uncertainties in catchment related hydrological forecasting tasks: (1) objectives define the need for uncertainty, (2) exploring the Catchment Puzzle, (3) selection of models is key, (4) choices of the method for quantifying uncertainties and calibration (5) finding the sources of uncertainties (6) advancements are a critical choice (7) prioritizing End User Needs for Reliable Forecasting Services. We derive these principles as a summary of understanding how modelers across the world have approached uncertainty handling from the analysis of recent literature on reducing uncertainties in hydrological forecasting. The triangulated interdependence and uncertainty contributions between the hydrological processes, epistemic uncertainties, and model development inevitably impact the forecast. Yet, the mapping of these principles provided in this study can assist the modelers in developing an improved framework for hydrological forecasting. Further, this work calls for discussions among the hydrological science community to establish these principles.

In this letter a smart parking application based on Internet of things paradigm have been demonstrated. The application that uses PlacePod sensors, LoRaWan network and an Android mobile app is implemented at University car parking to deliver real-time services to drivers. The feasibility and soundness of the theoretical concept underpinning the developed parking app is demonstrated through a set of testing experiment. The approach further contributes to mining user's behavior when dealing with car parking, providing insights to urban planners and policy-makers to adapt their strategies accordingly by taking into account user's feedback and actions.

Smart drainage management to limit summer drought damage in Nordic agriculture under the circular economy conceptSyed Md Touhidul Mustafa 1, *, Kedar Ghag1, Anandharuban Panchanathan2, Bishal Dahal 1, Amirhossein Ahrari1, Toni Liedes 3, Hannu Marttila1, Tamara Avellán1, Mourad Oussalah2, Björn Klöve 1, & Ali Torabi Haghighi11Water, Energy and Environmental Engineering Research Unit, University of Oulu, P.O. Box 4300, FIN90014, Oulu, Finland2Center for Machine Vision and Signal Analysis, University of Oulu, Finland3Intelligent Machines and Systems, University of Oulu, PO Box 4200, 90014 Oulu, Finland