A cryptocurrency is a digitized, encrypted, and decentralized virtual currency, which is impossible to counterfeit or double-spend. It is one of the very popular investment instruments and traded in blockchain based crypto exchanges on ever growing volume. It is quite volatile due to imbalance of supply and demand, government regulations, investor sentiment and above all media hype. Cryptocurrency price forecasting is an active area of research and several approaches have been proposed recently. This study proposed a price forecasting model based on three vital characteristics (i) a feature selection and weighting approach based on Mean Decrease Impurity(MDI) features. (ii) Bi-directional LSTM and (iii) with a trend preserving model bias correction (CUSUM control charts for monitoring the model performance over time) to forecast Bitcoin and Ethereum values for long and short term spans. The data for both currencies were analyzed in three different intervals: (i) April 01, 2013 to April 01, 2016 (ii) April 01, 2013 to April 01, 2017 and (iii) April 01, 2013 to December 31, 2019. Extensive series of experiments were performed and evaluated on Root Mean Square Errors (RMSE). Comparing with the prevalent forecasting models we report a new state of the art in cryptocurrency forecasting.
Disasters such as earthquakes, droughts, floods, and volcanoes adversely affect human lives and valuable resources. Therefore, various response systems have been designed, which assist in mitigating the impact of disasters and facilitating relief activities in the aftermath of a disaster. These response systems require timely and accurate information about affected areas. In recent years, social media has provided access to high-volume real-time data, which can be used for advanced solutions to numerous problems, including disasters. Social-media data combines two modalities (text and associated images), and this information can be used to detect disasters, such as floods. This paper proposes an ensemble learning-based Deep Social Media Data Classification (DeepSDC) approach for social-media flood-event classification. The proposed algorithm uses datasets from Twitter to detect the flooding event. The Deep Social Media Data Classification (DeepSDC) uses a two-staged ensemble-learning approach which combines separate models for textual and visual data. These models obtain diverse information from the text and images and combine the information using an ensemble-learning approach. Additionally, DeepSDC utilizes different augmentation, upsampling and downsampling techniques to tackle the class-imbalance challenge. The performance of the proposed algorithm is assessed on three publically available flood-detection datasets. The experimental results show that the proposed DeepSDC is able to produce superior performance when compared with several state-of-the-art algorithms. For the three datasets, FRMT, FCSM and DIRSM, the proposed approach produced F1 scores of 46.52, 92.87, and 92.65, respectively. The mean average precision (MAP@480) of 91.29 and 98.94 were obtained on textual and a combination of textual and visual data, respectively.
Enterprise networks face a large number of threats that are managed and mitigated with a combination of proprietary and third-party security tools and services. However, the techniques and principles employed by the said tools, processes, and services are quite conventional. They lack the rapid evolution, as required to protect against modern, state-of-the-art threats faced, specifically, against distributed denial of service (DDoS) attacks. The lack of efficiency of a network is directly proportional to the number of applications and services it hosts, mainly to protect against external and internal threats. Moreover, the effectiveness of such security mechanisms relies on their independent and proactive approach, which is useful for known malware and their attack vectors, but become obsolete when there is a new malware or zero-day vulnerability is exploits. This paper presents an intelligent, highly responsive, and scalable security framework for enterprise networks. The proposed framework incorporates Apache Spark Framework for security analytics. It accurately identifies anomalies related to DDoS attacks from real-time network traffic by using customized machine learning algorithms, meticulously trained against selected feature-set. Encouraging results are obtained when tested against different scenarios and bench-marked with the results achieved by related studies in similar scenarios.
The aim of personalized news recommendation is to suggest news stories to the users that are most interesting for them. To improve the user experience, it is important that these news items are not only relevant to the user but also get recommended to them as soon as they are available. The inability of traditional collaborative filtering approach to recommend such cold start items has led to techniques that incorporate latent features of items in order to make cold start recommendations such as content based filtering and deep neural network-based approaches. However, these existing techniques do not make use of any collaborative information between users and items as well as latent features at the same time and thus fail to provide any serendipity which is an important aspect of any recommender system. Moreover, these underlying collaborative signals between users and items are crucial to improving the overall quality of recommender systems and can also be utilized to make cold start recommendations. In this paper, we propose the Generative Collaborative Zero-Shot Recommender System framework (GCZRec) which makes use of both the latent user and item features as well as the underlying collaborative information to generate both warm start and cold start recommendations. We evaluate our framework for news recommendation task given cold start and warm start cases for both users and news items. We also discuss that our model can be plugged in and used as preprocessing to improve the performance of an existing recommender system.
Multi-label classification aims to associate multiple labels to a given data/object instance to better describe them. Multi-label data sets are common in a lot of emerging application areas like: Text/Multimedia classification, Bio-Informatics, Medical image annotations and Computer Vision to name a few. There is a growing interest in efficient and accurate multi-label classification. There are two major approaches to perform multi-label classification (i) problem transformation methods and (ii) algorithm adaptation methods. In algorithm adaptation, the traditional classification algorithms are modified to handle multi-label data sets. One classification algorithm which is often modified to do multi-label classification is k- nearest neighbor (kNN). k-nearest neighbor is popular due to its simplicity, easy to implement and seamlessly adaptability. Despite its merits it has several drawbacks like: sensitivity of noisy data, missing values and outliers; feature scaling and often becoming inaccurate for large overlapping solution space. In this paper, a modification to kNN method is suggested for multi-label classification with three improvement strategies (i) selection of local example w.r.t. unknown example – the motivation for this comes from the fact that local and relevant space is vital for the improvement in multi-label classification; (ii) Splitting the input space into multiple sub-spaces for optimal label estimation – the motivation is to estimate label accurately in the presence of noisy labels; And (iii) selection of labels using Mean Average Precision (MAP) estimates – here our motivation is to utilize the training data effectively to maximize the hidden distribution and optimal parameters for the method. The proposed method is implemented and compared with state-of-the-art approaches based on kNN or similar approaches that effectively select and optimize relevant spaces for multi-label classification. Evaluation based on multiple metrics like Hamming loss, Precision/Recall and F-measure are used for evaluation. The suggested approach performed much better than the state-of-the-art on the datasets with strong label cardinalities.
A flood is an overflow of water that swamps dry land. The gravest effects of flooding are the loss of human life and economic losses. An early warning of these events can be very effective in minimizing the losses. Social media websites such as Twitter and Facebook are quite effective in the efficient dissemination of information pertinent to any emergency. Users on these social networking sites share both textual and rich content images and videos. The Multimedia Evaluation Benchmark (MediaEval) offers challenges in the form of shared tasks to develop and evaluate new algorithms, approaches and technologies for explorations and exploitations of multimedia in decision making for real time problems. Since 2015, the MediaEval has been running a shared task of predicting several aspects of flooding and through these shared tasks, many improvements have been observed. In this paper, the classification framework VRBagged-Net is proposed and implemented for flood classification. The framework utilizes the deep learning models Visual Geometry Group (VGG) and Residual Network (ResNet), along with the technique of Bootstrap aggregating (Bagging). Various disaster-based datasets were selected for the validation of the VRBagged-Net framework. All the datasets belong to the MediaEval Benchmark Workshop, this includes Disaster Image Retrieval from Social Media (DIRSM), Flood Classification for Social Multimedia (FCSM) and Image based News Topic Disambiguation (INTD). VRBagged-Net performed encouraging well in all these datasets with slightly different but relevant tasks. It produces Mean Average Precision at different levels of 98.12, and Average Precision at 480 of 93.64 on DIRSM. On the FCSM dataset, it produces an F1 score of 90.58. Moreover, the framework has been applied on the dataset of Image-Based News Topic Disambiguation (INTD), and exceeds the previous best result by producing an F1 evaluation of 93.76. The VRBagged-Net with a slight modification also ranked first in the flood-related Multimedia Task at the MediaEval Workshop 2020.