Search

Discrimination of circular RNA from long non-coding RNA is important to understand its role in different biological processes, disease prediction and cure. Identifying circular RNA through manual laboratories work is expensive, time-consuming and prone to errors. Development of computational methodologies for identification of circular RNA is an active area of research. State-of-the-art circular RNA identification methodologies make use of handcrafted features, which not only increase the feature space, but also extract irrelevant and redundant features. The paper in hand proposes an end-to-end deep learning-based framework named as CircNet, which does not require any handcrafted features. It takes raw RNA sequence as an input and utilises encoder–decoder based convolutional operations to learn lower-dimensional latent representation. This latent representation is further passed to another convolutional architecture to extract discriminative features followed by a classification layer. We performed extensive experimentation to highlight different regions of genome sequence that preserve the most important information for identifying circular RNAs. CircNet significantly outperforms state-of-the-art approaches with a considerable margin 10.29% in terms F1 measure.

Traditional neural networks trained using point-based maximum likelihood estimation are deterministic models and have exhibited near-human performance in many image classification tasks. However, their insistence on representing network parameters with point-estimates renders them incapable of capturing all possible combinations of the weights; consequently, resulting in a biased predictor towards their initialisation. Most importantly, these deterministic networks are inherently unable to provide any uncertainty estimate for their prediction which is highly sought after in many critical application areas. On the other hand, Bayesian neural networks place a probability distribution on network weights and give a built-in regularisation effect making these models able to learn well from small datasets without overfitting. These networks provide a way of generating posterior distribution which can be used for model's uncertainty estimation. However, Bayesian estimation is computationally very expensive since it greatly widens the parameter space. This paper proposes a hybrid convolutional neural network which combines high accuracy of deterministic models with posterior distribution approximation of Bayesian neural networks. This hybrid architecture is validated on 13 publicly available benchmark classification datasets from a wide range of domains and different modalities like natural scene images, medical images, and time-series. Our results show that the proposed hybrid approach performs better than both deterministic and Bayesian methods in terms of classification accuracy and also provides an estimate of uncertainty for every prediction. We further employ this uncertainty to filter out unconfident predictions and achieve significant additional gain in accuracy for the remaining predictions.

In-air signature verification is vital for biometric user identification in contact-less mode. The state-of-the-art methods use heuristics for signature acquisition, and provide insufficient data to train neural networks for the verification. In this article, we present a novel method for end-to-end deep learning based in-air signature verification using a depth sensor. In this regard, we propose a new medium-scale in-air signature dataset which is created using an accurate convolutional neural network (CNN) based 3D hand pose estimation algorithm. The proposed dataset offers a total of 1800 signatures collected from 40 subjects. So far, dynamic time warping (DTW) has been the most effective and commonly used method for verification. Keeping in view the significant advancement in deep learning, we present a more accurate deep learning based alternative which outperforms DTW by 67.6%. To this end, we train a personalized autoencoder to reconstruct the signature of each subject. Thereafter, the signature is verified by thresholding the reconstruction loss. We perform extensive experiments by formulating spatial and depth features of the signature in images and point clouds based representations. Moreover, for comparisons, we implement several deep learning algorithms (i.e. linear autoencoder, convolutional autoencoder, and Deep One-Class classifier). Our verification approach achieves an EER of 0.055%. The dataset is available at https://bit.ly/2mEJzOw .

With the advancement of powerful image processing and machine learning techniques, CAD has become ever more prevalent in all fields of medicine including ophthalmology. Since optic disc is the most important part of retinal fundus image for glaucoma detection, this paper proposes a two-stage framework that first detects and localizes optic disc and then classifies it into healthy or glaucomatous. The first stage is based on RCNN and is responsible for localizing and extracting optic disc from a retinal fundus image while the second stage uses Deep CNN to classify the extracted disc into healthy or glaucomatous. In addition to the proposed solution, we also developed a rule-based semi-automatic ground truth generation method that provides necessary annotations for training RCNN based model for automated disc localization. The proposed method is evaluated on seven publicly available datasets for disc localization and on ORIGA dataset, which is the largest publicly available dataset for glaucoma classification. The results of automatic localization mark new state-of-the-art on six datasets with accuracy reaching 100% on four of them. For glaucoma classification we achieved AUC equal to 0.874 which is 2.7% relative improvement over the state-of-the-art results previously obtained for classification on ORIGA. Once trained on carefully annotated data, Deep Learning based methods for optic disc detection and localization are not only robust, accurate and fully automated but also eliminates the need for dataset-dependent heuristic algorithms. Our empirical evaluation of glaucoma classification on ORIGA reveals that reporting only AUC, for datasets with class imbalance and without pre-defined train and test splits, does not portray true picture of the classifier's performance and calls for additional performance metrics to substantiate the results., 16 Pages, 10 Figures

Traditional distance and density-based anomaly detection techniques are unable to detect periodic and seasonality related point anomalies which occur commonly in streaming data, leaving a big gap in time series anomaly detection in the current era of the IoT. To address this problem, we present a novel deep learning-based anomaly detection approach (DeepAnT) for time series data, which is equally applicable to the non-streaming cases. DeepAnT is capable of detecting a wide range of anomalies, i.e., point anomalies, contextual anomalies, and discords in time series data. In contrast to the anomaly detection methods where anomalies are learned, DeepAnT uses unlabeled data to capture and learn the data distribution that is used to forecast the normal behavior of a time series. DeepAnT consists of two modules: time series predictor and anomaly detector. The time series predictor module uses deep convolutional neural network (CNN) to predict the next time stamp on the defined horizon. This module takes a window of time series (used as a context) and attempts to predict the next time stamp. The predicted value is then passed to the anomaly detector module, which is responsible for tagging the corresponding time stamp as normal or abnormal. DeepAnT can be trained even without removing the anomalies from the given data set. Generally, in deep learning-based approaches, a lot of data are required to train a model. Whereas in DeepAnT, a model can be trained on relatively small data set while achieving good generalization capabilities due to the effective parameter sharing of the CNN. As the anomaly detection in DeepAnT is unsupervised, it does not rely on anomaly labels at the time of model generation. Therefore, this approach can be directly applied to real-life scenarios where it is practically impossible to label a big stream of data coming from heterogeneous sensors comprising of both normal as well as anomalous points. We have performed a detailed evaluation of 15 algorithms on 10 anomaly detection benchmarks, which contain a total of 433 real and synthetic time series. Experiments show that DeepAnT outperforms the state-of-the-art anomaly detection methods in most of the cases, while performing on par with others.

Time series forecasting is one of the challenging problems for humankind. The traditional forecasting methods using mean regression models have severe shortcomings in reflecting real-world fluctuations. While new probabilistic methods rush to rescue, they fight with technical difficulties like quantile crossing or selecting a prior distribution. To meld the different strengths of these fields while avoiding their weaknesses, as well as, to push the boundary of the state-of-the-art, we introduce ForGAN - one step ahead probabilistic forecasting with generative adversarial networks. ForGAN utilizes the power of the conditional generative adversarial network to learn the data generating distribution and compute probabilistic forecasts from it. We argue how to evaluate ForGAN in opposition to regression methods. To investigate probabilistic forecasting of ForGAN, we create a new dataset and demonstrate our method abilities on it. This dataset will be made publicly available for comparison. Furthermore, we test ForGAN on two publicly available datasets, namely Mackey-Glass dataset and Internet traffic dataset (A5M), where the impressive performance of ForGAN demonstrate its high capability in forecasting future values.

Deep neural networks are black boxes by construction. Explanation and interpretation methods therefore are pivotal for a trustworthy application. Existing methods are mostly based on heatmapping and focus on locally determining the relevant input parts triggering the network prediction. However, these methods struggle to uncover global causes. While this is a rare case in the image or NLP modality, it is of high relevance in the time series domain.This paper presents a novel framework, i.e. Conceptual Explanation, designed to evaluate the effect of abstract (local or global) input features on the model behavior. The method is model-agnostic and allows utilizing expert knowledge. On three time series datasets Conceptual Explanation demonstrates its ability to pinpoint the causes inherent to the data to trigger the correct model prediction.

Exponential growth of genome-wide assays of gene expressions and their public access open new horizons for machine learning methodologies to effectively perform genetic analysis. In this work, domain specific pre-train k-mer embeddings of DNA sequences are generated by utilising FastText approach. Sequence co-expression pattern information is embedded into 200 dimensional vectors by training Fasttext model on 317,151 samples of DNA sequences (with k-mers representation). We propose a novel idea to utilize the information of various codons present in amino acids for the evaluation of learned sequence vectors. We employ two diverse techniques to compare the performance of generated task-specific k-mer embeddings with state-of-the-art publicly available generic k-mer embeddings of genome. Firstly, we utilize a dimensionality reduction approach namely PCA to alleviate the dimensions of DNA sequences upto 50 features by preserving almost 85% of sequence features information. Afterwards, TSNE algorithms is used to visualize k-mer embeddings and to make sure whether different codons representing the same amino acid are more closer to each other than the ones representing different amino acids. Secondly, to assess the analogy of k-mer embeddings, generated domain specific k-mer embeddings are compared with state-of-the-art k-mer embeddings by estimating the cosine similarity among those codons vectors which represent same amino acid. Overall, we believe that task-specific distributed representation of k-mers would be useful for DNA methylation and Histone occupancy prediction tasks.

The contribution of this paper is two-fold. First, we present ProbCast - a novel probabilistic model for multivariate time-series forecasting. We employ a conditional GAN framework to train our model with adversarial training. Second, we propose a framework that lets us transform a deterministic model into a probabilistic one with improved performance. The motivation of the framework is to either transform existing highly accurate point forecast models to their probabilistic counterparts or to train GANs stably by selecting the architecture of GAN's component carefully and efficiently. We conduct experiments over two publicly available datasets namely electricity consumption dataset and exchange-rate dataset. The results of the experiments demonstrate the remarkable performance of our model as well as the successful application of our proposed framework.

In this paper, we propose a novel, two-staged system, for keyword detection and ontology-driven topic modeling. The first stage specializes in keyword detection in which we introduce a novel graph-based unsupervised approach called Collective Connectivity-Aware Node Weight (CoCoNoW) for detecting keywords from the scientific literature. CoCoNoW builds a connectivity aware graph from a given publication text and eventually assigns weight to the extracted keywords to sort them in order of relevance. The second stage specializes in topic modeling, where a domain ontology serves as an attention-map/context for topic modeling based on the detected keywords. The use of an ontology makes this approach independent of domain and language. CoCoNoW is extensively evaluated on three publicly available datasets Hulth2003, NLM500 and SemEval2010. Analysis of results reveals that CoCoNoW consistently outperforms the state-of-the-art approaches on the respective datasets.

The adversarial vulnerability of deep networks has spurred the interest of researchers worldwide. Unsurprisingly, like images, adversarial examples also translate to time-series data as they are an inherent weakness of the model itself rather than the modality. Several attempts have been made to defend against these adversarial attacks, particularly for the visual modality. In this paper, we perform detailed benchmarking of well-proven adversarial defense methodologies on time-series data. We restrict ourselves to the \(L_{\infty }\) threat model. We also explore the trade-off between smoothness and clean accuracy for regularization-based defenses to better understand the trade-offs that they offer. Our analysis shows that the explored adversarial defenses offer robustness against both strong white-box as well as black-box attacks. This paves the way for future research in the direction of adversarial attacks and defenses, particularly for time-series data.

Deep learning methods have shown great success in several domains as they process a large amount of data efficiently, capable of solving difficult classification, forecast, segmentation, and other tasks. However, these networks suffer from their inexplicability that limits their applicability and trustworthiness. Although there exists work addressing this perspective, most of the existing approaches are limited to the image modality due to the intuitive and prominent concepts. Unfortunately, the patterns in the time-series domain are more complex and non-comprehensive, and an explanation for the network decision is pivotal in critical areas like medical, financial, or industry. Addressing the need for an explainable approach, we propose a novel interpretable network scheme, designed to inherently use an explicable reasoning process inspired by the human cognition without the need of additional post-hoc explainability methods. Therefore, the approach uses class-specific patches as they cover local patterns, relevant to the classification, to reveal similarities with samples of the same class. Besides, we introduce a novel loss concerning interpretability and accuracy that constraints P2ExNet to provide viable explanations of the data that include relevant patches, their position, class similarities, and comparison methods without compromising performance. An analysis of the results on eight publicly available time-series datasets reveals that P2ExNet reaches similar performance when compared to its counterparts while inherently providing understandable and traceable decisions.

Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth analysis of the methods which attempt to identify the influence of these data points on the resulting classifier. To quantify the quality of the influence, we curated a set of experiments where we debugged and pruned the dataset based on the influence information obtained from different methods. To do so, we provided the classifier with mislabeled examples that hampered the overall performance. Since the classifier is a combination of both the data and the model, therefore, it is essential to also analyze these influences for the interpretability of deep learning models. Analysis of the results shows that some interpretability methods can detect mislabels better than using a random approach, however, contrary to the claim of these methods, the sample selection based on the training loss showed a superior performance., Comment: 8 pages, 11 figures, Accepted for the IEEE International Joint Conference on Neural Networks (IJCNN) 2020

Social media has become a substitute for social interaction, thus the amount of medical and clinical-related information on the web is increasing. Monitoring of Personal Health Mentioning (PHM) on social media is an active area of research that predicts whether a given piece of text contains a health condition or not. To this end, the main idea is to consider the usage of disease or symptom words in the text. However, due to their usage in a figurative sense, disease or symptom words may not always indicate the presence of the health condition. Prior work attempts to address this by considering contextual word representations along with the utilization of the sentiment information. However, these methods are unable to capture the complete context in which symptom word is used. In this work, we incorporate permutation-based contextual word representation for the task of health mention detection which captures the context of disease words efficiently, in the given piece of text, and hence improves the performance of the classifier. To evaluate the integrity of the proposed method, we perform experimentation on the public benchmark dataset that shows an improvement of 5.5% in F-score in comparison to the state of the art health mention detection classifier. (Code is available at https://github.com/pervaizniazi/Figurative-Mention).

The potential of microalgae as an alternative energy source has been adequately studied. However, exclusive use of microalgae as an energy feedstocks cannot warrant their scalability and economical sustainability due to the high cost involved in their biomass processing. The co-processing of microalgae biomass with other related bio-refinery applications can offset their cost and improve their sustainability. Thus, it triggers up the need of exploring the potential of microalgae biomass beyond their typical use. Microalgae offer interesting features to qualify them as alternative feedstocks for various bio-refinery applications. Microalgae have unique abilities to utilize them for industrial and environmental applications. Thus, this review discusses to expand the scope of integrating microalgae with other biotechnological applications to enhance their sustainability. The use of microalgae as a feed for animal and aquaculture, fertilizers, medicine, cosmetic, environmental and other biotechnological applications is thoroughly reviewed. It also highlights the barriers, opportunities, developments, and prospects of extending the scope of microalgae. This study concludes that sustained research funding, and a shift of microalgae focus from biofuels production to bio-refinery co-products can qualify them as promising feedstocks. Moreover, technology integration is inevitable to off-set the cost of microalgae biomass processing. It is expected that this study would be helpful to determine the future role of microalgae in bio-refinery applications.

This paper presents a novel approach for the detection of tables present in documents, leveraging the potential of deep neural networks. Conventional approaches for table detection rely on heuristics that are error prone and specific to a dataset. In contrast, the presented approach harvests the potential of data to recognize tables of arbitrary layout. Most of the prior approaches for table detection are only applicable to PDFs, whereas, the presented approach directly works on images making it generally applicable to any format. The presented approach is based on a novel combination of deformable CNN with faster R-CNN/FPN. Conventional CNN has a fixed receptive field which is problematic for table detection since tables can be present at arbitrary scales along with arbitrary transformations (orientation). Deformable convolution conditions its receptive field on the input itself allowing it to mold its receptive field according to its input. This adaptation of the receptive field enables the network to cater for tables of arbitrary layout. We evaluated the proposed approach on two major publicly available table detection datasets: ICDAR-2013 and ICDAR-2017 POD. The presented approach was able to surpass the state-of-the-art performance on both ICDAR-2013 and ICDAR-2017 POD datasets with a F-measure of 0.994 and 0.968, respectively, indicating its effectiveness and superiority for the task of table detection.

For signature verification systems, micro deformations can be defined as the small differences in the same strokes of signatures or special writing habits of different signers. These micro deformations can reveal the core distinction between the genuine signatures and skilled forgeries. In this paper, we prove that Convolutional Neural Networks (CNNs) have the potential to extract those micro deformations by max-pooling. More specifically, the micro deformations can be determined by watching the location coordinates of the maximum values in pooling windows of max-pooling. Extensive analysis and experiments demonstrate that it is possible to achieve state-of-the-art performance by using this location information as a new feature for capturing micro deformations, along with convolutional features. The proposed method outperforms the state-of-the-art systems on four publicly available datasets of different languages, i.e., English (GPDSsynthetic, CEDAR), Persian (UTSig), and Hindi (BHSig260).

In this work, we present a novel and generic approach, Figure and Formula Detector (FFD) to detect the formulas and figures from document images. Our proposed method employs traditional computer vision approaches in addition to deep models. We transform input images by applying connected component analysis (CC), distance transform, and colour transform, which are stacked together to generate an input image for the network. The best results produced by FFD for figure and formula detection are with F1-score of 0.906 and 0.905, respectively. We also propose a new dataset for figures and formulas detection to aid future research in this direction. The obtained results advocate that enhancing the input representation can simplify the subsequent optimization problem resulting in significant gains over their conventional counterparts.

With the Internet of Things (IoT) devices becoming an integral part of human life, the need for robust anomaly detection in streaming data has also been elevated. Dozens of distance-based, density-based, kernel-based, and cluster-based algorithms have been proposed in the area of anomaly detection. Recently, because of the robustness of the deep neural networks (DNN), different deep learning-based anomaly detection methods have also been proposed. With all these rapid developments, there exists a small number of comparative studies for anomaly detection methods. Even in those studies, the comparison is done only in typical anomaly detection settings without taking the streaming data into consideration. The presence of intrinsic time-series characteristics like trend, seasonality, and change-point makes it important to study the behavior of commonly used anomaly detection methods on streaming data. Moreover, the comparison of traditional methods with deep learning-based methods also brings exciting insights about the data which are generally overlooked by traditional methods. In this study, we compare 13 anomaly detection methods on two commonly used streaming data sets. We used four different evaluation metrics to evaluate the methods from different perspectives. Our analysis reveals that the deep learning-based anomaly detection methods are superior to traditional anomaly detection methods.

In this paper we study the performance evaluation of state-of-the-art object detection models for the task of bibliographic reference detection from document images. The motivation of evaluating object detection models for the task in hand is inspired from how human perceive a document containing bibliographic references. Humans can easily distinguish between different references just by exploiting the layout with a glimpse of an eye, without understanding the content. Existing state-of-the-art systems for bibliographic reference detection are purely based on textual content. By contrast, we employed four state-of-the art object detection models and compared their performance with state-of-the-art text based reference extraction models. Evaluations are performed on the publicly available dataset (ICONIP) for image based reference detection, containing 455 scanned bibliographic documents with 8766 references from Social Sciences books and journals. Evaluation results reveal the superiority of image based methods for the task of reference detection in document images.

Text document classification is an important task for diverse natural language processing based applications. Traditional machine learning approaches mainly focused on reducing dimensionality of textual data to perform classification. This although improved the overall classification accuracy, the classifiers still faced sparsity problem due to lack of better data representation techniques. Deep learning based text document classification, on the other hand, benefitted greatly from the invention of word embeddings that have solved the sparsity problem and researchers focus mainly remained on the development of deep architectures. Deeper architectures, however, learn some redundant features that limit the performance of deep learning based solutions. In this paper, we propose a two stage text document classification methodology which combines traditional feature engineering with automatic feature engineering (using deep learning). The proposed methodology comprises a filter based feature selection (FSE) algorithm followed by a deep convolutional neural network. This methodology is evaluated on the two most commonly used public datasets, i.e., 20 Newsgroups data and BBC news data. Evaluation results reveal that the proposed methodology outperforms the state-of-the-art of both the (traditional) machine learning and deep learning based text document classification methodologies with a significant margin of 7.7% on 20 Newsgroups and 6.6% on BBC news datasets., ICDAR Conference

This paper presents a novel two-stream approach for document image classification. The proposed approach leverages textual and visual modalities to classify document images into ten categories, including letter, memo, news article, etc. In order to alleviate dependency of textual stream on performance of underlying OCR (which is the case with general content based document image classifiers), we utilize a filter based feature-ranking algorithm. This algorithm ranks the features of each class based on their ability to discriminate document images and selects a set of top 'K' features that are retained for further processing. In parallel, the visual stream uses deep CNN models to extract structural features of document images.Finally, textual and visual streams are concatenated together using an average ensembling method. Experimental results reveal that the proposed approach outperforms the state-of-the-art system with a significant margin of 4.5% on publicly available Tobacco-3482 dataset.

Based on the recent advancements in the domain of semantic segmentation, Fully-Convolutional Networks (FCN) have been successfully applied for the task of table structure recognition in the past. We analyze the efficacy of semantic segmentation networks for this purpose and simplify the problem by proposing prediction tiling based on the consistency assumption which holds for tabular structures. For an image of dimensions H × W, we predict a single column for the rows (ŷ_row ∊ H) and a predict a single row for the columns (ŷ_row ∊ W). We use a dual-headed architecture where initial feature maps (from the encoder-decoder model) are shared while the last two layers generate class specific (row/column) predictions. This allows us to generate predictions using a single model for both rows and columns simultaneously, where previous methods relied on two separate models for inference. With the proposed method, we were able to achieve state-of-the-art results on ICDAR-13 image-based table structure recognition dataset with an average F-Measure of 92.39% (91.90% and 92.88% F-Measure for rows and columns respectively). With the proposed method, we were able to achieve state-of-the-art results on ICDAR-13. The obtained results advocate that constraining the problem space in the case of FCN by imposing valid constraints can lead to significant performance gains.

This paper presents a novel method for the analysis of tabular structures in document images using the potential of deformable convolutional networks. In order to assess the suitability of the model to the task of table structure recognition, most of the prior methods have been tested on the smaller ICDAR-13 table structure recognition dataset comprising of just 156 tables. We curated a new image-based table structure recognition dataset, TabStructDB2, comprising of 1081 tables densely labeled with row and column information. Instead of collecting new images for this purpose, we leveraged the famous Page-Object Detection dataset from ICDAR-17, and added structural information for all the tabular regions present in the dataset. This new publicly available dataset will enable the development of more sophisticated table structure recognition techniques in the future. We performed extensive evaluation on the two datasets (ICDAR-13 and TabStructDB) including crossdataset testing in order to evaluate the efficacy of the proposed approach. We achieved state-of-the-art results with deformable models on ICDAR-13 with an average F-Measure of 92.98% (89.42% for rows and 96.55% for columns) and report baseline results on TabStructDB for guiding future research efforts with an F-Measure of 93.72% (91.26% for rows and 95.59% for columns). Despite promising results, structural analysis of tables with arbitrary layouts is still far from achievable at this point.

The need for robust unsupervised anomaly detection in streaming data is increasing rapidly in the current era of smart devices, where enormous data are gathered from numerous sensors. These sensors record the internal state of a machine, the external environment, and the interaction of machines with other machines and humans. It is of prime importance to leverage this information in order to minimize downtime of machines, or even avoid downtime completely by constant monitoring. Since each device generates a different type of streaming data, it is normally the case that a specific kind of anomaly detection technique performs better than the others depending on the data type. For some types of data and use-cases, statistical anomaly detection techniques work better, whereas for others, deep learning-based techniques are preferred. In this paper, we present a novel anomaly detection technique, FuseAD, which takes advantage of both statistical and deep-learning-based approaches by fusing them together in a residual fashion. The obtained results show an increase in area under the curve (AUC) as compared to state-of-the-art anomaly detection methods when FuseAD is tested on a publicly available dataset (Yahoo Webscope benchmark). The obtained results advocate that this fusion-based technique can obtain the best of both worlds by combining their strengths and complementing their weaknesses. We also perform an ablation study to quantify the contribution of the individual components in FuseAD, i.e., the statistical ARIMA model as well as the deep-learning-based convolutional neural network (CNN) model.

Currently, there are rapid changes in the supermarket sector, as more and more companies provide home delivery services of most of their products. Recently, perishable groceries are also directly shipped to people's home, which leads to new logistical challenges. By only using statistical data known as location factors, problems arose for metropolises like Berlin. These cities have several millions of inhabitants, but are only modeled as one geographic entity with a single attributes like average net income. In order to provide insights into cities down to street level, this geodata model was enriched with information of OpenStreetMap (OSM). Additionally, the road network of OSM was used to dynamically calculate catchment areas and combine them with location factors of the geodata model. This combination enables dynamic and data-driven customer, competitor, and supplier analysis. The evaluation was performed on the application scenario of online food delivery models of Edeka, Rewe and Amazon-Fresh. The results indicate, that Edeka's delivery model-currently evaluated by Edeka in Berlin-only reaches 0,28 % of the inhabitants, whereas Amazon fresh achieves nearly 100 % coverage. As a conclusion, the presented data-driven business analysis enables new possibilities for site selection and potential for future applications.

Artificial Intelligence (AI) can roughly be categorized into two streams, knowledge driven and data driven both of which have their own advantages. Incorporating knowledge into Deep Neural Networks (DNN), that are purely data driven, can potentially improve the overall performance of the system. This paper presents such a fusion scheme, DeepEX, that combines these seemingly parallel streams of AI, for multi-step time-series forecasting problems. DeepEX achieves this in a way that merges best of both worlds along with a reduction in the amount of data required to train these models. This direction has been explored in the past for single step forecasting by opting for a residual learning scheme. We analyze the shortcomings of this simple residual learning scheme and enable DeepEX to not only avoid these shortcomings but also scale to multi-step prediction problems. DeepEX is tested on two commonly used time series forecasting datasets, CIF2016 and NN5, where it achieves competitive results even when trained on a reduced set of training examples. Incorporating external knowledge to reduce network’s reliance on large amount of accurately labeled data will prove to be extremely effective in training of neural networks for real-world applications where the dataset sizes are small and labeling is expensive.

Neural networks (NN) are considered as black-boxes due to the lack of explainability and transparency of their decisions. This significantly hampers their deployment in environments where explainability is essential along with the accuracy of the system. Recently, significant efforts have been made for the interpretability of these deep networks with the aim to open up the black-box. However, most of these approaches are specifically developed for visual modalities. In addition, the interpretations provided by these systems require expert knowledge and understanding for intelligibility. This indicates a vital gap between the explainability provided by the systems and the novice user. To bridge this gap, we present a novel framework i.e. Time-Series eXplanation (TSXplain) system which produces a natural language based explanation of the decision taken by a NN. It uses the extracted statistical features to describe the decision of a NN, merging the deep learning world with that of statistics. The two-level explanation provides ample description of the decision made by the network to aid an expert as well as a novice user alike. Our survey and reliability assessment test confirm that the generated explanations are meaningful and correct. We believe that generating natural language based descriptions of the network's decisions is a big step towards opening up the black-box.

This paper has a threefold contribution. First, it presents a novel online handwriting database captured using a digital/sensor pen (Apple pencil) and digital/sensor screen (iPad). The captured data are continuous streams of multi-dimensional points, analyzed and processed to classify handwritten sequences into plain text, mathematical expressions, and plots/graphs. Second, a new feature set for online handwritten sequence classification is proposed. The said feature set is used to establish a benchmark for the proposed dataset using various machine-learning classifiers. Third, an ablation study is performed to look into the performance of the proposed feature set compared to the existing feature sets. Here, the proposed feature set has outperformed all the existing feature sets in various evaluation metrics. Furthermore, the proposed dataset and the feature set have been made publicly available along with the benchmark evaluation to enable further research in the field.

We propose a novel hybrid approach that fuses traditional computer vision techniques with deep learning models to detect figures and formulas from document images. The proposed approach first fuses the different computer vision based image representations, i.e., color transform, connected component analysis, and distance transform, termed as Fi-Fo image representation. The Fi-Fo image representation is then fed to deep models for further refined representation-learning for detecting figures and formulas from document images. The proposed approach is evaluated on a publicly available ICDAR-2017 Page Object Detection (POD) dataset and its corrected version. It produces the state-of-the-art results for formula and figure detection in document images with an f1-score of 0.954 and 0.922, respectively. Ablation study results reveal that the Fi-Fo image representation helps in achieving superior performance in comparison to raw image representation. Results also establish that the hybrid approach helps deep models to learn more discriminating and refined features.

Propensity of skin diseases to manifest in a variety of forms, lack and maldistribution of qualified dermatologists, and exigency of timely and accurate diagnosis call for automated Computer-Aided Diagnosis (CAD). This study aims at extending previous works on CAD for dermatology by exploring the potential of Deep Learning to classify hundreds of skin diseases, improving classification performance, and utilizing disease taxonomy. We trained state-of-the-art Deep Neural Networks on two of the largest publicly available skin image datasets, namely DermNet and ISIC Archive, and also leveraged disease taxonomy, where available, to improve classification performance of these models. On DermNet we establish new state-of-the-art with 80% accuracy and 98% Area Under the Curve (AUC) for classification of 23 diseases. We also set precedence for classifying all 622 unique sub-classes in this dataset and achieved 67% accuracy and 98% AUC. On ISIC Archive we classified all 7 diseases with 93% average accuracy and 99% AUC. This study shows that Deep Learning has great potential to classify a vast array of skin diseases with near-human accuracy and far better reproducibility. It can have a promising role in practical real-time skin disease diagnosis by assisting physicians in large-scale screening using clinical or dermoscopic images.

In-air signature is a new modality which is essential for user authentication and access control in noncontact mode and has been actively studied in recent years. However, it has been treated as a conventional online signature, which is essentially a 2D spatial representation. Notably, this modality bears a lot more potential due to an important hidden depth feature. Existing methods for in-air signature verification neither capture this unique depth feature explicitly nor fully explore its potential in verification. Moreover, these methods are based on heuristic approaches for fingertip or hand palm center detection, which are not feasible in practice. Inspired by the great progress in deep-learning-based hand pose estimation, we propose a real-time in-air signature acquisition method which estimates hand joint positions in 3D using a single depth image. The predicted 3D position of fingertip is recorded for each frame. We present four different implementations of a verification module, which are based on the extracted depth and spatial features. An ablation study was performed to explore the impact of the depth feature in particular. For matching, we employed the most commonly used multidimensional dynamic time warping (MD-DTW) algorithm. We created a new database which contains 600 signatures recorded from 15 different subjects. Extensive evaluations were performed on our database. Our method, called 3DAirSig, achieved an equal error rate (EER) of 0.46 %. Experiments showed that depth itself is an important feature, which is sufficient for in-air signature verification.

This paper presents a simple yet effective method for improving the performance of zero-shot learning (ZSL). ZSL classifies instances of unseen classes, from which no training data is available, by utilizing the attributes of the classes. Conventional ZSL methods have equally dealt with all the available attributes, but this sometimes causes misclassification. This is because an attribute that is effective for classifying instances of one class is not always effective for another class. In this case, a metric of classifying the latter class can be undesirably influenced by the irrelevant attribute. This paper solves this problem by taking the importance of each attribute for each class into account when calculating the metric. In addition to the proposal of this new method, this paper also contributes by providing a dataset for pose classification based on wearable sensors, named HDPoseDS. It contains 22 classes of poses performed by 10 subjects with 31 IMU sensors across full body. To the best of our knowledge, it is the richest wearable-sensor dataset especially in terms of sensor density, and thus it is suitable for studying zero-shot pose/action recognition. The presented method was evaluated on HDPoseDS and outperformed relative improvement of 5.9% in comparison to the best baseline method., The paper was published at Sensors, an open access journal (http://www.mdpi.com/1424-8220/18/8/2485). This article belongs to the Special Issue Artificial Intelligence and Machine Learning in Sensors Networks

The competent handling of representations is required for understanding physics' concepts, developing problem-solving skills, and achieving scientific expertise. Using eye-tracking methodology, we present the contributions of this paper as follows: We first investigated the preferences of students with the different levels of knowledge; experts, intermediates, and novices, in representational competence in the domain of physics problem-solving. It reveals that experts more likely prefer to use vector than other representations. Besides, a similar tendency of table representation usage was observed in all groups. Also, diagram representation has been used less than others. Secondly, we evaluated three similarity measures; Levenshtein distance, transition entropy, and Jensen-Shannon divergence. Conducting Recursive Feature Elimination technique suggests Jensen-Shannon divergence is the best discriminating feature among the three. However, investigation on mutual dependency of the features implies transition entropy mutually links between two other features where it has mutual information with Levenshtein distance (Maximal Information Coefficient = 0.44) and has a correlation with Jensen-Shannon divergence (r(18313) = 0.70, p

This paper presents a novel framework for demystification of convolutional deep learning models for time-series analysis. This is a step towards making informed/explainable decisions in the domain of time-series, powered by deep learning. There have been numerous efforts to increase the interpretability of image-centric deep neural network models, where the learned features are more intuitive to visualize. Visualization in time-series domain is much more complicated as there is no direct interpretation of the filters and inputs as compared to the image modality. In addition, little or no concentration has been devoted for the development of such tools in the domain of time-series in the past. TSViz provides possibilities to explore and analyze a network from different dimensions at different levels of abstraction which includes identification of parts of the input that were responsible for a prediction (including per filter saliency), importance of different filters present in the network for a particular prediction, notion of diversity present in the network through filter clustering, understanding of the main sources of variation learnt by the network through inverse optimization, and analysis of the network's robustness against adversarial noise. As a sanity check for the computed influence values, we demonstrate results regarding pruning of neural networks based on the computed influence information. These representations allow to understand the network features so that the acceptability of deep networks for time-series data can be enhanced. This is extremely important in domains like finance, industry 4.0, self-driving cars, health-care, counter-terrorism etc., where reasons for reaching a particular prediction are equally important as the prediction itself. We assess the proposed framework for interpretability with a set of desirable properties essential for any method., 7 Pages (6 + 1 for references), 7 figures

This paper presents a novel end-to-end system for table understanding in document images called DeepDeSRT. In particular, the contribution of DeepDeSRT is two-fold. First, it presents a deep learning-based solution for table detection in document images. Secondly, it proposes a novel deep learning-based approach for table structure recognition, i.e. identifying rows, columns, and cell positions in the detected tables. In contrast to existing rule-based methods, which rely on heuristics or additional PDF metadata (like, for example, print instructions, character bounding boxes, or line segments), the presented system is data-driven and does not need any heuristics or metadata to detect as well as to recognize tabular structures in document images. Furthermore, in contrast to most existing table detection and structure recognition methods, which are applicable only to PDFs, DeepDeSRT processes document images, which makes it equally suitable for born-digital PDFs (as they can automatically be converted into images) as well as even harder problems, e.g. scanned documents. To gauge the performance of DeepDeSRT, the system is evaluated on the publicly available ICDAR 2013 table competition dataset containing 67 documents with 238 pages overall. Evaluation results reveal that DeepDeSRT outperforms state-of-the-art methods for table detection and structure recognition and achieves F1-measures of 96.77% and 91.44% for table detection and structure recognition, respectively. Additionally, DeepDeSRT is evaluated on a closed dataset from a real use case of a major European aviation company comprising documents which are highly unlike those in ICDAR 2013. Tested on a randomly selected sample from this dataset, DeepDeSRT achieves high detection accuracy for tables which demonstrates the sound generalization capabilities of our system.

This paper presents detailed anomaly detection evaluation on operational time-series data of Internet of Things (IoT) based household devices in general and Heating, Ventilation and Air Conditioning (HVAC) systems in specific. Due to the number of issues observed during evaluation of widely used distance-based, statistical-based, and cluster-based anomaly detection techniques, we also present a pattern-based approach for anomaly detection in HVAC time-series data. The usage and number of IoT based HVAC systems are enormously increasing and will have a major share in IoT based household devices in the near future. The operational and usage log of these devices contains different sensor values logged with time, containing normal data points, and long-term anomalies. The state-of-the-art methods for anomaly detection are unable to detect these long-term anomalies, which reflect the deteriorating effect of a sensor. The presented approach overcomes this problem by building a knowledge base of long/short -term patterns based on normal data points which keep growing over the time. In addition to the detected anomalies and in contrast to the existing methods, the presented method gives meaningful anomaly score for a number of HVAC systems. We evaluate the presented approach on real operational data, collected over the period of 2.5 years. Evaluation results show that the presented approach outperforms the state-of-the-art methods for anomaly detection with the area under the curve (AUC) value of 99.4%. Discord detection results of the proposed technique on another dataset from a different domain show the generic and adaptive nature of our technique.

This paper presents a novel approach, called AirScript, for creating, recognizing and visualizing documents in air. We present a novel algorithm, called 2-DifViz, that converts the hand movements in air (captured by a Myo-armband worn by a user) into a sequence of x, y coordinates on a 2D Cartesian plane, and visualizes them on a canvas. Existing sensor-based approaches either do not provide visual feedback or represent the recognized characters using prefixed templates. In contrast, AirScript stands out by giving freedom of movement to the user, as well as by providing a real-time visual feedback of the written characters, making the interaction natural. AirScript provides a recognition module to predict the content of the document created in air. To do so, we present a novel approach based on deep learning, which uses the sensor data and the visualizations created by 2-DifViz. The recognition module consists of a Convolutional Neural Network (CNN). and two Gated Recurrent Unit (GRU) Networks. The output from these three networks is fused to get the final prediction about the characters written in air. AirScript can be used in highly sophisticated environments like a smart classroom, a smart factory or a smart laboratory, where it would enable people to annotate pieces of texts wherever they want without any reference surface. We have evaluated AirScript against various well-known learning models (HMM, KNN, SVM, etc.) on the data of 12 participants. Evaluation results show that the recognition module of AirScript largely outperforms all of these models by achieving an accuracy of 91.7% in a person independent evaluation and a 96.7% accuracy in a person dependent evaluation.

We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the DeepDoc-Classifier, apply standard Convolutional Network architectures with transfer learning from the object recognition domain. The contribution of the paper is threefold: First, it investigates recently introduced very deep neural network architectures (GoogLeNet, VGG, ResNet) using transfer learning (from real images). Second, it proposes transfer learning from a huge set of document images, i.e. 400; 000 documents. Third, it analyzes the impact of the amount of training data (document images) and other parameters to the classification abilities. We use two datasets, the Tobacco-3482 and the large-scale RVL-CDIP dataset. We achieve an accuracy of 91:13% for the Tobacco-3482 dataset while earlier approaches reach only 77:6%. Thus, a relative error reduction of more than 60% is achieved. For the large dataset RVL-CDIP, an accuracy of 90:97% is achieved, corresponding to a relative error reduction of 11:5%.

B This paper presents a novel approach, named D-StaR, for stamp segmentation from scanned document images. The presented approach is generic (applicable to stamps of any color, shape, size, and orientation) and based on deep learning. In particular, it uses Fully Convolutional networks for semantic analysis of documents to extract stamps. The presented approach is evaluated on a publicly available stamp dataset. Evaluation results show that the presented approach outperforms the state-of-the-art methods for stamp segmentation and achieves pixel based precision and recall of 87% and 84%, respectively. Deeper analysis of the evaluation reveals that the presented approach can segment both overlapping and non-overlapping stamps, which was always a problem for existing systems in the literature.

Demand Response (DR) programs under the umbrella of Demand Side Management (DSM) tend to involve end users in optimizing their Power Consumption (PC) patterns and offer financial incentives to shift the load at “low-priced” hours. However, users have their own preferences of anticipating the amount of consumed electricity. While installing an Energy Management System (EMS), the user must be assured that this investment gives optimum comfort of bill savings, as well as appliance utility considering Time of Use (ToU). Moreover, there is a difference between desired load distribution and optimally-scheduled load across a 24-h time frame for lowering electricity bills. This difference in load usage timings, if it is beyond the tolerance level of a user, increases frustration. The comfort level is a highly variable phenomenon. An EMS giving optimum comfort to one user may not be able to provide the same level of satisfaction to another who has different preferences regarding electricity bill savings or appliance utility. Under such a diversity of human behaviors, it is difficult to select an EMS for an individual user. In this work, a numeric performance metric,“User Comfort Level (UCL)”isformulatedonthebasisofuserpreferencesoncostsaving,toleranceindelayregardinguse of an appliance and return of investment. The proposed framework (UCL) allows the user to select an EMS optimally that suits his.her preferences well by anticipating electricity bill reduction, tolerable delay in ToU of the appliance and return on investment. Furthermore, an extended literature analysis is conducted demonstrating generic strategies of EMSs. Five major building blocks are discussed and a comparative analysis is presented on the basis of the proposed performance metric.