Search

Light microscopy combined with well-established protocols of two-dimensional cell culture facilitates high-throughput quantitative imaging to study biological phenomena. Accurate segmentation of individual cells in images enables exploration of complex biological questions, but can require sophisticated imaging processing pipelines in cases of low contrast and high object density. Deep learning-based methods are considered state-of-the-art for image segmentation but typically require vast amounts of annotated data, for which there is no suitable resource available in the field of label-free cellular imaging. Here, we present LIVECell, a large, high-quality, manually annotated and expert-validated dataset of phase-contrast images, consisting of over 1.6 million cells from a diverse set of cell morphologies and culture densities. To further demonstrate its use, we train convolutional neural network-based models using LIVECell and evaluate model segmentation accuracy with a proposed a suite of benchmarks., The LIVECell dataset comprises annotated phase-contrast images of over 1.6 million cells from different cell lines during growth from sparse seeding to confluence for improved training of deep learning-based models of image segmentation.

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.

Small non-coding RNAs (ncRNAs) are attracting increasing attention as they are now considered potentially valuable resources in the development of new drugs intended to cure several human diseases. A prerequisite for the development of drugs targeting ncRNAs or the related pathways is the identification and correct classification of such ncRNAs. State-of-the-art small ncRNA classification methodologies use secondary structural features as input. However, such feature extraction approaches only take global characteristics into account and completely ignore co-relative effects of local structures. Furthermore, secondary structure based approaches incorporate high dimensional feature space which is computationally expensive. The present paper proposes a novel Robust and Precise ConvNet (RPC-snRC) methodology which classifies small ncRNAs into relevant families by utilizing their primary sequence. RPC-snRC methodology learns hierarchical representation of features by utilizing positioning and information on the occurrence of nucleotides. To avoid exploding and vanishing gradient problems, we use an approach similar to DenseNet in which gradient can flow straight from subsequent layers to previous layers. In order to assess the effectiveness of deeper architectures for small ncRNA classification, we also adapted two ResNet architectures having a different number of layers. Experimental results on a benchmark small ncRNA dataset show that the proposed methodology does not only outperform existing small ncRNA classification approaches with a significant performance margin of 10% but it also gives better results than adapted ResNet architectures. To reproduce the results Source code and data set is available at https://github.com/muas16/small-non-coding-RNA-classification.

In order to provide benchmark performance for Urdu text document classification, the contribution of this paper is manifold. First, it provides a publicly available benchmark dataset manually tagged against 6 classes. Second, it investigates the performance impact of traditional machine learning-based Urdu text document classification methodologies by embedding 10 filter-based feature selection algorithms which have been widely used for other languages. Third, for the very first time, it assesses the performance of various deep learning-based methodologies for Urdu text document classification. In this regard, for experimentation, we adapt 10 deep learning classification methodologies which have produced best performance figures for English text classification. Fourth, it also investigates the performance impact of transfer learning by utilizing Bidirectional Encoder Representations from Transformers approach for Urdu language. Fifth, it evaluates the integrity of a hybrid approach which combines traditional machine learning-based feature engineering and deep learning-based automated feature engineering. Experimental results show that feature selection approach named as normalized difference measure along with support vector machine outshines state-of-the-art performance on two closed source benchmark datasets CLE Urdu Digest 1000k, and CLE Urdu Digest 1Million with a significant margin of 32% and 13%, respectively. Across all three datasets, normalized difference measure outperforms other filter-based feature selection algorithms as it significantly uplifts the performance of all adopted machine learning, deep learning, and hybrid approaches. The source code and presented dataset are available at Github repository https://github.com/minixain/Urdu-Text-Classification .

Apart from protein-coding Ribonucleic acids (RNAs), there exists a variety of non-coding RNAs (ncRNAs) which regulate complex cellular and molecular processes. High-throughput sequencing technologies and bioinformatics approaches have largely promoted the exploration of ncRNAs which revealed their crucial roles in gene regulation, miRNA binding, protein interactions, and splicing. Furthermore, ncRNAs are involved in the development of complicated diseases like cancer. Categorization of ncRNAs is essential to understand the mechanisms of diseases and to develop effective treatments. Sub-cellular localization information of ncRNAs demystifies diverse functionalities of ncRNAs. To date, several computational methodologies have been proposed to precisely identify the class as well as sub-cellular localization patterns of RNAs). This paper discusses different types of ncRNAs, reviews computational approaches proposed in the last 10 years to distinguish coding-RNA from ncRNA, to identify sub-types of ncRNAs such as piwi-associated RNA, micro RNA, long ncRNA, and circular RNA, and to determine sub-cellular localization of distinct ncRNAs and RNAs. Furthermore, it summarizes diverse ncRNA classification and sub-cellular localization determination datasets along with benchmark performance to aid the development and evaluation of novel computational methodologies. It identifies research gaps, heterogeneity, and challenges in the development of computational approaches for RNA sequence analysis. We consider that our expert analysis will assist Artificial Intelligence researchers with knowing state-of-the-art performance, model selection for various tasks on one platform, dominantly used sequence descriptors, neural architectures, and interpreting inter-species and intra-species performance deviation.

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.

The revolution of the Internet of Things (IoT) is transforming many concepts, making them “Smart”. It has revolutionized many areas of real life. Smart City is one of the key concepts of this revolution. Although cities are being digitally transformed, it still has obstacles along the way. In this paper, we have analyzed different publications for our Systematic Literature Review (SLR). This study highlights the areas where the blockchain is used and determines the benefits of using blockchain. The main contribution is to explore and identify the barriers and hurdles in Smart City Domain and how these hurdles are mitigated by the blockchain technology. This Systematic Study also addresses different challenges and issues such as security, immutability, interoperability, decentralization, privacy, and trust in the development of Smart Cities. An overview of the systematic research is also presented that would help identify the most and least studied concerns addressed in this study. This paper aims at analyzing how blockchain technology is used in different smart city business models, what are the features of blockchain that could consider it to be used beyond crypto currencies. We hope that this study can inspire interest in theory and exercise to stand-in discussions in this area adhere to these limits.

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

There is a rising interest in investigating mechanisms and engineering of integral membrane proteins (MPs) which make crucial contribution in perceiving and controlling cellular response against different external signals. MPs need to be inserted, folded and expressed correctly in lipid bi-layer and transferred to appropriate cellular location to perform its diverse range of functions. Channelrhodopsins (ChRs), light gated ion-channel proteins belonging to microorganisms are imminent for diverse neurobiology applications where expression as well as localization to plasma membrane is a pre-condition for function. Developing robust computational methodologies to accurately identify ChRs localization is an active area of research. Existing computational approaches make use of one-hot-vector encoding or protein embeddings to encode MP sequences that are fed to Gaussian process regression model. These approaches lack to accurately predict the localization of MP proteins. The paper in hand proposes ChRsLoc-Net predictor that makes use of composition-transition-distribution (CTDC) physico-chemical properties based sequence encoder along with Hubber regressor. Over benchmark dataset, proposed ChrSLoc-Net approach outperforms state-of-the-art MP localization predictor with a significant margin of 9% in terms of mean absolute error. We anticipate that this study will largely assist biologist to comprehend diverse biological processes subject to localization patterns of MPs within plasma membrane.

Accurate cell segmentation in microscopic images is a useful tool to analyze individual cell behavior, which helps to diagnose human diseases and development of new treatments. Cell segmentation of individual cells in a microscopic image with many cells in view allows quantification of single cellular features, such as shape or movement patterns, providing rich insight into cellular heterogeneity. Most of the cell segmentation algorithms up till now focus on segmenting cells in the images without classifying the culture of the cell in the images. Discrimination among cell types in microscopic images can lead to a new era of high-throughput cell microscopy. Multiple cell types in coculture can be easily identified and studying the changes in cell morphology can lead to many applications such as drug treatment. To address this gap, DeepCIS is proposed to detect, segment, and classify the culture of the cells and nucleus in the microscopic images. We have used the EVICAN60 dataset which contains microscopic images from a variety of microscopes having numerous cell cultures, to evaluate the proposed pipeline. To further demonstrate the utility of the DeepCIS, we have designed various experimental settings to uncover its learning potential. We have achieved a mean average precision score of 24.37% for the segmentation task averaged over 30 classes for cell and nucleus.

A comprehensive understanding of miRNA sub-cellular localization may leads towards better understanding of physiological processes and support the fixation of diverse irregularities present in a variety of organisms. To date, diverse computational methodologies have been proposed to automatically infer sub-cellular localization of miR-NAs solely using sequence information, however, existing approaches lack in performance. Considering the success of data transformation approaches in Natural Language Processing which primarily transform multi-label classification problem into multi-class classification problem, here, we introduce three different data transformation approaches namely binary relevance, label power set, and classifier chains. Using data transformation approaches, at 1st stage, multi-label miRNA sub-cellular localization problem is transformed into multi-class problem. Then, at 2nd stage, 3 different machine learning classifiers are used to estimate which classifier performs better with what data transformation approach for hand on task. Empirical evaluation on independent test set indicates that L2S-MirLoc selected combination based on binary relevance and deep random forest outperforms state-of-the-art performance values by significant margin.

With the evolution of deep learning in the past decade, more biomedical related problems that seemed strenuous, are now feasible. The introduction of U-net and Mask R-CNN architectures has paved a way for many object detection and segmentation tasks in numerous applications ranging from security to biomedical applications. In the cell biology domain, light microscopy imaging provides a cheap and accessible source of raw data to study biological phenomena. By leveraging such data and deep learning techniques, human diseases can be easily diagnosed and the process of treatment development can be greatly expedited. In microscopic imaging, accurate segmentation of individual cells is a crucial step to allow better insight into cellular heterogeneity. To address the aforementioned challenges, DeepCeNS is proposed in this paper to detect and segment cells and nucleus in microscopic images. We have used EVICAN2 dataset which contains microscopic images from a variety of microscopes having numerous cell cultures, to evaluate the proposed pipeline. DeepCeNS outperforms EVICAN-MRCNN by a significant margin on the EVICAN2 dataset.

The field of explainable AI (XAI) has quickly become a thriving and prolific community. However, a silent, recurrent and acknowledged issue in this area is the lack of consensus regarding its terminology. In particular, each new contribution seems to rely on its own (and often intuitive) version of terms like "explanation" and "interpretation". Such disarray encumbers the consolidation of advances in the field towards the fulfillment of scientific and regulatory demands e.g., when comparing methods or establishing their compliance with respect to biases and fairness constraints. We propose a theoretical framework that not only provides concrete definitions for these terms, but it also outlines all steps necessary to produce explanations and interpretations. The framework also allows for existing contributions to be re-contextualized such that their scope can be measured, thus making them comparable to other methods. We show that this framework is compliant with desiderata on explanations, on interpretability and on evaluation metrics. We present a use-case showing how the framework can be used to compare LIME, SHAP and MDNet, establishing their advantages and shortcomings. Finally, we discuss relevant trends in XAI as well as recommendations for future work, all from the standpoint of our framework.

With the advent of machine learning in applications of critical infrastructure such as healthcare and energy, privacy is a growing concern in the minds of stakeholders. It is pivotal to ensure that neither the model nor the data can be used to extract sensitive information used by attackers against individuals or to harm whole societies through the exploitation of critical infrastructure. The applicability of machine learning in these domains is mostly limited due to a lack of trust regarding the transparency and the privacy constraints. Various safety-critical use cases (mostly relying on time-series data) are currently underrepresented in privacy-related considerations. By evaluating several privacy-preserving methods regarding their applicability on time-series data, we validated the inefficacy of encryption for deep learning, the strong dataset dependence of differential privacy, and the broad applicability of federated methods., Comment: 9 pages, 4 figures. 6 tables

Document image classification is one of the most important components in business automation workflow. Therefore, a range of different supervised image classification methods have been proposed, which rely on a large amount of labeled data, which is rarely available in practice. Furthermore, retraining of these models is necessary upon the introduction of new classes. In this paper, we analyze the potential of zero-shot document image classification based on computing the agreement between the images and the textual embeddings of class names/descriptions. This enables the deployment of document image classification models without the availability of any training data at zero training cost, alongside providing seamless integration of new classes. Our results show that using zero-shot recognition achieves significantly better than chance performance on document image classification benchmarks (49.51% accuracy on Tobacco-3482 in contrast to 10% random classifier accuracy and 39.22% on RVL-CDIP dataset in contrast to 6.25% random classifier accuracy). We also show that the representation learned by a vision transformer using image-text pairs is competitive to CNNs by training a linear SVM on top of the pre-computed representations which achieves comparable performance to state-of-the-art convolutional networks (85.74% on Tobacco-3482 dataset in contrast to 71.67% from ImageNet pretrained ResNet-50). Even though the initial results look encouraging, there is still a large gap to cover for zero-shot recognition within the domain of document images in contrast to natural scene image classification, which achieves comparable performance to fully supervised baselines. Our preliminary findings pave the way for the deployment of zero-shot document image classification in production settings.

Compression of neural networks has become a common norm in industrial settings to reduce the cost of inference and deployment. As document classification is a common process in business workflows, there is a dire need of analyzing the potential of compressed models for the task of document image classification. Surprisingly, no such analysis has been done in the past. Furthermore, once a compressed model is obtained using a particular compression algorithm (which achieves similar accuracy to the uncompressed model), the model is directly deployed without much consideration. However, such compression process results in its own set of challenges which have large implications, especially when the uncompressed model is ensured to be fair or unbiased such as a fair model making critical hiring decisions based on the applicant’s resume. In this paper, we show that current state-of-the-art compression algorithms can be successfully applied for the task of document image classification. We further analyze the impact of model compression on network outputs and highlight the discrepancy that arises during the compression process. Building on recent findings in this direction, we employ a principled approach based on logit-pairing for minimizing this deviation from the functional outputs of the uncompressed model. Our results on Tobacco-3482 dataset show that we can reduce the number of mismatches between the compressed and the uncompressed model drastically in both structured and unstructured cases (by more than 2x in some cases) by employing label-preservation-aware loss functions. These findings shed light on some important considerations before the compressed models are ready for deployment in the real world.

Water is one of the basic resources required for human survival. However, pollution of water has become a global problem. 2.4 billion people worldwide live without any form of water sanitation. This work focuses on case study of water pollution in Pakistan where only 20% of the population has an access to good-quality water. Drinking bad-quality water causes diseases such as hepatitis, diarrhea and typhoid. Moreover, people living close to the industrial areas are more prone to drinking polluted water and catching diseases as a result. Yet, there is no system that can monitor the quality of water or help in disease prevention. In this work, an Internet of Things (IoT)-enabled water quality monitoring system is developed that works as a stand-alone portable solution for monitoring water quality accurately and in real time. The real-time results are stored in a cloud database. The public web portal shows these results in the form of data sheets, maps and charts for analyzing data. Further, this data along with the collected data of past water quality is used to generate machine learning (ML) models for prediction of water quality. As a consequence, a model for prediction of water quality is trained and tested on a test set. The predictions on the test set resulted in a mean squared error (MSE) of 0.264.

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.

Scarcity of large publicly available retinal fundus image datasets for automated glaucoma detection has been the bottleneck for successful application of artificial intelligence towards practical Computer-Aided Diagnosis (CAD). A few small datasets that are available for research community usually suffer from impractical image capturing conditions and stringent inclusion criteria. These shortcomings in already limited choice of existing datasets make it challenging to mature a CAD system so that it can perform in real-world environment. In this paper we present a large publicly available retinal fundus image dataset for glaucoma classification called G1020. The dataset is curated by conforming to standard practices in routine ophthalmology and it is expected to serve as standard benchmark dataset for glaucoma detection. This database consists of 1020 high resolution colour fundus images and provides ground truth annotations for glaucoma diagnosis, optic disc and optic cup segmentation, vertical cup-to-disc ratio, size of neuroretinal rim in inferior, superior, nasal and temporal quadrants, and bounding box location for optic disc. We also report baseline results by conducting extensive experiments for automated glaucoma diagnosis and segmentation of optic disc and optic cup., Accepted in IJCNN-2020, 7 pages, 5 figures

Deep learning based medical image classifiers have shown remarkable prowess in various application areas like ophthalmology, dermatology, pathology, and radiology. However, the acceptance of these Computer-Aided Diagnosis (CAD) systems in real clinical setups is severely limited primarily because their decision-making process remains largely obscure. This work aims at elucidating a deep learning based medical image classifier by verifying that the model learns and utilizes similar disease-related concepts as described and employed by dermatologists. We used a well-trained and high performing neural network developed by REasoning for COmplex Data (RECOD) Lab for classification of three skin tumours, i.e. Melanocytic Naevi, Melanoma and Seborrheic Keratosis and performed a detailed analysis on its latent space. Two well established and publicly available skin disease datasets, PH2 and derm7pt, are used for experimentation. Human understandable concepts are mapped to RECOD image classification model with the help of Concept Activation Vectors (CAVs), introducing a novel training and significance testing paradigm for CAVs. Our results on an independent evaluation set clearly shows that the classifier learns and encodes human understandable concepts in its latent representation. Additionally, TCAV scores (Testing with CAVs) suggest that the neural network indeed makes use of disease-related concepts in the correct way when making predictions. We anticipate that this work can not only increase confidence of medical practitioners on CAD but also serve as a stepping stone for further development of CAV-based neural network interpretation methods., Accepted for the IEEE International Joint Conference on Neural Networks (IJCNN) 2020

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.

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.

Book covers usually provide a good depiction of a book’s content and its central idea. The classification of books in their respective genre usually involves subjectivity and contextuality. Book retrieval systems would utterly benefit from an automated framework that is able to classify a book’s genre based on an image, specifically for archival documents where digitization of the complete book for the purpose of indexing is an expensive task. While various modalities are available (e.g., cover, title, author, abstract), benchmarking the image-based classification systems based on minimal information is a particularly exciting field due to the recent advancements in the domain of image-based deep learning and its applicability. For that purpose, a natural question arises regarding the plausibility of solving the problem of book classification by only utilizing an image of its cover along with the current state-of-the-art deep learning models. To answer this question, this paper makes a three-fold contribution. First, the publicly available book cover dataset comprising of 57k book covers belonging to 30 different categories is thoroughly analyzed and corrected. Second, it benchmarks the performance on a battery of state-of-the-art image classification models for the task of book cover classification. Third, it uses explicit attention mechanisms to identify the regions that the network focused on in order to make the prediction. All of our evaluations were performed on a subset of the mentioned public book cover dataset. Analysis of the results revealed the inefficacy of the most powerful models for solving the classification task. With the obtained results, it is evident that significant efforts need to be devoted in order to solve this image-based classification task to a satisfactory level.

MicroRNAs are special RNA sequences containing 22 nucleotides and are capable of regulating almost 60% of highly complex mammalian transcriptome. Presently, there exists very limited approaches capable of visualizing miRNA locations inside cell to reveal the hidden pathways, and mechanisms behind miRNA functionality, transport, and biogenesis. State-of-the-art miRNA sub-cellular location prediction MIRLocatar approach makes use of sequence to sequence model along with pre-train k-mer embeddings. Existing pre-train k-mer embedding generation methodologies focus on the extraction of semantics of k-mers. In RNA sequences, rather than semantics, positional information of nucleotides is more important because distinct positions of four basic nucleotides actually define the functionality of RNA molecules. Considering the dynamicity and importance of nucleotides positions, instead of learning representation on the basis of k-mers semantics, we propose a novel kmerRP2vec feature representation approach that fuses positional information of k-mers to randomly initialized neural k-mer embeddings. Effectiveness of proposed feature representation approach is evaluated with two deep learning based convolutional neural network CNN and recurrent neural network RNN methodologies using 8 evaluation measures. Experimental results on a public benchmark miRNAsubloc dataset prove that proposed kmerRP2vec approach along with a simple CNN model outperforms state-of-the-art MirLocator approach with a significant margin of 18% and 19% in terms of precision and recall.

Knitted auxetic fabrics (AF) are in common practice but their stability and thickness are major problems in commercial applications. Therefore, a simple method of developing woven AF is proposed here. Differential shrinking property of different weaves is utilized to visualize auxetic honey comb geometry in fabric structure. Based on this fabric structure, auxeticity is induced in 2-D-woven fabric. AF is developed using conventional nonauxetic materials (i.e., cotton in warp and elastane [Lycra] yarn in the weft). Auxetic nature and auxetic structure in the fabric were characterized by microscope. Comfort properties (air permeability, thermal resistance, stiffness, and wicking) of AF were compared with conventional nonauxetic fabrics (NAF). Piezoresistive nature of conductive AF and NAF is also compared. AF showed superior comfort properties and higher sensitivity as compared to conventional NAF. Based on results, AF can be considered better replacement of conventional NAF in wearable and medical applications.

With the rise in the employment of deep learning methods in safety-critical scenarios, interpretability is more essential than ever before. Although many different directions regarding interpretability have been explored for visual modalities, time series data has been neglected, with only a handful of methods tested due to their poor intelligibility. We approach the problem of interpretability in a novel way by proposing TSInsight, where we attach an auto-encoder to the classifier with a sparsity-inducing norm on its output and fine-tune it based on the gradients from the classifier and a reconstruction penalty. TSInsight learns to preserve features that are important for prediction by the classifier and suppresses those that are irrelevant, i.e., serves as a feature attribution method to boost the interpretability. In contrast to most other attribution frameworks, TSInsight is capable of generating both instance-based and model-based explanations. We evaluated TSInsight along with nine other commonly used attribution methods on eight different time series datasets to validate its efficacy. The evaluation results show that TSInsight naturally achieves output space contraction, therefore, it is an effective tool for the interpretability of deep time series models.

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).

Identification of enhancers and their strength prediction plays an important role in gene expression regulation and currently an active area of research. However, its identification specifically through experimental approaches is extremely time consuming and labor-intensive task. Several machine learning methodologies have been proposed to accurately discriminate enhancers from regulatory elements and to estimate their strength. Existing approaches utilise different statistical measures for feature encoding which mainly capture residue specific physico-chemical properties upto certain extent but ignore semantic and positional information of residues. This paper presents “Enhancer-DSNet”, a two-layer precisely deep neural network which makes use of a novel k-mer based sequence representation scheme prepared by fusing associations between k-mer positions and sequence type. Proposed Enhancer-DSNet methodology is evaluated on a publicly available benchmark dataset and independent test set. Experimental results over benchmark independent test set indicate that proposed Enhancer-DSNet methodology outshines the performance of most recent predictor by the figure of 2%, 1%, 2%, and 5% in terms of accuracy, specificity, sensitivity and matthews correlation coefficient for enhancer identification task and by the figure of 15%, 21%, and 39% in terms of accuracy, specificity, and matthews correlation coefficient for strong/weak enhancer prediction task.

MicroRNAs (miRNA) are small noncoding RNA sequences consisting of about 22 nucleotides that are involved in the regulation of almost 60% of mammalian genes. Presently, there are very limited approaches for the visualization of miRNA locations present inside cells to support the elucidation of pathways and mechanisms behind miRNA function, transport, and biogenesis. MIRLocator, a state-of-the-art tool for the prediction of subcellular localization of miRNAs makes use of a sequence-to-sequence model along with pretrained k-mer embeddings. Existing pretrained k-mer embedding generation methodologies focus on the extraction of semantics of k-mers. However, in RNA sequences, positional information of nucleotides is more important because distinct positions of the four nucleotides define the function of an RNA molecule. Considering the importance of the nucleotide position, we propose a novel approach (kmerPR2vec) which is a fusion of positional information of k-mers with randomly initialized neural k-mer embeddings. In contrast to existing k-mer-based representation, the proposed kmerPR2vec representation is much more rich in terms of semantic information and has more discriminative power. Using novel kmerPR2vec representation, we further present an end-to-end system (MirLocPredictor) which couples the discriminative power of kmerPR2vec with Convolutional Neural Networks (CNNs) for miRNA subcellular location prediction. The effectiveness of the proposed kmerPR2vec approach is evaluated with deep learning-based topologies (i.e., Convolutional Neural Networks (CNN) and Recurrent Neural Network (RNN)) and by using 9 different evaluation measures. Analysis of the results reveals that MirLocPredictor outperform state-of-the-art methods with a significant margin of 18% and 19% in terms of precision and recall.

This paper introduces a novel approach to quantify the quality of human actions. The presented approach uses expert action data to define the space in order to gauge the performance of any user to identify expertise level. The proposed approach uses pose estimation model to identify different body attributes (legs, shoulders, head ...) status (left, right, bend, curl ...), which is further passed to autoencoder to have a latent representation encoding all the relevant information. This encoded representation is further passed to OneClass SVM to estimate the boundaries based on latent representation of expert data. These learned boundaries are used to gauge the quality of any questioned user with respect to the selected expert. The proposed approach enables identifying any critical situations in real work environment to avoid risky positions.

Document digitization is an active and important field of Machine Learning research that involves various Natural Language Processing tasks such as Optical Character Recognition and Machine Translation. One form of said digitization is the recognition and parsing of mathematical equations where structure, syntax, and smaller details are essential properties that must be preserved. More specifically, we focus this work around mathematical formula image to Latex generation, where we use input images of printed equations to predict the corresponding Latex code. We present an exploration of Deep Learning techniques that we believe could benefit existing state of the art models. We base our exploration on an attentional encoder-decoder architecture with a convolutional neural network to extract features from the input images. In our evaluations of the various modifications we also find and propose a model with two novel components, Max-Blur-Pooling and a Fine-Grained Feature map. Our proposed model outperforms state of the art models in all evaluation metrics.

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.

Visual artefacts of early diabetic retinopathy in retinal fundus images are usually small in size, inconspicuous, and scattered all over retina. Detecting diabetic retinopathy requires physicians to look at the whole image and fixate on some specific regions to locate potential biomarkers of the disease. Therefore, getting inspiration from ophthalmologist, we propose to combine coarse-grained classifiers that detect discriminating features from the whole images, with a recent breed of fine-grained classifiers that discover and pay particular attention to pathologically significant regions. To evaluate the performance of this proposed ensemble, we used publicly available EyePACS and Messidor datasets. Extensive experimentation for binary, ternary and quaternary classification shows that this ensemble largely outperforms individual image classifiers as well as most of the published works in most training setups for diabetic retinopathy detection. Furthermore, the performance of fine-grained classifiers is found notably superior than coarse-grained image classifiers encouraging the development of task-oriented fine-grained classifiers modelled after specialist ophthalmologists.

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).

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.