A deep learning approach for Named Entity Recognition in Urdu language.

Named Entity Recognition (NER) is a natural language processing task that has been widely explored for different languages in the recent decade but is still an under-researched area for the Urdu language due to its rich morphology and language complexities. Existing state-of-the-art studies on Urdu NER use various deep-learning approaches through automatic feature selection using word embeddings. This paper presents a deep learning approach for Urdu NER that harnesses FastText and Floret word embeddings to capture the contextual information of words by considering the surrounding context of words for improved feature extraction. The pre-trained FastText and Floret word embeddings are publicly available for Urdu language which are utilized to generate feature vectors of four benchmark Urdu language datasets. These features are then used as input to train various combinations of Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), CRF, and deep learning models. The results show that our proposed approach significantly outperforms existing state-of-the-art studies on Urdu NER, achieving an F-score of up to 0.98 when using BiLSTM+GRU with Floret embeddings. Error analysis shows a low classification error rate ranging from 1.24% to 3.63% across various datasets showing the robustness of the proposed approach. The performance comparison shows that the proposed approach significantly outperforms similar existing studies.

Lightweight ResGRU: a deep learning-based prediction of SARS-CoV-2 (COVID-19) and its severity classification using multimodal chest radiography images.

The new COVID-19 emerged in a town in China named Wuhan in December 2019, and since then, this deadly virus has infected 324 million people worldwide and caused 5.53 million deaths by January 2022. Because of the rapid spread of this pandemic, different countries are facing the problem of a shortage of resources, such as medical test kits and ventilators, as the number of cases increased uncontrollably. Therefore, developing a readily available, low-priced, and automated approach for COVID-19 identification is the need of the hour. The proposed study uses chest radiography images (CRIs) such as X-rays and computed tomography (CTs) to detect chest infections, as these modalities contain important information about chest infections. This research introduces a novel hybrid deep learning model named Lightweight ResGRU that uses residual blocks and a bidirectional gated recurrent unit to diagnose non-COVID and COVID-19 infections using pre-processed CRIs. Lightweight ResGRU is used for multi-modal two-class classification (normal and COVID-19), three-class classification (normal, COVID-19, and viral pneumonia), four-class classification (normal, COVID-19, viral pneumonia, and bacterial pneumonia), and COVID-19 severity types' classification (i.e., atypical appearance, indeterminate appearance, typical appearance, and negative for pneumonia). The proposed architecture achieved f-measure of 99.0%, 98.4%, 91.0%, and 80.5% for two-class, three-class, four-class, and COVID-19 severity level classifications, respectively, on unseen data. A large dataset is created by combining and changing different publicly available datasets. The results prove that radiologists can adopt this method to screen chest infections where test kits are limited.

Efficient anomaly recognition using surveillance videos.

Smart surveillance is a difficult task that is gaining popularity due to its direct link to human safety. Today, many indoor and outdoor surveillance systems are in use at public places and smart cities. Because these systems are expensive to deploy, these are out of reach for the vast majority of the public and private sectors. Due to the lack of a precise definition of an anomaly, automated surveillance is a challenging task, especially when large amounts of data, such as 24/7 CCTV footage, must be processed. When implementing such systems in real-time environments, the high computational resource requirements for automated surveillance becomes a major bottleneck. Another challenge is to recognize anomalies accurately as achieving high accuracy while reducing computational cost is more challenging. To address these challenge, this research is based on the developing a system that is both efficient and cost effective. Although 3D convolutional neural networks have proven to be accurate, they are prohibitively expensive for practical use, particularly in real-time surveillance. In this article, we present two contributions: a resource-efficient framework for anomaly recognition problems and two-class and multi-class anomaly recognition on spatially augmented surveillance videos. This research aims to address the problem of computation overhead while maintaining recognition accuracy. The proposed Temporal based Anomaly Recognizer (TAR) framework combines a partial shift strategy with a 2D convolutional architecture-based model, namely MobileNetV2. Extensive experiments were carried out to evaluate the model's performance on the UCF Crime dataset, with MobileNetV2 as the baseline architecture; it achieved an accuracy of 88% which is 2.47% increased performance than available state-of-the-art. The proposed framework achieves 52.7% accuracy for multiclass anomaly recognition on the UCF Crime2Local dataset. The proposed model has been tested in real-time camera stream settings and can handle six streams simultaneously without the need for additional resources.

A New Sequential Forward Feature Selection (SFFS) Algorithm for Mining Best Topological and Biological Features to Predict Protein Complexes from Protein-Protein Interaction Networks (PPINs).

Protein-protein interaction plays an important role in the understanding of biological processes in the body. A network of dynamic protein complexes within a cell that regulates most biological processes is known as a protein-protein interaction network (PPIN). Complex prediction from PPINs is a challenging task. Most of the previous computation approaches mine cliques, stars, linear and hybrid structures as complexes from PPINs by considering topological features and fewer of them focus on important biological information contained within protein amino acid sequence. In this study, we have computed a wide variety of topological features and integrate them with biological features computed from protein amino acid sequence such as bag of words, physicochemical and spectral domain features. We propose a new Sequential Forward Feature Selection (SFFS) algorithm, i.e., random forest-based Boruta feature selection for selecting the best features from computed large feature set. Decision tree, linear discriminant analysis and gradient boosting classifiers are used as learners. We have conducted experiments by considering two reference protein complex datasets of yeast, i.e., CYC2008 and MIPS. Human and mouse complex information is taken from CORUM 3.0 dataset. Protein interaction information is extracted from the database of interacting proteins (DIP). Our proposed SFFS, i.e., random forest-based Brouta feature selection in combination with decision trees, linear discriminant analysis and Gradient Boosting Classifiers outperforms other state of art algorithms by achieving precision, recall and F-measure rates, i.e. 94.58%, 94.92% and 94.45% for MIPS, 96.31%, 93.55% and 96.02% for CYC2008, 98.84%, 98.00%, 98.87 % for CORUM humans and 96.60%, 96.70%, 96.32% for CORUM mouse dataset complexes, respectively.

Coronavirus (COVID-19) detection from chest radiology images using convolutional neural networks.

Coronavirus disease (Covid-19) has been spreading all over the world and its diagnosis is attracting more research every moment. It is need of the hour to develop automated methods, which could detect this disease at its early stage, in a non-invasive way and within lesser time. Currently, medical specialists are analyzing Computed Tomography (CT), X-Ray, and Ultrasound (US) images or conducting Polymerase Chain Reaction (PCR) for its confirmation on manual basis. In Pakistan, CT scanners are available in most hospitals at district level, while X-Ray machines are available in all tehsil (large urban towns) level hospitals. Being widely used imaging modalities to analyze chest related diseases, produce large volume of medical data each moment clinical environments. Since automatic, time efficient and reliable methods for Covid-19 detection are required as alternate methods, therefore an automatic method of Covid-19 detection using Convolutional Neural Networks (CNN) has been proposed. Three publically available and a locally developed dataset, obtained from Department of Radiology (Diagnostics), Bahawal Victoria Hospital, Bahawalpur (BVHB), Pakistan have been used. The proposed method achieved on average accuracy (96.68 %), specificity (95.65 %), and sensitivity (96.24 %). Proposed model is trained on a large dataset and is being used at the Radiology Department, (BVHB), Pakistan.

Skin Disease Classification using Neural Network.

BACKGROUND: In this study, a novel and fully automatic skin disease classification approach is proposed using statistical feature extraction and Artificial Neural Network (ANN) based classification using first and second order statistical moments, the entropy of different color channels and texture-based features. AIMS: The basic aim of our study is to develop an automated system for skin disease classification that can help a general physician to automatically detect the lesion and classify it to disease types. METHOD: The performance of the proposed approach is corroborated by extensive experiments performed on a dataset of 588 images containing 6907 lesion regions. RESULTS: The results show that the proposed methodology can be effectively used to construct a skin disease classification system. CONCLUSION: Our proposed method is designed for a specific skin tone. Future investigation is needed to analyze the impact of different skin tones on the performance of lesions detection and classification system.

Facial Asymmetry-Based Age Group Estimation: Role in Recognizing Age-Separated Face Images.

Face recognition aims to establish the identity of a person based on facial characteristics. On the other hand, age group estimation is the automatic calculation of an individual's age range based on facial features. Recognizing age-separated face images is still a challenging research problem due to complex aging processes involving different types of facial tissues, skin, fat, muscles, and bones. Certain holistic and local facial features are used to recognize age-separated face images. However, most of the existing methods recognize face images without incorporating the knowledge learned from age group estimation. In this paper, we propose an age-assisted face recognition approach to handle aging variations. Inspired by the observation that facial asymmetry is an age-dependent intrinsic facial feature, we first use asymmetric facial dimensions to estimate the age group of a given face image. Deeply learned asymmetric facial features are then extracted for face recognition using a deep convolutional neural network (dCNN). Finally, we integrate the knowledge learned from the age group estimation into the face recognition algorithm using the same dCNN. This integration results in a significant improvement in the overall performance compared to using the face recognition algorithm alone. The experimental results on two large facial aging datasets, the MORPH and FERET sets, show that the proposed age group estimation based on the face recognition approach yields superior performance compared to some existing state-of-the-art methods.

In vitro Salmonella typhi biofilm formation on gallstones and its disruption by Manuka honey.

Biofilm is a complex community of single or different types of microorganisms (bacteria, viruses, fungi, protozoa) attached to a surface and stick to each other through production of extracellular matrix. Salmonella typhi forms biofilm on cholesterol gallstones resulting in carrier state. Once formed, biofilm is difficult to treat. To date cholecystectomy is the only cure for this condition. Manuka honey is known to have tremendous antibiofilm activity against various organisms. S. typhi biofilm was grown in vitro on clinical samples of human cholesterol gallstones by Gallstone tube assay method for 12 days. Biofilm mass was quantified on day 1, 5, 7, 9 and 12 by crystal violet assay and was also examined by scanning electron microscope. Three concentrations w/v of Manuka honey (40%, 60% and 80%) were used, each one at 24, 48 and 72 hours. The most effective concentration (80% w/v) was repeated on two sets of gallstones. Biofilm mass was re quantified by crystal violet assay and was examined by scanning electron microscope. S. typhi formed uniform biofilm on cholesterol gallstone surface. The optical density measurements exhibited a rising pattern with time thereby indicating an increase in biofilm mass. It was 0.2 on day 1 and 0.9 on day 12. With 80% w/v Manuka honey, biofilm mass decreased most effectively with 0.5 OD after 72 hours. Biofilm formation by S, typhi on gallstones is surface specific and bile dependant. Either increasing the duration (beyond 72 hours) of the effective concentration (80% w/v) of honey or increasing the concentration (above 80%) of honey for a specific duration (72 hour) may cause complete disruption of the S. typhi biofilm on gallstone. S. typhi forms biofilm on cholesterol gallstones surface in vitro and it can be visualized by scanning electron microscopy. Biofilm mass can be quantified using crystal violet assay. Among various concentrations 80% Manuka honey for 72 hours is most effective in disrupting S. typhi biofilm on gallstones in vitro as evident from crystal violet assay.

Bilateral symmetry detection on the basis of Scale Invariant Feature Transform.

The automatic detection of bilateral symmetry is a challenging task in computer vision and pattern recognition. This paper presents an approach for the detection of bilateral symmetry in digital single object images. Our method relies on the extraction of Scale Invariant Feature Transform (SIFT) based feature points, which serves as the basis for the ascertainment of the centroid of the object; the latter being the origin under the Cartesian coordinate system to be converted to the polar coordinate system in order to facilitate the selection symmetric coordinate pairs. This is followed by comparing the gradient magnitude and orientation of the corresponding points to evaluate the amount of symmetry exhibited by each pair of points. The experimental results show that our approach draw the symmetry line accurately, provided that the observed centroid point is true.

Mapping urban and peri-urban breeding habitats of Aedes mosquitoes using a fuzzy analytical hierarchical process based on climatic and physical parameters.

The spread of dengue fever depends mainly on the availability of favourable breeding sites for its mosquito vectors around human dwellings. To investigate if the various factors influencing breeding habitats can be mapped from space, dengue indices, such as the container index, the house index and the Breteau index, were calculated from Ministry of Public health data collected three times annually in Phitsanulok, Thailand between 2009 and 2011. The most influential factors were found to be temperature, humidity, rainfall, population density, elevation and land cover. Models were worked out using parameters mostly derived from freely available satellite images and fuzzy logic software with parameter synchronisation and a predication algorithm based on data mining and the Decision Tree method. The models developed were found to be sufficiently flexible to accommodate additional parameters and sampling data that might improve prediction of favourable breeding hotspots. The algorithm applied can not only be used for the prediction of near real-time scenarios with respect to dengue, but can also be applied for monitoring other diseases influenced by environmental and climatic factors. The multi-criteria model presented is a cost-effective way of identifying outbreak hotspots and early warning systems lend themselves for development based on this strategy. The proposed approach demonstrates the successful utilisation of remotely sensed images to map mosquito breeding habitats.

Morpheme matching based text tokenization for a scarce resourced language.

Text tokenization is a fundamental pre-processing step for almost all the information processing applications. This task is nontrivial for the scarce resourced languages such as Urdu, as there is inconsistent use of space between words. In this paper a morpheme matching based approach has been proposed for Urdu text tokenization, along with some other algorithms to solve the additional issues of boundary detection of compound words, affixation, reduplication, names and abbreviations. This study resulted into 97.28% precision, 93.71% recall, and 95.46% F1-measure; while tokenizing a corpus of 57000 words by using a morpheme list with 6400 entries.

A multifaceted independent performance analysis of facial subspace recognition algorithms.

Face recognition has emerged as the fastest growing biometric technology and has expanded a lot in the last few years. Many new algorithms and commercial systems have been proposed and developed. Most of them use Principal Component Analysis (PCA) as a base for their techniques. Different and even conflicting results have been reported by researchers comparing these algorithms. The purpose of this study is to have an independent comparative analysis considering both performance and computational complexity of six appearance based face recognition algorithms namely PCA, 2DPCA, A2DPCA, (2D)(2)PCA, LPP and 2DLPP under equal working conditions. This study was motivated due to the lack of unbiased comprehensive comparative analysis of some recent subspace methods with diverse distance metric combinations. For comparison with other studies, FERET, ORL and YALE databases have been used with evaluation criteria as of FERET evaluations which closely simulate real life scenarios. A comparison of results with previous studies is performed and anomalies are reported. An important contribution of this study is that it presents the suitable performance conditions for each of the algorithms under consideration.