Pneumonia is a major cause of death among children below the age of 5 years, globally. It is especially prevalent in developing and underdeveloped nations where the risk factors for the disease such as unhygienic living conditions, high levels of pollution and overcrowding are higher. Radiological examination (usually X-ray scans) is conducted to detect pneumonia, yet it is prone to subjective variability and can lead to disagreements among different radiologists. To detect traces of pneumonia from X-ray images, a more robust method is therefore required, which can be achieved by using a computer-aided diagnosis (CAD) system. In this study, we develop a two-stage framework, using the combination of deep learning and optimization algorithms, which is both accurate and time-efficient. In its first stage, the proposed framework extracts feature using a customized deep learning model called DenseNet-201 following the concept of transfer learning to cope with the scanty available data. In the second stage, we then reduce the feature dimension using an improved sine cosine algorithm equipped with adaptive beta hill climbing-based local search algorithm. The optimized feature subset is utilized for the classification of “Pneumonia” and “Normal” X-ray images using a support vector machines classifier. Upon an evaluation on a publicly available data set, the proposed method demonstrates the highest accuracy of 98.36% and sensitivity of 98.79% with a feature reduction of 85.55% (74 features selected out of 512), using a five-fold cross-validation scheme. Extensive additional experiments on continuous benchmark functions as well as the CEC-2017 test suite further showcase the superiority and suitability of our proposed approach in application to real-valued optimization problems. The relevant codes for the proposed method can be found in https://github.com/soumitri2001/Pneumonia-Detection-Local-Search-aided-SCA.

Abstract Compared to other features of the human body, voice is quite complex and dynamic, in a sense that a speech can be spoken in various languages with different accents and in different emotional states. Recognizing the gender, i.e. male or female from the voice of an individual, is by all accounts a minor errand for human beings. Similar goes for speaker identification if we are well accustomed with the speaker for a long time. Our ears function as the front end, accepting the sound signs which our cerebrum processes and settles on our disposition. Although being trivial for us, it becomes a challenging task to mimic for any computing device. Automatic gender, emotion and speaker identification systems have many applications in surveillance, multimedia technology, robotics and social media. In this paper, we propose a Golden Ratio-aided Neural Network (GRaNN) architecture for the said purposes. As deciding the number of units for each layer in deep NN is a challenging issue, we have done this using the concept of Golden Ratio. Prior to that, an optimal subset of features are selected from the feature vector extracted, common for all three tasks, from spectral images obtained from the input voice signals. We have used a wrapper-filter framework where minimum redundancy maximum relevance selected features are fed to Mayfly algorithm combined with adaptive beta hill climbing (A $$\beta$$ β HC) algorithm. Our model achieves accuracies of 99.306% and 95.68% for gender identification in RAVDESS and Voice Gender datasets, 95.27% for emotion identification in RAVDESS dataset and 67.172% for speaker identification in RAVDESS dataset. Performance comparison of this model with existing models on the publicly available datasets confirms its superiority over those models. Results also ensure that we have chosen the common feature set meticulously, which works equally well on three different pattern classification tasks. The proposed wrapper-filter framework reduces the feature dimension significantly, thereby lessening the storage requirement and training time. Finally, strategically selecting the number units in each layer in NN help increases the overall performance of all three pattern classification tasks.

Handwritten script classification is still considered as a challenging research problem in the domain of document image analysis. Although some research attempts have been made by the researchers for solving the challenging issues, a comprehensive solution is yet to be achieved. The case study, undertaken here, analyzes the performances of various state-of-the art handwritten script classification methods for Indian scripts where features, needed for the script classification task, are extracted from the script images at four different granularity levels, i.e., page, block, text line, or word. The results of handwritten script classification at each level have been obtained and compared using eight different feature sets and six different state-of-the-art classifiers. Based on the classification results, an ideal level for performing the handwritten script classification task is suggested among these four classification levels. The results have also been improved by using two feature dimensionality reduction methods. All these experiments are done on two different handwritten Indic script databases, of which one is an in-house developed dataset and the other one is a freely available dataset. Finally, some future research directions that may be undertaken by the researchers as an application of the handwritten Indic script classification problem are also highlighted. The work presented here provides a basic foundation for the construction of a comprehensive handwritten script classification method for official Indian scripts.

Abstract Handwritten numeral recognition is a challenging research problem because of the enormous varieties of styles in which human beings write the numerals. Several researchers have tried to find solutions to this problem with exceptional recognition accuracies. However, most of these solutions have been dedicated to single script numerals. Such methods are inappropriate for multi‐lingual nations such as India where a large number of scripts are used. Keeping this issue in mind, a new feature descriptor named symbolization of binary images (SBI) is introduced here for the recognition of handwritten numerals of different scripts. Effectiveness of SBI is supported with experiments showing its script‐invariant nature. Classification of numerals using a multiclass support vector machine (SVM) classifier yields the recognition accuracies of 98.18, 96.22, 96.52, and 95.53% on datasets of numerals written in four popular scripts of the world: Arabic, Bangla, Devanagari, and Latin, respectively. This scheme has also been extended to the situation when the script used is not known a priori or the numerals written in a document belong to pairs of mixed scripts of {Arabic, Devanagari, Bangla} with Latin producing recognition rates of 92.97, 91.25, and 91.67%, respectively. When all four scripts are mixed, the recognition rate is still 90.98% overall. Encouraging outcomes suggest that the proposed SBI feature descriptor can recognize numerals invariant of the script class.

Action recognition based on skeleton key joints has gained popularity due to its cost effectiveness and low complexity. Existing Convolutional Neural Network (CNN) based models mostly fail to capture various aspects of the skeleton sequence. To this end, four feature representations, which capture complementary characteristics of the sequence of key joints, are extracted with novel contribution of features estimated from angular information, and kinematics of the human actions. Single channel grayscale images are used to encode these features for classification using four CNNs, with the complementary nature verified through Kullback-Leibler (KL) and Jensen-Shannon (JS) divergences. As opposed to straightforward classifier combination generally used in existing literature, fuzzy fusion through the Choquet integral leverages the degree of uncertainty of decision scores obtained from four CNNs. Experimental results support the efficacy of fuzzy combination of CNNs to adaptively generate final decision score based upon confidence of each information source. Impressive results on the challenging UTD-MHAD, HDM05, G3D, and NTU RGB+D 60 and 120 datasets demonstrate the effectiveness of the proposed method. The source code for our method is available at https://github.com/theavicaster/fuzzy-integral-cnn-fusion-3d-har

Abstract In India, which has numerous officially recognized scripts, there is a primary need for categorizing the documents on the basis of the scripts used therein. Identification of script used in a document is essential for its effective handling both manually and digitally. Identification of script in a document image is an important research problem in the pattern recognition field, which, at times, suffers from the issue of growing dimensionality of the feature vector and requires an efficient feature selection technique. Keeping this fact in mind, in this paper, we propose a clustering‐based filter feature selection framework in order to extract an optimal and effective feature subset from the original feature vector. The present feature selection methodology is evaluated on a script classification problem involving handwritten documents in 12 major Indic scripts. Experiments are done at word‐level, text‐line‐level, and block‐level. Experiments demonstrate that a reasonable increment in classification accuracy has been realized using comparatively lesser number of features. The proposed framework for feature selection is computationally inexpensive and can be applied to other pattern recognition problems as well.

Abstract Classifier combination methods have proved to be an effective tool to increase the performance of classification techniques that can be used in any pattern recognition applications. Despite a significant number of publications describing successful classifier combination implementations, the theoretical basis is still not matured enough and achieved improvements are inconsistent. In this paper, we propose a novel statistical validation technique known as correlation‐based classifier combination technique for combining classifier in any pattern recognition problem. This validation has significant influence on the performance of combinations, and their utilization is necessary for complete theoretical understanding of combination algorithms. The analysis presented is statistical in nature but promises to lead to a class of algorithms for rank‐based decision combination. The potentials of the theoretical and practical issues in implementation are illustrated by applying it on 2 standard datasets in pattern recognition domain,namely, handwritten digit recognition and letter image recognition datasets taken from UCI Machine Learning Database Repository ( http://www.ics.uci.edu/_mlearn ). An empirical evaluation using 8 well‐known distinct classifiers confirms the validity of our approach compared to some other combinations of multiple classifiers algorithms. Finally, we also suggest a methodology for determining the best mix of individual classifiers.

This article presents a set of novel features for robust online Bangla handwritten character recognition. Two feature extraction methods are presented here. The first describes the transition from background to foreground pixels and vice versa. The second uses a combination of topological features and centre-of-gravity- (CG) based circular features where global information, local information, and Circular Quadrant Mass Distribution information have been extracted. The impact of each along with their combination have also been analyzed. A total of 15,000 isolated online Bangla character samples have been collected and used for the evaluation. A Support Vector Machine classifier records the best recognition rate when the transition count feature, CG-based circular features, and topological features are combined.

Automatic script identification from handwritten document images facilitates many important applications such as indexing, sorting and triage. A given Optical Character Recognition (OCR) system is typically trained on only a single script but for documents or collections containing different scripts, there must be some way to automatically identify the script prior to OCR. For Indic script research, some results have been reported in the literature but the task is far from solved. In this paper, we propose a word-level script identification technique for six handwritten Indic scripts- Bangla, Devanagari, Gurumukhi, Malayalam, Oriya Telugu and the Roman script. A set of 82 features has been designed using a combination of elliptical and polygonal approximation techniques. Our approach has been evaluated on a dataset of 7000 handwritten text words, using multiple classifiers. A Multi-Layer Perceptron (MLP) classifier was found to be the best classifier resulting in 95.35% accuracy. The result is progressive considering the complexities and shape variations of the Indic scripts.