Browse Items (11855 total)
Sort by:
-
Data Augmentation for Handwritten Character Recognition of MODI Script Using Deep Learning Method
Deep learning-based methods such as convolutional neural networks are extensively used for various pattern recognition tasks. To successfully carry out these tasks, a large amount of training data is required. The scarcity of a large number of handwritten images is a major problem in handwritten character recognition; this problem can be tackled using data augmentation techniques. In this paper, we have proposed a convolutional neural network-based character recognition method for MODI script in which the data set is subjected to augmentation. The MODI script was an official script used to write Marathi, until 1950, the script is no more used as an official script. The preparation of a large number of handwritten characters is a tedious and time-consuming task. Data augmentation is very useful in such situations. Our study uses different types of augmentation techniques, such as on-the-fly (real-time) augmentation and off-line method (data set expansion method or traditional method). A performance comparison between these methods is also performed. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Convolutional Autoencoder Based Feature Extraction and KNN Classifier for Handwritten MODI Script Character Recognition
Character recognition is the process of identifying and classifying the images of printed or handwritten text and the conversion of that into machine-coded text. Deep learning techniques are efficiently used in the character recognition process. A Convolutional Autoencoder based technique for the character recognition of handwritten MODI script is proposed in this paper. MODI script was used for writing Marathi until the twentieth century. Though at present, Devnagari is taken over as the official script of Marathi, the historical importance of MODI script cannot be overlooked. MODI character recognition will not be an easy feat because of the various complexities of the script. Character recognition-related research of MODI script is in its initial stages. The proposed method is aimed to explore the use of a deep learning-based method for feature extraction and thereby building an efficient character recognition system for isolated handwritten MODI script. At the classification stage, the features extracted from the autoencoder are categorized using KNN classifier. Performance comparison of two different classifiers, such as KNN and SVM, is also carried out in this work. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
A Review of Various Line Segmentation Techniques Used in Handwritten Character Recognition
Segmentation is a very critical stage in the character recognition process as the performance of any character recognition system depends heavily on the accuracy of segmentation. Although segmentation is a well-researched area, segmentation of handwritten text is still difficult owing to several factors like skewed and overlapping lines, the presence of touching, broken and degraded characters, and variations in writing styles. Therefore, researchers in this area are working continuously to develop new techniques for the efficient segmentation and recognition of characters. In the character recognition process, segmentation can be implemented at the line, word, and character level. Text line segmentation is the first step in the text/character recognition process. The line segmentation methods used in the character recognition of handwritten documents are presented in this paper. The various levels of segmentation which include line, word, and character segmentation are discussed with a focus on line segmentation. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Efficient handwritten character recognition of modi script using wavelet transform and svd
MODI script has historical importance as it was used for writing the Marathi language, until 1950. Due to the complex nature of the script, the character recognition of MODI script is still in infancy. The implementation of more efficient methods at the various stages of the character recognition process will increase the accuracy of the process. In this paper, we present a hybrid method called WT-SVD (Wavelet Transform-Singular Value Decomposition), for the character recognition of MODI script. The WT-SVD method is a combination of singular value decomposition and wavelet transform, which is used for the feature extraction. Euclidean distance method is used for the classification. The experiment is conducted using Symlets and Biorthogonal wavelets, and the results are compared. The method using Biorthogonal wavelet feature extraction achieved the highest accuracy The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021. -
Machine Transliteration of Handwritten MODI Script to Devanagari using Deep Neural Networks
The transliteration process involves transcribing words from the source language into the target language that uses a different script. Language and scriptural hurdles can be overcome via transliteration systems. There is a demand for automated transliteration systems due to the existence of several languages and the growing number of multilingual speakers. This study focuses on the Machine Transliteration of handwritten MODI script to Devanagari. MODI script was the official script for Marathi till 1950. Although Devanagari has, since then, taken over as the Marathi languages official script, the MODI script has historical significance as large volumes of its manuscripts are preserved in libraries across different parts of India. However, MODI into Devanagari transliteration is a difficult task because MODI script documents are complex in nature and there is no standard dataset available for the experiment. Machine Transliteration can be approached either as a Natural Language Processing task or as a pattern recognition task. In this research work, the transliteration task is carried out using the pattern recognition technique. The transliteration of MODI script to Devanagari is implemented using Convolutional Recurrent Neural Network (CRNN) based Calamari OCR, which is open-source software. An accuracy of 88.14% is achieved in character level matching of each word in the MODI to Devanagari transliteration process. When considering the entire word matching, the accuracy achieved is 61%. Machine Transliteration of MODI script documents results in the retrieval of large repositories of knowledge from ancient MODI manuscripts. (2024), (Research Institute of Intelligent Computer Systems). All rights reserved. -
Ocr system framework for modi scripts using data augmentation and convolutional neural network
Character recognition is one of the most active research areas in the field of pattern recognition and machine intelligence. It is a technique of recognizing either printed or handwritten text from document images and converting it to a machine-readable form. Even though there is much advancement in the field of character recognition using machine learning techniques, recognition of handwritten MODI script, which is an ancient Indian script, is still in its infancy. It is due to the complex nature of the script that includes similar shapes of character and the absence of demarcation between words. MODI was an official language used to write Marathi. Deep learning-based models are very efficient in character recognition tasks and in this work an ACNN model is proposed using the on-the-fly data augmentation method and convolution neural network. The augmentation of the data will add variability and generalization to the data set. CNN has special convolution and pooling layers which have helped in better feature extraction of the characters. The performance of the proposed method is compared with the most accurate MODI character recognition method reported so far and it is found that the proposed method outperforms the other method. The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021. -
Play therapy as a rehabilitative measure among child survivors of bonded labour
A bonded labour condition is customarily because of relocation of persons due to the situations that are obligatory in nature. Bonded labour, which is characterized by a long-term affiliation between employer and employee, is usually congealed over a loan, and is entrenched complexly in India’s socio-economic culture - a culture that is a creation of class relations, a colonial history, and tenacious scarcity of resources among many citizens. The children living in such conditions face a lot of mistreatment and go through undeniable exploitation. The children present at the facility may or may not work with the parents yet go through a lot of pain, distress and abuse as the journey of cruelty and suffering is just the same as what their parent’s ordeal with. Children as young as 4 Years old are molested, beaten and abused on an average basis traumatizing the children before and after the rescue. These children are not permitted to enroll in schools as they do not have identity proofs or birth certificates. The only way of addressing the subject of emotional, physical and mental turbulence of the child in this perimeter is by enforcing play as a rehabilitative measure to help with past experiences and impending consequences. Play is essential to development because it contributes to the cognitive, physical, social, and emotional well-being of children and youth. Play also offers an ideal opportunity for parents or facilitators to engage fully with the children. Play allows children to use their creativity while developing their imagination, dexterity, and physical, cognitive, and emotional strength. When forms of play like puppetry, art, story-telling etc are added the child conjectures unpleasant feelings which she cannot hide the child is better able to act differently in relation to what he/she is feeling. The study aims to see if play therapy is a technique of rehabilitating child survivors of bonded labour. -
Predicting Stock Market Trends: Machine Learning Approaches of a Possible Uptrend or Downtrend
This paper delves into a statistical analysis of the stock market, emphasizing the significance of accuracy in stock predictions. Large data sets can be handled by machine learning algorithms, which can also forecast outcomes based on past data and spot intricate patterns in financial data. They assist control risks, automate decision-making procedures, and adjust to changing circumstances. Multi-source data can be combined by ML models to provide a comprehensive picture of market circumstances. They can manage intricate, nonlinear interactions, provide impartial analysis, and lessen human bias. Models are able to adjust to shifting market conditions through ongoing learning and retraining. They must, however, exercise caution when deploying models in real-world situations and ensure that they are validated. Although machine learning has advantages for stock market analysis, it must be carefully evaluated for dangers and validated before being used in practical situations. The traditional machine learning model, Logistic Regression has been used in order to predict stock prices. It focuses on binary classification based on the trend of the stock. Through the model training and evaluation and additional analysis done on the results, this research contributes towards obtaining predictions and studying reasons of a possible uptrend or downtrend to further assist companies. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. -
Curvit: An open-source Python package to generate light curves from UVIT data
Curvit is an open-source Python package that facilitates the creation of light curves from the data collected by the Ultra-Violet Imaging Telescope (UVIT) onboard AstroSat, Indias first multi-wavelength astronomical satellite. The input to Curvit is the calibrated events list generated by the UVIT-Payload Operation Center (UVIT-POC) and made available to the principal investigators through the Indian Space Science Data Center. The features of Curvit include: (i) automatically detecting sources and generating light curves for all the detected sources and (ii) custom generation of light curve for any particular source of interest. We present here the capabilities of Curvit and demonstrate its usability on the UVIT observations of the intermediate polar FO Aqr as an example. Curvit is publicly available on GitHub at https://github.com/prajwel/curvit. 2021, Indian Academy of Sciences. -
UVIT view of Centaurus A: A detailed study on positive AGN feedback
Supermassive black holes at the centre of active galactic nuclei (AGNs) produce relativistic jets that can affect the star formation characteristics of the AGN hosts. Observations in the ultraviolet (UV) band can provide an excellent view of the effect of AGN jets on star formation. Here, we present a census of star formation properties in the Northern Star-forming Region (NSR) that spans about 20 kpc of the large radio source Centaurus A hosted by the giant elliptical galaxy NGC 5128. In this region, we identified 352 UV sources associated with Cen A using new observations at an angular resolution of <1.5 arcsec observed with the Ultra-Violet Imaging Telescope (UVIT) onboard AstroSat. These observations were carried out in one far-ultraviolet (FUV; ?mean = 1481 and three near-ultraviolet (NUV; with ?mean of 2196, 2447, and 2792 respectively) bands. The star-forming sources identified in UV tend to lie in the direction of the jet of Cen A, thereby suggesting jet triggering of star formation. Separating the NSR into Outer and Inner regions, we found the stars in the Inner region to have a relatively younger age than the Outer region, suggesting that the two regions may have different star formation histories. We also provide the UVIT source catalogue in the NSR. 2022 The Author(s) Published by Oxford University Press on behalf of Royal Astronomical Society. -
Active galactic nucleus feedback in NGC 3982
The energetic feedback from supermassive black holes can influence star formation at the centres of galaxies. Observational evidence for active galactic nucleus (AGN) impact on star formation can be searched for in galaxies by combining ultraviolet imaging and optical integral field unit data. The ultraviolet flux directly traces recent star formation, and the integral field unit data can reveal dust attenuation, gas ionisation mechanisms, and gas kinematics from the central regions of the galaxy disk. A pilot study on NGC 3982 shows star formation suppression in the central regions of the galaxy, likely due to negative AGN feedback, and enhanced star formation in the outer regions. The case of NGC 3982 could be observational evidence of AGN feedback operating in a Seyfert galaxy. 2022 EDP Sciences. All rights reserved. -
Exploring the agency of policy through ecological urbanism for climate action: water and sanitation systems of Bengaluru
The cities of the world have been the exploiters of resources and the largest generators of waste. This paper explores the concept of Ecological Urbanism as a framework to convert cities from being waste generators to resource producers. The example of the wastewater from Bengaluru going into the lakes of Kolar is studied. The treated wastewater of the city reaches Kolar to fill its lakes, which subsequently recharges the groundwater. One citys waste becomes anothers resource in this process. The case of Kolar-Bengaluru is studied while asking critical questions of urban-rural planning with ecology as a main premise. 2022 Informa UK Limited, trading as Taylor & Francis Group. -
Rupturing Terracotta: Entangled Exchanges of the Hand and the Machine in South India
Through an examination of changing methods for making and using terracotta tile and brick this article explores the complex hybridity and productive tensions that emerged in the nineteenth century between indigenous and colonial systems of architecture and construction in South India. Outlining a general shift from handmade to mechanized processes, it further argues that a decolonial reading may provide a fruitful new approach to comprehending architectural history on the subcontinent. The article brings to the forefront how the indigenous-colonial encounter caused a rupture in the making of buildings that complicated the language and processes of architecture and construction in India forever. 2023, International Association for the Study of Traditional Environments (IASTE). All rights reserved. -
Polymer-Carbon nanocomposite: Synthesis, optical and biocidal properties
Microorganism contamination of food storage, water treatment, pharmaceuticals, and especially biomedical equipment is a severe problem. Bacteria frequently contaminate permanent implantations after long-term usage. To successfully treat these infections, it is essential to monitor microbial activity and know how it interacts with antibodies in real-time. In this work, a nanocarbon-polymer nanocomposite (ARPD) is successfully developed, and its antibacterial activity against selected microorganisms is successfully validated. Obtained antibacterial results confirm that the photoluminescent ARPD demonstrated outstanding antibacterial action against the microorganism Escherichia coli from the selected group of bacteria. The fluorescent diagnostics and treatments offer exciting possibilities for the luminescence and biocidal activity of nanocomposite produced from ARH-PVDF nanomaterials. 2023 The Author(s) -
Green Synthesized Fluorescent Nano-Carbon derived from Indigofera Tinctora (L.) leaf extract for sensing of Pb2+ ions
Plant-based synthesis of nanomaterials is a more reliable method since it is easy, quick, and environmentally friendly, and it does not require any specific conditions, unlike other methods. For the first time, we report the sensing of metal ions using a fluorescent nano-carbon material via a plant-based synthesis from the medicinal plant, Indigofera Tinctora (L.) (IBLH). This nanomaterial from the leaf extract of IBLH was synthesized by hydrothermal assisted green synthesis method. The as-synthesized sample was characterized by various spectroscopic techniques for confirming the formation of nano-carbon material. Optical studies revealed that IBLH was influential in determining toxic heavy metal ions (Pb2+). Detection of Pb2+ was observed from a range of 1 Molar to as low as 1Nano-Molar using IBLH as the probe. Stern-Volmer plot exhibits the progressive detection of the metal ion, proving that the IBLH nano-carbon material is capable of progressive sensing of various heavy metal ions. The Electrochemical Society -
Nanomaterials-Based Chemical Sensing
Nanotechnology is an achievement in the modern period because of its adaptable properties as per its size alterations. Nanomaterials with their size ranging from 1 to 100nm hold incredible novel properties and functionalities because of their molecular arrangements in nano-scale. Nanotechnologies add to pretty much every field of science, including material science, materials chemistry, physics, biology, software and computational engineering and so on. Lately, nanotechnology has been applied to different fields with promising outcomes, particularly in the field of detecting and remediation of toxicity levels, imperilling the ecological solidness just as it does to human wellbeing. One of the principal research interests using nanomaterials is detecting poisonous heavy metal ions. Carbon-based nanomaterials, which are remarkable in view of their toxic-free nature, high surface area and biocompatibility, are valuable for ecological treatments. Heavy metal pollution of water resources is a major issue that poses danger to health and wellbeing. Carbon-based nanomaterials have incredible potential for the detection as well as treatment of heavy metals from water sources in light of their large surface area, nano-scale and accessibility towards various functionalities as they are simpler to be chemically altered and hence reused. Apart from the conventional gas sensors based on SnO2, Fe2O3, In2O3 etc., gas sensors based on nanocarbons materials like carbon nanotubes (CNTs), nanosheets of graphene, carbon nano-fibres etc. exhibit high efficacy when it comes to gas-sensing strategy. Likewise, nanocarbon with hybrids of noble metals or semiconducting oxides can lead to a better performance considering gas-sensing applications. Here in this review, we describe the progress of carbon-based nanomaterials in toxicity detection and remediation. In addition to that, recent trends in nanomaterials-based sensing revealed the advancement of gas sensors based on nanocarbons. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Development of Green Synthesized Novel Carbon Dots from Ruta Graveolens L. for Fluorescent and Intracellular Sensing of Mercury Ions in Pico-molar (pm) Concentration
Green nanotechnology, which uses carbon nanomaterials for environmental remediation, is the pioneer among the prevailing approaches for the production and characterization. In the present study, highly fluorescent carbon dots (CDs) from Ruta Graveolens (ARH-CD) is developed, and its efficacy as a fluorescent sensor and biomarker is investigated. They act as a fluorescence sensor for Hg2+ over an extensive concentration range of 1 picomolar (pm) to 1 molar (m), with a detection limit as low as 26.75 pm. The studies reveal ARH-CD as an effective biomarker for intracellular toxicity analysis and a fluorescent probe for multi-colored (blue, green, and red) imaging of HEK293 cell lines. After 24 h of incubation, it is found that the ARH material reveals noticeable biocompatibility and visible fluorescence, with a viability of 98.88% at 5 gmL?1 and over 78.33% even at a concentration of 100 gmL?1. The IC50 value for the MTT assay for cell viability results is calculated to be 224.56 4.67 g, which further confirms the appreciable biocompatibility of the ARH-CD. The obtained samples are effective in being inspected for the intracellular detection of Hg2+ and serve as a possible candidate for cell imaging. 2024 Wiley-VCH GmbH. -
Recent advances in cancer nanotheranostics
The innovative synthetic approaches coupled with bioengineering aptitude created multiple functional materials in the nanoscale dimension aiming for a combination of therapeutic and diagnostic capacities, often referred to as nanotheranostics. The diverse role played by nanomaterials has been broadly examined in biomedicine, especially in the disciplines of imaging and drug delivery. In this view, cancer is an intimidating foe to the entire human species by adopting various survival skills. Conventional therapies remain to be a failure in meeting the anticipations of the entire medical community. Stepping to the emphasis on cancer nanotheranostics, which requires more advancement to amalgamate and fine-tune diagnosis and therapy, has already attracted significant research interest among researchers in chemistry, material science, life science, and clinicians. Monitoring the therapeutic response in a real-time manner with the intelligent fabrication of nanotheranostic agents could strike down the daunting claws of cancer by facilitating personalized treatment approaches. Here, we aimed to portrait the key approaches and recent developments in nanotheranostics with a focus on its clinical impact in oncology. 2024 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies. -
Emerging Novel Functional Materials from Biomass for Environmental Remediation
The Earth faces complex environmental challenges caused by both human activities and natural processes, affecting all life forms and ecosystems. Biomass-derived materials, sourced from renewable resources, serve as effective adsorbents, catalysts, and ion exchangers, providing sustainable solutions to environmental issues like water and air pollution, soil contamination, and waste management. Their significance lies not only in their biodegradability and sustainability but also in standardized testing and scalability considerations. The field of functional materials from biomass has the potential to transform environmental remediation, leading to a cleaner and more sustainable world. Here, we aimed to portrait the key approaches and recent developments in emerging functional materials from biomass tailored for environmental remediation, delving into their fundamental theories and concepts, various applications, and potential to reshape the remediation landscape. It evaluates the sustainability and biodegradability aspects of these materials, addresses challenges, and peers into the dynamic and rapidly evolving future of this field. Collaborative efforts between researchers, industry, and policymakers are pivotal to establishing guidelines and regulations ensuring the safe and responsible use of these materials. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
New bounds of induced acyclic graphoidal decomposition number of a graph
An induced acyclic graphoidal decomposition (IAGD) of a graph G is a collection ? of nontrivial induced paths in G such that every edge of G lies in exactly one path of ? and no two paths in ? have a common internal vertex. The minimum cardinality of an IAGD of G is called the induced acyclic graphoidal decomposition number denoted by ? ia (G). In this paper we present bounds for ? ia (G) in terms of cut vertices and simplicial vertices of G. Springer Nature Switzerland AG 2019.