Browse Items (16488 total)
Sort by:
-
Disease Identification from Illegible Medical Prescriptions Using OCR and NLP Techniques
Medical prescriptions that are challenging to interpret present significant issues for the healthcare industry because they increase the possibility of errors in patient care and medication administration. This study presents an efficient workflow that uses Optical Character Recognition (OCR) technology, specifically, Tesseract OCR, along with a preprocessing step to extract text from handwritten prescriptions. The preprocessing stage uses grayscale conversion, noise reduction, and contrast enhancement to increase the accuracy of OCR. Significant results from experiments on a publicly accessible dataset show that preprocessing greatly improves performance, lowering the error rate from 34.7 to 18.3% and raising average accuracy from 65.3 to 81.7%. The enhanced accuracy outweighs the modest increase in processing time (from 0.8 to 1.2s), emphasizing the potential of using these techniques in practical healthcare applications. The studys findings also demonstrated the successful analysis of the text using Natural Language Processing (NLP) and Clinical Bidirectional Encoder Representations from Transformers (ClinicalBERT) techniques by identifying four distinct diseases, Common Cold, Diabetes Mellitus, Bronchitis, and disease caused by Anemia, as validated by a medical professional. This demonstrates the systems potential to improve health care processes by automatically digitizing handwritten prescriptions. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026. -
Disease Identification for Tea Leaves Using Explainable Artificial Intelligence
Infection can consequently reduce both quality and yield, and causes major threats to tea production round the world. It is therefore sometime difficult to achieve fast, reliable, and precise identification of disease in tea plants and hence the need to embrace new methods of disease identification. To enable realisation of accurately understandable models for classification of the diseases in tea leaves, Explainable Artificial Intelligence (XAI) approaches are applied in this work. In order to train and test machine learning models, we collected a set of repos of high-resolution images of tea leaves affected by various diseases along with meta information. CNN models were trained with the help of our approach and adopting XAI tools as tools for explanation of predictions. From this study, the field of agricultural AI is benefitted from the illustration of how XAI might enhance disease management strategies in tea agriculture. The results demonstrate an accuracy of 87.85%, with precision, recall and F1-scores ranging between 0.78 and 0.95 across different classes. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Discussion on ostracised transgender individuals and entrepreneurship through review of literature
Transgender individuals are the most deteriorated individuals in society. They face a wide range of trodden lives and setbacks in their everyday life. They encounter challenges and difficulties from the time they violate the social norms, they are also humiliated from their biological families and are sent to live a life of their own. In India, the Mughal period was termed to be the golden years for transgender individuals. It was after colonisation and implementation of the Criminal Tribes Act 1871 transgender individuals were treated brutally and eventually begging and sex work became their only source of income. Alongside, entrepreneurship proved to be a success factor as it brought the shunned women into the mainstream society. Thereby, entrepreneurship increases social capital and thus encourages transgenders in job creation activities. Despite a dire situation, there are transgender individuals who have faced all odds and have proved to set benchmarks in the society in varied fields. There are sporadic transgender individual entrepreneurs in the country who have paved their way into the entrepreneurial world, which is an important area to be explored. The study focuses on literature relating to transgender individuals, challenges faced by transgender individuals, entrepreneurial motivations and also transgender entrepreneurs. 2020 SERSC. -
Discriminative Gait Features Based on Signal Properties of Silhouette Centroids
Among the biometric recognition systems, gait recognition plays an important role due to its attractive advantages over other biometric systems. One of the crucial tasks in gait recognition research is the extraction of discriminative features. In this paper, a novel and efficient discriminative feature vector using the signal characteristics of motion of centroids across video frames is proposed. These centroid based features are obtained from the upper and lower regions of the gait silhouette frames in a gait cycle. Since gait cycle contains the sequence of motion pattern and this pattern possesses uniqueness over individuals, extracting the centroid features can better represent the dynamic variations. These variations can be viewed as a signal and therefore the signal properties obtained from the centroid features contains more discriminant information of an individual. Experiments are carried out with CASIA gait dataset B and the proposed feature achieves 97.3% of accuracy using SVM classifier. 2019, Springer Nature Singapore Pte Ltd. -
Discrimination Experiences of Old Settlers in Sikkim: A Qualitative Exploration
Race-based stigma and discrimination have been extensively studied from the perspective of the northeastern community due to their minority status in most states of India. Discrimination experiences of the mainland Indians in the northeastern states, where they are a minority, are little discussed. The Rajya Sabha (upper house of the parliament) Committee of Petitions in 2014 acknowledged that the old settlers were treated as second-class citizens in Sikkim. In the present study, we explored the existence and manifestation of discrimination experiences of old settlers who settled in Sikkim before 1975 and perceive themselves to be stigmatized. This study focused on Sikkim because the state merged with India in 1975 and has had less time integrating with migrants or mainlanders than other northeastern states. We conducted nine semi-structured interviews with seven male and two female participants from the Marwari, Bihari, and Punjabi mainland communities. Using thematic analysis, we developed 1 global theme, 2 organizing themes, and 24 basic themes. The analysis showed the existence of discrimination and racism against old settlers and their manifestations at institutional and interpersonal levels. The findings are important from a policymaking perspective as they provide evidence to the conclusion reached by the Rajya Sabha Committee on Petitions and provide valued suggestions for reports on race-based discrimination in India. The Author(s) under exclusive licence to National Academy of Psychology (NAOP) India 2023. -
Discrimination between scheduled and non-scheduled groups in access to basic services in urban India
Access to basic services such as water, sanitation, and electricity is a key determinant of an individuals well-being. Nevertheless, access to these services is unequally distributed among different social groups in many countries. India is no exception, with the scheduled castes (SC) and scheduled tribes (ST) being one of the countrys most marginalised and disadvantaged groups. This paper analyses the disparities in access to basic services between scheduled and non-scheduled households, investigates the factors contributing to the unequal access, and suggests policy recommendations. Using data from the National Sample Survey 76th Round, we analyse the access to basic services such as durable housing, improved water and sanitation, and access to electricity. The papers objectives are (a) to investigate the factors impacting the quality of basic service delivery in urban India separately for scheduled and non-scheduled households and (b) to quantify the discrimination between scheduled and non-scheduled households in urban India concerning access to quality of basic services through computing a comprehensive index and by using the Fairlie decomposition approach. The analysis corroborates the finding that systemic discrimination exists between scheduled and non-scheduled households in urban India regarding access to good quality basic services up to an extent of 24%. 2024 The Authors. -
Discrimination and Coping of Old Settlers in Sikkim
The study was conducted to explore the existence and manifestation of discrimination in Sikkim. In the Indian context, race-based discrimination has been extensively studied from the point of view of the northeasterners residing in mainland India. An important reason for this is the differences in race, culture, language, and minority status of the northeasterners in mainland India. However, within the northeastern states all of the above mentioned aspects are reversed newlineand the minority is the mainland Indian community, race-based discrimination has not been studied. Sikkim was considered as the region for study as it is part of the sister states of the northeastern region and the Rajya Sabha Committee on Petitions has acknowledged that discrimination has been practiced in the state. An exploratory sequential mixed design was adopted for the newlinestudy. Eleven telephonic semi-structured interviews were conducted for the qualitative phase with members of the old settlers of Sikkim. A survey was conducted for the quantitative phase. Thematic analysis revealed two global theme, five organizing themes and 44 basic themes. Survey method revealed that 51% of old settlers felt discriminated daily in Sikkim. The results newlinerevealed that race based discrimination does exist in Sikkim with it being purported at newlineinstitutional and interpersonal levels. -
-
Discriminated-SDS: A Novel Hybrid Approach for Optimizing EEG Based Brain-Computer Interface Signals Faced by Metaheuristic Algorithms
Brain Computer Interfaces (BCIs) will convert the thoughts of individuals with physical disabilities into commands for devices to enable them autonomous mobility. The Electroencephalogram (EEG) is widely favoured as a control signal due to its ease of acquisition compared to invasive recordings. While the affordability of EEG equipment allows for the use of numerous recording channels, this abundance increases computational complexity, necessitating optimal channel selection strategies to improve efficiency and classification accuracy. Deep Neural Networks (DNNs) often face scalability issues with multidimensional, locally correlated inputs, making them impractical for such applications. Convolutional Neural Networks (CNNs) are efficient for analysing BCI data but require careful hyperparameter tuning to achieve optimal performance. This paper introduces a framework for classifying BCI channel selection using deep learning techniques. The study primarily concentrates on refining the hyper parameters of deep learning algorithms through metaheuristic techniques, specifically employing Discriminated Stochastic Diffusion Search (SDS) to enhance BCI channel selection. The findings indicate that the proposed hyperparameter optimization methods, such as Discriminated-SDS, significantly enhance classification accuracy. The proposed D-SDS balances exploration and exploitation, mitigates the local optima issue, and is especially advantageous for intricate deep learner architectures such as VGGNet, ResNet, and InceptionNet. Hyperparameter optimization in EEG-based BCI systems can substantially improve performance, enhancing their efficiency and reliability. 2026, Iquz Galaxy Publisher. All rights reserved. -
Discrete Integrity Assuring Slice-Based Secured Data Aggregation Scheme for Wireless Sensor Network (DIA-SSDAS)
In a wireless sensor network, data privacy with a minimum network bandwidth usage is addressed using homomorphic-based data aggregation schemes. Most of the schemes which ensure the end-to-end privacy provide collective integrity verification of aggregated data at the receiver end. The presence of corrupted values affects the integrity of the aggregated data and results in the rejection of the whole data by the base station (BS) thereby leading to the wastage of bandwidth and other resources of energy constraint wireless sensor network. In this paper, we propose a secured data aggregation scheme by slicing the data generated by each sensor node deployed in layered topology and enabling en route aggregation. Novel encoding of data and hash slices based on child order is proposed to enable concatenation-based additive aggregation and smooth extraction of slices from the aggregate by the BS. Elliptic curve-based homomorphic encryption is adopted to ensure end-to-end confidentiality. To the best of our knowledge, the proposed scheme is the first which facilitates the BS to perform node-wise integrity verification, filter out only the corrupted portion, and implement dynamic query over the received data. Communication- and computation-based performance analysis shows the efficiency of the proposed scheme for varied network sizes. The scheme can resist eavesdropping attack, node compromising attack, replay attack, malleability attack, selective dropping attack, and collusion attack. 2021 D. Vinodha and E. A. Mary Anita. -
Discrete financial in sentimental analysis using exploring patterns and trends
In todays rapidly evolving financial environment, its crucial for investors and decision-makers to effectively analyze stakeholder communications to gain valuable insights. This research conducts a comprehensive evaluation of a range of models that utilize machine learning, such as CNN (Convolutional Neural Network), LR (Logistic Regression), Doc2vec, and LSTM (Long Short-Term Memory), to determine their efficacy in interpreting investors sentiments and predicting business assessments and trading dynamics. The justification for preferring deep neural architectures compared to conventional data analysis lies in the challenge of handling extensive amounts of diverse and unorganized data. Deep learning techniques have shown impressive capacity in automatically detecting complex characteristics and unveiling concealed patterns within written records, rendering them well-suited for sentiment analysis in financial dialogue. This research questions the notion that depending exclusively on data from a solitary origin leads to persistently effective investment moves. In fact, stakeholder communication is impacted by numerous influential elements, leading to diverse sentiments and sentiments. Through our comparative assessment, we aim to illuminate how various deep learning models can adeptly capture the intricate nuances of sentiment within fiscal messaging. 2024, Taru Publications. All rights reserved. -
Discovery of quasi-periodic oscillations in the persistent X-ray emission of accreting binary X-ray pulsar LMC X-4
We report the discovery of quasi-periodic oscillations (QPOs) in the high-mass X-ray binary (HMXB) pulsar LMC X-4 in its non-flaring (persistent) state using observations with XMM-Newton. In addition to the 74 mHz coherent pulsations, the persistent emission light curve shows a QPO feature in the frequency range of 20-30 mHz. Quasi-periodic flares have been previously observed from LMC X-4 in observations made with Rossi X-ray Timing Explorer (RXTE). However, this is the first time QPOs have been observed in the persistent emission observations of LMC X-4. QPOs in X-ray binaries are generally thought to be related to the rotation of the inhomogeneous matter distribution in the inner accretion disc. In HMXBs such as LMC X-4 where the compact object is a neutron star with a high magnetic field, the radius of the inner accretion disc is determined by the mass accretion rate and the magnetic moment of the neutron star. In such systems, the QPO feature, along with the pulse period and X-ray luminosity measurement, helps us to constrain the magnetic field strength of the neutron star. We use considerations of magnetospheric accretion to have an approximate value of the magnetic field strength of the neutron star in LMC X-4. 2022 The Author(s) Published by Oxford University Press on behalf of Royal Astronomical Society. -
Discovery of inverse-Compton X-ray emission and estimate of the volume-averaged magnetic field in a galaxy group
Observed in a significant fraction of clusters and groups of galaxies, diffuse radio synchrotron emission reveals the presence of relativistic electrons and magnetic fields permeating large scale systems of galaxies. Although, these non-thermal electrons are expected to upscatter cosmic microwave background photons up to hard X-ray energies, such inverse-Compton (IC) X-ray emission has so far not been unambiguously detected on cluster/group scales. Using deep, new proprietary XMM-Newton observations (?200 ks of clean exposure), we report a 4.6 ? detection of extended IC X-ray emission in MRC 0116 +111, an extraordinary group of galaxies at z = 0.131. Assuming a spectral slope derived from low frequency radio data, the detection remains robust to systematic uncertainties. Together with low frequency radio data from the Giant Metrewave Radio Telescope (GMRT), this detection provides an estimate for the volume-averaged magnetic field of (1.9 0.3) ?G within the central part of the group. This value can serve as an anchor for studies of magnetic fields in the largest gravitationally bound systems in the Universe. 2023 The Author(s) Published by Oxford University Press on behalf of Royal Astronomical Society. -
Discovery of fullerenes in the shell of candidate luminous blue variable WRAY 16-232
We report the discovery of fullerene in the circumstellar environment of WRAY 16-232, a strong candidate luminous blue variable. Multiple pointings of archival Spitzer Infrared Spectrograph spectra reveal, for the first time, the presence of prominent vibrational bands of C60 at 17.4 and 18.9 ?m in a luminous blue variable (LBV) envelope, along with the strong polycyclic aromatic hydrocarbon features. These observations suggest that, despite the harsh radiative conditions, large carbonaceous molecules can form, process, and survive in the ejecta of massive stars. Complementary optical spectroscopy with South African Large Telescope High-Resolution Spectrograph shows multiple P Cygni profiles in H ?, He i, and Fe ii lines, which are indicative of a dense, expanding wind and substantial mass-loss. Furthermore, analysis of decade long photometric data shows short-term brightness variations of ?0.5 mag. These results not only reinforce the classification of WRAY 16-232 as a strong LBV candidate but also provide new insights into the mechanisms of dust formation and the chemical enrichment of the interstellar medium by massive stars. We discuss various scenarios for fullerene formation in such environments, and find that shock processing due to wind-wind interactions could be playing a vital role. The shell of WRAY 16-232 has an ideal UV field strength and the time-scales appear to match with shock processing time-scales. The results highlight the need for further high spatial/spectral resolution and temporal observations to confirm the formation and survival scenario of C60 in its shell. The Author(s) 2025. Published by Oxford University Press on behalf of Royal Astronomical Society. -
Discovery of an M-type companion to the Herbig Ae Star V1787 Ori
The intermediate-mass Herbig Ae star V1787 Ori is a member of the L1641 star-forming region in the Orion A molecular cloud. We report the detection of an M-type companion to V1787 Ori at a projected separation of 6.66 arcsec (corresponding to 2577 au), from the analysis of VLT/NACO adaptive optics Ks-band image. Using astrometric data from Gaia DR2, we show that V1787 Ori A and B share similar distance (d ?387 pc) and proper motion, indicating that they are physically associated. We estimate the spectral type of V1787 Ori B to be M5 2 from colour-spectral type calibration tables and template matching using SpeX spectral library. By fitting PARSEC models in the Pan-STARRS colour-magnitude diagram, we find that V1787 Ori B has an age of 8.1$^{+1.7}_{-1.5}$ Myr and a mass of 0.39$^{+0.02}_{-0.05}$ M. We show that V1787 Ori is a pre-main-sequence wide binary system with a mass ratio of 0.23. Such a low-mass ratio system is rarely identified in Herbig Ae/Be binary systems. We conclude this work with a discussion on possible mechanisms for the formation of V1787 Ori wide binary system. 2020 The Author(s) Published by Oxford University Press on behalf of Royal Astronomical Society. -
Discovery of a 459 Hz Burst Oscillation in XTE J1810?189 with NICER
We present a detailed temporal study of a type I X-ray burst from the neutron star low-mass X-ray binary (NS-LMXB) XTE J1810?189, observed on 2023 April 27 using the Neutron Star Interior Composition Explorer. The burst exhibited a rapid rise time of 2.55 s, followed by an exponential decay lasting for 7.5 s, with a total duration of ?13 s. Type I X-ray bursts are driven by thermonuclear burning on the surface of a neutron star in an NS-LMXB. As these bursts originate from the stellar surface they can exhibit highly coherent signals known as burst oscillations, which serve as probes of the neutron stars spin frequency. We report the detection of a burst oscillation signal at ?459 Hz at the cooling tail of the burst. The oscillation showed a strong Leahy-normalized power of PL = 35.95 at 458.92 Hz, corresponding to a single-trial significance of 5.53? and a multiple-trial corrected significance of 3.14?. The folded pulse profile in the 0.212 keV band is well described by a constant plus sinusoid with a fractional rms amplitude of 14.63%. These results suggest that the burst oscillation frequency of XTE J1810-189 directly reflects on the neutron stars spin, measured here to be ?2.18 ms, placing it among the rapidly rotating NS-LMXBs. This burst oscillation signal at the cooling tail of the burst can be interpreted through surface mode model or the asymmetric cooling wake model. 2025. The Author(s). Published by the American Astronomical Society. -
Discovery of 2716 hot emission-line stars from LAMOST DR5
We present a catalog of 3339 hot emission-line stars (ELSs) identified from 451 695 O, B and A type spectra, provided by LAMOST Data Release 5 (DR5). We developed an automated Python routine that identified 5437 spectra having a peak between 6561 and 6568 False detections and bad spectra were removed, leaving 4138 good emission-line spectra of 3339 unique ELSs. We re-estimated the spectral types of 3307 spectra as the LAMOST Stellar Parameter Pipeline (LASP) did not provide accurate spectral types for these emission-line spectra. As Herbig Ae/Be stars exhibit higher excess in near-infrared and mid-infrared wavelengths than classical Ae/Be stars, we relied on 2MASS and WISE photometry to distinguish them. Finally, we report 1089 classical Be, 233 classical Ae and 56 Herbig Ae/Be stars identified from LAMOST DR5. In addition, 928 B[em]/A[em] stars and 240 CAe/CBe potential candidates are identified. From our sample of 3339 hot ELSs, 2716 ELSs identified in this work do not have any record in the SIMBAD database and they can be considered as new detections. Identification of such a large homogeneous set of emission-line spectra will help the community study the emission phenomenon in detail without worrying about the inherent biases when compiling from various sources. 2021 National Astronomical Observatories, CAS and IOP Publishing Ltd.. -
Discovering the Micro-Clusters from a group of DHH learners: An approach using machine learning techniques
The e-learning environment is essentially helpful for improving the autonomous learning skills of the DHH learners. Facing numerous resources online, DHH learners need support to choose the right learning materials. This can be done by recommending suitable learning objects to similar types of learners. Hence, this research attempts to explore the possibilities of forming micro clusters from the group of DHH learners to improve the recommendation. As a result of k-means, three different micro clusters are formed. So, from the initial analysis, it is identified that the formation of micro clusters is possible, and features such as communication and learning ways play an important role in forming the well-defined micro clusters. This will definitely help the teachers in traditional classrooms and recommendation engines in e-learning to explore the micro clusters of learners with same learning patterns and communication preferences to appropriately stream the right pedagogical methods. 2024, IGI Global. All rights reserved. -
Discovering patterns using feature selection techniques and correlation
Term Frequency and inverse document frequency is reported to have a significant contribution for various text categorization, document clustering and many other text mining related tasks. A collection of the applications and the enhancements of the Term Frequency and Inverse Document Frequency based document representation technique is examined in this work. The document representation algorithm is essential in the field of text - script mining. In this algorithm, unstructured data is converted into a vector space model where each related document is considered as a point in the vector space. Related documents come in proximity to the other related documents while the documents that are very far away from being coherent remain different from each other. In this paper, four feature selection techniques are implemented to discover the patterns from a repository of unstructured data by using correlation similarity measure. Analysis and comparison with other existing technique is also included. The validation of the patterns formed is performed by using silhouette values. Experiments are conducted to compare performance. Results indicate that TDMp1 performance is poor compared to others. Springer Nature Switzerland AG 2020. -
Discovering patterns of live birth occurrence before in vitro fertilisation treatment using association rule mining
According to estimates, in-vitro fertilisation (IVF) is credited for the delivery of over 9 million children globally, constituting it to be a highly remarkable as well as commercialised advanced healthcare treatment. Nonetheless, the majority of IVF treatments are now constrained by factors such as expense, access and most notably, labour-intensive, technically demanding processes carried out by qualified professionals. Advancement is thus crucial to maintaining the IVF markets rapid growth while also streamlining current procedures. This might also improve access, cost, and effectiveness while also managing therapeutic time efficiently and at a reasonable cost. IVF has become a renowned technique for addressing problems like endometriosis, poor embryo development, hereditary diseases of the parents, issues with the biological function, problems with counteracting agents that harm either eggs or sperm, the limited capacity of semen to penetrate cervical bodily fluid, and lower sperm count that lead to infertility in humans. Copyright 2023 Inderscience Enterprises Ltd.