Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
24 results
Search Results
Item Enhancing Data Quality in Hybrid Cloud Architectures(Institute of Electrical and Electronics Engineers Inc., 2024) Fernandes, G.H.; Divakarla, U.; Chandrasekaran, K.The emergence of the hybrid cloud model has completely changed how businesses handle, store and use their data. A common option for businesses looking to combine the benefits of cloud services and on-premises infrastructure is the hybrid cloud strategy. However, because of the complexity of data management across contexts and the integration of disparate systems, this paradigm presents serious hurdles to preserving data quality. Since data is the primary source for many important business decisions, ensuring data quality - which includes correctness, consistency, completeness, security, and reliability - remains a top priority. This study presents a unique method that makes use of cloud computing and machine learning (ML) algorithms to improve data quality in hybrid cloud environments. The detection, prevention and remediation of data quality issues by integrating state-of-the-art machine learning techniques into hybrid cloud systems is thoroughly examined in this study. The suggested architecture seeks to deliver more dependable and trustworthy data for decision-making processes by offering real-time monitoring, analysis and quality enhancement of data throughout the hybrid infrastructure. The efficacy of methodology in tackling data quality issues in hybrid cloud settings is illustrated using experiments and case studies. © 2024 IEEE.Item A simple, rapid and accurate complexometric method for the determination of palladium(II) is proposed, based on the selective demasking property of 2-mercapto propionyl glycine (MPGH2) towards palladium(II). In the presence of diverse metal ions, palladium(II) is complexed with excess of EDTA and the surplus EDTA is back titrated at pH 5-5.5 (acetic acid-acetate buffer) with standard zinc sulphate solution using xylenol orange as indicator. An excess of a 0.2% aqueous solution of MPGH2 is then added to displace EDTA from Pd(II)-EDTA complex. The released EDTA is titrated with the same standard zinc sulphate solution as before. Reproducible and accurate results are obtained in the concentration range 2-22 mg of palladium with relative error of ±0.36% and coefficient of variation (n=6) not exceeding 0.31%. The effect of diverse ions are studied. The method is used for the determination of palladium in its complexes, catalysts and synthetic alloy mixtures.(Complexometric determination of palladium(II) using 2-mercapto propionyl glycine as demasking agent) Shetty, P.; Nityananda Shetty, A.N.; Gadag, R.V.2002Item A simple, rapid, selective and sensitive spectrophotometric method for the determination of palladium is proposed using piperonal thiosemicarbazone (PATS) as a reagent. The reagent forms a 1:2 complex (Pd:Reagent) with palladium. The yellow complex is soluble in 32-40% ethanol and has an absorption maximum at 363 nm. Beer's law is obeyed upto 3.85 ppm of palladium and the optimum concentration range is 0.5-2.45 ppm of Pd. The molar absorptivity and Sandell's sensitivity are 3. 80 x 104 dm3 mol-1 cm -1 and 2.8 x 10-3 ?g cm-2, respectively. The experimental conditions for complete colour development and the interference from various ions are investigated. The method is used for the determination of palladium in its complexes and synthetic mixtures.(Spectrophotometric determination of palladium(II) using piperonal thiosemicarbazone) Shetty, P.; Nityananda Shetty, A.N.; Gadag, R.V.2003Item A selective complexometric method is described for the determination of mercury(II) using sodium metabisulphite as a masking reagent. An excess of EDTA is added to mercury(II) solution containing associated diverse metal ions and the surplus EDTA is back titrated at pH 5-6 (hexamine buffer) with standard zinc sulphate solution using xylenol orange as indicator. An aqueous solution of sodium metabisulphite is then added to displace EDTA selectively from Hg-EDTA complex and the released EDTA is then titrated against the same standard zinc sulphate solution. Reproducible and accurate results are obtained in the range 4-100 mg of mercury with a relative error ? 0.26% and coefficient of variation ?0.40%. The method is useful for the analysis of mercury in complexes and alloy samples.(Complexometric method for the determination of mercury using sodium metabisulphite as selective masking reagent) Shetty, P.; Nityananda Shetty, A.N.2004Item Efficient shape descriptors for feature extraction in 3D protein structures(2007) Ranganath, A.; Shet, K.C.; Vidyavathi, N.Structural Genomics initiatives are generating an increasing number of protein structures with very limited biochemical characterization. Characterization of a protein's function and understanding the specific nature of a protein's binding is a critical part of both protein engineering and structure-based drug discovery. The accurate detection of binding site in these protein structures can be valuable in determining its function. As shape plays a crucial role in bimolecular recognition and function, the development of shape analysis techniques is important for understanding protein structure-function relationships. This paper describes the use of the continuous wavelet transforms (CWT) for characterizing shape features of 3D protein structures. The goal is to explore the CWT as a multiscale tool to generate rotation- and translation-invariant shape features. © 2007 IOS Press. All rights reserved.Item Epileptic EEG detection using neural networks and post-classification(2008) Patnaik, L.M.; Manyam, O.K.Electroencephalogram (EEG) has established itself as an important means of identifying and analyzing epileptic seizure activity in humans. In most cases, identification of the epileptic EEG signal is done manually by skilled professionals, who are small in number. In this paper, we try to automate the detection process. We use wavelet transform for feature extraction and obtain statistical parameters from the decomposed wavelet co-efficients. A feed-forward backpropagating artificial neural network (ANN) is used for the classification. We use genetic algorithm for choosing the training set and also implement a post-classification stage using harmonic weights to increase the accuracy. Average specificity of 99.19%, sensitivity of 91.29% and selectivity of 91.14% are obtained. © 2008 Elsevier Ireland Ltd. All rights reserved.Item Spectrophotometric determination of platinum(IV) in alloys, complexes, environmental, and pharmaceutical samples using 4-[N,N-(diethyl)amino] benzaldehyde thiosemicarbazone(2010) Naik, P.P.; Karthikeyan, J.; Nityananda Shetty, A.N.4-[N,N-(Diethyl)amino] benzaldehyde thiosemicarbazone (DEABT) is proposed as an analytical reagent for the spectrophotometric determination of platinum(IV). The DEABT forms 1:2 yellow complex with Pt(IV), which is sparingly soluble in water and completely soluble in water-ethanol-DMF medium. The Pt(IV)-DEABT complex shows maximum absorbance at 405 nm. Beer's law is valid up to 7.80 ?g cm-3, and optimum concentration range for the determination of platinum(IV) is 0.48-7.02 ?g cm-3. The molar absorptivity and Sandell's sensitivity of the method are found to be 1.755 × 104 dm3 mol-1 cm-1 and 0.0012 ?g cm-2, respectively. The relative error and coefficient of variation (n=6) for the method does not exceed ±0.43% and 0.35%, respectively. Since the method tolerates a number of metal ions commonly associated with platinum, it can be employed for the determination of platinum in environmental samples, pharmaceutical samples, alloys, catalysts, and complexes. The method is rapid as the Pt(IV)-DEABT complex is soluble in water-ethanol-DMF medium and not requiring any time consuming extraction method for the complex. © 2010 Springer Science+Business Media B.V.Item Analytical properties of p-[N,N-bis(2-chloroethyl)amino]benzaldehyde thiosemicarbazone: Spectrophotometric determination of palladium(II) in alloys, catalysts, and complexes(2011) Karthikeyan, J.; Parameshwara, P.; Nityananda Shetty, A.N.p-[N,N-bis(2-chloroethyl)amino]benzaldehyde thiosemicarbazone (CEABT) is proposed as a new, sensitive, and selective analytical reagent for the spectrophotometric determination of palladium(II). The reagent reacts with palladium(II) in the pH range 1-2 to form a yellow-colored complex. Beer's law is obeyed in the concentration range up to 2.64 ?g cm-3. The optimum concentration range for minimum photometric error as determined by Ringbom's plot method is 0.48-2.40 ?g cm-3. The yellowish Pd(II)-reagent complex shows a maximum absorbance at 395 nm, with molar absorptivity of 4.05 × 104 dm3 mol-1 cm-1 and Sandell's sensitivity of the complex from Beer's data, for D= 0.001, is 0.0026 ?g cm-2. The composition of the Pd(II)-CEABT reagent complex is found to be 1:2 (M-L). The interference of various cations and anions in the method were studied. The proposed method was successfully used for the determination of Pd(II) in alloys, catalysts, complexes, water samples, and synthetic alloy mixtures with a fair degree of accuracy. © 2010 Springer Science+Business Media B.V.Item A study about evolutionary and non-evolutionary segmentation techniques on hand radiographs for bone age assessment(Elsevier Ltd, 2017) Simu, S.; Lal, S.In this paper, a study and performance comparison of various evolutionary and non-evolutionary segmentation techniques on digital hand radiographs for bone age assessment is presented. The segmented hand bones are of vital importance in process of automated bone age assessment (ABAA). Bone age assessment is a technique of checking the skeletal development and detecting growth disorder in a person. However, it is very difficult to segment out the bone from the soft tissue. The problem arises from overlapping pixel intensities between bone region and soft tissue region and also between soft tissue region and background. Thus there is a requirement for a robust segmentation technique for hand bone segmentation. Taking this into consideration we make a comparison between non-evolutionary and evolutionary segmentation algorithms implemented on hand radiographs to recognize bone borders and shapes. The simulation and experimental results demonstrate that multiplicative intrinsic component optimization (MICO) algorithm provides better results as compared to other existing evolutionary and non-evolutionary algorithms. © 2016 Elsevier LtdItem A visual attention guided unsupervised feature learning for robust vessel delineation in retinal images(Elsevier Ltd, 2018) Srinidhi, C.L.; Aparna., P.; Rajan, J.Background and objective: Accurate segmentation of retinal vessels from color fundus images play a significant role in early diagnosis of various ocular, systemic and neuro-degenerative diseases. Segmenting retinal vessels is challenging due to varying nature of vessel caliber, the proximal presence of pathological lesions, strong central vessel reflex and relatively low contrast images. Most existing methods mainly rely on carefully designed hand-crafted features to model the local geometrical appearance of vasculature structures, which often lacks the discriminative capability in segmenting vessels from a noisy and cluttered background. Methods: We propose a novel visual attention guided unsupervised feature learning (VA-UFL) approach to automatically learn the most discriminative features for segmenting vessels in retinal images. Our VA-UFL approach captures both the knowledge of visual attention mechanism and multi-scale contextual information to selectively visualize the most relevant part of the structure in a given local patch. This allows us to encode a rich hierarchical information into unsupervised filtering learning to generate a set of most discriminative features that aid in the accurate segmentation of vessels, even in the presence of cluttered background. Results: Our proposed method is validated on the five publicly available retinal datasets: DRIVE, STARE, CHASE_DB1, IOSTAR and RC-SLO. The experimental results show that the proposed approach significantly outperformed the state-of-the-art methods in terms of sensitivity, accuracy and area under the receiver operating characteristic curve across all five datasets. Specifically, the method achieved an average sensitivity greater than 0.82, which is 7% higher compared to all existing approaches validated on DRIVE, CHASE_DB1, IOSTAR and RC-SLO datasets, and outperformed even second-human observer. The method is shown to be robust to segmentation of thin vessels, strong central vessel reflex, complex crossover structures and fares well on abnormal cases. Conclusions: The discriminative features learned via visual attention mechanism is superior to hand-crafted features, and it is easily adaptable to various kind of datasets where generous training images are often scarce. Hence, our approach can be easily integrated into large-scale retinal screening programs where the expensive labelled annotation is often unavailable. © 2018 Elsevier Ltd
- «
- 1 (current)
- 2
- 3
- »