Wyniki wyszukiwania - BazTech

1

An analysis of denoising neural networks for noise removal in images

Ramakotti Raksha, Paneerselvam Surekha, Kumar Vinodh, Kumar Sachin, Evangeline Jebarani

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 2

27--31

EN

Clean images, when subjected to prolonged transmission, improper image acquisition or conditioned to multiple feature changes, lead to image tarnishing due to unwanted noisy pixels. This proposes to be a major threat in image-processing and computer vision fields. With the evolution of denoising models in the field of Neural Networks, efficient noise removal has become achievable, in a real-time scenario. In this work, two approaches to noise modelling have been considered, i.e., noise as an inverse problem and noise as a residual problem, this has been done by constructing convolutional auto encoders and denoising convolutional networks and their performance in the process of noise removal has been evaluated based on Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM).

PL

Czyste obrazy poddane przedłużonej transmisji, niewłaściwej akwizycji obrazu lub poddane wielokrotnym zmianom cech prowadzą do zmatowienia obrazu z powodu niechcianych zaszumionych pikseli. Sugeruje to, że jest to poważne zagrożenie w dziedzinie przetwarzania obrazu i widzenia komputerowego. Wraz z ewolucją modeli odszumiania w dziedzinie sieci neuronowych, efektywne usuwanie hałasu stało się osiągalne w scenariuszu czasu rzeczywistego. W niniejszej pracy rozważono dwa podejścia do modelowania hałasu, tj. hałas jako problem odwrotny i hałas jako problem rezydualny. Dokonano tego poprzez skonstruowanie autoenkoderów splotowych i odszumianie sieci splotowych, a ich wydajność w procesie usuwania hałasu oceniane na podstawie stosunku sygnału szczytowego do szumu (PSNR) i wskaźnika podobieństwa strukturalnego (SSIM).

2

Novel N,N’-bis(2,4-dimethoxybenzylidene)ethylenediamine PVC membrane electrode for the potentiometric iron selective sensor based on Schiff base ligand

Kumar Sachin, Sandhu Susheel K., Patel Agnik K., Parmar Ketankumar H.

Polimery

|

2022

|

Vol. 67, nr 5

197--204

EN

N,N’-bis(2,4-dimethoxybenzylidene)ethylenediamine was synthesized and used as a membrane carrier to create a novel poly(vinyl chloride) membrane potentiometric sensor that is selective especially for Fe3+ ions. The super-Nernstian slope of the projected sensor was 19.5 mV per decade over a concentration range of 7.3•10-8–1•10-1 M having detection limit at 7.3•10-8 M. The sensor displayed a linear potential response for the detection of Fe3+ ions in about 30 seconds, and it had a lifespan of no less than 9 weeks without lacking any potential divergence. The selected sensor showed high selectivity in water solutions in relation to Fe3+ ions, even in the presence of other metal cations in the pH range of 3.6–10.

PL

Przedmiotem badań był potencjometryczny czujnik do selektywnego oznaczania jonów Fe3+ oparty na membranie wykonanej z poli(chlorku winylu) i N,N’-bis(2,4-dimetoksybenzylideno)etylenodiaminy. Nachylenie super-nernstowskie (ang. super-Nernstian slop) badanego czujnika wynosiło 9,5 mV na dekadę w zakresie stężeń 7,3•10-8–1•10-1 M z limitem detekcji 7.3•10-8 M. Czujnik wykazywał w obecności jonów Fe3+ liniową odpowiedź przez około 30 s, a jego czas życia bez rozbieżności potencjałów wynosił nie mniej niż 9 tygodni. Wybrany czujnik wykazywał w roztworach wodnych wysoką selektywność w stosunku do jonów Fe3+ nawet w obecności innych kationów metali w zakresie pH 3,6–10.

3

Determination of moxifloxacin hydrochloride in AVELOX pharmacological formulations using modified potentiometer sensors

Kumar Sachin, Sindhu Sushil K., Kumar Praveen, Sharma Amit, Sagadevan Suresh

Polimery

|

2021

|

T. 66, nr 11-12

589--601

EN

Three different carbon paste (CP), silk-screen (SP) and poly (vinyl chloride) (PVC) modified electrodes were obtained to verify the reliability of AVELOX, the generic name of which is Moxifloxacin HCl (AV-MOXH). The sensing membranes were containing AVELOX ion associated complexes with sodium tetraphenylborate (NaTPB), phosphomolybdic acid (PMA), phosphotungstic acid (PTA), and ammonium reineckate (RN) as electroactive materials. All three electrodes gave fast, viable, and near-Nernstian linear responses over a relative wide concentration range that ranged from 1.010-6 to 1.010-2 mol/L AV-MOXH at 25°C with a monovalent cationic decrease. The sensors demonstrated a good discernment of AV-MOXH from numerous inorganic and organic compounds such as glucose, sucrose, Na+, Ca+, etc. Additionally, the isothermal coefficients along with selectivity coefficients were calculated. The modified Screen Printed Electrode sensor appeared to be highly sensitive for the determination of AV-MOXH. The electrode response was observed in pH range 2–6 for ISPE electrodes and IPVC electrodes and 3–7 for ICPE electrodes under various temperature conditions. The short response time, lifetime validity, recovery, and all the methods of validation such as limit of detection and limit of quantification were estimated. The potentiometric method turned out to be suitable for determining AV-MOXH in pharmacological formulations, and the findings obtained are comparable to the “HPLC official method” in terms of the agreement. As a result, the postulated potentiometric approach was verified in accordance with IUPAC guidelines.

PL

Otrzymano trzy różne elektrody modyfikowane pastą węglową (CP), sitodrukiem (SP) i polichlorkiem winylu (PVC), w celu oceny skuteczności działania leku AVELOX (nazwa rodzajowa Moxifloxacin HCl, AV-MOXH). Membrany czujników zawierały kompleksy jonu AVELOX z tetrafenyloboranem sodu (NaTPB), kwasem fosfomolibdenowym (PMA), kwasem fosfowolframowym (PTA) i soli Reineckego (RN) jako materiałami elektroaktywnymi. Wszystkie trzy elektrody dały szybkie i bliskie zależności liniowe Nernsta w zakresie stężeń AV-MOXH od 1.0-10-6 do 1.0-10-2 mol/l (w 25°C). Elektrody wykazały dobrą selektywność w oznaczaniu AV-MOXH względem wielu jonów i związków organicznych i nieorganicznych, jak glukoza, sacharoza, Na+, Ca+ itp. Dodatkowo obliczono współczynniki izotermiczne oraz współczynniki selektywności. Zmodyfikowany czujnik z elektrodą sitodrukową okazał się być bardzo czuły do oznaczania AV-MOXH. Badania prowadzono w zakresie pH 2–6 w przypadku elektrod ISPE i IPVC oraz 3–7 w przypadku elektrod ICPE w różnych temperaturach. Oszacowano czas odpowiedzi elektrod, ich czas życia, możliwość regeneracji, odzysk oraz granicę wykrywalności i granicę oznaczalności. Metoda potencjometryczna okazała się być odpowiednia do oznaczania AV-MOXH w preparatach farmakologicznych, a uzyskane wyniki są porównywalne z „oficjalną metodą HPLC”.

4

DFT study of optoelectronic spectra of barium cadmium chalcogenides (Ba2CdX3, X = S, Se and Te)

Kumar Sachin, Kumar Naven, Yadav Kamna, Annveer, Singh R. P.

Materials Science Poland

|

2019

|

Vol. 37, No. 3

417--425

EN

DFT analyses of electronic and optical spectra of barium cadmium chalcogenides (Ba2CdX3, X = S, Se, Te) have been carried out. The study of electronic spectra has been made in terms of band structure and density of states using full potential linear augmented plane wave plus local orbital method. Band structure calculations have been carried out under the approximations PBE-GGA, PBE-Sol, LDA and TB-mBJ. Band structures of these materials show that Ba2CdS3, Ba2CdSe3 and Ba2CdTe3 crystals possess a band gap less than 1 eV, underestimated relative to the experimental/theoretical literature values. Optical spectra of these chalcogenides have been analyzed in terms of real and imaginary parts of dielectric function, reflectivity, refractive index, extinction coefficient, absorption coefficient, optical conductivity and electron energy loss. Optical results show large anisotropy along different directions. These results provide a physical basis of barium cadmium chalcogenides for potential application in optoelectronic devices.

5

Passenger Abnormal Behaviour Detection using Machine Learning Approach

Dabral Sonal, Agarwal Amit, Kumar Sachin, Gautam Bhaskar

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

21--25

EN

In this paper we have proposed the clustering approach to classify the random walk trajectories from the synthetic bus station video. Bus station one of the most crowded locations that consist of more than thousands of passengers or travelers waiting for the buses to travel to the destination point. These crowded locations can be highly prone to accidents or terrorist activities. Work is classified into two steps i.e Firstly we find out the trajectories from the image by using the machine learning approach after that we apply the agglomerative clustering algorithm which is used to group the abnormal trajectories with the similar spatial patterns and normal trajectories with similar spatial patterns.

6

A Conjoint Analysis of Road Accident Data using K-modes Clustering and Bayesian Networks (Road Accident Analysis using clustering and classification)

Kumar Sachin, Semwal Vijay Bhasker, Solanki Vijender Kumar, Tiwari Prayag, Kalitin Denis

Annals of Computer Science and Information Systems

|

2017

|

Vol. 10

53--56

EN

Road and traffic accidents are one of the important concerns in today's world. Every country receives a huge damage from road accidents in terms of public health and property loss. Therefore, road accident analysis plays an important role in public health domain. Road accident analysis is performed in order to identify the associated factors that are responsible for road accidents. Knowledge of these factors would be very useful to understand the circumstances of road accidents and can be used to avoid the road accidents. One of the problems in accident analysis is that most of the road accident data is of biased nature. For example, the critical road accidents are very few in comparison to slight/minor injury accidents. Various studies has focused that clustering prior to analysis can increase the efficiency and accuracy of classification. The motive of this study is to perform a conjoint analysis on road accident data, to investigate improvement in the performance of classification of unbiased data after clustering.