Digital Eprints Services at Vignan's Foundation for Science, Technology & Research
Not a member yet
721 research outputs found
Sort by
Wireless Sensor Network using Control Communication and Monitoring of Smart Grid
No full textFor some countries around the world, meeting
demand is a serious concern. Power supply market is
increasingly increasing, posing a big challenge for various
countries throughout the world. The increasing expansion in
the market for power needs upgrading system dependability to
increase the smart grid's resilience. This smart electric grid has
a sensor that analyses grid power availability and sends
regular updates to the organisation. The internet is currently
being utilized to monitor processes and place orders for
running variables from faraway places. A large number of
scanners have been used to activate electrical equipment for
domestic robotics for a long period in the last several days.
Conversely, if it is not correctly implemented, it will have a
negative impact on cost-effectiveness as well as productivity.
For something like a long time, home automation has relied on
a large number of sensor nodes to control electrical equipment.
Since there are so many detectors, this isn't cost-effective. In
this article, develop and accept a wireless communication
component and a management system suitable for managing
independent efficient network units from voltage rises and
voltage control technologies in simultaneous analyzing system
reliability in this study. This research paper has considered
secondary method to collect relevant and in-depth data related
to the wireless sensor network and its usage in smart grid
monitoring
Multi-Class Classification and Prediction of Heart Sounds Using Stacked LSTM to Detect Heart Sound Abnormalities
Get PDFThe changes in lifestyle, food habits, and working conditions cause various diseases in human lives, cardiovascular diseases are one of those. Not only aged people, middle-aged and young people are also suffering due to this and lead to death in the early ages. So there is a significant need in detecting cardiovascular diseases in beginning itself. Through early detection and persistent treatment, the death rate in the early ages due to cardiovascular diseases can be reduced. However, it is necessary to have an efficient model to detect heart disease at an early stage even without the presence of a trained clinical expert. This paper studies the implementation of deep learning models to classify heartbeat sounds into various classes. We proposed a stacked LSTM model to classify the heartbeat sound into multiple classes based on the features obtained from the audio signals. The implementation can even predict the class of an unlabelled heartbeat sound. The model classifies the heartbeat sounds into 4 classes with accuracies 85% and 87% on training and validation sets respectively. In further the proposed model parameters can be improved to increase the classification and prediction accuracy
Prediction of COVID-19 using machine learning techniques
No full textIn Dec. 2019, Hubei, China, was the first place where infected cases of coronavirus disease-2019 (COVID-19) were found. Over 214 countries and regions worldwide have been affected by the COVID-19 pandemic and have shaped every aspect of our daily lives. Despite these increases at the stage of composition, the incidence rate with dirty flow has increased, and there is no very controlled situation, for example, a cumulative total of 3,754,253 (265,415) COVID-19 deaths have been registered worldwide since Apr. 2020. This chapter emphasizes the importance of reacting to the COVID-19 epidemic and predicting its significant effects through late progress and the use of artificial intelligence (AI), machine learning (ML), and deep learning (DL) in different areas. We summarize information provided by AI, ML, and DL and then separate the applications for combating COVID-19; finally, we predict COVID-19 using ML models. This chapter provides the experts and networks of people with knowledge about how AI, ML, and DL are developing COVID-19 and contributes to research to stop the COVID-19 epidemic
Multi-objective optimization-based privacy in data mining
Get PDFThis paper addresses the data privacy based on interactive computation using an optimization model in data mining. When
data are computed or sharing among users in online, it needs to maintain privacy for all computation during sharing of data.
But user choice-based privacy is not available when sharing of data is required for data mining computation which is a big
challenge for data privacy. Thus, we proposed the framework for anonymity of data privacy using various methods of
multi-objective models as per the requirement of privacy. The proposed framework is designed with the help of two objects
such as computational cost and privacy based on optimization model. Our framework maintains the balance between above
objects as per user demands, i.e., increasing the privacy with decreasing the computational cost. In this model, the domain
of privacy and computational cost for optimization problem solves the entity privacy requirements in a computing
environment. We have used various methods such as Gaussian and uniform distribution, confidence interval, activation
function, linear membership function with distinguish manner for maintaining of privacy and cost. As per the uniform distribution and parameter a-cut value for noise data, the optimal value is made accordingly. Example: for a = 0.2, and uniform distribution (- 1, 1), the optimal value is 0.0058. Similarly, as per different a values, classifiers result is different like a = 0.2 and 0.4, Multilayer perceptron values are 4.01 and 1.61 respectively. The solution of the proposed model controls the amount of privacy with complete freedom of choice of users with utmost flexibility
Variations of generalized weak contractions in partially ordered b-metric space
Get PDFAbstract Objectives
This paper explored the fixed point results for the mappings satisfying generalized weak contractive conditions in a complete partially ordered b -metric space. These contractions are some variations of the work done by the authors (Mituku et al. in BMC Res Notes 13:537. https://doi.org/10.1186/s13104-020-05354-1 , 2020; Seshagiri et al. in BMC Res Notes 13:451. https://doi.org/10.1186/s13104-020-05273-1 , 2020, BMC Res Notes 14:390. https://doi.org/10.1186/s13104-021-05801-7 , 2021, BMC Res Notes 14:263. https://doi.org/10.1186/s13104-021-05649-x , 2021) in the same context. To validate the results a few examples are provided.
Result
The aim of this work is to prove some fixed point results of the self mappings in ordered b -metric space satisfying variant generalized weak contraction conditions. These results generalize some known results in the provided literature
Knowledge Discovery in a Recommender System: The Matrix Factorization Approach
Get PDFTwo famous matrix factorization techniques, the Singular Value Decomposition (SVD) and the Nonnegative Matrix Factorization (NMF), are popularly used by recommender system applications. Recommender system data matrices have many missing entries, and to make them suitable for factorization, the missing entries need to be filled. For matrix completion, we use mean, median and mode as three different cases of imputation. The natural clusters produced after factorization are used to formulate simple out-of-sample extension algorithms and methods to generate recommendation for a new user. Two cluster evaluation measures, Normalized Mutual Information (NMI) and Purity are used to evaluate the quality of clusters
Vehicle count prediction using machine learning
Get PDFAn important part of network security is a network intrusion detection system (NIDS). In the face of the need for new networks, there are issues regarding the feasibility of traditional approaches. More directly, these difficulties are connected to the increasing degrees of human contact required and the diminishing levels of detection precision. A new deep learning intrusion detection approach is presented in this research to overcome these problems. The recurrent non-symmetric deep autoencoder we’ve suggested for learning unsupervised features is described here (RNDAE). A new deep learning classification model based on LightGBM RNDAEs is also shown.
NSL-KDD, CICIDS2017, and CSECICIDS2018 datasets were used to evaluate our proposed classifier in Tensor-Flow. If our model holds up, it has the potential to be used in the latest generation of network intrusion detection systems (NIDS)
A Reverse Phase LC Method Development and Validation for the Quantification of Acetazolamide and its Specified and Unspecified Degradation Products in Hard Gelatin Capsule Formulations
No full textAcetazolamide, a carbonic anhydrase inhibitor, is used orally to reduce intraocular pressure in patients suffering from glaucoma. A simple, specific, accurate, precise and stability-indicating reverse-phase HPLC method has been developed and validated to identify and quantify acetazolamide and its specified and unspecified degradation products in hard shell capsules formulations. The chromatographic separation was achieved on Agilent Zorbax SB-CN, (4.6 mm × 150 mm, 3.5 μm) using mobile phase-A (methanol: water: phosphoric acid; 1:9:0.1 v/v/v) and mobile phase-B (methanol: water: phosphoric acid; 4:6:0.1 v/v/v). The flow rate was set at 1.0 mL min−1, and the column temperature was 40 °C. The wavelength 254 nm was used to detect and quantify acetazolamide and its related impurities with an injection volume of 30μL. The retention time for the acetazolamide and its impurities was found at 4.601 min (Acetazolamide), 4.221 min (Acetazolamide impurity A), 14.303 min (Acetazolamide impurity B), 8.342 min (Acetazolamide impurity C), 2.488 min (Acetazolamide impurity D) and 3.411 min (Acetazolamide impurity E), respectively. The linearity study was conducted in a range of 0.5 µg mL−1 to 82 µg mL−1 for acetazolamide and 0.1 µg mL−1 to 4 µg mL−1 for its related impurities. The proposed method was accurate, precise, stability indicating and convenient for the quantitative analysis of acetazolamide and related impurities in the drug product
Biosorption of Cu(II), Pb(II) from electroplating industry effluents by treated shrimp shell
No full textThe current investigation focuses on a systematic study of application of treated shrimp shell waste (TSSW) as a potential biosorbent in removal of Cu(II) and Pb(II) from hazardous industrial effluents. The surface characterization and morphological studies indicated that biosorption is owing to ion complexation and exchange, and chemical adsorption mechanism. The effects of pH (1–10), time dependency (1–60 min), initial concentration of Cu(II) and Pb(II) (20–100 mg L−1), TSSW loading (0.1–0.5 g) and temperature (303–333 K) on biosorption efficiency using TSSW were examined through experiments. The experimental discoveries indicated that maximum biosorption efficacies were 96.42% at pH 5, 40 min for Cu (II) and 89.77% at pH 6, 30 min for Pb(II), 20 mg L−1 concentration, 0.1 g loading and 303 K temperature. Langmuir, Freundlich, Temkin, and Dubinin - Radushkevich isotherm models were used to examine experimental findings and the Langmuir model was well fitted one. The maximum Cu(II), Pb(II) removal capacities by TSSW were 22.67, 15.32 mg g−1 according to Langmuir model. Pseudo second order model was excellent suited to kinetics which shows that chemisorption was involved for the transfer of Cu(II), Pb(II) to TSSW surface with three different intra particle diffusional stages. Hence, this study revealed that TSSW has a great potential to be an environment friendly and economic biosorbent for removal of Cu(II) and Pb(II) containing industrial effluent
A Comprehensive Review on Pharmacological Activities of Alkaloids: Evidence from Preclinical Studies
Get PDFPlant alkaloids are a broad range of chemical entities that make up one of the biggest classes of natural goods. Even though man has used alkaloids-containing plants for at least 3000 years as medicines, teas, and potions, the chemicals implicated for their action were not determined till the 19th century. Alkaloids' essential nature causes them to form salts when mixed with alkaline solutions or organic acids. Except in extraordinary circumstances, alkaloids salts are generally soluble in water and dilute alcohols, but not in organic solvents. They are classified using a variety of markers, such as natural origins or chemical composition. The distribution of alkaloids according to their
primary structure, the major C-N skeleton, is the most correct and frequent categorization. Alkaloids, which are compounds isolated from natural sources, exhibit promising pharmacological activity, including pharmacological activity for the curing of neurogenerative illnesses like vascular dementia, which currently treated with a variety of medications. As a result, the article focuses on the technological prospecting of alkaloids with important properties for curing the illness, such as antioxidant, anxiolytic, anti-inflammatory, antiviral, antiemetic, antifungal, antihyperlipedemic, antihypoglycemic, muscle relaxant, antiulcer, antitussive, expectorant, anticancer, antimicrobial, antimalarial, immunosuppressant, antidepressant