Browse Items (16481 total)
Sort by:
-
An attention-based loss function and synthetic minority oversampling technique for alleviating class imbalance in predicting diabetes
Diabetes is a chronic disease due to higher blood sugar (or Glucose) levels in the blood. This study proposes a novel attention-based loss function and a lightweight artificial neural network (ANN) called Diabetic Lite (DB-Lite) for diabetes prediction in the Pima Indian Diabetes Dataset (PIDD). We show that the Pima dataset has many challenges. It is a small and imbalanced dataset; moreover, many features are non-linearly correlated in this dataset. The novelties of this research work are as follows: (i) A novel loss function of attention-based binary cross entropy (ABCE) is proposed for the first time to alleviate the statistical imbalance present within the Pima dataset. This ABCE loss function is incorporated in the DB-Lite model, which is trained from scratch. (ii) A Swish activation function is deployed in the hidden layer of DB-Lite instead of Rectified Linear Unit (ReLU) to deal with the non-linear dependency of features with the final outcome. (iii) The synthetic minority oversampling technique (SMOTE) is used as a pre-processing technique to mitigate the class imbalance problem from the Pima dataset. (iv) An adaptive learning rate is utilized while training the model to speed up the convergence of the DB-Lite model. Our final proposed framework has achieved 99.7% accuracy, 99.4% precision, 99.8% recall, and 99.6% F1 score in testing, which is the best result on this Pima dataset. The Welch t-testing (as a statistical hypothesis testing) and 10-fold cross-validation are utilized to prove the validity of the proposed loss function. 2025 -
An asymmetric analysis of overall globalization on financial inclusion
Purpose: Financial inclusion is acknowledged as a critical facilitator of the United Nations Sustainable Development Goals agenda for 2030. Therefore, this study aims to examine the asymmetric role of overall globalization on financial inclusion by controlling economic growth, urbanization and population for the selected South Asian countries. Design/methodology/approach: Applying the nonlinear autoregressive distributed lag approach to cointegration explores the impact of overall globalization on financial inclusion in the presence of additional variables like economic growth, urbanization and population in the designed financial inclusion function. Findings: The estimated econometric outcomes show that increasing overall globalization fosters financial inclusion while decreasing overall globalization reduces financial inclusion. Furthermore, a positive (negative) change in economic growth leads to an increase (decrease) in financial inclusion while varying short-run findings. Moreover, both positive and negative changes increase financial inclusion in the long run in connection with urbanization. Although the short-run results are not significant, the study finds that an increase (decrease) in population leads to a decrease (increase) in financial inclusion. Finally, to support the promotion of financial inclusivity throughout South Asia, several policies pertaining to financial inclusion are suggested. Originality/value: To the best of the authors knowledge, this is the first study to examine the asymmetries related to overall globalization on financial inclusion by controlling economic growth, urbanization and population. 2024, Emerald Publishing Limited. -
An asymmetric analysis of overall globalization on financial inclusion
Purpose: Financial inclusion is acknowledged as a critical facilitator of the United Nations Sustainable Development Goals agenda for 2030. Therefore, this study aims to examine the asymmetric role of overall globalization on financial inclusion by controlling economic growth, urbanization and population for the selected South Asian countries. Design/methodology/approach: Applying the nonlinear autoregressive distributed lag approach to cointegration explores the impact of overall globalization on financial inclusion in the presence of additional variables like economic growth, urbanization and population in the designed financial inclusion function. Findings: The estimated econometric outcomes show that increasing overall globalization fosters financial inclusion while decreasing overall globalization reduces financial inclusion. Furthermore, a positive (negative) change in economic growth leads to an increase (decrease) in financial inclusion while varying short-run findings. Moreover, both positive and negative changes increase financial inclusion in the long run in connection with urbanization. Although the short-run results are not significant, the study finds that an increase (decrease) in population leads to a decrease (increase) in financial inclusion. Finally, to support the promotion of financial inclusivity throughout South Asia, several policies pertaining to financial inclusion are suggested. Originality/value: To the best of the authors knowledge, this is the first study to examine the asymmetries related to overall globalization on financial inclusion by controlling economic growth, urbanization and population. 2024, Emerald Publishing Limited. -
An Assessment of Farmers' Perception and Adaptive Capacity for Climate Change
In the past decades, various regions in U.P. had experienced severe floods. The effects of climate change also affected agricultural production. This study investigated the farmers' perception of climate change and suggested strategies for mitigating its effects using a primary survey with the help of a pre-structured schedule. Change in rainfall pattern, problems in seed quality, the emergence of new pests and diseases, changes in the crop cycle were the few effects that farmers' perceived due to climate change. Even the most mitigation efforts by the farmers cannot prevent some of the impacts of climate change within the following decades. It makes adaptation a must-have for addressing these impacts. 2022, The Society of Economics and Development. All rights reserved. -
An artificial intelligence based smart cap with voice assistant for blind person /
Patent number: 202241013502, Applicant: Dr. Aruna S K.
People who are completely blind or have reduced eyesight confront numerous challenges while navigating. Every day, they face a variety of challenges, particularly in terms of mobility. Several systems have been developed to assist visually impaired people and improve their quality of life. This invention helps the blind to navigate independently using smart cap. It enables visually impaired people to see the world by voice assistance. It enables the blind and visually impaired to navigate freely by allowing them to experience their surroundings through audio output that describes the identified things. -
An artificial intelligence based smart cap with voice assistant for blind person /
Patent number: 202241013502, Applicant: Dr. Aruna S K.
People who are completely blind or have reduced eyesight confront numerous challenges while navigating. Every day, they face a variety of challenges, particularly in terms of mobility. Several systems have been developed to assist visually impaired people and improve their quality of life. This invention helps the blind to navigate independently using smart cap. It enables visually impaired people to see the world by voice assistance. It enables the blind and visually impaired to navigate freely by allowing them to experience their surroundings through audio output that describes the identified things. -
An artificial intelligence based smart cap with voice assistant for blind person /
Patent number: 202241013502, Applicant: Dr. Aruna S K.
People who are completely blind or have reduced eyesight confront numerous challenges while navigating. Every day, they face a variety of challenges, particularly in terms of mobility. Several systems have been developed to assist visually impaired people and improve their quality of life. This invention helps the blind to navigate independently using smart cap. It enables visually impaired people to see the world by voice assistance. It enables the blind and visually impaired to navigate freely by allowing them to experience their surroundings through audio output that describes the identified things. -
An artificial intelligence based smart cap with voice assistant for blind person /
Patent number: 202241013502, Applicant: Dr. Aruna S K.
People who are completely blind or have reduced eyesight confront numerous challenges while navigating. Every day, they face a variety of challenges, particularly in terms of mobility. Several systems have been developed to assist visually impaired people and improve their quality of life. This invention helps the blind to navigate independently using smart cap. It enables visually impaired people to see the world by voice assistance. It enables the blind and visually impaired to navigate freely by allowing them to experience their surroundings through audio output that describes the identified things. -
An artificial intelligence based smart cap with voice assistant for blind person /
Patent number: 202241013502, Applicant: Dr. Aruna S K.
People who are completely blind or have reduced eyesight confront numerous challenges while navigating. Every day, they face a variety of challenges, particularly in terms of mobility. Several systems have been developed to assist visually impaired people and improve their quality of life. This invention helps the blind to navigate independently using smart cap. It enables visually impaired people to see the world by voice assistance. It enables the blind and visually impaired to navigate freely by allowing them to experience their surroundings through audio output that describes the identified things. -
An artificial intelligence based smart cap with voice assistant for blind person /
Patent number: 202241013502, Applicant: Dr. Aruna S K.
People who are completely blind or have reduced eyesight confront numerous challenges while navigating. Every day, they face a variety of challenges, particularly in terms of mobility. Several systems have been developed to assist visually impaired people and improve their quality of life. This invention helps the blind to navigate independently using smart cap. It enables visually impaired people to see the world by voice assistance. It enables the blind and visually impaired to navigate freely by allowing them to experience their surroundings through audio output that describes the identified things. -
An Area-Efficient Unique 4:1 Multiplexer Using Nano-electronic-Based Architecture
Quantum dot cellular automata computing methodology is a new way to develop systems with less power consumption. Nanotechnology-based computing technology has enabled the QCA principles to be more relevant with respect to the critical limitations of current VLSI-based design. In this paper, a novel 4:1 multiplexer design based on the QCA concept is presented. As compared to the previous designs of a multiplexer, this novel design is area efficient and power efficient. A five-input majority voter is used for the design of the multiplexer. The 4:1 multiplexer is constructed by making use of three 2:1 multiplexer. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
An ARDL approach: case study of COVID-19 death and insurance stock returns
The movement of investment vehicles helps investors communicate as a stock market shield via a diverse portfolio. The COVID-19 outbreak had impacted the India along with other countries across the globe. The diseases progression and economic impact are highly uncertain. The current study is a novel effort to untangle the dynamic relationship between COVID-19 death and returns of NSE-listed life insurance stocks. We look at COVID-19 death data as well as returns from SBI Life, HDFC Life, and ICICI PRU from April 2020 to July 2021, when pandemic was the leading cause of death. Using the autoregressive distributed lag (ARDL) model technique, we discover that COVID-19 death has no dynamic relationship with the returns of selected life insurance stocks. In conclusion, our findings will provide stockholders, investment advisors, and policy experts with significant foresight into guaranteeing returns on life insurance stocks free from uncertain calamities such as COVID-19. Copyright 2025 Inderscience Enterprises Ltd. -
An Architecture for Risk-Based Authentication System in a Multi-Server Environment
Identity authentication, a vital part of any application access, is also one way for imposters to gain access to an application using various fingerprint authentication technologies. Therefore, because of the lack of security in the authentication architecture, this paper proposes an architecture for a risk-based authentication system using a machine learning model in a multi-server environment. Since the recent study mainly focuses on the multi-server environment and adaptive authentication independently, very little work has been proposed using a multi-server environment for adaptive authentication. The study aims to estimate risk for the user during the initial login process and when the user's data is extracted enough for prediction in a multi-server environment. 2023 IEEE. -
An Aqueous Phase TEMPO-Mediated Electrooxidation of Benzyl Alcohol at ?-CD-PPy-Modified Carbon Fibre Paper Electrode
A green and facile electrocatalytic method for the oxidation of benzyl alcohol in an acidic aqueous medium was developed using an anionic micellar system. ?-cyclodextrin-polypyrrole-modified carbon fibre paper (?-CD-PPy/CFP) electrode was successfully used in the oxidation of benzyl alcohol with TEMPO as the mediator. The modified electrode was characterized by cyclic voltammetry (CV), electrochemical impedance spectroscopy (EIS), scanning electron microscopy (SEM), fourier transform infrared spectroscopy (FTIR) and Raman spectroscopy. The modified electrode exhibited a strong electrocatalytic activity towards TEMPO-mediated oxidation of benzyl alcohol. [Figure not available: see fulltext.]. 2020, Springer Science+Business Media, LLC, part of Springer Nature. -
An aqueous phase TEMPO mediated electrooxidation of 2-thiophenemethanol using MnO2-Pi dispersed nanocarbon spheres on a carbon fiber paper electrode
An environmentally benign and economic method was developed for the electrocatalytic oxidation of 2-thiophenemethanol in an aqueous acidic medium. Nanocarbon spheres (NCS) coated on carbon fiber paper (CFP) were used as a host matrix to disperse manganese dioxide nanoparticles from phosphate buffer solution through electrochemical deposition. The developed electrode (MnO2-Pi-NCS/CFP) was used as a working electrode for electrochemical oxidation of 2-thiophenemethanol in the presence of a mediator TEMPO in 0.01 M H2SO4 medium. Different analytical methods were used to characterize the modified electrodes. Cyclic voltammetry (CV) and electrochemical impedance spectroscopy (EIS) were used to study the electrochemical properties of the modified electrodes. The electrochemically active surface area values calculated for bare CFP, NCS coated CFP and MnO2-Pi-NCS/CFP electrodes were found to be 1.43 cm2, 2.86 cm2, and 6.72 cm2 respectively for the geometric area of 0.7 cm2 of the electrodes. Coating of NCS and MnO2-Pi resulted in porosity and roughness of the CFP electrode which enhances the surface area. MnO2-Pi-NCS/CFP demonstrated higher electrocatalytic activity for oxidation of 2-thiophenemethanol to 2-thiophenemethanal in aqueous acidic media with a TEMPO mediator compared to unmodified electrodes. This journal is 2021 The Royal Society of Chemistry. -
An Approach to Introduce Mobile Application Development for Teaching and Learning by Adapting Allans Dual Coding Theory
This paper reveals around methodology that could be powerful to teach mobile applications in a class by including a decent utilization of innovative technology alongside a system. Appraisal instruments within the cloud were utilized to encourage this sort of methodology toward teaching application development. The new methodology is executed by teaching in the lab with desktops or in the classroom with students laptops. It adapted Allans dual code Theory. The adequacy of this methodology is obvious through an examination of outcomes. 2020, Springer Nature Switzerland AG. -
An approach to improvise recognition rate from occluded and pose variant faces
Face recognition is increasingly gaining popularity in today's field mainly because one of the major applications of face recognition, surveillance cameras are being used in real world applications. At the same time, researchers are trying to increase the accuracy of recognition as recognizing face from an unconstrained faces is naturally difficult. In the case of real world application, during image capture there are high chances of faces appearing with different poses, face subjected to illumination and occlusion. In this paper we propose a model that can increase the recognition rate with faces of different pose and faces subjected to occlusion. We introduce the technique of in-painting to restore the occluded face in a frame of video. A dictionary set is created with restored occluded face and faces with varying inclination. In our proposed model, Discrete Curvelet Transform is used to extract features. Comparison with traditional method shows a better recognition rate. 2015 IEEE. -
An approach to finding customer-value and devising marketing strategies by using data-mining techniques
The digital marketing space is an outcome of the advent of digital age and the booming network technology. The earlier methods of marketing have almost been eclipsed with this digital marketing, which could include any material, information, videos on the internet and social media, etc. The marked distinction between a digital and traditional marketing is that the former uses digital devices in the traditional space. People today consume innumerable products daily and getting to know the customer's interests, their transaction's history, identifying a loyal customer and estimating their lifetime value are all at the very heart of digital marketing. It is here, in this context, that data mining techniques play a key role. This unique blending of data mining techniques with digital marketing will help merchants increase their sales and revenue exponentially. This research paper explores the possibility of finding the frequent item-set generated by a customer while making purchases, tracking their loyalty based on the number of purchases and their frequency and thereafter devising an appropriate marketing strategy for that particular product type. It is the analysis of the product based on the previous marketing experiences of the consumer. This system will boost a merchant's businesses by identifying their loyal customers (customer segmentation), best sold products (product recommendation) and reveal the different marketing strategies that can be adopted by them to reach out to their potential customers and thus increase their sales (Strategy selection/combination). IAEME Publication. -
An approach to develop content based video modules /
Researchers World Journal Of Arts Science And Commerce, Vol.7, Issue 1, pp.101-104, ISSN: 2231-4172. -
An approach for mobile application design using Figma
With the increased mobile usage throughout the world, there is an enormous demand for mobile applications that provide not only good functionality but also good experience to the user, which is why it is important to have a good user interface for a mobile application. In this chapter, various components of an app are designed and illustrated in Figma software to make the work easier for a developer to create them. It also demonstrates the usage of Fig-ma. Meanwhile it shows the design thinking behind adding the correct colour schemes, right font, using proper white space, proper placement of buttons, and other design principles. 2023, IGI Global. All rights reserved.