Browse Items (2150 total)
Sort by:
-
Classification of Vitiligo using CNN Autoencoder
Precise recognition of skin ailment is a time-consuming procedure even for Professionals. With the invention of deep learning and medical image processing, the identification of skin disease is possible in a time-efficient manner and accurately. Autoencoder is the generative algorithm but in the proposed work it is used as a generator and as well as a classifier. In this work, a Convolutional (CNN) autoencoder was used to classify the skin disease Vitiligo. In this work encoding and decoding layers were used but in the last layer in place of reproducing the original image, the classification layer was used to classify the image. The proposed work gave training accuracy of 87.71 % whereas validation accuracy was 90.16%. 2022 IEEE. -
Corroboration of skin diseases: Melanoma, vitiligo vascular tumor using transfer learning
The precise identification of skin disease is an exigent process even for more experienced doctors and dermatologists because there is a small variation between surrounding skin and lesions, a visual affinity between different skin diseases. Transfer learning is the approach which stores acquired knowledge while solving one problem and apply that knowledge to similar problems. It is a type of machine learning task where a model proposed for a task can be used again. Transfer learning is used in various areas like image processing and gaming simulation. Image processing is an evolving field in the diagnosis of various kinds of skin diseases. Here transfer learning is used to identify three skin diseases such as melanoma, vitiligo, and vascular tumors. The inception V3 model was used as a base model. Networks were pre-trained and then fine-tuned. Considerable growth of training accuracy and testing accuracy were achieved. 2021 IEEE. -
Effective Emoticon Based Framework for Sentimental Analysis of Web Data
The Explosive development in the social media domain has created a platform for mass generation of textual and emoticon based web data from micro blogging sites. Sentimental Analysis refers to analysis of sentiments or emotions from such heterogeneous reviews are the present urge of the market. Thus, an effective emoticon based framework is proposed which generates scores of both textual and emoticons into seven layered categories using SentiWordNet and weighs performance of various machine learning techniques like SVM/SMO, K-Nearest Neighbor (IBK), Multilayer Perception (MLP) and Naive Bayes (NB). Using Jsoup crawler input reviews are obtained and processed with initial pre-processing model for emoticons and text data followed by stemming and POS tagger. Projected framework is investigated on college and hospital dataset obtaining upper attainment level by Kappa statistic metrics having 98.4% correctness and lesses bug value. Proposed Framework showcases greater competence score with lesser FP Rate based on weighted average of correctness measures. The investigational outcomes are tested on training data with Ten-Fold cross validation. The outcome reveals that suggested emoticon based framework for the task of Sentimental analysis can be efficaciously applied in online decision job. 2019, Springer Nature Singapore Pte Ltd. -
Feature Based Fuzzy Framework for Sentimental Analysis of Web Data
Social mass media has emerged as a projectile platform for the evolution of web data. The sentimental Analysis where the huge textual online reviews are analyzed to extract the actual sentiment or emotions hidden in the reviews. In this paper an effective approach for sentimental analysis of web data is proposed which deploys the fuzzy based machine learning algorithm to accomplish fine-level sentiment analysis of huge online opinions by assimilating the fuzzy linguistic hedges influence on opinion descriptors. The seven layered categories are designed that uses SentiWordNet which has three stages: Pre-processing phase, Feature Selection Phase and Fuzzy based Sentiment Analysis phase. Various machine learning algorithms like AdaBoost, (IBK) K-Nearest Neighbour, (NB) Nae Bayes and (SVM)/SMO Support Vector Machine are used for classification. Jsoup is implemented for gathering web opinions which are subjected to initial processing task later applied with stemming and tagging. This fuzzy based methodology is investigated for Mobile, Laptops dataset, also compared with state-of-the-art approaches which demonstrate upper indication of 94.37% accurateness through Kappa indicators showcasing lesser error rates. The investigational outcomes are tested on training data using Ten-Fold cross validation which concludes that this approach can be efficaciously used in Sentimental analysis as an aid for online decision. 2019 IEEE. -
An Innovative Method for Enterprise Resource Planning (ERP) for Business and knowledge Management Based on Tree MLP Model
This strategy highlights the benefits of utilizing cutting-edge IT to back up company goals and genuinely assist in changing internal procedures by implementing an ERP-appropriate solution. Any organization, no matter how big or little, can benefit from an enterprise resource planning (ERP) system, which is an integrated suite of tools designed to streamline and improve internal business operations. Staying true to this approach will ensure that you get the greatest results while training the model, selecting features, and doing preprocessing. In order to use dense vector embedding for preparing the raw system logs, ERP system logs are typically represented by a combination of alphanumeric characters. While selecting features, SIM uses Particle Swarm Optimization (PSO) to create uniform product configurations. Using a Tree-MLP, the model was trained. This new strategy outperforms the old one, including Decision Tree and MLP. A 94.30% improvement in accuracy was achieved after implementing the technique. 2024 IEEE. -
Multimodal Emotion Recognition in HumanComputer Interaction Using MFF-CNN
The rise of technology in the digital era has amplified the importance of understanding human emotions in enhancing humancomputer interactions. Traditional interfaces, mainly focused on logical tasks, often miss the nuances of human emotion, creating a gap between human users and technology. Addressing this gap, the development of the HumanComputer Interface for emotional intelligence uses advanced algorithms and deep learning models to accurately recognize emotions from various cues like facial expressions, voice, and written text. This paper presented a significant approach for emotion detection in HCI and the challenges faced in capturing genuine emotional responses. Historically, the emphasis in HCI design was on operational tasks, neglecting emotional nuances. However, the tide is changing toward embedding emotional intelligence into these interfaces, leading to enhanced user experiences. This research introduces the MFF-CNN, a neural network model combining both textual and visual data for accurate emotion detection. Through sophisticated algorithms and the integration of advanced machine learning techniques, this paper presents a refined approach to emotion detection in HCI, supported by a comprehensive review of related works and a detailed methodology. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
A Systematic Study on Unimodal and Multimodal Human Computer Interface for Emotion Recognition
A systematic study for human-computer interface (HCI) for emotion recognition is presented in this paper, with a focus on various methods used to identify and interpret human emotions. It delves into various methods used to identify and interpret human emotions and highlights the limitations of unimodal HCI for emotion recognition systems. The paper emphasizes the benefits of multimodal HCI and how combining different types of data can lead to more accurate results. Additionally, it highlights the importance of using multiple modalities for emotion recognition. The study has significant implications for mental health assessments and interventions as it offers insights into the latest techniques and advancements in emotion recognition. Future research can use these insights to improve the accuracy of emotion recognition systems, ultimately leading to better mental health assessments and interventions. Overall, the paper provides a valuable contribution to the field of HCI and emotion recognition, and it underscores the importance of taking a multimodal approach for this critical area of research. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Business and Environmental Perspectives of Submarine Cables in Global Market
If an individual uses any of the social media networking sites, such as Facebook, Instagram, YouTube, Twitter and the like, a subsea cable is involved there. Submarine cables are considered as critical global communications infrastructure. These cables are used by various telecom providers and content provider companies such as Google, Facebook, and Microsoft to provide seamless transmission of data for their services. Growing internet users and increasing internet traffic for various social media sites is the major reason for the growth of this market. Submarine cables enable data services such as the email, internet banking, social media networking, search engines and all other aspects related to internet that are taken for granted in daily life. These submarine cables scales up the ubiquity of cloud computing and builds digitization of activities. Undersea cable network is the new economic trade route and acts a commodity in Information age. This paper reviews the business and environmental impacts of submarine cables in the global market. Springer Nature Switzerland AG 2020. -
Performance analysis of OFF-GRID solar photo voltaic system
Day by day the demand for electrical energy is increasing. We can't rely on conventional energy sources for meeting this increasing demand as they are depleting. So it is necessary to find an alternative method to harness the energy that we are lacking. Solar energy generation seems to be a promising technology for this dilemma. It is environmental friendly and infinite source of energy. Photovoltaic systems can be broadly classified into two-an on-grid system or an off-grid system. The energy generated from a solar PV system is based on several factors like irradiance, types of solar PV used and temperature. Analyzing the existing system efficiency is of prime importance for the characterization of the problems and for the improvements. This study deals with the performance analysis of an on-grid and off-grid system. The analysis is carried out by modeling an existing system in MATLAB/SIMULINK which is already in operation. It can be extended to analyze the grid stability. This study aims the quantification of various performance parameters like power output, losses in the system, system efficiency and the total energy transfer. 2015 IEEE. -
An Effective Deep Learning Classification of Diabetes Based Eye Disease Grades: An Retinal Analysis Approach
Diabetic Retinopathy (DR) is a common misdiagnosis of diabetes mellitus, which damages the retina and impairs eyesight. It can lead to vision impairment if it is not caught early. Tragically, DR is an unbreakable cycle, and treatment only serves to reinforce the perception. Early detection of DR and effective treatment can significantly lower the risk of visual loss. In comparison to PC-aided conclusion frameworks, the manual analysis process used by ophthalmologists to diagnose DR retina fundus images takes a lot of time, effort, and money and is prone to error. As of late, profound learning has become quite possibly the most well-known procedure that has accomplished better execution in numerous areas, particularly in clinical picture examination and classification. Thereby, this paper brings an effective deep learning-based diabetes-based retinography in which the following are the stages: a) Data collection from MESSIDOR which contains 1200 images classified into 4 levels and graded from 03 followed by b) Preprocessing using grayscale normalized data. Then followed by c) feature extraction using Discrete Wavelet Transform (DWT), d) feature selection using Particle Swarm Optimization (PSO) and finally given for e) classification using Densenet 169. Experimental states that the proposed model outperforms and effectively classified grades compared to other state-of-art models (accuracy:0.95, sensitivity:0.96, specificity;0.97). 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Retention of a Community Healthcare Worker for Three Decades in a Rural and Remote CHC of Bolba in Jharkhand: A Case Study
The dearth of healthcare personnel in rural areas is a global problem. Even developed countries are struggling to meet demand. In such circumstances, identifying a health worker who worked for a single CHC for three decades necessitates deeper exploration. Individual case studies were employed to investigate the phenomenon, then thematically evaluated using QAD Miner Lite following a lengthy telephonic interview. The study's findings revealed that a rural upbringing, social class, economic factors, and behaviourism influenced the altruism of Community Healthcare Workers (CHWs). As a result, external and internal factors influenced CHW to service rural areas. But extrinsic factors worked in tandem with intrinsic factors to influence CHW's willingness to serve the rural areas. Rural healthcare shortages exist despite the National Rural Health Mission (NRHM) execution. A substantial amount of the population's health is entrusted to 20 percent of health workers, who account for disproportionately 75.05 percent of rural health outcomes. The Electrochemical Society -
Impact of AI in Financial Technology- A Comprehensive Study and Analysis
Presently across the world, financial institutions strive tremendously hard to make financial services smarter to benefit from the advantages of digitization. To enhance client services, financial technology (Fintech) uses a variety of modern breakthrough technologies, including Artificial Intelligence (AI), 5G/6G, Blockchain, Metaverse, IoT, and others, in the financial sector. Many important financial services and procedures, including loans, authentication, fraud detection, quality control, creditworthiness, and several more, would be streamlined and improved by the adoption of technology. However, a need exists for the development of innovative financial products as well as the corresponding technological ecosystem. To launch Information and Communication Technology (ICT) alternatives, various major tech companies have placed their emphasis on Fintech. In this paper, we first explore the latest opportunities in Fintech. Furthermore, we also attempt to present a foundation of the Fintech accelerators, such as IoT, 5G, Digital twins, and Metaverse. Additionally, we also outline recommendations for future research directions in Fintech while looking forwards to potential difficulties. 2023 IEEE. -
Convective instability in a horizontal porous layer saturated with a chemically reacting Maxwell fluid
The problem of onset of convective instability in a horizontal inert porous layer saturated with a Maxwell viscoelastic fluid subject to zero-order chemical reaction is investigated by linear stability analysis. Modified Darcy-Maxwell model is used to describe the fluid motion. The horizontal porous layer is cooled from the upper boundary while an isothermal boundary condition is imposed at the lower boundary. Closed form solution pertaining to the basic quiescent state is obtained. The resulting eigenvalue problem is solved approximately using the Galerkin method. The Rayleigh number, characterizing the stability of the system, is calculated as a function of viscoelastic parameter, Darcy-Prandtl number, normalized porosity, and the Frank-Kamenetskii number. The possibility of oscillatory instability is discussed. 2013 AIP Publishing LLC. -
Fabrication of Didactic Model to Demonstrate Bottle Filling System Using Programmable Logic Controller
Automation is the evolution of manufacturing process which will ideally lead to e-governance. It helps humans and machines to be connected at the hip, blending the cerebral aptitudes of human and specialized abilities of automated bots to immune the workspace. Automated system has enhanced the modern day market by increasing the quality of the product as well as making the fabricating process time efficient. Lights out technology in industry promotes the robots to do work even after working hours when the lights are shut down in industry. In this research paper, a unique approach is used to fabricate a didactic model which demonstrates the working of a bottling plant which may be preferred for medium and small scale industries. To implement the process, CODESYS is used to program CPX-CEC-C1 PLC, a digital computerized system which performs logical decisions and provides outputs based on sensor inputs. The main focus is towards interfacing pneumatics and hydraulic components with PLC. 2021, Springer Nature Singapore Pte Ltd. -
The Influence of Mobile Commerce on Consumer Behavior: A FCM-RF-DNN Analysis
For m-commerce vendors, the difficulty is to decipher what factors impact customer actions in the ubiquitous mobile setting. In addition, companies are attempting to incorporate social media into their mobile approach in some way. This proposed approach to the findings of a qualitative exploratory study regarding the use of social media and smartphones within the framework of mobile commerce. Keep in mind the order of importance while doing data preprocessing, feature selection, and training the model. The usual steps in getting data ready for processing, such as cleaning it, identifying users and sessions, and finding episodes. The IS-DT suggested method's implementation technique is utilized in feature selection. Unified FCM-RF-DNN models need to be trained after features have been retrieved. Two state-of-the-art approaches, RF and DNN, are outperformed by the suggested approach. Following the implementation of the method, accuracy improved by 96.13%. 2024 IEEE. -
A Novel Approach to Enhance Influencer Marketing in E-commerce: A Cross-A-Siamese Perspective
One of the most notable aspects of the Internet is the fact that the cost of (global) communication has been drastically decreased. Individuals may potentially reach massive audiences with their messages over the Internet due to its widespread use. With the rise of blog services, social networking platforms, etc., people's technological talents are no longer a limiting factor. Data preprocessing, feature selection, and model training should all be done in this sequence of significance. Applying fundamental data preparation techniques guaranteed the data's accuracy and relevancy. Feature selection includes the computation of an influencer's overall rank based on six important criteria, which are used for influencer identification and ranking. Feature retrieval is the first step in training Unified Cross-A-Siamese models. The proposed method outperforms two cutting-edge methods: Attention module and siamese. Accuracy increased by 95.70 percent once the approach was used. 2024 IEEE. -
Machine Learning Based recommendation system Using User-Item Interaction
Electronic commerce, or e-commerce, is the activity of trading services and commodities through the internet. Identifying the item that the consumer may buy from the enormous number of possibilities accessible to solve this difficulty is now one of the key difficulties encountered by most E-commerce businesses. Recommender systems have been implemented. Recommender systems (RS) are systems that collect information from users about their preferences and allow them to make decisions from the available options. Today, various recommender systems are growing with the advent of web-based information. As you can see from various articles, such recommender systems are used in a variety of industries, from simple objects to more sophisticated objects.RS has gained popularity in the previous decade, particularly in the realm of E-Commerce and related sectors. This report aims to identify recent developments as well as their potential for improvement. It is intended to elaborate on a number of points. And also work more on user-item based recommendation. These types of user-item based recommendation will be more effective in fashion area. 2022 IEEE. -
Modernizing Electrical Grids with TCR-Based Flexible AC Transmission Systems
Modernizing electrical grids is imperative to meet the growing demand for reliable, efficient, and sustainable energy. Thyristor-Controlled Reactors (TCRs) are integral components of modern Flexible AC Transmission Systems (FACTS). These systems offer a robust solution for enhancing grid stability, improving power quality, and optimizing transmission efficiency, ensuring that electric grids can support future energy needs. TCR-based FACTS are a collection of technologies designed to enhance the controllability, stability, and power transfer capability of AC electrical grid systems. In this paper, we will discuss the role of TCRs in modernizing AC transmission systems and their role in addressing grid challenges and improving performance, highlighting their critical role in future grid infrastructure. To discuss the future prospects and developments in TCR technology, with ongoing advancements and research efforts paving the way for more efficient, reliable, and flexible grid management solutions. The Authors, published by EDP Sciences, 2024. -
Internet of Things and Machine Learning based Intelligent Irrigation System for Agriculture
Irrigated agriculture methods need a significant volume of water, and causes water waste. It is critically necessary to install an efficient watering system and lessen the volume of water wasted on this tiresome chore. It is a huge benefit of the computer vision (ML) - the Internet of Everything (Ot) era to construct expert machines that carry out this work successfully with little human endeavour. This work suggests an Embedded device Fluid ounces suggestion method for efficient water use with little farm involvement. In the agricultural field, IoT sensors are set up to capture important atmospheric and surface data. The obtained information is sent to and stored on a cloud-based server, where machine learning techniques are used to evaluate the information and recommend treatment to the farmers. This recommender system has an internal development process that makes the solution resilient and flexible. The test demonstrates that the suggested method operates admirably on the agricultural dataset from the National Institutes of Technology (Kit) Bhubaneswar as well as the information that we obtained. 2022 IEEE. -
Oppositional Glowworm Swarm based Vector Quantization Technique for Image Compression in Fiber Optic Communication
In recent times, fiber optic communication networks have become commonly applied for commercial as well as military applications. Fiber optic networks have gained popularity owing to the high data rate. At the same time, the generation of huge quantity of data at a faster rate poses a major challenge in the storing and transmission process. To resolve this issue, data compression approaches have been presented to reduce the quantity of transmitted data and thereby minimizes bandwidth utilization and memory. Vector quantization (VQ) is a commonly employed image compression technique and Linde Buzo Gray (LBG) is used to construct an optimum codebook to compress images. With this motivation, this paper presents a new oppositional glowworm swarm optimization based LBG (OGSO-LBG) technique for image compression in fiber optic communication. The OGSO algorithm involves the integration of oppositional based learning (OBL) concept into the GSO algorithm to boost its convergence rate. The OGSO-LBG algorithm produces the codebook at a faster rate with minimal computation complexity. In order to highlight the enhanced compression performance of the OGSO-LBG technique, a series of experiments were carried out and the results are examined under different dimensions. 2021 IEEE