Browse Items (2150 total)
Sort by:
-
A Road to Become Successful in The Fashion Industry of China: A Case Study of Zara
In this research, it was found that Zara is facing issues while maintain its profitability and also while maintaining its large stores. Existing information collected from websites and articles show that Zara provides inferior quality products, does not have factory in China, focuses less on e-commerce activities and contributes directly to environment pollution through waste generation in China. These are reasons that the organization is losing its brand image in China. To improve its current condition, it is recommended that Zara should improve its products, focus more on marketing, develop factories in China and reduce environment pollution. The Electrochemical Society -
Plant Disease Detection and Classification using Emperor Penguin Optimizer (EPO) based Region Convolutional Neural Network (RCNN)
Agriculture stands as India's most crucial industry, despite grappling with a 35% annual loss in crop yield attributed to plant diseases. Traditionally, the detection of plant diseases has been a laborious process, hampered by insufficient laboratory infrastructure and expert knowledge. Plant disease detection methods that are automated provide a useful way to expedite the labor-intensive process of keeping an eye on large-scale agricultural fields and recognizing disease symptoms as soon as they appear on plant leaves. Current developments in deep learning (DL) and computer vision have highlighted the benefits of creating autonomous models for plant disease identification based on visible symptoms on leaves. In this study, we propose a novel method for detecting and classifying plant diseases by combining the Emperor Penguin Optimizer (EPO) with a Region Convolutional Neural Network (RCNN). The suggested methodology uses EPO to improve the discriminative power of features extracted from plant pictures, allowing for a more robust and accurate classification procedure. The Classification Region Convolutional Neural Network (RCNN) is used to leverage spatial correlations within the image, allowing for exact disease region localization. The goal of this integration is to increase the overall efficiency and dependability of plant disease detection systems. The investigations made use of the well-known PlantVillage dataset, which comprises 54,305 data of different plant disease types in 38 categories. Furthermore, an analysis was carried out in comparison with similar advanced investigations. According to the experiment results, RCNN-EPO outperformed in terms of classification accuracy, achieving 94.552%. 2024 IEEE. -
Bibliometric Analysis: A Trends and Advancement in Clustering Techniques on VANET
In recent years, Traffic management and road safety has become a major concern for all countries around the globe. Many techniques and applications based on Intelligent Transportation Systems came into existence for road safety, traffic management and infotainment. To support the Intelligent Transport System, VANET has been implemented. With the highly dynamic nature of VANET and frequently changing topology network with high mobility of vehicles or nodes, dissemination of messages becomes a challenge. Clustering Technique is one of the methods which enhances network performance by maintaining communication link stability, sharing network resources, timely dissemination of information and making the network more reliable by using network bandwidth efficiently. This study uses bibliometric analysis to understand the impact of Clustering techniques on VANET from 2017 to 2022. The objective of the study was to understand the trends & advancement in clustering in VANET through bibliometric analysis. The publications were extracted from the Dimension database and the VOS viewer was used to visualize the research patterns. The findings provided valuable information on the publication author, authors country, year, authors organization affiliation, publication journal, citation etc. Based on the findings of this analysis, the other researchers may be able to design their studies better and add more perception or understanding to their empirical studies. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Comparative Performance Analysis of Machine Learning and Deep Learning Techniques in Pneumonia Detection: A Study
Pneumonia is a bacterial or viral infection that inflames the air sacs in one or both lungs. It is a severe life-threatening disease, making it increasingly necessary to develop accurate and reliable artificial intelligence diagnosis models and take early action. This paper evaluates and compares various Machine Learning and Deep Learning models for pneumonia detection using chest X-rays. Six machine learning models -Logistic Regression, KNN, Decision Tree, Random Forest, Naive Bayes, and Support Vector Machines - and three deep learning models - CNN, VGG16, and ResNet - were created and compared with each other. The results exhibit how just the model choice can significantly affect the quality and inerrancy of the final diagnostic tool. 2023 IEEE. -
Impact of green bonds issuance on stock prices - Evidence from India
Today, with the increasing global warming, many companies are trying to adopt sustainable ways of producing the product and preserve the atmosphere. A green bond is one such financial tool that helps companies to raise the funds for social and eco-friendly projects. Keeping this in view and the Indian market emerging as the second-largest bond market in terms of green bond issuance; this paper aims to identify the impact on stock prices due to the issuance of green bonds by the companies. We conduct an event study to understand how the stock prices are subject to volatility due to green bond issuance during the period 2018-2021. The data is collected from secondary sources like Economic Times, Business Standard, Climate Bond Initiative, and the BSE website. The event window is assumed to be [-30,30], [-15, 15] and [-7, 7] days. Using Cumulative Average Abnormal returns and t-tests we understand the volatility of stock prices due to green bond issuance. The empirical results show that green bonds have a short-term impact on stock prices. Overall, the study can be a great input for the investors to understand the behavior of stocks due to the issuance of green bonds. 2023 Author(s). -
A comparitive study on traditonal healthcare system and present healthcare system using cloud computing and big data
Cloud computing is one the emerging technology which provides all the necessary resources required for day to day operations of an organization in a virtual environment. It is also known as green computing as it reduces the physical existence of the hardware resources. Health is being considered as a basic right for an individual. Even though there are advancements in the healthcare sector of India when compared to earlier stages, there is still a need for betterment in this sector. In order to make progress in this field, constant learning and better economic standards are needed. This paper provides a comparative view of the progress made by India in the healthcare sector after the introduction of two major technologies such as cloud computing and big data. 2017 IEEE. -
Analysis on emotion-aware healthcare and Google cloud messaging
Cloud computing has the potential to get integrated with the healthcare sector. It provides functionality for managing data in a distributed environment. The concept of Healthcare services is becoming popular in the Healthcare sector as it helps the patients to get immediate access regarding his/her health related information whenever needed and wherever needed using cloud computing technology. The Big Data Application in Emotion-aware Healthcare system [BDAEH], gives attention to both the emotion factor and logical reasoning of the user. The basic functions of this system are collecting health-related data, transmitting the collected data, analyzing the received data, storing them and making it available to a user in order to perform diagnosis and predict medications. Mobile devices are becoming an essential tool in our day to day lives. By integrating the concept of Google Cloud messaging alongside BDAEH system, numerous tasks can be done efficiently. 2017 IEEE. -
Performance analysis of Clustering algorithms for dyslexia detection
Clustering algorithms plays vital role in analysing and evaluating vast number of high dimensional health care data ranging from medical data repositories, clinical data, electronic health records, body sensor networks, IoT devices, and so on. Dyslexia, a learning disorder is a common problem that is found in children during the initial stages of formal education, which is detected as mild to severe. It can also be one of the reasons of failure in the school. According to the literature this difficulty is commonly seen among Special Education Need children. There are few studies focussed on the application of classification algorithms for detecting the presence of dyslexia. This paper focusses one of SDG, goal 4:Quality Education, as dyslexic students can be given equal and quality education. Analyses of an online gamified test-based dataset is done by applying various clustering techniques such as K-means, Fuzzy c-means, and Bat K-means to assess their effectiveness in detecting the problem dyslexia. As the dataset is large, it is observed that usage of clustering methods gives us gain insight into the distribution of data to observe characteristics of each cluster. The clustering results are evaluated using root mean squared error (RMSE), mean absolute error (MAE), Xie-Beni index and it is found K Means outperforms FCM, Bat K Means algorithm for analysing different levels of the learning disorder. The Electrochemical Society -
Dynamic job sequencing of converging-diverging conveyor system for manufacturing optimization
Some sectors, such as dairy, automobile, pharmaceutical, computer and electronics, require a range of manufacturing steps to produce a component. The goods in these industries are produced in varieties and the output volume varies from low to high. Typically, these types of businesses use a conveyor system that could have a combination of a diverging and converging conveyor system due to a variety of processing phases involved in the development of the commodity. A conceptual model of the of conveyor system is described, which works manually and to illustrate the importance of the sequence using buffer the buffer layout is modeled and compared to the manual layout. The genetic algorithm is used to find the optimal buffer storage. It can be observed that by adapting various sequencing methods there will be reduction in manufacturing time and setup cost. 2022 Elsevier Ltd. All rights reserved. -
Consolidation of Cloud Computing in Smart and Sustainable Environment
Cloud computing has revolutionized IoT device data collection, administration, and analysis by offering a scalable and sustainable solution for managing vast amounts of data. The paper highlights cloud computing's benefits in data processing, device management, cost efficiency and scalability. However, challenges related to security, data ownership, and vendor lock-in require attention. A novel sustainable cloud-IoT model is presented by integrating smart computing with cloud infrastructure. It is observed that the model records promising performance. The mean response delay is 1.9 seconds and the 89.5% is the generated mean computational storage accuracy rate. In conclusion, the cloud computing empowered sustainable model can be used in organizations to gain insights from IoT data and make informed decisions, shaping future research in this rapidly evolving field. 2023 IEEE. -
Deep Learning Character Recognition of Handwritten Devanagari Script: A Complete Survey
Recognition of handwritten characters is a concept in which the single characters are classified, it is a facility of an electronic device to scan and decipher the handwritten input from a variety of sources, including written texts, images, and other digital touch-screen devices. This concept is being used in distinctive sectors such as the processing of bank checks, form data entry, and parcel posting and nowadays it is becoming a very important issue in the pattern recognition domain and a very challenging task to resolve it. Since deep learning is a crucial strategy in solving detection and pattern recognition problems, several algorithms are available to classify the characters with better prediction rates on different datasets, and ultimately, whichever algorithm gives the optimized results will be considered the best solution for the character recognition problem. As a result, various solutions proposed by the existing researchers are discussed using deep learning algorithms in this survey article. 2023 IEEE. -
A Comparative Investigation on the use of Machine Learning Techniques for Currency Authentication
In the present banking sector, identifying the real and the fake note is a very challenging task because if we do it manually, it takes a long time to check which is real and which is fake. This research study article aims to authenticate the money between real and fake by using different machine algorithms facilitating learning, such as K-means Clustering, Random Forest Classification, Support Vector Machines, and logistics Regression. Specifically, we consider the banknote dataset. The data of money is extracted from various banknote images by using the wavelet transform tool, which is primarily used to remove elements from the images. However, we are mainly concerned with the different machine learning algorithms, so we take the two variables, where the first variable indicates image variance and the second indicates image skewness. We use these two variables to train our machine learning algorithms. So, majorly, by applying the different machine learning algorithms, which are supervised and unsupervised, we find the accuracy for the respective machine learning algorithms and then visualize and classify the real and fake notes separately. Finally, the prediction is based on integrity, which means the efficiency value is based on how much the mechanism system can uncover the fake notes. Then, after calculating the accuracy of currency authentication, there is a high possibility that the accuracy of the particular algorithm is the best algorithm, so the application of currency authentication will be very useful for the bank to easily find duplicate notes. 2022 IEEE. -
Profit function Optimization for Growing Items Industry
The economy of a country depends on many industries; growing item industries are one of them. Growing items also exhibit mortality in the growth period, which creates a complex environment for the procurement decision. A practical inventory model is required to overcome this situation, which provides the optimum solution. This work describes an economics ordering quantity model for growing items with constant demand and mortality. We also take into consideration that one of the real-life management practices for businesses is the allowance of a delay in payment. There is a solution procedure with a numerical example. We have discussed analytical results to verify the concavity of the profit function. Sensitivity analysis provides us with some very useful information. . 2023 IEEE. -
An Inventory Model for Growing Items with Deterioration and Trade Credit
Growing items industry plays a vital role in the economy of most of the countries. Growing item industries consists of live stocks like sheep, fishes, pigs, chickens etc. In this paper, we developed a mathematical model for growing items by considering various operational constraints. The aim of the present model is to optimize the net profit by optimizing decision variables like time after growing period and shortages. Also, the delay in payment policy has been used to maximize the profit. A numerical example is provided in support of the solution procedure. Sensitivity analysis provides some important insights. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Brain Tumor Classification: A Comparison Study CNN, VGG 16 and ResNet50 Model
Brain tumors pose a severe threat to global health and may be lethal. Early detection and classification of brain tumors are essential for successful therapy and better patient outcomes. The good news is that advances in deep learning techniques have shown tremendous promise in medical image analysis, particularly in the detection and classification of brain tumors. Convolutional Neural Networks (CNN), a class of deep learning models, are used to process and analyze visual input, notably images, and movies. They excel in computer vision tasks like object detection, image segmentation, and categorization. Popular and efficient image analysis methods include CNNs. VGG 16 and ResNet 50 are two examples of deep convolutional neural network architectures used for image categorization applications. A number of image identification problems have been successfully solved using the 16 layer VGG 16. ResNet50, a well known 50 layer architecture, employs residual connections to get over the vanishing gradient issue and permits the training of deeper networks. A proprietary CNN model, VGG 16, and ResNet50 were compared in studies to see how well they performed on a dataset. The VGG 16, ResNet50, and the tailored CNN model were the most precise models. As a consequence, VGG 16 accurately detects brain cancers in the dataset that was supplied. Overall, this study highlights the value of deep learning techniques for medical image processing and their potential to improve the accuracy and efficacy of brain tumor diagnosis and treatment. 2023 IEEE. -
Pattern Recognition: An Outline of Literature Review that Taps into Machine Learning to Achieve Sustainable Development Goals
The sustainable development goals (SDGs) as specified by the United Nations are a blueprint to make the Earth to be more sustainable by the year 2030. It envisions member nations fighting climate change, achieving gender equality, quality education for all, and access to quality healthcare among the 17 goals laid out. To achieve these goals by the year 2030, member nations have put special schemes in place for citizens while experimenting with newer ways in which a measurable difference can be made. Countries are tapping into ancient wisdom and harnessing newer technologies that use artificial intelligence and machine learning to make the world more liveable. These newer methods would also lower the cost of implementation and hence would be very useful to governments across the world. Of much interest are the applications of machine learning in getting useful information and deploying solutions gained from such information to achieve the goals set by the United Nations for an imperishable future. One such machine learning technique that can be employed is pattern recognition which has applications in various areas that will help in making the environment sustainable, making technology sustainable, and thus, making the Earth a better place to live in. This paper conducts a review of various literature from journals, news articles, and books and examines the way pattern recognition can help in developing sustainably. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Powering Ahead: Navigating Opportunities and Challenges in the Electric Vehicle Revolution
The technology is clearing ways for buzz in the market brimming with innovative items and new prospects. The government has planned to shift to electric vehicles by 2030, whether it is for personal or commercial use. As innovative improvements are developing quickly, it is blasting the market with the EVs industry which expected to transform the future (Rajkumar S, in Indian electric vehicle conundrum: a tale of opportunities amid uncertainties, 2020). Volvo company has also announced that it will be fully electric by 2030 (https://gadgets.ndtv.com, in Volvo to go all electric by 2030, sell exclusively online, 2021). It is expected that EVs will generate more demand for electricity and help in settling the focus on resources problem. It will also help in improving the financial feasibility of power sector projects. In India, there is more dependency on renewable energy so this is a chance to be independent and provide cheap power to the people. The EVs are more economical than petrol or diesel vehicles. The government is also giving incentives to the makers of electric vehicles. GST on electric vehicles is 12% as compared to petrol and diesel vehicles with 28% GST. As per the Electricity Act, 2003, a distribution license is needed to supply power from respective state electricity regulatory commissions. Another challenge is that charging the EVs will lead to a rise in the demand of electricity which is risky for the electricity distribution companies (www.livemint.com, in Indias electric vehicle drive: challenges and opportunities, 2017). Indians are very price conscious. A recent study revealed that Indians are ready to compromise on more charging time, but they are not ready to pay higher price for EVs (Gupta NS, in Electric vehicle adoption in India: study reveals three tipping points, 2020). From Fig.1, it can be seen that in 2014 investment in EVs was $2.2 billion which has increased to $406 billion in 2019 (Shanti S, in The road to green: what makes electric vehicle adoption a challenge for India. 2020). This shows that people are shifting toward EVs. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Comparing keyframe extraction for video summarization in CPU and GPU
Most of the information is captured through multimedia techniques. Videos contain many frames which might be redundant. Since processing of many frames is involved, these redundant frames must be removed for better and efficient results. Summarizing these frames by removing similar frames can speed up processing. In this paper video summarization is achieved by generating key frames. Key frames are generated using discrete wavelet transforms (DWT) technique and we subtract background from the keyframes to get region of interest. A video of 920&Times;720 resolution and length 120 second was used as test video and the run-time was 111 second in CPU and 60 second in GPU. The speed up is nearly 100%. A HD video which took 23 minutes in serial implementation to extract foreground object from key frames generated was reduced to 7 minutes using GPU acceleration. 2015 IEEE. -
Radon transform processed neural network for lung X-ray image based diagnosis
A novel method for image diagnosis with artificial learning is presented-ray images tuberculosis patients is subjected to neural network learning for prediction of diagnosis. The X-ray images of lungs are normally difficult for diagnosis, since its similarity to lung cancer. Under and over diagnosis of lung X-ray images is a difficult medical problem to resolve. In the present work radon transform of the x-ray images is fed to back propagation neural network trained with Levenberg algorithm. The present methodology gives sharp results, distincting the normal and abnormal images. 2014 IEEE. -
Parallelizing keyframe extraction for video summarization
In current era, most of the information is captured using multimedia techniques. Most used methods for information capturing is through images and videos. In processing a video, large information needs to be processed and a number of frames could contain similar information which could cause unnecessary delay in gathering the required information. Video summarization can speed up video processing. There are different techniques for video summarization. In this paper key frames are used for summarization. Key frames are extracted using discrete wavelet transforms. Two HD videos having 356 frames and 7293 frames were used as test videos and the runtime was 17 seconds and 98 seconds respectively in CPU and 11 seconds and 53 seconds respectively in GPU. 2015 IEEE.