Browse Items (11858 total)
Sort by:
-
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. -
Farming Futures: Leveraging Machine Language for Potato Leaf Disease Forecasting and Yield Optimization
Crop yield prediction is of paramount importance in modern agriculture. It serves as a linchpin for ensuring food security, efficient resource management, risk mitigation, environmental sustainability, and socioeconomic development. Accurate predictions enable us to maintain a stable food supply, optimize resource allocation, and manage the uncertainties associated with climate and market fluctuations. By fostering sustainable farming practices, crop yield prediction also plays a crucial role in reducing environmental impact and promoting rural development. Integrating artificial intelligence (AI) and machine learning (ML) in modern agricultural practices offers the potential to revolutionize the way we produce food, making it more sustainable, efficient, and resilient. This study has demonstrated the effectiveness of convolutional neural networks (CNNs) in the classification of potato leaf disease, achieving remarkable results with a test loss of 0.0757 and a test accuracy of 0.9741. 2024 Taylor & Francis Group, LLC. -
Elevating medical imaging: AI-driven computer vision for brain tumor analysis
Artificial Intelligence (AI) applications in the realm of computer vision have witnessed remarkable advancements, reshaping various industries and solving complex problems. In this context, this research focuses on the use of convolutional neural networks (CNNs) for classifying brain tumors - a crucial domain within medical imaging. Leveraging the power of CNNs, this research aimed to accurately classify brain tumor images into "No Tumor" and "Tumor" categories. The achieved test loss of 0.4554 and test accuracy of 75.89% exemplify the potential of AI-powered computer vision in healthcare. These results signify the significance of AI-driven image analysis in assisting healthcare professionals with early tumor detection and improved diagnostics, underlining the need for continuous refinement and validation to ensure its clinical effectiveness. This research adds to the expanding research and applications that harness AI and computer vision to enhance healthcare decisionmaking processes. 2024, IGI Global. All rights reserved. -
Wearable Sensors for Pervasive and Personalized Health Care
Healthcare systems are designed to provide commendable services to cater health needs of individuals with minimum expenditure and limited use of human resources. Pervasive health care can be considered as a major development in the healthcare system which aims to treat patients with minimal human resources. This provides a solution to several existing healthcare problems which might change the future of the healthcare systems in a positive way. Pervasive health care is defined as a system which is available to anyone at any point of time and at any place without any location constraints. At a broader definition, it helps in monitoring the health-related issues at a home-based environment by medical stakeholders which is very beneficial in case of emergency situations. This chapter elaborates architecture of IoT, how wearable sensors can be used to help people to get personalized and pervasive healthcare systems, and it also gives a detailed working of different types of IoT-enabled wearable devices for pervasive health care. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Internet of Things: Immersive Healthcare Technologies
Internet of Things (IoT) can be defined as a system that consists of a group of things where information is exchanged with the help of the internet, sensors, and devices. The boom of IoT is mainly because of the factor that it does not require human influence and can take place independently in utilizing digital information from physical devices. The main concern is how the integration of these technologies creates unique applications for the ease of human life. This chapter discusses various technologies of IoT in healthcare and their numerous applications in medical field. It also introduces the involvement of augmented reality that is acquiring a new dimension in the Internet of Things. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
An Iot Application to Monitor the Variation in Pressure to Prevent the Risk of Pressure Ulcers in Elderly
Pressure sores are a common form of skin problem which occurs with patients who are bedridden or immobile. It is believed that the occurrence of ulcers due to pressure can be prevented. Making best use of resources available and providing comfort to the patient, it is very much important to identify people at risk and provide preventive measures. This work is associated with a method to analyze pressure from pressure points on bedridden patients. A system is presented in this work that continuously monitors the pressure from pressure points using force sensors and sends an alarm to the nurses or caretakers if there is a variation in the pressure exerted on a specific area. 2018 IEEE. -
Functionalities and Approaches of Multi-cloud Environment
Cloud computing is a paradigm that envisions fast access to any resources from anywhere at any time with the most significant advantages of enabling an intuitive environment that offers plethora of services to mankind. The exponential increase in technological advances has been an advantage for the growth of cloud computing. The advancement in technology has enabled the shift in organizations from using a single cloud toward multi-cloud strategy. Multi-cloud uses multiple services from various cloud vendors which has been advantageous in several ways. Multi-cloud strategy has been designed to enable a hybrid mode for the organizations with ample security and savings in cost. This chapter gives an overview of multi-cloud computing and the security issues with respect to cloud computing. 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
A Study on Music Recognition Technology-Shazam
International Journal of Advanced Research in Computer Science and Software Engineering, Vol-4 (2), ISSN-2277-128X -
A Modified Seven-Level Inverter with Inverted Sine Wave Carrier for PWM Control
The conventional multilevel inverter necessitates more active switching devices and high dc-link voltages. To minimalize the employment of switching devices and dc-link voltages, a novel topology has been proposed. In this paper, a novel minimum switch multilevel inverter is established using six switches and two dc-link voltages in the proportion of 1: 2. In addition, the proposed topology is proficient in making seven-level voltages by appropriate gate signals. The PWM signals were produced using several inverted sine carriers and a single trapezoidal reference. When compared to other existing inverters, this configuration needs fewer components, as well as fewer gate drives. Furthermore, this module can generate a negative level without the use of a supplementary circuit such as an H-Bridge. As a result, overall cost and complexity are greatly reduced. The proposed minimum switch multilevel inverter operation is validated through simulations followed by experimental results of a prototype. 2022 Arun Vijayakumar et al. -
LENN: Laplacian Probability Based Extended Nearest Neighbor Classification Algorithm for Web Page Retrieval
Web page prediction is the area of interest that enables to tackle the problem of dealing with the massive collection of the web pages, mainly, in retrieving the highly relevant web pages. The hectic challenge of the web page prediction methods relied on time-effective and cost-effective management. The problem of dealing with the issue is tackled using the efficient web page retrieval algorithm. The paper proposes a new classifier called, Laplacian probability based Extended Nearest Neighbor (LENN)that is formed through the integration of the Laplacian probability with the Extended Nearest Neighbor (ENN)classifier. The proposed LENN classifier determines the nearest web pages of the query. Accordingly, the web page retrieval is done in three important steps, such as pre-processing, feature indexing and web page retrieval. The key words are stored in the database for performing the feature match such that the highly relevant web page is retrieved based on the maximum value of the score. The experimentation using five benchmarks prove that the proposed method is effective compared with the existing methods of web page retrieval. The maximum precision, recall, and F-measure of the proposed method is found to be 98%, 96.7%, and 97.3%, respectively. 2019 IEEE. -
Deep Learning Enabled Object Detection and Tracking Model for Big Data Environment
Recently, big data becomes evitable due to massive increase in the generation of data in real time application. Presently, object detection and tracking applications becomes popular among research communities and finds useful in different applications namely vehicle navigation, augmented reality, surveillance, etc. This paper introduces an effective deep learning based object tracker using Automated Image Annotation with Inception v2 based Faster RCNN (AIA-IFRCNN) model in big data environment. The AIA-IFRCNN model annotates the images by Discriminative Correlation Filter (DCF) with Channel and Spatial Reliability tracker (CSR), named DCF-CSRT model. The AIA-IFRCNN technique employs Faster RCNN for object detection and tracking, which comprises region proposal network (RPN) and Fast R-CNN. In addition, inception v2 model is applied as a shared convolution neural network (CNN) to generate the feature map. Lastly, softmax layer is applied to perform classification task. The effectiveness of the AIA-IFRCNN method undergoes experimentation against a benchmark dataset and the results are assessed under diverse aspects with maximum detection accuracy of 97.77%. 2022 Tech Science Press. All rights reserved. -
Riding the La Poderosa Politics, Youth, and Motorcycle Diaries in Kerala
[No abstract available] -
Kunde Habba The Profane and the Sacred
[No abstract available] -
Memorialisation and Identity in Mah India: Revealing French Colonial Legacies
Mah nestled in the Mahdistrict of the Puducherry Union Territory in India, holds profound historical ties to French colonial India. Unlike the broader Indian subcontinent, which witnessed fervent anti-colonial movements against British rule leading to political decolonisation in 1947, Mahexperienced a belated political awakening, reluctantly integrating into the Indian Union in 1954. Despite the withdrawal of the French, the enduring legacy of French colonial ideology and culture continued to shape the ethos of Mah In contemporary times, a significant presence of French nationals in India, particularly in Pondicherry, Karaikal, and Mah has fostered the evolution of a unique linguistic identity known as Indian French. Within Mah landmarks such as St. Teresas Shrine, the Statue of Marianne in Tagore Park at Cherukallayi, remnants of St. George Fort, and sculptures inspired by M. Mukundans novel On the Banks of the Mayyazhi stand as tangible vestiges of the erstwhile French presence. Serving as repositories of bygone French culture, these sites emerge as dynamic arenas of memory production. Notably, Tagore Park in Mah adorned with fictional documentation through sculptures, assumes a pivotal role as a space that harmonizes memory and history, functioning as a reservoir for collective memory concerning French colonial rule. Mah deliberate urban planning reflects a nuanced approach, embodying the concept of a living testament to French colonialism rather than a conventional museum. This architectural strategy underscores the deliberate preservation and commemoration of Mah historical past. Through interviews with French nationals residing in Mah this research explores how these landmarks have become pivotal in the production of memories and the construction of identities for the French community in India and Mah Leveraging Maurice Halbwachs theoretical framework, the study unveils the intricate interplay between collective memory and present-day identity formation, shedding light on the transformation of personal memory into historical memory and its subsequent amalgamation into collective memory. With close to 50 French families residing in and around Mahstill, the study involves interviews with ten families, focusing on landmarks like St. Teresas Shrine, the Statue of Marianne, the ruins of St. George Fort, and sculptures based on one of M. Mukundans novels. So, through interviews of the French citizens of Mah this paper highlights how the cultural artefacts and popular landmarks of Mahbecome sites of memory of the French colonisation. 2024, The International Academic Forum (IAFOR). All rights reserved. -
Mahe's Memorialisation of French Colonialism
[No abstract available] -
Exploring the synergy of IIoT, AI, and data analytics in Industry 6.0
This chapter delves into the transformative intersection of artificial intelligence (AI), Industrial Internet of Things (IIoT), and data analytics within the context of emerging Industry 6.0. As industries continue to emerge towards greater connectivity and automation, the chapter delivers a comprehensive analysis of the convergence of these cutting-edge technologies in reshaping the industrial landscape. It explores the synergistic relationships among IIoT, AI, and data analytics, examining their collaborative potential to enhance efficiency, productivity, and decision-making processes. The chapter begins by offering an in-depth overview of Industry 6.0, highlighting the technological advancements and paradigm shifts that characterize this era. Subsequently, it dissects the role of IIoT as a pivotal enabler, connecting physical devices and systems to facilitate real-time data exchange. The incorporation of artificial intelligence is explored as a premeditated augmentation, empowering machines to learn, adapt, and optimize operations autonomously. Simultaneously, the chapter investigates the significance of advanced data analytics techniques in extracting actionable insights from big data, fueling informed decision-making and predictive maintenance strategies. Furthermore, the chapter delves into practical applications and case studies showcasing successful implementations of this triad in diverse industrial sectors. 2025 selection and editorial matter, C Kishor Kumar Reddy, Srinath Doss, Lavanya Pamulaparty, Kari Lippert and Ruchi Doshi; individual chapters, the contributors. -
Approaches Towards A Recommendation Engine for Life Insurance Products
Recommender engines are powerful tools in today's world to overcome the problem of over choice. As the world is moving towards information overload, the life insurance industry is no more immune than any other domain. Three broad categories of life insurance plans are namely - Endowment, Term and ULIP. This paper discusses a variety of ML models that aim to classify the right fit product category for a new customer (extendable to existing customers) on a real-time life insurance company dataset. The dataset used for the modelling were of 2 kinds. The first kind contained features of customer demographics - age, location, education and occupation. The second dataset included these customer demographics as well as the bureau information of the respective customers which included multiple features describing their credit history. By the means of clustering, collaborative filtering approaches were tried on. Also, the problem was tackled using predictive modelling techniques such as Random Forest, Decision Trees and XGBoost. 2021 IEEE. -
Comparing Strategies for Post-Hoc Explanations in Machine Learning Models
Most of the machine learning models act as black boxes, and hence, the need for interpreting them is rising. There are multiple approaches to understand the outcomes of a model. But in order to be able to trust the interpretations, there is a need to have a closer look at these approaches. This project compared three such frameworksELI5, LIME and SHAP. ELI5 and LIME follow the same approach toward interpreting the outcomes of machine learning algorithms by building an explainable model in the vicinity of the datapoint that needs to be explained, whereas SHAP works with Shapley values, a game theory approach toward assigning feature attribution. LIME outputs an R-squared value along with its feature attribution reports which help in quantifying the trust one must have in those interpretations. The R-squared value for surrogate models within different machine learning models varies. SHAP trades-off accuracy with time (theoretically). Assigning SHAP values to features is a time and computationally consuming task, and hence, it might require sampling beforehand. SHAP triumphs over LIME with respect to optimization of different kinds of machine learning models as it has explainers for different types of machine learning models, and LIME has one generic explainer for all model types. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Real-Time Fire Detection Through the Analysis of Surveillance Videos
The Forest Fire Detection System is an intelligent system that can detect forest fires and alert authorities in real-time. It uses a YOLOv5 deep learning algorithm to process live video feeds captured by a web camera which is trained with the sizable dataset of inputs to locate the fire accurately, making it an ideal choice for real-time fire detection in the forest. Upon detecting a fire, the system sends an email alert to a designated email address, containing a picture of the fire and location information. The email alert system is built using the standard SMTP protocol, which ensures that the message is delivered to the recipient in a timely and reliable manner. The system is also equipped with a speaker that triggers an alarm upon detecting a fire. The alarm is designed to alert people in the vicinity of the fire so that they can take the necessary action. It is activated using the Pygame library, a collection of Python modules specifically crafted for game development across multiple platforms. Overall, the Forest Fire Detection System is a fast, efficient, and accurate system that can help prevent the spread of forest fires. It is an intelligent system that can detect fires quickly and send alerts to authorities, giving them the information they need to take the necessary action to control the fire. The system is built using a web camera, a computer, and a speaker, making it easy to install and maintain. 2024 IEEE. -
A Comprehensive Survey on Deep Learning Techniques for Digital Video Forensics
With the help of advancements in connected technologies, social media and networking have made a wide open platform to share information via audio, video, text, etc. Due to the invention of smartphones, video contents are being manipulated day-by-day. Videos contain sensitive or personal information which are forged for one's own self pleasures or threatening for money. Video falsification identification plays a most prominent role in case of digital forensics. This paper aims to provide a comprehensive survey on various problems in video falsification, deep learning models utilised for detecting the forgery. This survey provides a deep understanding of various algorithms implemented by various authors and their advantages, limitations thereby providing an insight for future researchers. 2024 World Scientific Publishing Co.