Browse Items (14421 total)
Sort by:
-
IEEHR: Improved Energy Efficient Honeycomb Based Routing in MANET for Improving Network Performance and Longevity
In present scenario, efficient energy conservation has been the greatest focus in Mobile Adhoc Networks (MANETs). Typically, the energy consumption rate of dense networks is to be reduced by proper topological management. Honeycomb based model is an efficient parallel computing technique, which can manage the topological structures in a promising manner. Moreover, discovering optimal routes in MANET is the most significant task, to be considered with energy efficiency. With that motive, this paper presents a model called Improved Energy Efficient Honeycomb based Routing (IEEHR) in MANET. The model combines the Honeycomb based area coverage with Location-Aided Routing (LAR), thereby reducing the broadcasting range during the process of path finding. In addition to optimal routing, energy has to be effectively utilized in MANET, since the mobile nodes have energy constraints. When the energy is effectively consumed in a network, the network performance and the network longevity will be increased in respective manner. Here, more amount of energy is preserved during the sleeping state of the mobile nodes, which are further consumed during the process of optimal routing. The designed model has been implemented and analyzed with NS-2 Network Simulator based on the performance factors such as Energy Efficiency, Transmission Delay, Packet Delivery Ratio and Network Lifetime. 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature. -
IIRM: Intelligent Information Retrieval Model for Structured Documents by One-Shot Training Using Computer Vision
Various information retrieval algorithms have matured in recent years to facilitate data extraction from structured (with a predefined template) digital document images, primarily to manage and automate different organizations invoice and bill reimbursement processes. The algorithms are designated either rule-based or machine-learning-based. Both approaches have respective advantages and disadvantages. The rule-based algorithms struggle to generalize and need periodic adjustments, whereas machine learning-based supervised approaches need extensive data for training and substantial time and effort for manual annotation. The proposed system attempts to address both problems by providing a one-shot training approach using image processing, template matching, and optical character recognition. The model is extensible for any structured documents such as closing disclosure, bill, tax receipt, besides invoices. The model is validated against six different structured document types obtained from a reputed title insurance (TI) company. The comprehensive analysis of the experimental results confirms entity-wise extraction accuracy between 73.91 and 100% and straight through pass 81.81%, which is within business acceptable precision for a live environment. Out of total 32 tested entities, 17 outperformed all state-of-the-art techniques, where max accuracy has been 93 % with only invoices or sales receipts. The system has been set operational to assist the robotic process automation of the TI mentioned above based on the experimental results. 2022, King Fahd University of Petroleum & Minerals. -
ILeHCSA: an internet of things enabled smart home automation scheme with speech enabled controlling options using machine learning strategy
Nowadays, communication schemes and the related automation logics have improved drastically, and people are moving from classical to intelligent applications. This naturally raises the growth ratio of the automation industry and enables researchers to work accordingly. The field of automation is essential in specific unavoidable environments such as hospitals, industrial units, individual residences, disaster areas, etc. In this paper, a novel machine-learning enabled speech-based home automation system is designed, called Intelligent Learning-enabled Home Controlling with Speech Assistance (ILeHCSA). This scheme integrates several latest technologies to control the home intelligently, including machine learning, speech assistance technology, and Internet of Things (IoT) support. Based on these advanced technologies, the logic of smart home automation systems has been designed in this approach, and it provides intellectual home controlling options to people. The following are the devices and sensors which are essential to control the electronic devices embedded into the home environment: Node Microcontroller Unit (MCU) Wi-Fi enabled Microcontroller, Relay Unit, Voice Capture Module with Mic, Speech-to-Text (STT) Converter Module, and Global Positioning System (GPS) to identify the location of the device. The machine-learning logic is utilized to provide a statistical analysis of device usage and to provide a clear summary and traces to maintain the device accordingly. These smart technologies can innovatively change the living atmosphere with sufficient support and comfort. The main intention of this paper is to provide a robust home automation system to support people efficiently, especially the people who are physically suffering from illness and the aged ones. The proposed work provides a 96.5% accuracy ratio when compared with other methods. 2021 Nismon Rio Robert et al. -
IM-EDRD from Retinal Fundus Images Using Multi-Level Classification Techniques
In recent years, there has been a significant increase in the number of people suffering from eye illnesses, which should be treated as soon as possible in order to avoid blindness. Retinal Fundus images are employed for this purpose, as well as for analysing eye abnormalities and diagnosing eye illnesses. Exudates can be recognised as bright lesions in fundus pictures, which can be the first indi-cator of diabetic retinopathy. With that in mind, the purpose of this work is to cre-ate an Integrated Model for Exudate and Diabetic Retinopathy Diagnosis (IM-EDRD) with multi-level classifications. The model uses Support Vector Machine (SVM)-based classification to separate normal and abnormal fundus images at the first level. The input pictures for SVM are pre-processed with Green Channel Extraction and the retrieved features are based on Gray Level Co-occurrence Matrix (GLCM). Furthermore, the presence of Exudate and Diabetic Retinopathy (DR) in fundus images is detected using the Adaptive Neuro Fuzzy Inference System (ANFIS) classifier at the second level of classification. Exudate detection, blood vessel extraction, and Optic Disc (OD) detection are all processed to achieve suitable results. Furthermore, the second level processing comprises Morphological Component Analysis (MCA) based image enhancement and object segmentation processes, as well as feature extraction for training the ANFIS clas-sifier, to reliably diagnose DR. Furthermore, the findings reveal that the proposed model surpasses existing models in terms of accuracy, time efficiency, and precision rate with the lowest possible error rate. 2023, Tech Science Press. All rights reserved. -
Image Analysis of MRI-based Brain Tumor Classification and Segmentation using BSA and RELM Networks
Brain tumor segmentation plays a crucial role in medical image analysis. Brain tumor patients considerably benefit from early discovery due to the increased likelihood of a successful outcome from therapy. Due to the sheer volume of MRI images generated in everyday clinical practice, manually isolating brain tumors for cancer diagnosis is a challenging task. Automatic segmentation of images of brain tumors is essential. This system aimed to synthesize previous methods for BSA-RELM-based brain tumor segmentation. The proposed methodology rests on four fundamental pillars: preprocessing, segmentation, feature extraction, and model training. Filtering, scaling, boosting contrast, and sharpening are all examples of preprocessing techniques. When doing segmentation, a clustering technique based on Fuzzy Clustering Means (FCM) is used to breakdown the overall dataset into numerous subsets. The proposed approach used the region of filling for feature extraction. After that, a BSA-RELM is used to train the models with the input features. The proposed technique outperforms BSA and RELM, two of the most common alternatives. There was a 98.61 percent success rate with the recommended method. 2023 IEEE. -
Image and signal processing in the underwater environment
To handle submerged action recognition, researchers must first understand the fundamental principles of photonic crystals mostly in the liquid phase. Deterioration effects are produced by the mediums physical attributes, which are not present in typical pictures captured in the air because light is increasingly reduced as it passes through water, submarine pictures are characterized by low readability. As a consequence, the sceneries are poorly contrasting and murky. Its vision capability is limited to approximately twenty meters in clear blue water and five meters or less in muddy water due to light dispersion. Absorbing (the removal of incident light) and dispersion are the two factors that produce light degradation. So the actual quality of submersible digital imaging is influenced by the destructive interference processes of light in water. Longitudinal scattered (haphazardly diverted light traveling from objects to the cameras) causes picture details to be blurred. 2021, SciTechnol, All Rights Reserved. -
Image contrast enhancement by scaling reconstructed approximation coefficients using SVD combined masking technique
The proposed method addresses the general issues of image contrast enhancement. The input image is enhanced by incorporating discrete wavelet transform, singular value decomposition, standard intensity deviation based clipped sub image histogram equalization and masking technique. In this method, low pass filtered coefficients of wavelet and its scaled version undergoes masking approach. The scale value is obtained using singular value decomposition between reconstructed approximation coefficients and standard intensity deviation based clipped sub image histogram equalization image. The masking image is added to the original image to produce a maximum contrast-enhanced image. The supremacy of the proposed method tested over other methods. The qualitative and quantitative analysis is used to justify the performance of the proposed method. 2015 The Science and Information (SAI) Organization Limited. -
Image Data Driven Lung Cancer Classification using Deep Learning and Optimization Algorithm
Lung cancer continues to be a major contributor to global cancer mortality, underscoring the importance of early detection and accurate diagnosis. This work introduces an integrated framework that leverages deep learning in combination with Bayesian optimization to achieve robust lung cancer classification. Convolutional Neural Networks (CNNs) are employed for feature extraction and image analysis, while Bayesian optimization is applied to automatically fine-tune critical hyperparameters, thereby improving accuracy and minimizing training overhead. The methodology focuses on the analysis of computed tomography (CT) images to distinguish between different lung cancer categories. By addressing the limitations of manual hyperparameter selection, the proposed framework enhances the efficiency and reliability of deep learning models in medical imaging. The outcomes of this study highlight its potential contribution to computer-aided diagnosis, offering clinicians an effective decision-support tool for precise and timely lung cancer detection. 2025 IEEE. -
Image Pre-Processing Algorithms for the Quality Detection of Tea Leaves
This Identification and prediction of the tea quality is the essential research focus nowadays in the field of agriculture. Nowadays the Artificial Intelligence has become the latest topic in the region of pattern recognition. The various combination and permutation of the different techniques has resulted in proper solving the problem as well as have better accuracy in recognition. Therefore, there is urge need of a detailed survey AI techniques used for the identification of the tea leaf quality for the different grades of tea plants. In this paper, we aim on the various methods used for the pre- processing of the input image to extract the processed image which will further be useful for the feature extraction and the classification of the proposed image. It is very important to get the effective and accurate processed data which will further act as an input for the next level modules. This paper shows various methods of edge detection are applied on the image like Canny, Sobel and Laplacian are used. The further results are compared for quality metrics parameters such as the Mean Square Error (MSE) & Structural Similarity Index Metric (SSIM). The main agenda of this paper is to perform the edge detection and to check the quality measure of the processed image. The software used here is python. 2022 IEEE. -
Image Processing and Artificial Intelligence for Precision Agriculture
Precision agriculture is a novel approach to increase the productivity of crops that employs recent technologies such as Artificial Intelligence, WSN, cloud computing, Machine Learning, and IoT. This paper reviews the development of different techniques effectively used in precision agriculture. The paper details the technological impact on precision agriculture followed by the different image processing schemes such as Satellite imagery and unmanned aerial vehicle (UAV). The role of precision agriculture is disease detection, weed detection from UAV images, and detection of trees and contaminated soils from satellite imagery is discussed. It reviews the impact of artificial intelligence (AI) namely machine learning &deep learning in precision agriculture. The performance of the recent image processing schemes in precision agriculture is analyzed. The paper also discusses the challenges that exist in implementing the precision agriculture system. 2022 IEEE. -
Image Recognition, Recusion Cellular Classification Using Different Techniques and Detecticting Microscopic Deformities
Deep convolutional neural networks (CNNs) have turn out to be one of the most advanced approaches trendy distinguishing snapshots in extraordinary fields. White blood cell classification is crucial for diagnosing anaemia, leukaemia, and a variety of other hematologic illnesses. Transfer learning with CNNs is frequently used in biological image categorization. Traditional methods for WBC classification is costly is terms of time and money. In the paper three convolutional neural network architectures are proposed which is based on transfer learning for microscopic image classification and compare the performance of models. The paper compares Transfer learning models like VGG-16, VGG-19, VGG-19 SVM hybrid and AlexNet. VGG-16 gives the best classification performance in comparison. VGG-16 model is which has a train accuracy of 0.9538 and train loss of 0.1322. 2022 IEEE. -
Image Steganography Using Discrete Wavelet Transform and Convolutional NeuralNetwork
The practice of steganography involves concealing messages within another thing, which is referred to as a carrier. Is thus performed in order to build up a covert communication channel in a rather way that any observers whom has access to such a channel will not be able to detect the act of communication itself. In this research, using the process of stenography, a secret text is transferred across a communication channel using an image as a cover. Discrete Wavelet Transform (DWT) and Convolutional Neural Network (CNN) is used in the above process. The encoding and decoding operation is done by using DWT while the preprocessing and training of images is done by CNN. The training and prediction rate of CNN is 72.4 %. 2022 IEEE. -
Imagined Communities in Bollywood: A Contrapuntal Reading of The Kashmir Files and Mulk
Under the Modi regime, Hindu nationalist ideologies have gained prominence, resulting in a growing utilisation of cinema as a political tool in India. This article explores Bollywoods role as a mass cultural medium in shaping communal identities through a contrapuntal analysis of two ideologically opposed films: Mulk (2018) and The Kashmir Files (2022). Utilising Benedict Andersons concept of imagined communities and Edward Saids contrapuntal reading technique, the research examines the role of these films in shaping narratives of majoritarian Hindus and minority Muslims. The Kashmir Files promotes a one-dimensional communal narrative that portrays Muslims as the aggressors and Hindus as the victims, thus bolstering Hindutva ideologies. Conversely, Mulk challenges this narrative by depicting the Muslim community as unjustly demonised and seeking justice in a pluralistic context. This article outlines Bollywoods involvement in the broader political discourse surrounding religious identity in India through a comparative analysis of themes like terrorism, visual stereotyping, and the representation of jihad. The findings are intended to contribute to the critical discussion surrounding nationalism, media representation, and communal politics in present-day South Asia. 2025, International Islamic University Malaysia. All rights reserved. -
Imagining the sustainable future with Industry 6.0: A smarter pathway for modern society and manufacturing industries
Industry is defined as the production of goods and services through the transformation of raw materials and resources into valuable products. It involves the creation of finished products or services through various stages of production that may include manufacturing, processing, assembly, packaging, and distribution. Industries have played a significant role in the economic growth and development of nations throughout history. They have contributed to the creation of employment opportunities, the development of new technologies, and the improvement of living standards. Over the years, the industrial sector has gone through numerous changes, and each of these changes has been termed as an "Industry Revolution." 2024, IGI Global. All rights reserved. -
Imidazopyridine chalcones as potent anticancer agents: Synthesis, single-crystal X-ray, docking, DFT and SAR studies
New imidazopyridinechalcone analogs were synthesized through the ClaisenSchmidt condensation reaction. The newly synthesized imidazopyridine-chalcones (S1S12) were characterized using spectroscopic and elemental analysis. The structures of compounds S2 and S5 were confirmed by X-ray crystallography. The global chemical reactivity descriptor parameter was calculated using theoretically (DFT-B3LYP-3-211, G) estimated highest occupied molecular orbital and lowest unoccupied molecular orbital values and the results are discussed. Compounds S1S12 were screened on A-549 (lung carcinoma epithelial cells) and MDA-MB-231 (M.D. Anderson-Metastatic Breast 231) cancer cell lines. Compounds S6 and S12 displayed exceptional antiproliferative activity against lung A-549 cancer cells with IC50 values of 4.22 and 6.89 M, respectively, compared to the standard drug doxorubicin (IC50 = 3.79 ?M). In the case of the MDA-MB-231 cell line, S1 and S6 exhibited exceptionally superior antiproliferative activity with IC50 of 5.22 and 6.50 ?M, respectively, compared to doxorubicin (IC50 = 5.48 ?M). S1 was found to be more active than doxorubicin. Compounds S1S12 were tested for their cytotoxicity on human embryonic kidney 293 cells, which confirmed the nontoxic nature of the active compounds. Further molecular docking studies verified that compounds S1S12 have a higher docking score and interacted well with the target protein. The most active compound S1 interacted well with the target protein carbonic anhydrase II in complex with pyrimidine-based inhibitor, and S6 with human Topo II? ATPase/AMP-PNP. The results suggest that imidazopyridine-chalcone analogs may serve as new leads as anticancer agents. 2023 Deutsche Pharmazeutische Gesellschaft. -
Imidazopyridine Hydrazine Conjugates as Potent Anti-TB Agents with their Docking, SAR, and DFT Studies
Novel imidazopyridines hydrazine conjugates were designed and synthesized for their anti-tubercular (anti-TB) activity. A cytotoxicity assay was conducted with Vero cells to determine the safety profile of the most effective compounds. It was found that compound (IA3) (MIC=0.78 ?M) and (IA8) (MIC=1.12 ?M) were nearly 3.7 and 2.5 times more active than pyrazinamide. Based on Density functional theory (DFT), these molecules exhibited better charge transfer between molecular orbital's, which made them suitable for biological applications. Molecular docking on Mycobacterium tuberculosis InhA bound to NITD-916 (PDB: 4R9S) revealed that compounds possessed greater binding affinity towards proteins. In addition, the most active anti-TB compounds (IA3) and (IA8) exhibited high levels of interaction with the target protein and exceptional safety profile, suggesting they may prove to be effective leads for new drugs. 2024 Wiley-VCH GmbH. -
Immersive Technologies: Navigating the Impacts, Challenges, and Opportunities
Immersive technology is going to govern the next generation in terms of education, health, military, tourism, and much more. Through its comprehensive exploration, didactic approach, and insightful analyses, this book provides an invaluable resource for understanding and harnessing the power of immersive technology. Immersive Technologies: Navigating the Impacts, Challenges, and Opportunities serves as a guiding compass through the immersive technology landscape and takes a multifaceted approach, addressing both the technical and human aspects. The book dissects the underlying methods and technologies that power immersive experiences, offering readers a clear understanding of how VR, AR, and MR function. The latest advancements, from cutting-edge hardware developments to revolutionary software applications are discussed in detail. The book also delves into the potential societal impacts and takes the reader on a journey from education to healthcare, entertainment to remote collaboration, so the reader can gain insights into the myriad of ways immersive technology is already shaping industries and human interaction. The ultimate benefit readers will derive from this book is a holistic grasp of the immersive technology landscape and they will be armed with knowledge about the challenges and opportunities presented by VR, AR, and MR. They will be well-equipped to navigate the future. This is a must-read for anyone interested in how this technology has the potential to reshape our world. Academicians will be enriched with the applications and practical perspectives. 2025 Sagaya Aurelia. -
Immersive Virtual Learning Experiences of Senior Secondary School Students from India and Russia: A Mixed Method Study
Virtual Reality (VR) provides an immersive learning (IL) experience by simulating real-world scenarios that bridge the gap between theory and application. VR simulations are interactive and enhance student engagement across a range of concepts, from simple to complex. India and Russia share similar cultural and historical backgrounds, and both are committed to creating a multipolar world. Both are large developing countries with several strategic partnerships and international cooperation. Hence, this study aims to capture the learning experiences of internationally paired students in an IL environment and their attitudes towards IL environments, to mutually contribute to teaching and learn in these countries. Students experienced immersive learning through stand-alone head-mounted virtual reality cameras with a controller. The study employed a mixed-methods research design involving a quantitative and qualitative explanatory approach. Researchers paired 100 senior secondary school students from Russia (n = 50) and India (n = 50) and exposed them to virtual IL experiences. Researchers used the user-experience IL environment scale, the VR-IL environment attitude scale, and an interview guide to collect the data of the study. Quantitative data were analyzed using descriptive statistics, a correlation test, and regression. Qualitative data were analyzed through narrative thematic analysis. Researchers triangulated the IL experiences measured through quantitative and qualitative methods. The study found a positive correlation between IL experiences and attitude towards the IL environment. Further, IL experiences accounted for 43.5% of positive attitudes towards the IL environment. The qualitative analysis revealed both positive and negative aspects of VR-IL environment experiences. The study's findings add value to the cognitive-affective theory of learning with media, as it includes knowledge construction, emotional connection, and motivation for learning. Future studies may explore the benefits of the IL environment with artificial intelligence (AI) and generative AI towards teaching and learning. (2024), (California State University). All Rights Reserved. -
Immobilization of TiO2 on Various Substrates
Recovery of photocatalytic materials after the degradation of organic pollutants remains a challenge. To address this issue, immobilizing the material on a suitable substrate presents a viable solution. Immobilization of the commonly used titanium dioxide (TiO2) photocatalyst onto various substrates is typically achieved through adsorption, hydrogen bonding, or chemical bonding. Coating TiO2 onto different substrates is a common approach to enhance its durability, reusability, and catalytic efficiency across multiple applications, such as photocatalysis, sensors, and heterogeneous catalysis. The choice of substrate depends on the specific application, desired properties, and its ability to improve the photocatalytic performance. Substrates such as glass/quartz, polymeric materials, metal oxides, carbon-based materials, textiles, and cellulose each offer unique characteristics that enhance the potential of the photocatalytic material. 2026 WILEY-VCH GmbH. -
Immobilized proline-based electro-organocatalyst for the synthesis of bis-?-diketone via Knoevenagel condensation reaction
In the quest for more sustainable chemical processes, we devised a technique using electro-organocatalysis to synthesize bis-?-diketone compounds via Knoevenagel condensation of benzaldehyde and dimedone. Our approach involves a modified electrode fabricated via anchoring L-proline onto a carbon fiber paper electrode supported by poly-3,4-diaminobenzoic acid (PDABA), which enhances efficiency in addition to the simple catalyst separation from the reaction mixture in heterogeneous catalysis. The electrochemical and surface topographical studies for the fabricated electrode were carried out, revealing high efficiency in comparison to the bare carbon fiber paper electrode. This electrochemical reaction operates under mild conditions utilizing lithium perchlorate and acetonitrile, yielding high amounts of the desired product. This study showcases a promising pathway for producing valuable organic compounds in an environmentally friendly manner, marking a significant stride forward in sustainable synthesis practices. 2024 Elsevier Ltd