Browse Items (2150 total)
Sort by:
-
Detection of Malicious Nodes in Flying Ad-hoc Network with Supervised Machine Learning
An Ad-hoc network (FANET) is a new upcoming technology which has been used in several sectors. Ad-hoc networks are mostly wireless local area networks (LANs). The devices communicate with each other directly instead of relying on a base station or access points as in wireless LANs for data transfer. In an Ad-hoc network the communication between one node to another in a FANET is not secured and there isn't any authorized protocol for secured communication. Therefore, we suggest an algorithm to detect the malicious node in a network. This algorithm uses Linear regression to calculate the reputation or trust value of a node in the network. Then the above found trust value is used to classify the node as normal node or malicious node based on the Logistic Regression Classification. Thus, allowing a secure communication of data and avoiding attacks. 2022 IEEE. -
Detection of toxic comments over the internet using deep learning methods
People now share their ideas on a wide range of topics on social media, which has become an integral part of contemporary culture. The majority of people are increasingly turning to social media as a necessity, and there are numerous incidents of social media addiction that have been reported. Socialmedia channels. Socialmedia platforms have established their worth over time by bringing individuals from different backgrounds together, but they have also shown harmful side effects that could have serious consequences. One such unfavourable result is how extremely poisonous many discussions on social media are. Online abuse, hate speech, and occasionally outrage culture are now all considered to be toxic. In this study, we leverage the Transformers Bidirectional Encoder Representations to build an efficient model to detect and classify toxicity in user-generated content on social media. The Kaggle dataset with labelled toxic comments, was used to refine the BERT pre-trained model. Other Deep learning models, including Bidirectional LSTM, Bidirectional-LSTM with attention, and a few other models, were also tested to see which performed best in this classification task. We further evaluate the proposed models utilising dataset obtained from Twitter in order to find harmful content (tweets) using relevant hashtags. The findings showed how well the suggested methodology classified and analysed toxic comments. 2024 The Author(s). -
Detection of Various Security Threats in IoT and Cloud Computing using Machine Learning
Due to the growth of internet technology, there is a sharp rise in the growth of IoT enabled devices. IoT (Internet of Things) refers to the connection of various embedded devices with limited processing and memory. With the heavy adoption of IoT applications, cloud computing is gaining traction with the ever-increasing demand to process and compute a massive amount of data coming from various devices. Hence, cloud computing and IoT are often related to each other. However, there are two challenges in deploying the IoT and cloud computing frameworks: security and Privacy. This article discusses various types of security threats affecting IoT and cloud computing, and threats are classified using machine learning (ML). ML has gained much momentum in recent years and is applied in various domains. One of the main subdomains of machine learning is used in IoT and cloud security. A machine learning model can be trained with data based on which the model can predict the impending security threats. Popular security techniques to protect IoT devices from hackers are IoT authentication, access control, malware detection, and secure overloading. Supervised learning algorithms can be used to detect malware in the runtime behavior of applications. The malware is detected from network traffic and is labeled based on its suspicious behavior. Post identification of malware, the application data is stored in a database trained via an ML classifier algorithm (KNN or Random Forest). With increased training, the model can identify malware applications with higher accuracy. 2022 IEEE. -
Determining the Antecedents and Consequences of Brand Experience: A Study to develop a Conceptual Framework
In the marketing literature, one of the most talked- about subjects is brand experience (BE). Through an examination of the numerous studies conducted by BE researchers, this report attempted to determine the significance of BE in the body of recent literature. This paper culminates in the creation of a conceptual framework that prospective investigators might utilize to discern the diverse pathways inside BE. 2024 IEEE. -
Development and characterization of carbon fiber reinforcement in Aluminium metal matrix composites
Carbon fibers (CF) possess exceptional mechanical properties and the highest degree of chemical stability. However, carbon reinforcement in metal matrix composites is extremely scarce due to production difficulties, particularly in obtaining a uniform distribution. Carbon fiber reinforced composites are typically made using high temperature processing processes. However, the fibers must be coated with Ni or Cu in order to achieve effective particle dispersion; otherwise, there is a larger likelihood of intermetallic compound formation, which reduces the chances for enhanced properties. In this work, the metallurgical, mechanical, and tribological characteristics of the carbon fiber reinforcement in AA 7050 are examined. Uncoated carbon fibers are reinforced into the Aluminium matrix using a low temperature processing technique known as powder metallurgy. The AA 7050 matrix reinforced with carbon fibers at various weight percentages between 0 and 1.5. The samples undergone mechanical and metallurgical testing in accordance with ASTM guidelines. The findings indicate that the 0.25 weight percent carbon fiber reinforcement in the matrix increased the material's hardness by 30% over the monolithic alloy, making it an excellent alternative for structural applications. Published under licence by IOP Publishing Ltd. -
Development and Evaluation of an Artificial Intelligence-Based System for Pancreatic Cancer Detection and Diagnosis
Due to its aggressive nature and late-stage manifestation, pancreatic cancer is a difficult illness to find and diagnose. The creation of a pancreatic cancer detection and diagnosis system based on artificial intelligence (AI) has the potential to increase early detection and improve treatment results. We have described the creation and assessment of an AI-based system in this paper that is intended for the identification of pancreatic cancer. A large dataset including a variety of medical pictures, including CT scans, MRI scans, and PET scans, as well as the related clinical information, was gathered for the study. With the help of the annotated dataset, a deep learning model built on convolutional neural networks was created. The proposed AI-based solution was then assessed using a separate test dataset made up of control cases and known pancreatic cancer patients. A significant effectiveness for the early diagnosis of the disease was shown by the systems excellent precision as well as sensitivity in identifying pancreatic tumors. The outcomes of this investigation demonstrate the promise of AI-based systems for pancreatic cancer detection and diagnosis. 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Development of Enhance-Net Deep Learning Approach for Performance Boosting on Medical Images
Only a few clinical procedures include the use of clinical methods for the early detection, observing, evaluation, and treatment evaluation of a range of medical illnesses. Knowing the analysis of medical images in computer vision necessitates being acquainted with the core concepts and uses of deep learning and artificial neural networks. The A rapidly expanding area of study is the Deep Learning Approach (DLA) in medical image processing. DLA is often used in medical imaging to determine if an ailment is present or not. By producing speedier, more accurate results in real time, deep learning algorithms may make the jobs of radiologists and orthopaedic surgeons easier. But the standard deep learning approach has reached its efficiencies. While offering an ideal solution known as boost-Net, we study numerous optimization strategies to increase the effectiveness of deep neural networks in this research. From a selection of well-known deep learning models, Champion-Net was selected as the deep learning model. The musculoskeletal radiograph-bone classification (MURA-BC) dataset is used in this investigation. Utilizing the train and test datasets, Enhance-Net's classification precision was evaluated. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Development of LIDAR-SLAM Integrated Low Cost Health Care Monitoring Robot with Sustainable Material
Beyond the global pandemic, healthcare has faced a myriad of challenges, from rising costs and accessibility issues to the need for precision in patient care and efficient medication delivery. This project embodies a visionary response to the multifaceted challenges faced by healthcare systems in health centers located in rural areas. The proposed research work focused on design and development of a health care monitoring robot with integration of 3D LIDAR Simultaneous Localization and Mapping (SLAM) based navigation approach, introduction of sustainable materials like bamboo and wood composites for development of robotic arm and robotic body frames. Also, from the initial tests it has been observed that with the developed mobile robot functions like precision medicine delivery, Open AI-Enabled continuous monitoring, hospital environment sanitization and emergency oxygen supply can be performed efficiently. 2024 IEEE. -
Diabetes Mellitus Classification Using Machine Learning Algorithms with Hyperparameter Tuning
Diabetes Mellitus is a prevalent condition globally, marked by elevated blood sugar levels resulting from either insufficient production of insulin or the body cells' inability to respond appropriately to released insulin. For people with diabetes to lead healthy, normal lives, early identification and treatment of the condition are essential. With the need to move away from current traditional procedures, towards a noninvasive methodology, machine learning and data mining technologies can be very useful in the classification of diabetes. Creating an effective machine learning model for the classification of diabetes mellitus was the primary goal of this research. This work is primarily carried out on combined Pima Indian diabetes dataset and German Frankfurt diabetes dataset. The class imbalance issue has been resolved using Synthetic Minority Oversampling Technique. One-hot encoding is applied to convert categorial features to numerical and various single and ensemble classifiers with the best hyperparameters obtained using GridSearchCV method were employed on the pre-processed dataset. With an AUC of 0.98 and maximum accuracy of 98.79%, the Random Forest ensemble technique outperformed the other models, according to the experimental results. As a result, the algorithm might be used to predict diabetes and alert doctors to serious cases that call for emergency care. 2024 IEEE. -
Diabetic Retinopathy Diagnosis Using Retinal Fundus Images through MobileNetV3
Diabetic Retinopathy (DR) is a major disease throughoutthe world. Diagnosis of diabetes at an early stage is so critical and could help save several lifestyles. One out of two individuals experiencing diabetes has been determined to have some phase of DR. Recognition of DR symptoms in time can turn away the vision weakness inmost the cases, nonetheless, such disclosure is troublesome with present devices and strategies. Existingmethods for determining whether a person is suffering from diabetes or maybe the chances of acquiring diabetesrely heavily on examiners. Most of the time, it can be treated if caught during the early stages. There is a need for creating models that are efficient and robust to detect DR holistically. In recent times the advent of Deep learning models has been used extensively in various Bio medical applications. In this work, we utilize a Hyper parameter tuned MobileNet-V3 model based on a multi-stage Convolutional Neural Network (CNN) to efficiently classify images from the IRDID dataset. A Multiclass classification model involving images collated from various sources were trained, validated and tested for classification accuracy. The network was evaluated based on parameters and the network was able to achieve an accuracy of 88.6% 2023 IEEE. -
Diagnosis of compromised accounts for online social performance profile network
Proliferation of internet technologies has changed the way content is created and exchanged through the Internet, prompting expansion of online networking applications and administrations. Online networking empower creation and exchanged the clients produced content and design of a scope of Internet-based applications. This development is fueled by more administrations as well as by the rate of their adoption by the users. While determined spammers misuse the built up trust connections between account proprietors and their companions to proficiently spread malignant spam, auspicious discovery of traded off records is quite challenge, because of the fixed trust association among the administration suppliers, account proprietors, and their companions. The proposed paper depicts a novel method to notice the cooperated user account in systems like Facebook and twitter. Our novel scheme consists of statistical method of modelling and detected to identity accounts that behaves a sudden change along with detected the compromised accounts. This paper gives validation of these behavioral elements by gathering and dissecting genuine client clickstreams to an OSN site. Taking into account our estimation study, further devise every client's social behavioral profile (SBP) by joining its separate behavioral element measurements. We assess the capacity of social behavioral profiles in recognizing distinctive OSN clients, and the simulation results demonstrate the social behavioral profiles precisely separate every OSN clients and distinguish traded off records. 2016 IEEE. -
Diagnosis of Osteoporosis from X-ray Images using Automated Techniques
Osteoporosis is Bone Disease most commonly seen in aged people due to various food habits and life style habits. The bone becomes so brittle and weak which may break just from a fall. So, it is required to attend this Issue as there are various challenges faced by medical domain to identify and treat Osteoporosis. In this paper we focus on identifying and detecting osteoporosis using X-ray images using modified U-net Architecture using Residual Block and skip connections and done comparison study with existing models, as per state-of-art our model outcomes issues in existing model and obtain better accuracy. 2022 IEEE. -
Diagnosis of Retinal Disease Using Retinal Blood Vessel Extraction
The eye is one of the important organs of the human body. In recent times, major parts of the eye are damaged due to various retinal diseases. Major diseases related to the retina are glaucoma, papilledema, retinoblastoma, diabetic retinopathy, and macular degeneration. These diseases can be detected using image processing techniques. These diseases can cause damage to the eye; hence the early diagnosis can prevent the loss of vision. Thus the early stage of rectification may lead to smaller damage than the risky ones. By extracting the blood vessels, various retinal diseases can be identified, and the severity of the disease can also be identified. Some of these diseases in the retina will occur due to hypertension, blood pressure, and diabetics. Thus, the tear in the blood vessels leads to the loss of visuality in human beings. The proposed work consists of image processing techniques such as segmentation, feature extraction, and boundary extraction which lead to the identification of various retinal diseases with a certain level of accuracy, sensitivity, and specificity by using image processing techniques. The training and testing of retinal images are carried out by using the artificial neural network (ANN) classifier for glaucoma detection and support vector machine (SVM) classifier for detecting diabetic retinopathy. 2021, Springer Nature Switzerland AG. -
Dictionary-Based BPT Compression with Trimodal Encryption for Efficient Fiber-Optic Data Management and Security
Fiber-optic transmission systems are capable of carrying tens of terabits per second of traffic and thereby form the core infrastructure for all Internet-based services and applications. While fiber-optic communication provides rapid data transfer, it faces the challenge of managing the substantial data volumes generated, stored, or transmitted. In the realm of fiber-optic communication, data interception is straightforward, necessitating robust security measures. One effective solution is compression-based encryption, which combines security with data compression benefits. Encryption safeguards data by transforming it into ciphertext during transmission, rendering it unreadable to attackers without knowledge of the encryption method. Data compression enhances bandwidth efficiency, enabling the efficient transmission of large data volumes using limited bandwidth. In the event of data compromise, attackers must grasp both compression and encryption methods to decipher the information, adding an additional layer of security. In this paper, an encoding technique named the Bounded Probability-Based Textual Data Compression (BPT) algorithm is introduced with trimodal encryption method for securing the short textual data while transferring from source to the destination. The BPT algorithm creates a codeword using a dictionary that assigns binary codes according to character occurrence probabilities in the input data. To decompress, the coding table must be transmitted alongside the compressed data. The trimodal encryption is used as a second tier for securing the data that was compressed using BPT algorithm. The trimodal encryption employs three encryption methods, and data is encrypted using one of these methods during transmission to the destination. The BPT algorithms performance is evaluated using benchmark textual datasets from the Calgary Corpus and the Canterbury Corpus. The experimental results demonstrate the unique characteristics of the BPT algorithm, including compression ratio (CR), compression factor (CF), bits per character (BPC), and space savings. Additionally, the Trimodal encryption algorithm (TME) method is evaluated using end-to-end delay analysis, packet loss analysis, and packet delivery ratio assessment. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Dielectric performance of graphene nanostructures prepared from naturally sourced material
Cost-effective and environmentally benign approach was adopted for the synthesis of oxidized graphene nanostructures from the precursor coke via Improved Hummers' method. The surface states of oxygen functional groups provided strong polarization for enhanced dielectric properties. Occurrence of dipole and interfacial polarizations in the low frequency region contributed to the dispersive behaviour of ?', ?", and tand.The relaxation phenomenon of the structure lead to an augmented electrical conductivity with increase in frequency. Our finding reveals the advantageous fabrication of graphene nanostructure having high dielectric constant (1 0 5) but with low loss which can be used in advanced nanodielectrics. 2020 Elsevier Ltd. All rights reserved. -
Dielectric performance of solid dielectric immersed in vegetable oil with antioxidant
Transformers are the most vital part of the power transmission and distribution system. Protecting them from all possible abnormalities is of very high priority. The insulation levels in the transformers need to be of very high grade as the power and voltage levels of a transformer are very high. Transformers are generally filled with petroleum based mineral oil as an insulator and also as a coolant inside them. These oils are highly inflammable and also highly toxic. They are also non-biodegradable, causing major harm to the environment. Vegetable oils which are abundant in nature unlike the mineral oil is being studied as a suitable substitute for mineral oils as transformer oil. The availability of vegetable oils differ from place to place. The work here focusses on the commercially available vegetable oils in India. Seven different samples of oil are tested for their dielectric properties and viscosity and the best one among them is tested with a solid dielectric (epoxy) immersed within it in order to simulate more appropriate conditions of a practical transformer. The tests are conducted based on Indian Standards (IS6792). 2016 IEEE. -
Differences in perceptions of employees towards knowledge management strategies in selected information technology companies in Bangalore
In older days, knowledge was passed verbally from one person to another. The industrial revolution changed the scenario and the emergence of factories and industries paved the need for systematic knowledge and it became more and more specialized as time passed. Since then, there has been an exponential growth in scientific and practical knowledge. In the twenty-first century, this process has taken rapid speed due to the improvements in information and communication technologies. Employees of the organizations have a varied opinion towards practicing knowledge management strategies in an organization. Some employees consider knowledge management as an opportunity and a few others like a burden. This article focuses on identifying and analyzing the differences in perceptions of employees towards knowledge management strategies in selected Information Technology companies in Bangalore. 2020 American Institute of Physics Inc.. All rights reserved. -
Digital Forensics Chain of Custody Using Blockchain
In todays world, Digital Forensics is a crucial subject with much scope as data storage becomes more decentralised. The collection and preservation of digital media is a topic of concern across the Cyber Security and Digital Forensics field. With Cloud Infrastructure and other technologies, data is not permanently stored in one place and gathering and analysing it can become a headache for Forensic Investigators. Blockchain, however, works as a decentralised, distributed peer-to-peer network and thus can be considered a suitable solution for the mentioned problems. With the help of a blockchain network and Smart Contracts, Digital Forensics can be significantly improved to adapt to modern digital architecture. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Digital Forensics Investigation for Attacks on Artificial Intelligence
The new research approaches are needed to be adopted to deal with security threats in AI based systems. This research is aimed at investigating the Artificial Intelligence (AI) attacks that are malicious by design. It also deals with conceptualization of the problem and strategies for attacks on Artificial Intelligence (AI) using Digital Forensic tools. A specific class of problems in Adversarial attacks are tampering of Images for computational processing in applications of Digital Photography, Computer Vision, Pattern Recognition (Facial Mapping algorithms). State-of-the-art developments in forensics such as 1. Application of end-to-end Neural Network Training pipeline for image rendering and provenance analysis, 2. Deep-fake image analysis using frequency methods, wavelet analysis & tools like - Amped Authenticate, 3. Capsule networks for detecting forged images 4. Information transformation for Feature extraction via Image Forensic tools such as EXIF-SC, Splice Radar, Noiseprint 5. Application of generative adversarial Networks (GAN) based models as anti-Image Forensics [8], will be studied in great detail and a new research approach will be designed incorporating these advancements for utility of Digital Forensics. The Electrochemical Society -
Digital Platforms and Techniques for Marketing in the Era of Information Technology
Digital marketing is the promotion of a product or service through at least one form of electronic media. This form of marketing is distinct from traditional marketing, but it uses some of the ideologies of traditional marketing. This research article examines the various technologies and platforms used in digital marketing that allow any organization or business to do this form of marketing and study what works for them and what does not. The article also explores the recent advancements in digital marketing due to the increase in users and the vast amount of data collected from these users. The two main advancements analyzed and discussed in this paper are machine learning (ML) and artificial intelligence (AI) tools. 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.