Browse Items (2150 total)
Sort by:
-
Exploring the Adaptability of Attention U-Net for Post-operative Brain Tumor Segmentation in MRI Scans
This study explores the adaptability of a segmentation model, originally trained on pre-operative MRI data, in post-operative recurrent brain tumor segmentation. We utilized the Attention U-Net model for this study. In pre-operative training, the model achieved a Dice Coefficient of 0.92 and an IOU of 0.86 for brain tumor MRI segmentation. Due to the surgical artifacts in post-operative data, performance reduced with Dice Coefficient of 0.54 and an IOU of 0. To improve the performance, the model's architecture is fine-tuned by introducing dilated convolutions and residual connections. This refinement yielded improvements in results, with a Dice Coefficient of 0.68 and an IOU of 0.62 in the post-operative context. This improvement underscores the need for further research to select and adapt efficient models, retrain specific layers with an extensive collection of post-operative images, and fine-tune model parameters to enhance feature extraction during the encoding phase. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Revolution of the Indian Agricultural Landscape using Machine Learning and Big Data Techniques: A Systematic Review
The world of Big Data has been rapidly expanding into the domains of Engineering and Machine Learning. The biggest challenge in the Big Data landscape is the incompetence of processing vast amounts of data in a time-efficient manner. The agriculture domain has so long only relied on traditional method for yield prediction. This can be bettered by using novel Machine Learning techniques and innovative thinking. The study provides the review of most of the techniques already implemented in the ML, Big Data and Agriculture domain- traditional and modern- while focusing on highlighting the difference in accuracy between the traditional methods and the more advanced methods. 2022 IEEE. -
Message efficient ring leader election in distributed systems
Leader Election Algorithm, not only in distributed systems but in any communication network, is an essential matter for discussion. Tremendous amount of work are happening in the research community on election as network protocols are in need of co-ordinator process for the smooth running of the system. These so called Coordinator processes are responsible for the synchronization of the system otherwise, the system loses its reliability. Furthermore, if the leader process crashes, the new leader process should take the charge as early as possible. New leader is one among the currently running processes with the highest process id. In this paper we have presented a modified version of ring algorithm. Our work involves substantial modifications of the existing ring election algorithm and the comparison of message complexity with the original algorithm. Simulation results show that our algorithm minimizes the number of messages even in worst case scenario. 2013 Springer Science+Business Media. -
Smart Product Packing and IoT Marketing: Enhancing Customer Interaction
The convergence of smart product packaging and IoT marketing has transformed commerce. This study examines the fundamental ramifications of convergence and its potential to improve customer engagement. Our research shows the transformational potential of these technologies via quantitative and qualitative analyses.Smart packaging outperforms non-smart items, giving firms an advantage, according to quantitative data. Regression and correlation analysis confirm IoT data-customer interaction. Our study also emphasizes ethical data acquisition, which supports data privacy and consumer protection.Consumers may expect personalized experiences, transparency, and real-time feedback from this technology transformation. Smart product packaging and IoT marketing enable readers to make educated decisions and influence product development to meet changing consumer expectations.This research allows academics to study the ideas and models that affect consumer engagement. Data privacy and consumer protection may inform IoT marketing and smart device packaging policy.Our research guides organizations and customers towards better customer interactions, data-driven decision-making, and ethical data practices in this changing age. The future promises revolutionary customer contact. 2023 IEEE. -
Prioritizing Factors Affecting Customers Satisfaction in the Internet Banking Using Artificial Intelligence
Internet banking has revolutionised the way customers interact with their banks, providing them with convenient access to a wide range of financial services from the comfort of their homes or mobile devices. Customer satisfaction the success of an endeavour is contingent upon a vital component internet banking Service provision, as it pertains directly impacts customer retention and loyalty. This research explores the application of artificial intelligence (AI) techniques, specifically random forest and convolutional neural networks (CNN), to prioritise the factors that affect customer satisfaction in internet banking. The study begins with data collection from a diverse sample of internet banking customers, including demographic information, transaction history, and customer feedback. These may include the ease of navigation, the response time of the platform, and the level of trust in the bank's security measures. Furthermore, convolutional neural networks (CNN) are utilised to analyse unstructured data such as customer feedback and reviews. By applying natural language processing techniques, CNN s extract sentiment and topic information from customer comments. This approach can ultimately lead to improved customer retention and loyalty, ensuring the long-term success and competitiveness of internet banking platforms. In conclusion, this study showcases the power of AI, specifically Random Forest and CNN, in prioritising factors affecting customer satisfaction in internet banking. It highlights the significance of using both quantitative and qualitative investigations in order to attain a comprehensive comprehension of customer sentiments and preferences in the digital banking landscape. 2024 IEEE. -
Stress Management among Employees in Information Technology Sector Using Deep Learning
Information technology is one of the areas in India that is developing the quickest India's information technology (IT) administrations industry has become more merciless. The information technology area has been managing additional difficult issues like specialized development, administration enhancement, and worldwide overhauling starting from the beginning of this long period. Along these lines, it is unimaginable for everybody to adjust to the moving difficulties they experience in the field of information technology, which causes stress. Stress is something that individuals battle with for most of their lives. Albeit the information technology (IT) industry is notable for its hazardous turn of events and development, it is likewise portrayed by high worker burnout and stress levels. This theoretical proposes an original strategy for overseeing stress in the IT business that utilizes deep learning methods. This study utilizes deep learning calculations to expect, distinguish, and decrease stress makes all together location the earnest issue of stress among IT experts. The principal objective is to make a shrewd framework that can help organizations proactively recognize stress-related issues in their labor force and proposition specific cures. 2024 IEEE. -
The Creation of Intelligent Surfaces for the Purpose of Next-Gen Wireless Networks
In preparation of the changing environment of 5th wave (5G) and prospective networks of cells, this study explores new methods to meet challenges that result from the erratic character of the communication medium. Traditionally viewed as a chance factor, the relationship between broadcast radio waves with surrounding factors lowers signal quality in modern times of wireless communications. This paper performs a full literature review on customizable autonomous surfaces (RISs) alongside their uses, stressing the chance for network managers to control radio wave features and minimize environmental spread problems. RISs allow effective control over waveform parameters, including the amplitude, phase, number, and polarization, that without needing complex encoder, decoder, or radio wave processing methods. Leveraging technical developments, metasurfaces, reflectarrays, phase shifts, and liquid crystals appear as potential options for RIS application, placing them as pioneers in the realization of 5G as well as subsequent networks. The study dives into current actions in the RIS-operated mobile phone network area and covers core research issues that deserve exploration to feed unlocking the full promise of RISs at wireless communication networks. 2024 IEEE. -
Framework for Controlling Interference and Power Consumption on Femto-Cells In-Wireless System
Utilization of femto-cells is one of the cost effective solution to increase the internal network connectivity and coverage. However, there are various impediment in achieving so which has caused a consistent research work evolving out with solution. Review of existing literature shows that maximum focus was given for energy problems in cellular network and not much on problems that roots out from interference. Therefore, the proposed system has presented a very simple and novel approach where the problems associated with interference and energy in using large groups of femto-cells are addressed. Adopting analytical research methodology, the proposed model offers on-demand utilization of the selective femto-cells on the basis of the traffic demands. The study outcome shows that proposed system offers better performance in contrast to existing approach. Springer Nature Switzerland AG 2019. -
Systematic Literature Review on Industry Revolution 4.0 to Predict Maintenance and Life Time of Machines in Manufacturing Industry
Industry 4.0 is digitized revolution for manufacturers or companies where in new technologies are imbibed into their production system for their day-to-day operations or activities. So that their overall economic needs and efficiency can be improved. In manufacturing industry maintenance of the equipment is the key concern. When the equipment requires maintenance, it has to be done at the earliest, failing which companies will have to face consequences in terms of loss of customers, time and money. Solution is provided to this problem in terms of a technique called predictive maintenance. The content of the article focuses on different predictive maintenance strategies, which help manufacturers to forecast if equipment/component will fail so that its maintenance and repair can be scheduled exactly before the component fails. The results will be useful for manufacturers to understand the importance of industry 4.0 for predictive maintenance. 2023 IEEE. -
Innovative Method for Detecting Liver Cancer using Auto Encoder and Single Feed Forward Neural Network
Liver cancer ranks sixth among all cancers in frequency of incidence. A CT scan is the gold standard for diagnosis. These days, CT scan images of the liver and its tumor can be segmented using deep learning and Neural Network techniques. In this proposed approach to identifying cancer cells, it's focus on four important areas: To enhance a photo by taking out imperfections and unwanted details. An ostu method is used for this purpose. Specifically, this proposed approach to use the watershed segmentation technique for image segmentation, followed by feature extraction, in an effort to isolate the offending cancer cell. After finishing the model training with AE-ELM. To do this, Extreme Learning Machine incorporates an auto encoder. To achieve effective and supervised recognition, the network's strengths of Extreme Learning Machine (ELM) are thoroughly leveraged, including its few training parameters, quick learning speed, and robust generalization ability. The auto encoder-extreme learning machine (AE-ELM) network has been shown to have a respectable recognition impact when the sigmoid activation function is used and the number of hidden layer neurons is set to 1200. According to the results of this investigation, a method based on AE-ELM can be utilized to detect the liver tumor. As compared to the CNN and ELM models, this technique achieves superior accuracy (around 99.23%). 2023 IEEE. -
X -ray diffraction and microhardness studies of tin monoselenide
Tin Monoselenide (SnSe) crystals have been grown by the Physical Vapour Deposition (PVD) method. X-ray diffraction studies were carried out on the as grown crystals and the lattice parameters were found to be a=11.506 b=4.149and c=4.447 The values were found to be comparable with that reported in the PDF card for SnSe. The microhardness of the crystals has been determined by using Vickers microhardness indenter. 2011 American Institute of Physics. -
Comparing Developmental Approaches for Game-Based Learning in Cyber-Security Campaigns
Digital game-based learning (DGBL) has been viewed as an effective teaching strategy that encourages students to pick up and learn a subject. This paper explores its viability to help increase the reach and efficiency of the existing cybersecurity awareness spreading campaigns that find adolescent students as their demographic. This work intends to reinforce the benefits of multimedia learning in schools and universities with the use of video games and further find the ideal type and genre of game that can be developed to spread awareness about cybersecurity to students in grades 8th to 12th (tailored towards the Indian context). Game genres were compared on the basis of having a simple gameplay loop, being easy for instructors to train themselves in, being inclusive to special needs children, being able to be published as an independent title, and having very low hardware specification requirements. Ideally, the paper proposes that this game would be a single-player experience that would follow a game-based learning approach to maximize the game's reach. Once identified, the model of the game was assessed using already existing implementations. Finally, the ideal model, a single-player visual novel is proposed. A future iteration of the paper will implement the proposed model of game design and perform an analysis of the effects the video game had on the learning experience of the students surveyed. 2023 IEEE. -
Anticounterfeiting Method for Drugs Using Synthetic DNA Cryptography
Counterfeited products are a significant problem in both developed and developing countries and has become more critical as an aftermath of COVID-19, exclusively for drugs and medical equipment's. In this paper, an innovative approach is proposed to resist counterfeiting which is based on the principles of Synthetic DNA. The proposed encryption approach has employed the distinctive features of synthetic DNA in amalgamation with DNA encryption to provide information security and functions as an anticounterfeiting method that ensures usability. The scheme's security analysis and proof of concept are detailed. Scyther is used to carry out the formal analysis of the scheme, and all of the modeled assertions are verified without any attacks. 2022 IEEE. -
An online signature method using DNA based bio-hash for positive identification and non-repudiation
This work focuses on using biological data as a unique feature to generate e-Signature. DNA, the blue print of life is of unique nature. The signature created using biological data will be difficult to repudiate in the scenario of a legal dispute. Applications of human DNA are not limited to molecular biology, with the advents of fast growing technologies it is possible to inject DNA into e-Signature for positive identification. The proposed methodology uses Signature DNA as a unique biological feature for the registrant. This work has various phases, the first phase includes creating the Signature DNA using hybridized unique DNA segments of the individual (Registrant) which is the unique identification of the user and difficult to duplicate and repudiate. It generates a Bio-Hash of the Signature DNA. The DNA-Hash generated serves for positive identification of the user which computed with the hash of the e-Document and a random value serve as a Bio-Sign (e-Signature) for the e-Document in the second phase. Bio-Sign converted into QR code with a link to the e-Sign service providers website will ensure usability for verification. In the verification phase the verifier scans the QR code which connects to the e-Service provider's web link. The service provider computes and verifies the document and ensures the e-Signature is valid or not to the verifier. If the signer repudiates the signature, positive identification using DNA helps to achieve Non-Repudiation, the last phase. In the scenario of a legal dispute, the registrant cannot repudiate as the authorities can provide positive identification using the DNA Signature for greater assurance. The proposed technique ensures authentication, integrity and Non-Repudiation with Zero knowledge scenario to the verifier. 2017 IEEE. -
A secure image-based authentication scheme employing DNA crypto and steganography
Authentication is considered as one of the critical aspects of Information security to ensure identity. Authentication is generally carried out using conventional authentication methods such as text based passwords, but considering the increased usage of electronic services a user has to remember many id-password pairs which often leads to memorability issues. This inspire users to reuse passwords across e-services, but this practice is vulnerable to security attacks. To improve security strength, various authentication techniques have been proposed including two factor schemes based on smart card, tokens etc. and advanced biometric techniques. Graphical Image based authentication systems has received relevant diligence as it provides better usability by way of memorable image passwords. But the tradeoff between usability and security is a major concern while strengthening authentication. This paper proposes a novel twoway secure authentication scheme using DNA cryptography and steganography considering both security and usability. The protocol uses text and image password of which text password is converted into cipher text using DNA cryptography and embedded into image password by applying steganography. Hash value of the generated stego image is calculated using SHA-256 and the same will be used for verification to authenticate legitimate user. 2015 ACM. -
DNA based cryptography to improve usability of authenticated access of electronic health records
The quality of health care has been drastically improved with the evolution of Internet. Electronic health records play a major role in interoperability and accessibility of patients data which helps in effective and timely treatment irrespective of the demographic area. The proposed model is to ensure and monitor maternal health during pregnancy and to create awareness alerts (options include messages, voice alerts or flash the system) based on the individual health record. The system aims to prevent maternal death due to medical negligence and helps to make recommendations to prevent future mortality based on medical history and take appropriate action. Authentication is a critical aspect considering the trade-off between usability and security whereas data breach and related cybercrime are major concerns in health care. The proposed model uses DNA based authentication techniques to ensure usability and confidentiality of electronic data, Aadhaar to prevent unauthorized access to patients data in case of emergency without affecting availability. 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. -
DNA for information security: A Survey on DNA computing and a pseudo DNA method based on central dogma of molecular biology
Biology is a life science which has high significance on the quality of life and information security is that aspect for social edification, which human beings will never compromise. Both are subjects of high relevance and inevitable for mankind. So, an amalgamation of these subjects definitely turns up as utility technology, either for security or data storage and is known as Bio computing. The secure transfer of information was a major concern from ancient civilizations. Various techniques have been proposed to maintain security of data so that only intended recipient should be able to receive the message other than the sender. These practices became more significant with the introduction of the Internet. Information varies from big data to a particular word, but every piece of information requires proper storage and protection which is a major concern. Cryptography is an art or science of secrecy which protects information from unauthorized access. Various techniques evolved through years for information protection, including Ciphers, Cryptography, Steganography, Biometrics and recent DNA for security.DNA cryptography was a major breakthrough in the field of security which uses Bio-molecular concepts and gives us a new hope of unbreakable algorithms. This paper discusses various DNA based Cryptographic methods proposed till now. It also proposes a DNA symmetric algorithm based on the Pseudo DNA Cryptography and Central dogma of molecular biology. The suggested algorithm uses splicing and padding techniques along with complementary rules which make the algorithm more secure as it is an additional layer of security than conventional cryptographic techniques. 2014 IEEE. -
Wavelet packet transform based fusion of misaligned images
This paper proposes an image fusion method based on wavelet packet transform (WPT) for images with misaligned region of interest, which finds wide application in target recognition and feature extraction. The region of interest of the images are first aligned and then fused in the transform domain. The various no-reference parameters such as standard deviation (SD), spatial frequency (SF) are measured for the fused image. The result obtained from this method is compared with the other methods such as image fusion using discrete wavelet transform (DWT), stationary wavelet transform and guided filtering. It is evident from the simulation results that the two parameters are high for the fused image using wavelet packet transform. 2016 IEEE. -
Smart Intravenous Infusion Monitoring and Alert System using IoT-based Force Sensitive Resistor and Whatabot API
Intravenous fluids with vitamins are given to people who are dehydrated and have an imbalance of electrolytes. When the IV bag is empty, the patient's blood flows through the IV line toward the empty bag because their blood pressure is higher than the IV bag's. This process, called diffusion can lead to pain and loss of blood. If the IV bag is empty and hooked up to the patient, air can get into the bloodstream. The air bubble enters the patient's bloodstream, causing the same catastrophic effects. This paper aims to eliminate the danger by creating Smart IV Bags in light of the rising number of risks in the medical sector brought on by the reverse flow of blood in an IV bag (intravenous bag). The Smart IV bags eliminate the need for constant physical monitoring of the IV bag's state while preventing reverse blood flow. For detection of the IV fluid state, a 0.5 ' diameter force-sensitive resistor is deployed. We integrate the system with a NodeMCU module and using Wi-Fi, it establishes communication between the smart IV bag and the person in charge at the hospital, like a nurse or a caretaker. In this study, the IV Bag is the 'thing' connected to the internet where the FSR readings are analyzed using NodeMCU script to determine if it needs to be emptied and send a WhatsApp message to the caretaker. This design establishes an IoT environment where the IV Bag automatically alerts the caretaker and eliminates the need for constant human intervention. 2023 IEEE. -
Clinical Text Classification of Medical Transcriptions Based on Different Diseases
Clinical text classification is the process of extracting the information from clinical narratives. Clinical narratives are the voice files, notes taken during a lecture, or other spoken material given by physicians. Because of the rapid rise in data in the healthcare sector, text mining and information extraction (IE) have acquired a few applications in the previous few years. This research attempts to use machine learning algorithms to diagnose diseases from the given medical transcriptions. Proposed clinical text classification models could decrease human efforts of labeled training data creation and feature engineering and for designing for applying machine learning models to clinical text classification by leveraging weak supervision. The main aim of this paper is to compare the multiclass logistic regression model and support vector classifier model which is implemented for performing clinical text classification on medical transcriptions. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.