Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
55
result(s) for
"Solanki, Arun"
Sort by:
Advanced AI techniques and applications in bioinformatics
\"The advanced AI techniques are essential for resolving various problematic aspects emerging in the field of bioinformatics. This book covers the recent approaches in artificial intelligence and machine learning methods and their applications in Genome and Gene editing, cancer drug discovery classification, and the protein folding algorithms among others. Deep learning, which is widely used in image processing, is also applicable in bioinformatics as one of the most popular artificial intelligence approaches. The wide range of applications discussed in this book are an indispensable resource for computer scientists, engineers, biologists, mathematicians, physicians, and medical informaticists. Features: Focusses on the cross-disciplinary relation between computer science and biology and the role of machine learning methods in resolving complex problems in bioinformatics Provides a comprehensive and balanced blend of topics and applications using various advanced algorithms Presents cutting-edge research methodologies in the area of AI methods when applied to bioinformatics and innovative solutions Discusses the AI/ML techniques, their use, and their potential for use in common and future bioinformatics applications Includes recent achievements in AI and bioinformatics contributed by a global team of researchers\"-- Provided by publisher.
Book
DL-CNN-based approach with image processing techniques for diagnosis of retinal diseases
Artificial intelligence has the potential to revolutionize disease diagnosis, classification, and identification. However, the implementation of clinical-decision support algorithms for medical imaging faces challenges with reliability and interpretability. This study presents a diagnostic tool based on a deep-learning framework for four-class classification of ocular diseases by automatically detecting diabetic macular edema, drusen, choroidal neovascularization, and normal images in optical coherence tomography (OCT) scans of the human eye. The proposed framework utilizes OCT images of the retina and analyses using three different convolution neural network (CNN) models (five, seven, and nine layers) to identify the various retinal layers extracting useful information, observe any new deviations, and predict the multiple eye deformities. The framework utilizes OCT images of the retina, which are preprocessed and processed for noise removal, contrast enhancements, contour-based edge, and detection of retinal layer extraction. This image dataset is analyzed using three different CNN models (of five, seven, and nine layers) to identify the four ocular pathologies. Results obtained from the experimental testing confirm that our model has excellently performed with 0.965 classification accuracy, 0.960 sensitivity, and 0.986 specificities compared with the manual ophthalmological diagnosis.
Journal Article
The internet of drones : AI applications for smart solutions
\"In recent years, drones have been integrated with the Internet of Things to offer a variety of exciting new applications in different sectors. This volume provides a detailed exploration of adapting and implementing Internet of Drones (IoD) technologies into real-world applications, with the emphasis on solutions to architectural challenges, providing a clear overview of standardization and regulation, implementation plans, and privacy concerns. The Internet of Drones : AI Applications for Smart Solutions discusses the architectures and protocols for drone communications, implementing and deploying of 5G-drone setups, security issues with drone technology, deep learning techniques applied on real-time footage, and more. It also explores some of the varied applications of IoD, such as for use in monitoring and analysis of troposphere pollutants, providing services and communications in smart cities (such as for weather forecasting, healthcare, communications, transport, agriculture, safety and protection, environmental reduction, service delivery, and e-disposal), for disaster relief management (such as for scanning the affected areas for radiation intensity in cases of nuclear disaster, gathering the location of hotspots, looking for the victims, assessing damage), and more. The authors cover package delivery, movement of traffic, crop monitoring, and mass detection. The problems and challenges associated with IoD in air traffic monitoring, communication between drones, optimum route discovery, and security are also addressed. This detailed exploration of adapting and implementing IoD technologies into real-world applications in this volume will be valuable for graduate students in computer science and especially drone technology, as well as researchers and professionals\"-- Provided by publisher.
BOOK
Intelligent Systems for IoE Based Smart Cities
Intelligent Systems for IoE Based Smart Cities provides simplified information about complexities of cyber physical systems, the Internet of Everything (IoE) and smart city infrastructure. It presents 11 edited chapters that reveal how intelligent systems and IoE are driving the evolution of smart cities, making them more efficient, interconnected, and responsive to the needs of citizens. The book content represents comprehensive exploration of the transformative potential and challenges of IoE-based smart cities, fueled by Artificial Intelligence (AI) and Machine Learning (ML) innovations. Key Topics: Physical layer design considerations that underpin smart city infrastructure Enabling technologies for intelligent systems within the context of smart computing environments Smart sensors and actuators, their applications, challenges, and future trends in IoE-based smart cities Applications, enabling technologies, challenges, and future trends of IoE for smart cities. The integration of Artificial Intelligence, Natural Language Processing, and smart cities for enhanced urban experiences machine learning-based intrusion detection techniques for countering attacks on the Internet of Vehicles Smartphone-based indoor positioning applications using trilateration and the role of sensors in IoT ecosystems IoT, blockchain, and cloud-based technology for secure frameworks and data analytics Blockchain and smart contracts in shaping the future of smart cities. This is a timely reference for researchers, professionals, and students interested in the convergence IoT, intelligent systems and urban studies into smart city planning and design. Audience Researchers, professionals, and students interested in the convergence of IoT, intelligent systems and urban studies into smart city planning and design.
eBook
A system to transform natural language queries into SQL queries
In the present scenario, every user is not familiar with the use of Structured Query Language (SQL). So, user is not able to understand or write complex queries in SQL. An enhanced application with intelligent interface is needed to improve communication between the naïve user and the databases application. The database is an efficient structure for handling data. To understand the structure of the database, a user has to learn SQL. The non-expert users who are not familiar with the use of SQL, need a system by which the user can interact with the database in their natural language. The system must have the ability to understand the natural language and interact with the database accordingly. In this research, an improved system with three-tier architecture is developed. Pattern matching and semantic matching techniques are used to develop the system which transforms natural language into SQL queries. The SQL query is generated with the production rules and the predefined data dictionary. The predefined data dictionary contains semantics for attributes and relation among attributes. The input given by the user is transformed by the system into SQL query by passing through steps like tokenization, escape word removal, classification of elements and query formation. Finally, the output is in the form of a SQL query. The results are compared with the existing system. The results given by the proposed system are better than the existing system. The proposed system has better recall value, accuracy, and precision in comparison to existing systems.
Journal Article
Improved SSD using deep multi-scale attention spatial–temporal features for action recognition
The biggest difference between video-based action recognition and image-based action recognition is that the former has an extra feature of time dimension. Most methods of action recognition based on deep learning adopt: (1) using 3D convolution to modeling the temporal features; (2) introducing an auxiliary temporal feature, such as optical flow. However, the 3D convolution network usually consumes huge computational resources. The extraction of optical flow requires an extra tedious process with an extra space for storage, and is usually modeled for short-range temporal features. To construct the temporal features better, in this paper we propose a multi-scale attention spatial–temporal features network based on SSD, by means of piecewise on long range of the whole video sequence to sparse sampling of video, using the self-attention mechanism to capture the relation between one frame and the sequence of frames sampled on the entire range of video, making the network notice the representative frames on the sequence. Moreover, the attention mechanism is used to assign different weights to the inter-frame relations representing different time scales, so as to reasoning the contextual relations of actions in the time dimension. Our proposed method achieves competitive performance on two commonly used datasets: UCF101 and HMDB51.
Journal Article
Music instrument recognition using deep convolutional neural networks
Musical instruments identification in polyphonic is a challenge in music information retrieval. In proposed work, a deep convolution neural network framework for predominant instrument recognition in real-world polyphonic music is accomplished. The network is trained on fixed-length music with a labeled predominant instrument and estimate an arbitrary number of instruments from an audio signal with variable length. The Mel spectrogram representation is used to map audio data into the matrix format. This work used eight layer convolution neural network for instrument recognition. ReLu activation function is used for the scaling of training data and introduces non-linearity in the network. At each layer, Max Pooling function is used for the dimension reduction. For the regularization, dropout is used which prevent the output from getting overfitting. The Softmax function gives the probability of particular instruments. The research excellent result with 92.8% accuracy.
Journal Article
An abstractive text summarization technique using transformer model with self-attention mechanism
Creating a summarized version of a text document that still conveys precise meaning is an incredibly complex endeavor in natural language processing (NLP). Abstract text summarization (ATS) is the process of using facts from source sentences and merging them into concise representations while maintaining the content and intent of the text. Manually summarizing large amounts of text are challenging and time-consuming for humans. Therefore, text summarization has become an exciting research focus in NLP. This research paper proposed an ATS model using a
Transformer Technique with Self-Attention Mechanism (T2SAM)
. The self-attention mechanism is added to the transformer to solve the problem of coreference in text. This makes the system to understand the text better. The proposed
T2SAM
model improves the performance of text summarization. It is trained on the
Inshorts News
dataset combined with the
DUC-2004 shared tasks
dataset. The performance of the proposed model has been evaluated using the ROUGE metrics, and it has been shown to outperform the existing state-of-the-art baseline models. The proposed model gives the training loss minimum to 1.8220 from 10.3058 (at the starting point) up to 30 epochs, and it achieved model accuracy 48.50% F1-Score on both the
Inshorts
and DUC-2004 news datasets.
Journal Article
TINB: a topical interaction network builder from WWW
Social network is a collection of people generally called ‘actors’ who are connected to each other based on some association criteria like a friend, follow, co-authorship, co-workers, etc. Interaction networks are the generalization of social networks. In recent developments of data sciences, analytics has applications in every significant area such as economy, general elections, epidemics, terrorism detection, clustering, marketing, etc. All of these areas require interaction data of various entities. Though the social network is a significant reservoir for such data, it covers only one segment of the information. A right amount of information is available on the web, but it is not useful for analytics in its raw form. This paper presents a framework that collects information from www using a parameterized crawler and prepares the social network-like structure of web pages, called interaction network. The interaction network prepared is similar to any traditional social network in every aspect. The web pages are selected based on contexts of the URLs found in the nearby vicinity of URLs, decided by predefined parameters. The proposed crawler is tested over several topics covering thousands of pages. More than 50 percent harvest rate is achieved by the proposed crawler. Properties of the interaction network such as degree distribution, clustering coefficient, modularity, distribution of communities, diameter and page rank have been investigated to establish the fact that it behaves like any traditional social network. The idea of preparing interaction network is extendible to the field of newage technologies like IoT, big data, deepweb, prediction models etc.
Journal Article
Elliptic Curve Signcryption-Based Mutual Authentication Protocol for Smart Cards
In the modern computing environment, smart cards are being used extensively, which are intended to authenticate a user with the system or server. Owing to the constrictions of computational resources, smart card-based systems require an effective design and efficient security scheme. In this paper, a smart card authentication protocol based on the concept of elliptic curve signcryption has been proposed and developed, which provides security attributes, including confidentiality of messages, non-repudiation, the integrity of messages, mutual authentication, anonymity, availability, and forward security. Moreover, the analysis of security functionalities shows that the protocol developed and explained in this paper is secure from password guessing attacks, user and server impersonation, replay attacks, de-synchronization attacks, insider attacks, known key attacks, and man-in-the-middle attacks. The results have demonstrated that the proposed smart card security protocol reduces the computational overhead on a smart card by 33.3% and the communication cost of a smart card by 34.5%, in comparison to the existing efficient protocols. It can, thus, be inferred from the results that using elliptic curve signcryption in the authentication mechanism reduces the computational cost and communication overhead by a significant amount.
Journal Article