Search

Vehicle detection in Remote Sensing Images (RSI) is a specific application of object recognition like satellite or aerial imagery. This application is highly beneficial in different fields like defense, traffic monitoring, and urban planning. However, complex particulars about the vehicles and the surrounding background, delivered by the RSIs, need sophisticated investigation techniques depending on large data models. This is crucial though the amount of reliable and labelled training datasets is still a constraint. The challenges involved in vehicle detection from the RSIs include variations in vehicle orientations, appearances, and sizes due to dissimilar imaging conditions, weather, and terrain. Both specific architecture and hyperparameters of the Deep Learning (DL) algorithm must be tailored to the features of RS data and the nature of vehicle detection tasks. Therefore, the current study proposes the Intelligent Water Drop Algorithm with Deep Learning-Driven Vehicle Detection and Classification (IWDADL-VDC) methodology to be applied upon the Remote Sensing Images. The IWDADL-VDC technique exploits a hyperparameter-tuned DL model for both recognition and classification of the vehicles. In order to accomplish this, the IWDADL-VDC technique follows two major stages, namely vehicle detection and classification. For vehicle detection process, the IWDADL-VDC method uses the improved YOLO-v7 model. After the vehicles are detected, the next stage of classification is performed with the help of Deep Long Short-Term Memory (DLSTM) approach. In order to enhance the classification outcomes of the DLSTM model, the IWDA-based hyperparameter tuning process has been employed in this study. The experimental validation of the model was conducted using a benchmark dataset and the results attained by the IWDADL-VDC technique were promising over other recent approaches.

The proposed research deals with constructing a sign gesture recognition system to enable improved interaction between sign and non-sign users. With respect to this goal, five types of features are utilized—hand coordinates, convolutional features, convolutional features with finger angles, convolutional features on hand edges and convolutional features on binary robust invariant scalable keypoints—and trained on ensemble classifiers to accurately predict the label of the sign image provided as input. In addition, a hybrid artificial neural network is also fabricated that takes two of the aforementioned features, namely convolutional features and convolutional features on hand edges to precisely locate the hand region of the sign gesture under consideration in an attempt for classification. Experiments are also performed with convolutional neural networks on those benchmark datasets which are not accurately classified by the previous two methods. Overall, the proposed methodologies are able to handle a diverse variety of images that include labyrinthine backgrounds, user-specific distinctions, minuscule discrepancies between classes and image alterations. As a result, they are able to produce accuracies comparable with state-of-the-art literature.

The sheer volume of data being generated by the resources is creating a form of cognitive overload for enterprises. The data will be useful to multiple processes in enterprises. Learning and understanding natural language for each process increases computer work in the organization. Enterprise Cognitive Computing (ECC) with the help of Semantic Technology generates structured and organized data for accurate decision making in enterprises. For developing ECC system there are many implementation challenges that need to resolve. ECC comprises Machine Learning, Artificial Intelligence and Question Answering machine that uses natural language processing technologies. These emerging technologies need to customize or combined with complementary solutions as semantic knowledge graphs, depending on the use case. This paper addresses problems of Enterprises that use unstructured data and how this problem can be resolved using semantic technology tools.

Web Services are software snippets that can be integrated in HTTP and XML based messages based on web technology. Security plays a crucial role in web services. Web services provide a basis for system integration without any programming language and operating system constraint. The security of web services are determined by the secrecy and reliability of the XML based SOAP message that are used for communication. The valuable data stored on computers and servers over the internet need to be secured based on information security features. The security of web services is an important part and security algorithms using encryption techniques are implemented in web services for key generation and encryption of the messages in SOAP and RESTful Services, to provide more secure communication between two electronic devices. Our work focuses on a systematic study on the security features provided by SOAP and RESTful Services and tries to address the different issues faced in security and presents the research scope in the area of web security

This study examined the different techniques utilized as a part of the preservation and conservation of library materials in selected college libraries in the district of Bagalkota of Karnataka especially, it investigate the causes and nature of deterioration, patterns and techniques utilized as a part of their control, presence of preservation and conservation strategies and constraints restricting successful preservation and conservation. The survey technique was used to gather information. Findings uncovered that preservation and conservation strategies, however adopted in the college libraries were not viably being used in spite of the fact that the libraries all have preservation policies. The review also uncovered that cleaning and dusting of library materials is the most commonly used technique. The study built up that there are indeed incidences of deterioration of the most prominent outcome being books becoming torn and c racking and scratching. Other findings uncovered that inadequate funding was the most serious inhibitor to compelling preservation and conservation activities in the college libraries. In view of the discoveries, recommendations were made towards enhancing preservation and conservation practices in the libraries. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) stands as a progressive neurodegenerative disorder with a significant global public health impact. It is imperative to establish early and accurate diagnoses of AD to facilitate effective interventions and treatments. Recent years have witnessed the emergence of machine learning (ML) and deep learning (DL) techniques, displaying promise in various medical domains, including AD diagnosis. This study undertakes a comprehensive contrast between conventional machine learning methods and advanced deep learning strategies for early AD diagnosis. Conventional ML algorithms like support vector machines, decision trees, and K nearest neighbor have been extensively employed for AD diagnosis through relevant feature extraction from heterogeneous data sources. Conversely, deep learning techniques such as multilayer perceptron (MLP) and convolutional neural networks (CNNs) have demonstrated exceptional aptitude in autonomously uncovering intricate patterns and representations from unprocessed data like EEG data. The findings reveal that while traditional ML methods may perform adequately with limited data, deep learning techniques excel when ample data is available, showcasing their potential for early and precise AD diagnosis. In conclusion, this research paper contributes to the ongoing discourse surrounding the choice of appropriate methodologies for early Alzheimer's disease diagnosis. [ABSTRACT FROM AUTHOR]

PURPOSEBeliefs on causes of cancer, although sometimes aligned with known risk factors, may be influenced by personal experiences, cultural narratives, and misinformation. We investigated the prevalence of beliefs on causes of cancer and their association with cancer risk perception and lifestyle in a multiethnic Asian population.METHODSIn total, 2,008 Malaysian adults with no previous cancer were surveyed using a 42-item questionnaire adapted from the Awareness Measure and the Cancer Awareness Measure–Mythical Causes Scale. Partial least squares structural equation modeling was used to evaluate measurement models.RESULTSDespite high educational attainment, only about half of the respondents believed that 7 of the 21 listed established risk factors caused cancer. Factors associated with accurate beliefs included higher socioeconomic status (SES) and having family or friends with cancer. However, 14 of the 21 listed mythical/unproven factors were correctly believed as not cancer-causing by the majority. Women and those with lower SES were more likely to hold misconceptions. Beliefs on established risk factors were significantly associated with perceived risk of cancer. Individuals with stronger beliefs in established risk factors were less likely to be associated with healthy behaviors. Conversely, stronger beliefs in mythical or unproven factors were more likely to be associated with healthy lifestyles.CONCLUSIONFindings highlight the importance of prioritizing cancer literacy as a key action area in national cancer control plans. The counterintuitive associations between cancer beliefs and lifestyle emphasize the complexity of this relationship, necessitating nuanced approaches to promote cancer literacy and preventive behaviors.