Search

Ovaries are important parts of the female reproductive system because they produce the egg or ovum needed for fertilization. Cysts frequently impact female follicles, so torsion, infertility, and cancer can result from an enormous ovarian cyst. As a result, this is critical to get a diagnosis as quickly as feasible an ultrasound examination is performed to diagnose an ovarian cyst. So, this work gathered ultrasound images of different women's ovaries and determined whether or not an ovarian cyst was detected. This work proposed a novel technique to detect the ovarian cyst using images of ovarian ultrasound cysts from an ongoing database. Initially pre-processed by removing noise, followed by feature extraction, and finally classifying using new deep reinforcement learning with Harris Hawks Optimization (HHO) classifier. Automatic feature extraction is implemented using the recent popular convolutional neural network (CNN) technique that extracts image features as conditions in the reinforcement learning algorithm. Deep Q-Network (DQN) is generated to train a Q-network and detect the disease, and the swarm-based method of HHO utilizes the optimization method to produce optimal hyperparameters in the DQN model known as HHO-DQN. Extensive experimental evaluations on datasets show that the proposed HHO- DQN approach outperforms existing active learning approaches for ovarian cyst classification. [ABSTRACT FROM AUTHOR]

Though artificial intelligence (AI) has been used in nuclear medicine for more than 50 years, more progress has been made in deep learning (DL) and machine learning (ML), which have driven the development of new AI abilities in the field. ANNs are used in both deep learning and machine learning in nuclear medicine. Alternatively, if 3D convolutional neural network (CNN) is used, the inputs may be the actual images that are being analyzed, rather than a set of inputs. In nuclear medicine, artificial intelligence reimagines and reengineers the field's therapeutic and scientific capabilities. Understanding the concepts of 3D CNN and U-Net in the context of nuclear medicine provides for a deeper engagement with clinical and research applications, as well as the ability to troubleshoot problems when they emerge. Business analytics, risk assessment, quality assurance, and basic classifications are all examples of simple ML applications. General nuclear medicine, SPECT, PET, MRI, and CT may benefit from more advanced DL applications for classification, detection, localization, segmentation, quantification, and radiomic feature extraction utilizing 3D CNNs. An ANN may be used to analyze a small dataset at the same time as traditional statistical methods, as well as bigger datasets. Nuclear medicine's clinical and research practices have been largely unaffected by the introduction of artificial intelligence (AI). Clinical and research landscapes have been fundamentally altered by the advent of 3D CNN and U-Net applications. Nuclear medicine professionals must now have at least an elementary understanding of AI principles such as neural networks (ANNs) and convolutional neural networks (CNNs). [ABSTRACT FROM AUTHOR]

The mobile ad hoc networks are a set of the autonomous nodes which arbitrarily moves out due to their autonomous nature. The topology of the network differs very often. Each and every autonomous node are powered by batteries with inadequate abilities and due to which the nodes fail to communicate the information packets from source to the target. The purpose is to design an energy efficient routing scheme in mobile ad hoc network with the aid of rough set calibration scheme. The rough set calibration scheme ultimately makes use of episodic based association where each and every metric like energy and distance are employed as the entity of rough set. Furthermore, the scheme aids in deciding the energy efficient routing. The analysis reveals that the scheme attempts for energy efficient routing with the aid of rough sets. The results of the simulation make use of the designed protocol with the aid of NS2 and estimate it with other conventional schemes based on which the designed scheme performs better in terms of energy efficiency. [ABSTRACT FROM AUTHOR]

The age of information has done it simple for storing huge amount of data. In actual fact, a considerable segment of existing information is accumulated in the text databases that have huge set of documents from different sources like research articles, news articles, books, e-mail messages, web pages and digital libraries. In many text databases, stored data are in the semi-structured format in that they are neither entirely structured nor entirely unstructured. IR (Information Retrieval) field has been growing in parallel using database systems for several years. Contrasting to the databases system fields that have concentrated mainly on transaction and query processing of the structured data, IR is concerned with firm and retrieval of data from a huge quantity of text-oriented documents. Thus, IR tackles with unstructured and/or semi-structured databases. Information security requirements within a firm have experience major variations in the past some decades. By the establishment of computer, the necessary for automated equipment for securing files as well as other information that stored on the computer turned into evident. This is particularly in case of shared information resources via public network. This is the origin for having a secure computer system / the need for computer security. Computer Security can be achieved by Intrusion Detection Systems. In this paper, we address these issues by applying Similarity Search in two diversified fields: Digital Libraries and Computer Security. The paper discusses a fast and efficient similarity search technique for approximate retrieval of books metadata in Digital Libraries. In DLI the books retrieval takes place just by using metadata such as title, year, edition, author, publishing of a book. Though, if metadata is missing, incorrect or unfinished, then it creates the library retrieval system inefficient, incorrect leads too much confusion to the user. In this context even if the query from the user matches partially or fully with a stored pattern, the information related to that be retrieved. The paper talks about a method that functions rapid and effective, language independent, and flexible library retrieval system signature based similarity search. This system is able to retrieve not only the metadata that exactly matches the query but also fairly accurate identical because of missing words, jumbled words and spell mistakes. Fundamentally, signature file approach is used here. A signature file approach looks like the most capable for huge database as it has superior text retrieval features and requires little storage overhead. [ABSTRACT FROM AUTHOR]

Security is a major concern in mobile ad hoc network (MANET) that ensure packet authentication and integrity. A data transmitted from source to destination node has to be protected from the active and passive attacks. Certificate based secure routing scheme are developed precisely to ensure authentication with certificate mechanism. However, this paper uses fuzzy enhanced secure multicast routing (FSMR) scheme ensure better security in network and data. To estimate the presence of misbehaving nodes, FSMR is established based on normal and abnormal behaviors from the statistical data. Certificateless routing is used in the proposed system and it authenticates the data from the concept of key generation, signcryption and unsigncryption. Packets are routed and validated without the knowledge of certificate routing. The evaluation on proposed system proves that the proposed system has better data packet authentication with lesser energy consumption. Further, the proposed system attains better performance in terms of authenticity, data integrity, network lifetime, average delay and maximum throughput. [ABSTRACT FROM AUTHOR]

• Gray-Level Co-occurrence matrix and vantage point tree were used which has excellent performance and classifier. • Networks with two segmentation such as U-Net and 3D CNN are proposed for better and accurate predictions. • 3D CNN was used to segment the enhancing tumor more accurately. • U-Net was used in the tumor core for the better performance used in the sub-region of final prediction. Analysis and monitoring of disease development rely heavily on automated segmentation of brain tumors using MRI data. Because gliomas are aggressive and diverse, effective and precise segmentation techniques are utilized to divide tumors into intra-tumoral groups. In the proposed work, the Gray Level Co-occurrence Matrix feature extraction is used to extract characteristics from the image. In the segmentation problem of Brain tumor, Convolutional Neural Networks, which are widely employed in biomedical image segmentation, have greatly enhanced the state-of-the-art accuracy. In this work, we propose a major but simple combinative approach that results in improved and more precise estimates by combining two segmentation networks: a U-Net and a 3D CNN. For each model, it was assessed independently on the dataset to produce segmentation maps that varied greatly in terms of segmented tumor sub-regions and were then ensembled to reach the final prediction. On the validation set, the accuracy (percentage) of 98.29, 98.45, and 99.4 for tumor core, enhanced tumor and whole tumor, respectively, performed well in contrast to state-of-the-art designs presently existing. [Display omitted] [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we study the controllability of second-order nonlinear integrodifferential systems in Banach spaces. Further, we derive a set of sufficient conditions for the controllability of second-order nonlinear integrodifferential evolution systems in Banach spaces. The results are established by using the theory of strongly continuous cosine families of bounded linear operators and the Schaefer fixed-point theorem. [Copyright &y& Elsevier]