Abstract:

Birds are the warm-blooded vertebrates constituting of class Aves, there are nearly 10 thousand living species of birds in the world with multifarious characteristics and appearances. Bird watching is often considered to be an interesting hobby by human beings in the natural environment. The human knowledge over the species isn’t enough to identify a species of bird accurately, as it requires lot of expertise in the field of Ornithology. This paper presents an automated model based on the deep neural networks which automatically identifies the species of a bird given as the test data set. The model was trained and tested for 20 species of birds with the total images 7637 and 1853 images for train and test respectively and the model has shown A promising accuracy of 98% when tested with the test datasets.

Keywords:

Convolution neural network, Artificial Intelligence, Machine Learning, Image Classification

Abstract:

With the rapid proliferation of Internet of Things (IoT) devices, ensuring reliable and efficient communication has become imperative. Quality-of-Service (QoS) in IoT networks plays a crucial role in guaranteeing the desired level of performance. This research paper provides a comprehensive review of QoS routing in IoT and investigates the application of bio-inspired optimization algorithms to address the associated challenges. The literature review covers traditional routing algorithms, their limitations, and the potential of bio-inspired optimization algorithms. The methodology involves a careful selection of bio-inspired algorithms, data collection from relevant research papers, and the development of a comparative analysis framework. Results and discussion focus on the performance of selected algorithms, providing insights and implications for QoS improvement in IoT networks.

Keywords:

Internet of Things, Quality-of-Service, QoS Routing, Bio-Inspired Optimization Algorithms, Literature Review, Comparative Analysis, IoT Networks, Routing Algorithms, Optimization

Abstract:

Community detection is a growing field of interest in the area of Social Networks. Many community detection methods in recent years, there are many real networks that are closely formed according to a community network. Many research efforts to develop algorithms and methods that can efficiently find the hidden pattern in the community network. This paper describes various community discovery algorithms such as Non overlapping community detection algorithms, Traditional Algorithm. Finally, research shows a comparison of Louvain algorithm, Label Propagation algorithm, Infomap algorithm concerning these parameters: Modularity of communities, Computational time, Normalized Mutual information, Execution Time, Accuracy. The identified communities by all the community detection algorithms for these four datasets Zachary’s Karate Club network, Amazon network, YouTube network, Football network data sets are described in this research.

Keywords:

Community Detection, Social network, Label propagation algorithm, Louvain Algorithm, Infomap Algorithm, Normalized Mutual Information