Recognition of Ziziphus lotus through Aerial Imaging and Deep Transfer Learning Approach

Abstract

There is a growing demand for the detection of endangered plant species through machine learning approaches. Ziziphus lotus is an endangered deciduous plant species in the buckthorn family (Rhamnaceae) native to Southern Europe. Traditional methods such as object-based image analysis have achieved good recognition rates. However, they are slow and require high human intervention. Transfer learning-based methods have several applications for data analysis in a variety of Internet of Things systems. In this work, we have analyzed the potential of convolutional neural networks to recognize and detect the Ziziphus lotus plant in remote sensing images. We fine-tuned Inception version 3, Xception, and Inception ResNet version 2 architectures for binary classification into plant species class and bare soil and vegetation class. The achieved results are promising and effectively demonstrate the better performance of deep learning algorithms over their counterparts.

An AI-Driven Hybrid Framework for Intrusion Detection in IoT-Enabled E-Health

“…e DL techniques have improved the area of computer engineering through various applicabilities, which are practically employed in every industry, from medical appliances to selfdriving cars. e deep neural network (DNN) models make use of the neural network architecture, which is why they are termed as deep neural networks [25][26][27]. ese models are trained on a large amount of labeled data and to extract features from it without the need for human intervention.…”

Early-Stage Alzheimer’s Disease Categorization Using PET Neuroimaging Modality and Convolutional Neural Networks in the 2D and 3D Domains

“…Machine and deep learning (ML/DL) techniques have received substantial attention for the assessment of data from different sets of inputs such as text, images or volumes for different applications such as depression recognition [8], opinion leader identification [9], multi-object fuse detection [10], AD classification [11][12][13], cancer prediction [14], joint Alzheimer's and Parkinson's diseases classification [15,16], automatic modulation classification [17,18], diabetic retinopathy classification [19], AD assessment using independent component analysis technique [20], and endangered plant species recognition [21]. These methods can optimally infer representations from raw data through the use of a stratified sampling approach with many varying levels of intricacies.…”

Improving the Survival Time of Multiagents in Social Dilemmas through Neurotransmitter-Based Deep Q-Learning Model of Emotions

“…As Shaver [ 8 ] defined, social dilemmas mean that individuals from a group, society, or culture compete to use limited public goods [ 9 ] shared among them. The case of social dilemmas occur in many computational problems such as in competitive structure during file sharing in peer-to-peer systems [ 10 ], limited food resources, and their high consumption during simulated survival scenarios [ 11 ] and common shared medium among all nodes during bandwidth allocation in telecommunication systems [ 12 ].…”

“…These works focused on facial expressions [ 20 ], motion control [ 21 ], hair [ 22 ], and dress [ 23 ] simulation of virtual agents. Later, many researchers argued that only the physical properties of agents are not sufficient to introduce believability, which can be introduced by making agents rationale that makes goal-oriented decisions [ 10 ]. Therefore, the focus was shifted towards the development of models for utility-maximizing rational agents [ 24 ].…”