Natural gas and oil are one of the mainstays of the global economy. However, many issues surround the pipelines that transport these resources, including aging infrastructure, environmental impacts, and vulnerability to sabotage operations. Such issues can result in leakages in these pipelines, requiring significant effort to detect and pinpoint their locations. The objective of this project is to develop and implement a method for detecting oil spills caused by leaking oil pipelines using aerial images captured by a drone equipped with a Raspberry Pi 4. Using the message queuing telemetry transport Internet of Things (MQTT IoT) protocol, the acquired images and the global positioning system (GPS) coordinates of the images' acquisition are sent to the base station. Using deep learning approaches such as holistically-nested edge detection (HED) and extreme inception (Xception) networks, images are analyzed at the base station to identify contours using dense extreme inception networks for edge detection (DexiNed). This algorithm is capable of finding many contours in images. Moreover, the CIELAB color space (LAB) is employed to locate black-colored contours, which may indicate oil spills. The suggested method involves eliminating smaller contours to calculate the area of larger contours. If the contour's area exceeds a certain threshold, it is classified as a spill; otherwise, it is stored in a database for further review. In the experiments, spill sizes of 1m2, 2m2, and 3m2 were established at three separate test locations. The drone was operated at three different heights (5 m, 10 m, and 15 m) to capture the scenes. The results show that efficient detection can be achieved at a height of 10 meters using the DexiNed algorithm. Statistical comparison with other edge detection methods using basic metrics, such as perimage best threshold (OIS = 0.867), fixed contour threshold (ODS = 0.859), and average precision (AP = 0.905), validates the effectiveness of the DexiNed algorithm in generating thin edge maps and identifying oil slicks. © 2023 Lavoisier. All rights reserved.
In this paper, a method is proposed to increase the compression ratio for the color images by
dividing the image into non-overlapping blocks and applying different compression ratio for these
blocks depending on the importance information of the block. In the region that contain important
information the compression ratio is reduced to prevent loss of the information, while in the
smoothness region which has not important information, high compression ratio is used .The
proposed method shows better results when compared with classical methods(wavelet and DCT).
Tremendous efforts have been exerted to understand first language acquisition to facilitate second language learning. The problem lies in the difficulty of mastering English language and adapting a theory that helps in overcoming the difficulties facing students. This study aims to apply Thomasello's theory of language mastery through usage. It assumes that adults can learn faster than children and can learn the language separately, and far from academic education. Tomasello (2003) studied the stages of language acquisition for children, and developed his theory accordingly. Some studies, such as: (Ghalebi and Sadighi, 2015, Arvidsson, 2019; Munoz, 2019; Verspoor and Hong, 2013) used this theory when examining language acquisition. Thus,
... Show MoreThe recent advancements in security approaches have significantly increased the ability to identify and mitigate any type of threat or attack in any network infrastructure, such as a software-defined network (SDN), and protect the internet security architecture against a variety of threats or attacks. Machine learning (ML) and deep learning (DL) are among the most popular techniques for preventing distributed denial-of-service (DDoS) attacks on any kind of network. The objective of this systematic review is to identify, evaluate, and discuss new efforts on ML/DL-based DDoS attack detection strategies in SDN networks. To reach our objective, we conducted a systematic review in which we looked for publications that used ML/DL approach
... Show MoreBackground/Objectives: The purpose of this study was to classify Alzheimer’s disease (AD) patients from Normal Control (NC) patients using Magnetic Resonance Imaging (MRI). Methods/Statistical analysis: The performance evolution is carried out for 346 MR images from Alzheimer's Neuroimaging Initiative (ADNI) dataset. The classifier Deep Belief Network (DBN) is used for the function of classification. The network is trained using a sample training set, and the weights produced are then used to check the system's recognition capability. Findings: As a result, this paper presented a novel method of automated classification system for AD determination. The suggested method offers good performance of the experiments carried out show that the
... Show MoreTo maintain a sustained competitive position in the contemporary environment of knowledge economy, organizations as an open social systems must have an ability to learn and know how to adapt to rapid changes in a proper fashion so that organizational objectives will be achieved efficiently and effectively. A multilevel approach is adopted proposing that organizational learning suffers from the lack of interest about the strategic competitive performance of the organization. This remains implicit almost in all models of organizational learning and there is little focus on how learning organizations achieve sustainable competitive advantage . A dynamic model that captures t
... Show MoreThis paper deals with a central issue in the field of human communication and reveals the roaming monitoring of the incitement and hatred speech and violence in media, its language and its methods. In this paper, the researcher seeks to provide a scientific framework for the nature of the discourse of incitement, hatred speech, violence, and the role that media can play in solving conflicts with their different dimensions and in building community peace and preventing the emergence of conflicts among different parties and in different environments. In this paper, the following themes are discussed:
The root of the discourse of hatred and incitement
The nature and dimensions of the discourse of incitement and hatred speech
The n
Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for
The use of deep learning.