General Background: Deep image matting is a fundamental task in computer vision, enabling precise foreground extraction from complex backgrounds, with applications in augmented reality, computer graphics, and video processing. Specific Background: Despite advancements in deep learning-based methods, preserving fine details such as hair and transparency remains a challenge. Knowledge Gap: Existing approaches struggle with accuracy and efficiency, necessitating novel techniques to enhance matting precision. Aims: This study integrates deep learning with fusion techniques to improve alpha matte estimation, proposing a lightweight U-Net model incorporating color-space fusion and preprocessing. Results: Experiments using the AdobeComposition-1k

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

The method of predicting the electricity load of a home using deep learning techniques is called intelligent home load prediction based on deep convolutional neural networks. This method uses convolutional neural networks to analyze data from various sources such as weather, time of day, and other factors to accurately predict the electricity load of a home. The purpose of this method is to help optimize energy usage and reduce energy costs. The article proposes a deep learning-based approach for nonpermanent residential electrical ener-gy load forecasting that employs temporal convolutional networks (TCN) to model historic load collection with timeseries traits and to study notably dynamic patterns of variants amongst attribute par

The rapid development of Internet of Things (IoT) devices and their increasing numbers have caused a tremendous increase in network traffic and a wider range of cyber-attacks. This growing trend has complicated the detection process for traditional intrusion detection systems and heightened the challenges faced by these devices, such as imbalanced and large training data. This study presents a cohesive methodology of a series of intelligent techniques to prepare clean and balanced data for training the first (core) layer of a robust hierarchical intrusion detection system. The methodology was built by cleaning and compressing the data using an Autoencoder and preparing a strong latent space for balancing using a hybrid method that combines

This paper represents an experimental study on the application of smart control represented by the use of the fuzzy logic controller. Two-link flexible manipulators that are used in airspace and military applications are made of flexible materials characterized by low frequency and damping ratio. To solve this problem, this paper proposes the use of smart materials (piezoelectric transducers), where each link is bonded with a pair of piezoelectric transducers that act as a sensor and another as an actuator. As the arm vibrates because of the movement generated by the motor, this voltage is controlled by a regulator inside the LABVIEW® 2020 software and sends the output control voltage to the piezoelectric actuator. Experimental results

Cutaneous leishmaniasis is one of endemic diseases in Iraq. It is considered as widely health problem and is an uncontrolled disease. The aim of the study is to identify of Leishmania species that cause skin lesions among patients in Thi-Qar Province, South of Iraq, also to detect some virulence factors of L. tropica. This study includes three local locations, Al-Hussein Teaching, Suq Al-Shyokh General and Al-Shatrah General Hospitals in Province for the period from the beginning of December 2018 to the end of September 2019. The samples were collected from 80 patients suffering from cutaneous leishmaniasis, both genders, different ages, various residence places and single and multiple lesions. Nested-PCR technique was

            The development of a new, cheap, efficient, and ecofriendly adsorbents has become an important demand for the treatment of waste water, so nano silica is considered a good choice. A sample of nanosilica (NS) was prepared from sodium silicate as precursor and the nonionic surfactant Tween 20 as a template. The prepared sample was characterized using various characterization techniques such as FT-IR, AFM, SEM and EDX analysis. The spectrum of FTIR confirms the presence of silica in the sample, while SEM analysis of sample shows nanostructures with pore ranging (2-100nm).The adsorptive properties of this sample were studied by removing Congo red dye (CR) from aqueous solution. Batch experimental methods were carried o

Enhanced oil recovery is used in many mature oil reservoirs to increase the oil recovery factor. Surfactant flooding has recently gained interest again. To create micro emulsions at the interface between crude oil and water, surfactant flooding is the injection of surfactants (and co-surfactants) into the reservoir, thus achieving very low interfacial tension, which consequently assists mobilize the trapped oil.

In this study a flooding system, which has been  manufactured and described at high pressure. The flooding processes included oil, water and surfactants. 15 core holders has been prepared at first stage of the experiment and  filled with washed sand grains 80-500 mm and then packing the sand to obtain sand packs

The proposal of nonlinear models is one of the most important methods in time series analysis, which has a wide potential for predicting various phenomena, including physical, engineering and economic, by studying the characteristics of random disturbances in order to arrive at accurate predictions.

In this, the autoregressive model with exogenous variable was built using a threshold as the first method, using two proposed approaches that were used to determine the best cutting point of [the predictability forward (forecasting) and the predictability in the time series (prediction), through the threshold point indicator]. B-J seasonal models are used as a second method based on the principle of the two proposed approaches in dete