Periodicals of Engineering and Natural Sciences (PEN - International University of Sarajevo)
Not a member yet
1290 research outputs found
Sort by
Analyzing satellite images by apply deep learning instance segmentation of agricultural fields
Get PDFThis novel research focuses on multi-exposure satellite images of agricultural fields using image analysis and deep learning techniques. The development of image edge smoothening system using CNN is in hot pursuit, with special attention being given to the smoothening of all the edges of image. Given its high propensity to meta-size, going hand in hand with severe decreases in preservation rates, and the high inter-edge variability in image appearance, as well as a strong requirement on the training of the physician properly de-noising an image can be considered a daunting task. The purpose of this advance research is to use a deep learning and image analysis pipeline for multi-exposure satellite image for the segmentation of edges in an image using with hybrid techniques in deep learning and imaging. The literature review of different papers was conducted with different imaging model architectures. The CNN custom model was created for the task, and deep learning technique (CNN) was used with different levels of fine tuning of hybrid satellite image analysis techniques. Screening for high edge filter to identify edges at high accuracy has been under debate. The custom deep learning model architectures were designed to represent different depths. Additionally, deep learning CNN model was created to represent traditional automated image analysis approach. The study also attempts to find solutions to practical deep learning challenges such as low training speed and lack of transparency with an accuracy of 98.17% absolutely. 
A comparison among different kinds of motors with evaluation of power requirements
Get PDFTractors have a large and effective role in agricultural works, and because Iraq is one of the large agricultural countries, so it was necessary to study the types of tractors that are used in performing these works and compare between them to show which one is better and preferable. The subject of the current research paper is based on a comparison, the comparison includes theoretical comparison among these tractors via the laws related to them and practical comparison that included studies conducted on two different types of capacity of tractors (4. D.W.) and (2. D.W.) at different times and conditions. It was determined through practical experience in the fields which tractors are best to work in terms of strength, traction capacity, rolling resistance and percentage of tire slip
Partial shading conditions for photovoltaic system using artificial neural networks technique
Get PDFPartial shading condition in solar photovoltaic (PV) systems is an inevitable problem due to the behavior of high nonlinear and unpredictable characteristics due to different shading states. However, several scientific works and research aimed to find approximate and expressive models of this nonlinear behavior using modern methods and techniques to allow researchers to find effective solutions to these critical situations. This paper aims to obtain the appropriate model for partial shading cases using artificial intelligence techniques through machine learning of neural network technology, based on experimental data of PV characteristics for different cases. This model allows for diagnosing the state of faults of Partial shading (PV) systems. Moreover, it allows the development of appropriate algorithms in order to maintain, perform, and prevent the complete shutdown of the systems. All results of the model photovoltaic partial shading characteristics for different situations based on the machine learning process confirm the effectiveness of the adopted technique after comparing it with the real data with a very acceptable margin of error
Analysis and testing of the most important factors affecting (COVID-19)
Get PDFFactor analysis is distinguished by its ability to shorten and arrange many variables in a small number of linear components. In this research, we will study the essential variables that affect the Coronavirus disease 2019 (COVID-19), which is supposed to contribute to the diagnosis of each patient group based on linear measurements of the disease and determine the method of treatment with application data for (600) patients registered in General AL-KARAMA Hospital in Baghdad from 1/4/2020 to 15/7/2020. The explanation of the variances from the total variance of each factor separately was obtained with six elements, which together explained 69.266% of the measure\u27s variability. The most important variable is cough, idleness, fever, headache, palpebral, and difficulty in breathing. In the first factor and the variable appetite, not smelling, not to taste and diarrhea in the second factor: variables (sex, work, smoking, drinking alcohol) in the third factor, variables (diabetes, age, pressure) in the fourth factor, variables (vomiting, heartburn) in the fifth factor, variables (Blood group, drinking alcohol) in the sixth factor. Therefore, we must wash hands and covering mouths, or wearing a face mask when sneezing or coughing. Social distancing, disinfecting surfaces, ventilation, air-filtering, monitoring, and self-isolation are exposed or symptomatic
Parallel robot for knee rehabilitation: Reduced order dynamic linear model, mechanical assembly and control system architecture
Get PDFIn this work we present the development of a dynamic linear model of a 3UPS+1RPU parallel robot for knee rehabilitation, which allows the reduction of the error with respect to simulation carried out based on its non-linear model. Furthermore, the design and implementation of a control algorithm in a real robot is detailed, for which a dynamic linear model has been developed based on inertial parameters including a friction model in Coulomb and viscosity parameters. Subsequently, the linear model has reduced applying the numerical method of decomposition into singular values, resulting in a model expressed as function of base parameters. This method uses a base parameter identification path obtained by finite Fourier series. This path is optimized through minimization algorithms restricted by distance, velocity and acceleration of the linear actuators of the robot, as well as the working space of its spherical joints. Then, the compatibility level of the reduced dynamic model is quantified by estimating mean square error determined between the generalized forces of the independent joints obtained from the model and compared with those resulting from simulations performed in Adams/View software for a trajectory obtained by finite Fourier series. Afterwards, mechanical components involved in the implementation of the prototype are selected and the control system of its actuators is designed. Finally, tests are performed in a laboratory through photogrammetry equipment, in order to validate joints mobility in the robot and study its performance, for this task defined trajectories based on criteria of a physiotherapist are used
An improved correlation to investigate the effect of chemical additives on the mobility ratio of two-phase flow
Get PDFWorld energy demand continues to increase, as they evolve, and developing countries consume more energy to keep their rising factories going. A significant portion of the energy demand is supplied by fossil fuels, especially crude oil. Therefore, in order to satisfy the world\u27s energy demand, oil reserves and oil production capability must be increased. This objective can be accomplished by enhancing the recovery efficiency of the existing generating or mature reservoirs through the application of increased oil recovery. The injection of fluids into oil reservoirs has the purpose of supplementing natural energy and is used in some cases to engage with the reservoir\u27s rock/oil system, standardizing for oil recovery, such as lower interfacial stress, oil swelling, reduction of oil viscosity and adjustment of wettability.
Subject to comprehensive studies, in heavy oil reservoirs, polymer injection is not dependent on large technological instruments, requiring only mixing and filtration equipment, except for those already used for traditional water injections. In addition, polymers are non-toxic and corrosive and can produce desirable mobility ratios. The implementation of this approach decreases the output ratio of water to oil, thus decreasing operating.
In the present work, thirty-five data points from experimental work had been investigated to develop a new correlation for viscosity of water by using the suitable program. It was analyzed the influence of the polymer additives on the mobility ratio, temperature and concentration effect on mobility ratio, and viscosity altering with the additives have been investigated. The results of the correlation showed acceptable agreement between the observed and predicted viscosity values. As a contrast to the polymer additives approach, pure water was proposed
Using the smartphone in carpooling for new mobility services
Get PDFThe principle of dynamic carpooling is in local real-time to send the "user-carpooler." If we choose to travel with standard vehicles, we can contact the service a few minutes before departure. The service then searches for the best driver to give the desired car-sharing service on the chosen route. In recent years, there has been growing creation of modern information and communication technology, particularly with the growth of the Internet and mobile telephones. New knowledge and networking systems are therefore closely linked with the changing area of mobility. Policies and processes introduced for sustainable mobility in this field. New forms of transportation aim to find a space for them and promote emerging mobility technologies such as shared cars. It has been shown that these programs utilize modern knowledge and communication technology, particularly recently, to evolve via telephone. The aim of this project is, in this sense, to decide how often smartphone car sharing access can be utilized. This tool seems important in specific typical vehicle use encounters and seems a significant factor in growing its scope by simplifying access and use. The method is versatile and provides a high standard of operation with a reasonable number of participants: the probability of having a shared vehicle is reasonable. This scheme complements mass transit – on-demand and daily – and complementary options such as bicycle terminals
Safety management in private construction project in Iraq
Get PDFThe construction industry considers one of the most dynamic industries due to the unique features such as the change in the project site and condition. These features make the application of specifications and codes more difficult. Occupational Safety requirements in project is also difficult to be implemented and monitored due to the unique features of this industry. The aim of the study is to propose a new method that will determine the performance and management of the occupational safety in the construction site, in order to increase the safety at work in the private construction sector in Iraq. Another purpose of this evaluation is to establish a fundamental point that can be graded according to the safety index for the Iraqi construction industry. The information has been collected through a checklist and a questionnaire; the study focused on data collection paradigm and framework based on a fuzzy logic approach, which is especially able to evaluate the efficiency and monitoring of management defects of private contractors in the fields of occupational safety management. The results show a high security management performance in the private construction sector in Iraq, and the survey results show that there is a great deficiency in training on job security, also study found out that the top three elements of occupational safety management in Iraq are: First Aid-medical needs, Safety committees, Hazard prevention and control
Fabrication of ZnO/nanobentonite as a new efficient adsorbent for rapid elimination of xylenol orange dye
Get PDFA novel ZnO-nanobentonite (ZnO/NB) nanocomposite was successfully prepared using hexadecyltrimethylammonium bromide (HDTMA) as a surfactant and used as an efficient adsorbent to remove the xylenol orange (XO) from aqueous solutions. The fabricated nanocomposite was fully characterized by FTIR, FESEM, XRD, EDX, and BET measurements. The ZnO33%/NB sample with a high SBET and low total pore volume compared with the nanobentonite clay, based on BET results, indicated an increase in SBET due to the incorporation of ZnO nanoparticles into the layer of nanobentonite. For achieving the optimum condition, the effect of ZnO33%/NB sorbent dosage, initial pH, reaction time, and primary dye concentration, on XO dye elimination was investigated. The result show that the 97% elimination of XO dye occurred at optimum condition (40 mgl/l of dye concentration, pH 2, 15 mg of ZnO33%/NB adsorbent at 30 minutes), and the adsorption capacity and residual XO after treatment at these conditions is 48.5 and 1.2 ppm, respectively. Langmuir models and Freundlich model were used to studying the adsorption isotherms of the elimination process and results authenticated that XO dye adsorption followed the Langmuir model. Also, the recycling experiments showed that ZnO33%/NB adsorbent had more stability and recoverability. High adsorption capacity, simple fabrication method, short reaction time, and supreme reusability of ZnO33%/NB nanocomposite make it an effective sorbent for the elimination of XO dye from wastewaters
Estimating parking generation rate for Karbala holy city using multi-variables approach
Get PDFCar parking planning, design, and management processes are very important to all cities and places to ensure efficient traffic system. Estimating the demand of car parking represents the significant start point for the success of these processes. Generally, there are many local and international estimating criteria, but such criteria need continuing update due to many reasons related to socioeconomic factors, lifestyle changes, development in technology, etc. Moreover, the majority of these criteria depend on single parameter for the estimation of parking demand; such as bed or employee for hospital, gross floor area or employee for office, and so on. The main aim of this research is to estimate the park generation rate for specific land uses depend on multivariable to increase the accuracy and limiting the effect of variation in parameters. Statistical analysis was conducted to create predicting models for each land use. The collected data was nominated for Karbala holy city, where different parameters are scaled for different city sectors. Groups of statistical models (i.e., simple, multi linear and nonlinear statistical models, and Weighted Linear Regression (WLR)) were used to create best representative relationship between the number of demands for car parking and multivariable parameters or factors affecting these lands used demands. Resulted statistical models were tested for best fit using statistical indices for model verification. Results disclose the significant of multivariable model compare with simple models. Also, WLR model shows it validity compare with multi-regression model for almost land use models. Consequently, for more accurate estimation the multi variable models are initiated with continuous need for updating