Wasit Journal of Engineering Sciences

There are several problems with waste collection, transportation, processing, and
disposal, particularly in major cities. The frequency of garbage collection is an important
concern for municipal control. If waste is not disposed of properly, environmental
problems such as air pollution and groundwater contamination may occur. This problem
raises the concern for the need for specialized solutions for averting potential calamities
that might occur throughout the world. Before deploying to actual situations, computer
modeling and planning of waste collection are frequently performed to minimize the
negative impact solid waste, that can have on the environment. As a result, choosing the
optimal waste collection policy has a large effect on cost savings. The paper objective is
to apply a Genetic Algorithm (GA) to reach the goals, illustrating the process of selecting
the optimal route for the vehicle with the lowest time and greatest weight among several
paths. The other goal is to create an improved time schedule for the vehicles, in order to
minimize the number of used vehicles. This time schedule could minimize vehiclerelated costs such as maintenance, gasoline, work staff salaries, and other vehicle-related
costs. MATLAB simulation tool was used to simulate and model the practical data of
10 vehicles from the AL-Rasheed Municipality waste collection center, processing has
been done for the collected data to be matched the input data format of the GA. Optimized
time for routes and weights of lifted trash shows that the majority of the results has been
improved dramatically. The final results reveal that the top five vehicles (8, 6, 7, 1, and
4) have a great percentage improvement in the number of collection points (133.3%,
100%, 100%, 66.7%, and 50%), respectively

In this study, we made a simple, low-cost algorithm for tracking eye
movements and eye blinks in real-time and non-real-time. Several methods are
being used right now. Show parts of the face, like the eyes, or the whole face.
For this reason, OpenCV enables high-level programming to implement reliable
and accurate detection algorithms like Haar Cascade. Pay attention to how
hardware, like a computer, can only use a certain amount of resources
(processing power). The system has been proven to work in tests with 15 people
of different ages and backgrounds. These tests are done to see how the user and
the device work together and ensure everything works correctly. The In the tests
done, the system worked between 80% and 100% of the time. The results
showed that Haar Cascade had a significant effect on the detection of faces in
100% of cases, while the eyes and pupil where they overlap (light and shade)
were less effective. In addition to looking at how well these activities worked,
the demo application also showed that user restrictions shouldn't stop people
from enjoying and using a certain type of technology. The programme was
written in C++, and the OpenCV library makes it work on Windows. This
system has many uses in the real world and in science. By looking at the data
from this algorithm from afar, for example, it can tell if someone has an eye
disease or is tired. It can also help people who have physical or mental problems.

The COVID-19 pandemic has been one of the most challenging crises attacking the world in the last three years. Many systems have been introduced in the field of COVID-19 detection. In this research, machine learning(ML)and deep learning (DL) modelsfor the detection of COVID-19 with a probability of the presence of COVID-19 are proposed. In the machine learning scenario, the COVID-19 dataset is split into 70% training and 30% testing, and a segmentation process is applied to the CT images in order to get the lung ROI only. The features of CT images are then extracted using Gabor-Wavelet and deep-based features. The SVM classifier is then trained and evaluated. For the deep learning model, the CT images are fed into the model without feature extraction, and three different DL models (CNN, GoogleNet, and ResNet50) are trained and evaluated. Other scenarios are proposed in which the SVM Gabor-Wavelet and deep features are fused, and the three deep learning models are also fused to get better performance. The experiments show that the best model is the deep-based fusion model by which the system achieved 96.4156%, 96.1905%, and 96.1905% for accuracy, precision, and recall, respectively.

Portable generators are now widely used in shops, offices, and homes to provide electrical power during power outages in Iraq. However, these generators produce a lot of noise from rotating mechanical parts and fuel combustion inside the engine chamber. This noise harms the neuroendocrine, cardiovascular, respiratory, and digestive systems. Therefore, the reduction of generator noise still attracts the interest of many researchers. In this work, the removal of generator noise using an acoustic enclosure made from local materials is investigated experimentally. Experimental work uses a 2kW generator and compares the sound intensity for two cases: a generator without enclosure and one with a section. The chamber comprises plywood, galvanized sheet, glass wool, cork, and a compressed sponge. The results include the measurement of sound intensity at day and night, at zero to full load, and at two different distances. The findings showed that generator noise reduction reaches 10.3 dB at night and 9.6 dB during the day. In addition, in the case of using the enclosure, the engine temperature is kept within the allowable range of air-cooled generators, which is 300 °C. Therefore, the maximum temperature at 100% load measured inside the enclosure was 77.86 °C at night and 91.75°C a day.

A stepped weir, a type of weir featuring steps on the weir chute to help disperse the kinetic energy of the descending water, is a frequently used construction. Depending on the discharge and the stepped weir's dimensions, flow over a stepped weir can be primarily divided into three different flow regimes: nappe, transition, and skimming. Five-stepped weir models have been used in experiments to determine the flow regime limits for these weirs. The models were made with various numbers of steps (3, 5,7, 10, and 14) and a downstream slope angle of 30 ̊. The configurations of steps were flat step, fully pooled step, and zig-zag pooled step. The results show that the sills on the end edges of the steps have a significant effect on determining the type of flow regime. In addition, they dissipate more energy than flat steps. Based on the experimental data for flow regimes (nappe flow, transition flow, and skimming flow),a new set of empirical equations was proposed, with a determination coefficient????2for these regimes (0.87, 0.71, 0.7), respectively.

In the present work, a three-dimensional model was performed to test a geometry and solar radiation effect on the cooling efficiency of a 250 kilovolt-ampere (kVA) oil-natural-air-natural (ONAN) electrical distribution transformer. The main contribution to the current study is to provide a design that contributes to reducing the temperature of the electrical transformer while maintaining its size equal to the size of a conventional transformer.Several fin shapes (trapezoidal, wavy, and triangle fins) and other geometric aspects of the transformer were analyzed numerically, using Ansys fluent22 R1. According to the findings, the trapezoidal fin shape was the most effective in lowering the transformer's average surface and core temperatures, followed by the wavy fins and the triangular fins compared to the traditional transformer shape (straight fins).The surface average temperature drop of the corrugated-finned transformer was 278.15 k compared to the referencetransformer, followed by the wavy-finned transformer by 276.15 k, and finally the triangular-finned transformer by 275.15 k.Moreover, the core temperature of transformer with trapezoidalfins dropped by 284.15 k than the core of reference transformer followed by the transformer with wavy fins by 280.15 k and transformer with triangularfins by 278.15 k.The study also showed that the temperature of the surface and the core of the transformer increases with increasing solar radiation, but the effect of high temperature asa result of electrical load is more influential than solar radiation.The results showed a good agreement with previous research.

Accurate water level (WL) prediction is essential for the efficient management of various water resource projects. The creation of a reliable model for WL forecasting is still a difficult task in water resource management.This study applies an artificial neural network (ANN) integratedwith the particle swarm optimisation algorithm (PSO-ANN) for simulating monthly WLof the Tigris River in Alkut City, Iraq. Data pre-treatmentmethods are utilised forimprovingraw data quality and detect the optimalpredictors. Monthly WLand climatic variablesfrom 2011 to 2020, were used to construct and validate the proposed technique. The results showed that singular spectrum analysis (SSA) is a high-performance technique for denoising time series. The PSO-ANN model produces goodresultscoefficient of determination(R2) of 0.85.

Precise streamflow forecasting is crucial when designing water resource planning and management, predicting flooding, and reducing flood threats. This study invented a novel approach for the monthly water streamflow of the Tigris River in Amarah city, Iraq, by integrating an artificial neural network (ANN) with the particle swarm optimization algorithm(PSO), depending on data pre-processing.Historical streamflow data were utilized from (2010 to 2020). The primary conclusions of this study are that data pre-processingenhances data quality and identifies the optimal predictor scenario.In addition, it was revealed that the PSO algorithm effectively forecaststhe parameters of the suggested model. Also, the outcomes indicated that the suggested approach successfully simulated the streamflow according tomultiple statistical criteria,includingR2, RMSE, and MAE.

In this study, nanocomposite from the lemon peel was synthesized after precipitation nano iron oxides (LE-Fe3O4) by co-precipitation method and used as an important adsorbent in the adsorption process to remove the MB Dye from the aqueous solution in the batch study taking into account the parameters (pH, dose, initial concentration, and contact time). The optimum condition obtained from the experiment appears to be pH 8, 15mg\50ml dose, 50 ppm initial MB concentration, and 40 min contact time. Max adsorption capacity was 80 mg/g, and the adsorption experimental data best fitted with langmuir isotherm model indicating that the adsorption was monolayer.