Al-Iraqia Journal for Scientific Engineering Research

This work examines the efficiency of the model known as “Coupled Voltages to Uncoupled Currents” for representing the mutual coupling phenomenon between the elements of a receiving antenna array. This model postulates the relationship between the couple-free currents induced in the elements of the array when receiving electromagnetic waves and the induced voltages developed at the terminals of these elements. These voltages will be contaminated by the coupled energy between the elements of the array due to retransmission when the elements are close to each other. The results of this work illustrate that using this model in the cost function of the MUSIC algorithm results in DOA estimation of signals received by a receiving antenna array with very high resolution and very low RMSE when compared with another mutual coupling model.

Within the period of savvy innovation, the administration of chemical capacity postures critical challenges, especially in guaranteeing security and natural compliance. This paper plan and usage of a keen chemical capacity framework utilizing Raspberry PI presents an imaginative arrangement to this squeezing issue by leveraging the capabilities of Raspberry PI4 and the Web of Things (WoT) innovation. This investigate expresses the advancement and sending of a exceedingly productive, cost-effective shrewd chemical capacity framework outlined to optimize security, energy saving and protecting the internal and external environment of the store from air pollution. By coordination sensors for identifying different chemical gasses, temperature, mugginess, and pH levels, washing column, the framework gives real-time information examination, guaranteeing a responsive and energetic approach to chemical capacity administration. The Raspberry PI4 serves as the central handling unit, coordinating information procurement, processing, and decision-making forms to preserve ideal capacity conditions and preemptively address potential risks. Through the utilization of K-Means Calculation for information investigation, the framework illustrates extraordinary capability in recognizing and cautioning to dangerous conditions, in this way essentially decreasing the hazard of chemical mischances and processed. The usage exhibits a versatile, versatile system that obliges the expansion of different sensors and gadgets, encouraging a comprehensive observing arrangement custom-made to the particular needs of chemical capacity offices. This investigate not only contributes to the field of chemical security but moreover sets a point of reference for the application of savvy advances in mechanical security administration, advertising experiences and techniques that can be adjusted over assorted segments.

Since electroencephalograms are non-invasive, inexpensive, and have high resolution, they are frequently used in diagnostic evaluations of a wide range of brain signals. However, manual EEG signal analysis can be exhausting and time-consuming. It takes a long time for physicians to become specialists in this field, and experts have low inter-rater agreement (IRA). To aid the last diagnosis and lessen the load, numerous Computer Aided Diagnostic (CAD) studies have looked into automating EEG interpretation. EEG signal classification provides an extra creative way of detecting emotions. Generic emotion recognition algorithms may face limitations and obstacles when restricting facial expression triggers and emotion masking. This study involves categorizing EEG data and evaluating the outcomes of several machine learning algorithms, such as Support Vector Machine (SVM), K-nearest Neighbor (KNN), Random Forest, Gradient Boosting, Logistic Regression, and Decision Trees. Grid search was also employed to reduce execution time for each of the machine learning models that were tested on the Spark cluster using hyperparameter tuning. This study used the Emotion Dataset, a multimodal dataset for classifying human affective states. Gradient Boosting outperformed other algorithms in terms of precision, recall, and F-Score, achieving 99.54%, 99.51%, and 99.52%, respectively, with an accuracy of 99.53%. According to the suggested model, several classification techniques are needed to differentiate between different emotional states, and gradient boosting is the most effective machine-learning technique. Current supervised classification techniques, including GBMs, are used to simulate a variety of typical machine-learning problems with high reliability. The recommended approach produced better accuracy and faster training speeds.

Sandwich panels are essential elements in many structures like space vehicles, airplanes, cars, buildings, bridges, ships, and submarines. This research focuses on analyzing the vibrations of a circular sheet composed of a sandwich panel. The circular sheet in the sandwich panel enhances its impact resistance, providing a significant advantage. A circular sandwich panel with three free states, one supporting support, and two supporting supports was designed with ANSYS software for modeling purposes. Three free boundary conditions, one supported support, and two supported supports were utilized to conduct the analysis in this research. The results obtained for all three conditions were compared. An increase of the sandwich panel thickness core generally does not impact the frequencies of its vibration modes, and this influence diminishes as the number of supports increases. Increasing the thickness of the top layers has a more significant impact on raising the vibration modes frequency of the studied sandwich panel compared to increasing the core thickness. An increase of 4 mm in the tops' thickness raises the frequency of the 10th mode to over 700 Hz. Meanwhile, a 20 mm increase in the core's thickness elevates the frequency of the 10th vibration mode from around 500 Hz to below 600 Hz. If a sandwich panel is supported, increasing the thickness of the upper layer has little or no effect on the frequency of low vibration modes up to the fourth mode. However, starting from the fifth mode, it becomes evident that increasing the thickness directly affects the frequency of vibration modes.

A false statement made with the goal of tricking someone is called a lie. Given how little there is to separate a falsehood from the truth, it can be difficult to tell the two apart. Lying requires more mental effort than telling the truth because the liar has to work hard to make the lie seem believable. When a person feels fear, anxiety, or extreme excitement, their oxygen consumption rate, blood pressure, galvanic skin resistance, and other physiological responses increase significantly. This is the basis for lie detection. In recent years, lie detection techniques have advanced beyond polygraphs to include methods such as electroencephalography, and analysis of eye blink patterns. In this work, we shall institute inspecting accurately Artificial Intelligence (AI) algorithms (Deep learning (DL) and machine learning (ML)) for built for EEG signal processing for lie detection. In this article, we reviewed literature from 2014 to 2023 to take previous and existing classification manner for EEG based-on the lie detection to focus and highlight newest in this field. In this review, we calculating more than 40 papers that utilized AI to EEG data for lie detection. The significance point of this paper is to helping the researchers and those interested in the field of deception detection to develop this field and make him more powerfully and effectively.

Permanent magnet synchronous motors (PMSM) are extensively utilized in aerospace industry, transportation, shipping industry, etc., due to their advantages of unpretentious structure, great power density, great efficiency and great torque current ratio. Model predictive control (MPC) has huge potential to be applied in PMSM drives with stable running and high efficiency. In (MPC-DTC), the cost function contains of torque and flux magnitude errors, and they are different in component and greatness. Thus, a suitable weight factor is essential to equilibrium the control execution between torque and flux. The traditional method showed the torque wave by (17.5%) and the torque wave was reduced in the improved method to (2.25%).

This paper present an innovative methodology in analyzing a universal motor which not having design data by extracted it via reverse engineering . These gained data were used to model the motor by Maxwell program and analyzing it by FEM to get motor performance results , which showed a good agreement with motor test results .The success of a paper methodology proved the possibility of analyzing any electric motor by Maxwell program even if the motor is without design data.

Positive characteristics physicians utilize electrocardiograms (ECGs) for the interpretation and diagnosis of cardiac conditions. Hence, it is imperative to automate the analyses of ECG heartbeats in order to diagnose cardiac diseases with optimal effectiveness. The rural in Iraq are deficient in essential equipment and require state-of-the- art medical technologies be low cost, easy to use and read, in addition to the students and researchers in the field of medicine and medical engineering who are interested to developing new technologies to monitor cardiac conditions. This research paper focuses on designing and implementing a technique for forecasting arrhythmia, while simultaneously monitoring the ECG signals, hence developing an arrhythmia predication model, based on Raspberry pi4, real-time ECG tracking system using the VVG-16 algorithm, NNC. The use of deep learning model and algorithms has an impressive overall accuracy of 97.1% in predicting arrhythmia and 98.4% in overall system accuracy. The machine is being developed using AD8232, Arduino UNO, Raspberry pi4, biomedical sensor pad and battery, this method can be viewed as a practical application of the Internet of Things (IOT) idea that describes the procedure for determining the number of heartbeats from the ECG signal and display the diseases type on the same screen from mobile application or computer.

Facial expression recognition (FER) technology is quite popular in the fields of computer vision, security monitoring, image classification, and many other related applications. Enhancing the computer's ability to read facial expressions is important for human-computer interaction, as it enables machines to understand and interact with human emotions. In this paper, a modified approach using neural networks (CNNs) is presented to accurately identify unique facial expressions. using the changes to a commonly used 12-layer CNN model to improve its performance in facial expression recognition (FER). The model is trained using dataset images, which allows it to better infer people's emotions from their facial features. To enhance the accuracy of the system, a preprocessing stage is incorporated. This stage involves several operations for data augmentation, including changing the color in images, such as HSV (Hue, Saturation, Value), YCbCr (Luma, Blue-difference Chroma, Red-difference Chroma), etc., to facilitate better interpretation of color information. Additionally, the preprocessing stage refines facial expression recognition by manipulating facial features and adding extra RGB details, improving the visual information provided by the images. The study specifically focuses on evaluating the effectiveness of this approach using the KDEF database. The KDEF database contains standardized images of facial expressions, making it suitable for assessing the performance of the proposed system. By combining the modified CNN model, training with images, and the preprocessing operations, the system's performance was significantly enhanced. As a result, it achieved recognition rates of up to 95%, indicating a notable improvement in accurately identifying unique facial expressions compared to previous approaches.