Showing 11 results for Type of Study: Closed - 2024 Special Issue on Applications of Deep Learning in Electrical and Electronic Engineerin
Sandra D’souza, Niranjan Reddy S, Saikonda Krishna Tarun, Sohan P, Aneesha Acharya K,
Volume 20, Issue 4 (11-2024)
Abstract
The incidence of heart-related illnesses is on the rise worldwide. Heart diseases are primarily caused by a multitude of parameters, including high blood pressure, diabetes, and excessive cholesterol, which are controlled by poor dietary and lifestyle choices. The growth in cardiovascular diseases (CVD) is mostly due to several other behaviors, such as smoking, drinking, and sleeplessness. In the research, machine learning-based prediction methods work on the audio recordings of heartbeats known as phonocardiograms (PCG) to develop an algorithm that differentiates a normal healthy heart from an abnormal heart based on the heart sounds. The data set consists of 831 normal and 260 abnormal data, and the duration of each sample is 5 seconds. Features extracted from the data are up-sampled and applied to the logistic regression and random forest classification models. The developed models record a classification accuracy of 71% for logistic regression and 94% for the random forest model. Further, artificial neural networks (ANN) and Deep learning networks have been trained to improve performance and demonstrated an accuracy of 94.5%.
Julian Herrera-Benavidez , Cesar Pachón-Suescún, Robinson Jimenez-Moreno,
Volume 20, Issue 4 (11-2024)
Abstract
This paper presents the design and results of using a deep learning algorithm for robotic manipulation in object handling tasks in a virtual industrial environment. The simulation tool used is V-REP and the environment corresponds to a production line based on a conveyor belt and a SCARA type robot manipulator. The main contribution of this work focuses on the integration of a depth camera located on the robot and the computation of the gripping coordinates by identifying and locating three different types of objects of interest with random locations on the conveyor belt, through a Faster R-CNN. The results show that the system manages to perform the indicated activities, obtaining a classification accuracy of 97.4% and a mean average precision of 0.93, which allowed a correct detection and manipulation of the objects.
Elahe Moradi,
Volume 20, Issue 4 (11-2024)
Abstract
With the intricate interplay between clinical and pathological data in coronary heart disease (CHD) diagnosis, there is a growing interest among researchers and healthcare providers in developing more accurate and reliable predictive methods. In this paper, we propose a new method entitled the robust artificial neural network classifier (RANNC) technique for the prediction of CHD. The dataset CHD in this paper has imbalanced data, and in addition, it has some outlier values. The dataset consists of information related to 4240 samples with 16 attributes. Due to the presence of outliers, a robust method has been used to scale the dataset. On the other hand, due to the imbalance of CHD data, three data balancing methods, including Random Over Sampling (ROS), Synthetic Minority Over Sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN) approaches, have been applied to the CHD data set. Also, six artificial intelligence algorithms, including LRC, DTC, RFC, KNNC, SVC, and ANN, have been evaluated on the considered dataset with criteria such as precision, accuracy, recall, F1-score, and MCC. The RANNC, leveraging ADASYN to address data imbalance and outliers, significantly improved CHD diagnostic accuracy and the reliability of healthcare predictive models. It outperformed other artificial intelligence methods, achieving precision, accuracy, recall, F1-score, and MCC scores of 95.57%, 96.90%, 99.70%, 97.59%, and 93.42%, respectively.
Aboubakeur Hadjaissa, Mohammed Benmiloud, Khaled Ameur, Halima Bouchenak, Maria Dimeh,
Volume 20, Issue 4 (11-2024)
Abstract
As solar photovoltaic power generation becomes increasingly widespread, the need for photovoltaic emulators (PVEs) for testing and comparing control strategies, such as Maximum Power Point Tracking (MPPT), is growing. PVEs allow for consistent testing by accurately simulating the behavior of PV panels, free from external influences like irradiance and temperature variations. This study focuses on developing a PVE model using deep learning techniques, specifically a Multi-Layer Perceptron (MLP) Artificial Neural Network (ANN) with backpropagation as the learning algorithm. The ANN is integrated with a DC-DC push-pull converter controlled via a Linear Quadratic Regulator (LQR) strategy. The ANN emulates the nonlinear characteristics of PV panels, generating precise reference currents. Additionally, the use of a single voltage sensor paired with a current observer enhances control signal accuracy and reduces the PVE system's hardware requirements. Comparative analysis demonstrates that the proposed LQR-based controller significantly outperforms conventional PID controllers in both steady-state error and response time.
Mr Ardalan Faezmehr, Mr Shahab Fatemi, Prof. Mohammad Reza Daliri ,
Volume 20, Issue 4 (11-2024)
Abstract
Reza Bayat Rizi, Amir R. Forouzan, Farshad Miramirkhani, Mohamad F. Sabahi,
Volume 20, Issue 4 (11-2024)
Abstract
Visible Light Communication, a key optical wireless technology, offers reliable, high-bandwidth, and secure communication, making it a promising soloution for a variety of applications. Despite its many advantages, optical wireless communication faces challenges in medical environments due to fluctuating signal strength caused by patient movement. Smart transmitter structures can improve system performance by adjusting system parameters to the fluctuating channel conditions. The purpose of this research is to examine how adaptive modulation performs in a medical body sensor network system that uses visible light communication. The analysis focuses on various medical situations and investigates machine learning algorithms. The study compares adaptive modulation based on supervised learning with that based on reinforcement learning. The findings indicate that both approaches greatly improve spectral efficiency, emphasizing the significance of implementing link adaptation in visible light communication-based medical body sensor networks. The use of the Q-learning algorithm in adaptive modulation enables real-time training and enables the system to adjust to the changing environment without any prior knowledge about the environment. A remarkable improvement is observed for photodetectors on the shoulder and wrist since they experience more DC gain.
Robinson Jimenez-Moreno, Anny Astrid Espitia Cubillos, Esperanza Rodríguez Carmona,
Volume 20, Issue 4 (11-2024)
Abstract
This document presents the design of a virtual robotic system for the supervision of physical training exercises, to be carried out in a closed environment, which only requires a computer equipment with a web camera. To do this, deep learning algorithms such as convolutional networks and short- and long-term memory networks are used to recognize voice commands and the user's video actions. A predefined dialogue template is used to guide a user's training cycle based on the execution of the exercises: push-ups, abdominal, jump or squat. The contribution of the work focuses on the integration of deep learning techniques to design and personalize virtual robotic assistants for everyday task. The results show a high level of accuracy by the virtual robot both in understanding the audio and in predicting the exercise to be performed, with a final accuracy value of 97.75% and 100%, respectively.
Srinivas Babu N, Shashikiran S, M Jayanthi, Rajani N, K M Palaniswamy, M R Kushalatha,
Volume 20, Issue 4 (11-2024)
Abstract
Tuberculosis (TB) is a dangerous disease caused by mycobacterium leads to mortality. Early detection and identification of tuberculosis is crucial for managing tuberculosis infections. Recent technological improvements use a machine learning-based SVM and Modified CNN to identify specific diseases more accurately, as demonstrated in this research. The modified CNN's improved feature extraction and classification accuracy are maintained throughout construction. To obtain good performance a TBX11K publicly accessible dataset is used it consists of 11000 images of which 4600 chest x-ray (CXR) images are considered in this research, and the suggested model is verified. This approach significantly increases the accuracy of categorizing TB symptoms. The PCA in this system locates the elements and extracts a large amount of variance technique applied to the full chest radiograph for pulmonary tuberculosis identification accuracy using SVM is 93.14% and modified CNN 96.72% respectively. When it comes to helping radiologists diagnose patients and public health professionals screen for tuberculosis in places where the disease is endemic, the proposed system SVM and modified CNN perform better than existing methods.
Haniye Merrikhi, Hossein Ebrahimnezhad,
Volume 20, Issue 4 (11-2024)
Abstract
Robots have become integral to modern society, taking over both complex and routine human tasks. Recent advancements in depth camera technology have propelled computer vision-based robotics into a prominent field of research. Many robotic tasks—such as picking up, carrying, and utilizing tools or objects—begin with an initial grasping step. Vision-based grasping requires the precise identification of grasp locations on objects, making the segmentation of objects into meaningful components a crucial stage in robotic grasping. In this paper, we present a system designed to detect the graspable parts of objects for a specific task. Recognizing that everyday household items are typically grasped at certain sections for carrying, we created a database of these objects and their corresponding graspable parts. Building on the success of the Dynamic Graph CNN (DGCNN) network in segmenting object components, we enhanced this network to detect the graspable areas of objects. The enhanced network was trained on the compiled database, and the visual results, along with the obtained Intersection over Union (IoU) metrics, demonstrate its success in detecting graspable regions. It achieved a grand mean IoU (gmIoU) of 92.57% across all classes, outperforming established networks such as PointNet++ in part segmentation for this dataset. Furthermore, statistical analysis using analysis of variance (ANOVA) and T-test validates the superiority of our method.
Amirreza Amirfathiyan, Hossein Ebrahimnezhad,
Volume 20, Issue 4 (11-2024)
Abstract
This paper presents an application of deep learning in computer graphics, utilizing learn-based networks for 3D shape matching. We propose an efficient method for shape matching between 3D models with non-isometric deformation. Our method organizes intrinsic and directional attributes in a structured manner. For this purpose, we use a hybrid feature derived from Diffusion-Net and spectral features. In fact, we combine learned-based intrinsic properties with orientation-preserving features and demonstrate the effectiveness of our method. We achieve this by first extracting features from Diffusion-Net. Then, we compute two maps based on the functional map networks to obtain intrinsic and directional features. Finally, we combine them to achieve a desired map that can resolve symmetry ambiguities on models with high deformation. Quantitative results on the TOSCA dataset indicate that the proposed method achieves lowest average geodetic error of 0.0023, outperforming state-of-the-art methods and reducing the error by 70.66%. We demonstrate that our method outperforms similar approaches by leveraging an accurate feature extractor and effective geometric regularizers, allowing for better handling of non-isometric shapes and resulting in reduced matching errors.
Dalila Yessad,
Volume 20, Issue 4 (11-2024)
Abstract
This paper introduces the CTDRCepstrum, a novel feature extraction technique designed to differentiate various human activities using Doppler radar classification. Real data were collected from a Doppler radar system, capturing nine return echoes while monitoring three distinct human activities: walking, fast walking, and running. These activities were performed by three subjects, either individually or in pairs. We focus on analyzing the Doppler signatures using time-frequency reassignment, emphasizing its advantages such as improved component separability. The proposed CTDRCepstrum explores different window functions, transforming each echo signal into three forms of Short-Time Fourier Transform reassignments (RSTFT): time RSTFT (TSTFT), time derivative RSTFT (TDSTFT), and reassigned STFT (RSTFT). A convolutional neural network (CNN) model was then trained using the feature vector, which is generated by combining the cepstral analysis results of each RSTFT form. Experimental results demonstrate the effectiveness of the proposed method, achieving a remarkable classification accuracy of 99.83% by using the Bartlett-Hanning window to extract key features from real-time Doppler radar data of moving targets.
