Pre-processing is very useful in a variety of situations since it helps to suppress information that is not related to the exact image processing or analysis task. Mathematical morphology is used for analysis, understanding and image processing. It is an influential method in the geometric morphological analysis and image understanding. It has befallen a new theory in the digital image processing domain. Edges detection and noise reduction are a crucial and very important pre-processing step. The classical edge detection methods and filtering are less accurate in detecting complex edge and filtering various types of noise. This paper proposed some useful mathematic morphological techniques to detect edge and to filter noise in metal parts image. The experimental result showed that the proposed algorithm helps to increase accuracy of metal parts inspection system.
Advancements in internet accessibility and the affordability of digital picture sensors have led to the proliferation of extensive image databases utilized across a multitude of applications. Addressing the semantic gap between low- level attributes and human visual perception has become pivotal in refining Content Based Image Retrieval (CBIR) methodologies, especially within this context. As this field is intensely researched, numerous efficient algorithms for CBIR systems have surfaced, precipitating significant progress in the artificial intelligence field. In this study, we propose employing a hard voting ensemble approach on features derived from three robust deep learning architectures: Inception, Exception, and Mobilenet. This is aimed at bridging the divide between low-level image features and human visual perception. The Euclidean method is adopted to determine the similarity metric between the query image and the features database. The outcome was a noticeable improvement in image retrieval accuracy. We applied our approach to a practical dataset named CBIR 50, which encompasses categories such as mobile phones, cars, cameras, and cats. The effectiveness of our method was thereby validated. Our approach outshone existing CBIR algorithms with superior accuracy (ACC), precision (PREC), recall (REC), and F1-score (F1-S), proving to be a noteworthy addition to the field of CBIR. Our proposed methodology could be potentially extended to various other sectors, including medical imaging and surveillance systems, where image retrieval accuracy is of paramount importance.
In this work, a healthcare monitoring system-based Internet of Medical Things (IoMT) is proposed, implemented, analyze it by artificial intelligence using fuzzy logic. Atmega microcontroller was used to achieve the function of the proposed work and provide the area for monitoring and Analytic(decision) to the caretakers or doctors through putting the results in the platform. In this paper, the heart rate pulse sensor and infrared temperature sensor are chosen, which give skin temperature and room temperature to provide their results to the caretaker. The decision that gives the patient is in a normal state, or the fuzzy logic does an abnormal state or risk state. The fuzzy logic is used for it accurate and fast in processing data and gives a result very closer to the reality in smart health services. IoMT enables the doctors and caretakers to monitor the patient easily at any time and any place by using their intelligent laptops, tablets, and phones. Finally, the proposed system can contribute to the construction of a wide healthcare monitoring system in the unit or in the department that follows on for the hospital. Therefore, Doctors can improve the accuracy of the diagnosis, as they receive all the patient data necessary.
The goal for collaborative robots has always driven advancements in robotic technology, especially in the manufacturing sector. However, this is not the case in service sectors, especially in the health sector. Thus, this lack of focus has now opened more room for the design and development of service robots that can be used in the health sector to help patients with ailments, cognitive problems, and disabilities. There is currently a global effort towards the development of new products and the use of robotic medical devices and computer-assisted systems. However, the major problem has been the lack of a thorough and systematic review of robotic research into disease and epidemiology, especially from a technology perspective. Also, medical robots are increasingly being used in healthcare to perform a variety of functions that improve patient care. This scoping review is aimed at discovering the types of robots used in healthcare and where they are deployed. Moreover, the current study is an overview of various forms of robotic technology and its uses the healthcare industry. The considered technologies are the products of a partnership between the healthcare sector and academia. They demonstrate the research and testing that are necessary for the service of robot development before they can be employed in practical applications and service scenarios. The discussion also focused on the upcoming research areas in robotic systems as well as some important technologies necessary for human-robot collaboration, such as wireless sensor networks, big data, and artificial intelligence.
With the recent developments of technology and the advances in artificial intelligence and machine learning techniques, it has become possible for the robot to understand and respond to voice as part of Human-Robot Interaction (HRI). The voice-based interface robot can recognize the speech information from humans so that it will be able to interact more naturally with its human counterpart in different environments. In this work, a review of the voice-based interface for HRI systems has been presented. The review focuses on voice-based perception in HRI systems from three facets, which are: feature extraction, dimensionality reduction, and semantic understanding. For feature extraction, numerous types of features have been reviewed in various domains, such as time, frequency, cepstral (i.e. implementing the inverse Fourier transform for the signal spectrum logarithm), and deep domains. For dimensionality reduction, subspace learning can be used to eliminate the redundancies of high-dimensional features by further processing extracted features to reflect their semantic information better. For semantic understanding, the aim is to infer from the extracted features the objects or human behaviors. Numerous types of semantic understanding have been reviewed, such as speech recognition, speaker recognition, speaker gender detection, speaker gender and age estimation, and speaker localization. Finally, some of the existing voice-based interface issues and recommendations for future works have been outlined.
Novel Coronavirus (Covid-2019), which first appeared in December 2019 in the Chinese city of Wuhan. It is spreading rapidly in most parts of the world and becoming a global epidemic. It is devastating, affecting public health, daily life, and the global economy. According to the statistics of the World Health Organization on August 11, the number of cases of coronavirus (Covid-2019) reached nearly 17 million, and the number of infections globally distributed among most European countries and most countries of the Asian continent, and the number of deaths from the Corona virus reached 700 thousand people around the world. . It is necessary to detect positive cases as soon as possible in order to prevent the spread of this epidemic and quickly treat infected patients. In this paper, the current literature on the methods used to detect Covid is presented. In these studies, the research that used different techniques of artificial intelligence to detect COVID-19 was reviewed as the convolutionary neural network (ResNet50, ResNet101, ResNet152, InceptionV3 and Inception-ResNetV2) were proposed for the identification of patients infected with coronavirus pneumonia using chest X-ray radiographs By using 5-fold cross validation, three separate binary classifications of four grades (COVID-19, normal (healthy), viral pneumonia and bacterial pneumonia) were introduced. It has been shown that the pre-trained ResNet50 model offers the highest classification performance (96.1 percent accuracy for Dataset-1, 99.5 percent accuracy for Dataset-2 and 99.7 percent accuracy for Dataset-2) based on the performance results obtained.
In recent years, artificial intelligence techniques such as wavelet neural network have been applied to control the speed of the BLDC motor drive. The BLDC motor is a multivariable and nonlinear system due to variations in stator resistance and moment of inertia. Therefore, it is not easy to obtain a good performance by applying conventional PID controller. The Recurrent Wavelet Neural Network (RWNN) is proposed, in this paper, with PID controller in parallel to produce a modified controller called RWNN-PID controller, which combines the capability of the artificial neural networks for learning from the BLDC motor drive and the capability of wavelet decomposition for identification and control of dynamic system and also having the ability of self-learning and self-adapting. The proposed controller is applied for controlling the speed of BLDC motor which provides a better performance than using conventional controllers with a wide range of speed. The parameters of the proposed controller are optimized using Particle Swarm Optimization (PSO) algorithm. The BLDC motor drive with RWNN-PID controller through simulation results proves a better in the performance and stability compared with using conventional PID and classical WNN-PID controllers.
Nowadays, the trend has become to utilize Artificial Intelligence techniques to replace the human's mind in problem solving. Vehicle License Plate Recognition (VLPR) is one of these problems in which the computer outperforms the human being in terms of processing speed and accuracy of results. The emergence of deep learning techniques enhances and simplifies this task. This work emphasis on detecting the Iraqi License Plates based on SSD Deep Learning Algorithm. Then Segmenting the plate using horizontal and vertical shredding. Finally, the K-Nearest Neighbors (KNN) algorithm utilized to specify the type of car. The proposed system evaluated by using a group of 500 different Iraqi Vehicles. The successful results show that 98% regarding the plate detection, and 96% for segmenting operation.
Since recent societies become more hooked into electricity, a higher level of power supply continuity is required from power systems. The expansion of those systems makes them liable to electrical faults and several failures are raised due to totally different causes, like the lightning strike, power system element failure caused by mechanical aging as well as human mistakes. These conditions impact the stability of the power as well as lead to costly maintenance and loss of output. This article examines the latest technologies and strategies to determine the location of faults in medium voltage distribution systems. The aim is to classify and assess different strategies in order to determine the best recommended models in practice or for further improvement. Several ways to locate failures in distribution networks have therefore been established. Because faults are unpredictable, quick fault location as well as isolating are necessary to reduce the impact of faults in distribution networks as well as removing the emergency condition from the entire system. This study also includes a comprehensive evaluation of several defect location methods depending on the algorithm employed, the input, the test system, the characteristics retrieved, and the degree of complexity. In order to gain further insight into the strengths and limitations of each method and also comparative analysis is carried out. Then the main problems of the fault location methods in distribution network are briefly expounded.
The main objective of designed the controller for a vehicle suspension system is to reduce the discomfort sensed by passengers which arises from road roughness and to increase the ride handling associated with the pitching and rolling movements. This necessitates a very fast and accurate controller to meet as much control objectives, as possible. Therefore, this paper deals with an artificial intelligence Neuro-Fuzzy (NF) technique to design a robust controller to meet the control objectives. The advantage of this controller is that it can handle the nonlinearities faster than other conventional controllers. The approach of the proposed controller is to minimize the vibrations on each corner of vehicle by supplying control forces to suspension system when travelling on rough road. The other purpose for using the NF controller for vehicle model is to reduce the body inclinations that are made during intensive manoeuvres including braking and cornering. A full vehicle nonlinear active suspension system is introduced and tested. The robustness of the proposed controller is being assessed by comparing with an optimal Fractional Order PI λ D μ (FOPID) controller. The results show that the intelligent NF controller has improved the dynamic response measured by decreasing the cost function.
This paper applied an artificial intelligence technique to control Variable Speed in a wind generator system. One of these techniques is an offline Artificial Neural Network (ANN-based system identification methodology, and applied conventional proportional-integral-derivative (PID) controller). ANN-based model predictive (MPC) and remarks linearization (NARMA-L2) controllers are designed, and employed to manipulate Variable Speed in the wind technological knowledge system. All parameters of controllers are set up by the necessities of the controller's design. The effects show a neural local (NARMA-L2) can attribute even higher than PID. The settling time, upward jab time, and most overshoot of the response of NARMA-L2 is a notable deal an awful lot less than the corresponding factors for the accepted PID controller. The conclusion from this paper can be to utilize synthetic neural networks of industrial elements and sturdy manageable to be viewed as a dependable desire to normal modeling, simulation, and manipulation methodologies. The model developed in this paper can be used offline to structure and manufacturing points of conditions monitoring, faults detection, and troubles shooting for wind generation systems.
The smart classroom is a fully automated classroom where repetitive tasks, including attendance registration, are automatically performed. Due to recent advances in artificial intelligence, traditional attendance registration methods have become challenging. These methods require significant time and effort to complete the process. Therefore, researchers have sought alternative ways to accomplish attendance registration. These methods include identification cards, radio frequency, or biometric systems. However, all of these methods have faced challenges in safety, accuracy, effort, time, and cost. The development of digital image processing techniques, specifically face recognition technology, has enabled automated attendance registration. Face recognition technology is considered the most suitable for this process due to its ability to recognize multiple faces simultaneously. This study developed an integrated attendance registration system based on the YOLOv7 algorithm, which extracts features and recognizes students’ faces using a specially collected database of 31 students from Mustansiriyah University. A comparative study was conducted by applying the YOLOv7 algorithm, a machine learning algorithm, and a combined machine learning and deep learning algorithm. The proposed method achieved an accuracy of up to 100%. A comparison with previous studies demonstrated that the proposed method is promising and reliable for automating attendance registration.
The monitoring of COVID-19 patients has been greatly aided by the Internet of Things (IoT). Vital signs, symptoms, and mobility data can be gathered and analyzed by IoT devices, including wearables, sensors, and cameras. This information can be utilized to spot early infection symptoms, monitor the illness’s development, and stop the virus from spreading. It’s critical to take vital signs of hospitalized patients in order to assess their health. Although early warning scores are often calculated three times a day, they might not indicate decompensation symptoms right away. Death rates are higher when deterioration is not properly diagnosed. By employing wearable technology, these ongoing assessments may be able to spot clinical deterioration early and facilitate prompt therapies. This research describes the use of Internet of Things (IoT) to follow fatal events in high-risk COVID-19 patients. These patients’ vital signs, which include blood pressure, heart rate, respiration rate, blood oxygen level, and fever, are taken and fed to a central server on a regular basis so that information may be processed, stored, and published instantly. After processing, the data is utilized to monitor the patients’ condition and send Short Message Service (SMS) alerts when the patients’ vital signs rise above predetermined thresholds. The system’s design, which is based on two ESP32 controllers, sensors for the vital signs listed above, and a gateway, provides real-time reports, high-risk alerts, and patient status information. Clinicians, the patient’s family, or any other authorized person can keep an eye on and follow the patient’s status at any time and from any location. The main contribution in this work is the designed algorithm used in the gateway and the manner in which this gateway collects, analyze, process, and send the patient’s data to the IoT server from one side and the manner in which the gateway deals with the IoT server in the other side. The proposed method leads to reduce the cost and the time the system it takes to get the patient’s status report.
Low-quality data can be dangerous for the machine learning models, especially in crucial situations. Some large-scale datasets have low-quality data and false labels, also, datasets with images type probably have artifacts and biases from measurement errors. So, automatic algorithms that are able to recognize low-quality data are needed. In this paper, Shapley Value is used, a metric for evaluation of data, to quantify the value of training data to the performance of a classification algorithm in a large ImageNet dataset. We specify the success of data Shapley in recognizing low-quality against precious data for classification. We figure out that model performance is increased when low Shapley values are removed, whilst classification model performance is declined when high Shapley values are removed. Moreover, there were more true labels in high-Shapley value data and more mislabeled samples in low-Shapley value. Results represent that mislabeled or poor-quality images are in low Shapley value and valuable data for classification are in high Shapley value.