The number of suffocation cases among babies during their sleeping is increased due to the presence of blankets and sheets. Therefore, it is crucial to have a reliable system that can monitor babies during bedtime. In...
详细信息
ISBN:
(数字)9798331506995
ISBN:
(纸本)9798331507008
The number of suffocation cases among babies during their sleeping is increased due to the presence of blankets and sheets. Therefore, it is crucial to have a reliable system that can monitor babies during bedtime. In order to ensure the safety of children, we have developed an AI-based comprehensive smart system that provides real-time monitoring to predict suffocation incidents as soon as possible. The proposed system offers babies protection by promoting suffocation prediction within an appropriate time frame. The system is built based on the BlazeFace detection model to monitor the baby and send notifications and sound alarms if the baby's face is covered or missing for a certain amount of time. The notification is sent through the mobile application to alert the baby's parents or caregivers if there is a suffocation case that may occur. Additionally, an audible alarm is activated to grab the attention of the child's parents or caregivers and ensure quick intervention. We conducted an experiment to assess the system's effectiveness, and the prototype shows adequate accuracy and quick response. There is still space for further development, which we suggest as future work.
Stroke, a persistent medical condition with a rising yearly occurrence, can be triggered by the sudden interruption of blood flow to a section of the brain or heart. Early symptom detection can provide valuable inform...
详细信息
ISBN:
(数字)9798331522100
ISBN:
(纸本)9798331522117
Stroke, a persistent medical condition with a rising yearly occurrence, can be triggered by the sudden interruption of blood flow to a section of the brain or heart. Early symptom detection can provide valuable information for prognosticating stroke and promoting healthy lifestyles. This research proposes guidelines for developing effective machine learning-based methods to identify heart stroke disorders. The study incorporates various ML techniques alongside key factors such as hypertension, BMI, cardiac disease, mean glucose levels, tobacco use, previous stroke incidents, and patient age. A comparative analysis and review of diverse machine learning techniques employed to predict heart stroke occurrence has been presented in the paper. A performance analysis of Gradient Boosting Classifier (GBC), AdaBoost Classifier, Support Vector Classifier (SVC), Random Forest Classifier (RFC), and Logistic Regression Classifier (LR) has been performed and the results have been evaluated using the confusion matrix followed by key findings.
Object detection technologies offer attractive pos-sibilities to visually impaired people, enabling them to avoid full-on collision with obstacles and recognize objects. This paper represents a modern real-time object...
详细信息
ISBN:
(数字)9798331527495
ISBN:
(纸本)9798331527501
Object detection technologies offer attractive pos-sibilities to visually impaired people, enabling them to avoid full-on collision with obstacles and recognize objects. This paper represents a modern real-time object detection system with integrated audio feedback is presented in this study in an effort to improve accessibility and situational awareness. The YOLO (You Only Look Once) algorithm is used by the system to efficiently recognize objects in images, videos, and real-time object detection (WebCam), and the IDE we used is Jupyter Notebook. It is implemented with OpenCV. Our method combines visual and audio output using text-to-speech technology to announce the presence of detected items, while also showing bounding boxes and labels on them. The method exhibits great precision in distinguishing numerous objects in intricate settings, maintaining a 0.5 confidence threshold to guarantee dependable identifications. Important features include threaded audio announcements to eliminate interface lag, dynamic label positioning for clear visual feedback, and nonmaximum suppression to reduce overlapping detections. This multimodal method creates opportunities for applications in autonomous systems, augmented reality, and assistive technologies, in addition to improving the interpretability of detection data. Our study advances computer vision by providing an integrated system that combines real- time auditory feedback with visual detection. This technology could help visually impaired users and improve human-computer interaction in a range of applications.
Breast cancer remains a leading cause of mortality among women worldwide, where early detection significantly improves survival rates. Traditional diagnostic methods like mammography, biopsy, and ultrasonography face ...
详细信息
Many electronic components can be combined into a single chip using VLSI technology. However, as Moore predicted, this technology will soon reach a limit, making it impossible to reduce the size of VLSI circuits furth...
详细信息
The power optimization of mixed polarity Reed–Muller(MPRM)logic circuits is a classic combinatorial optimization *** optimization approaches often suffer from slow convergence and a propensity to converge to local op...
详细信息
The power optimization of mixed polarity Reed–Muller(MPRM)logic circuits is a classic combinatorial optimization *** optimization approaches often suffer from slow convergence and a propensity to converge to local optima,limiting their effectiveness in achieving optimal power ***,we propose a novel multi-strategy fusion memetic algorithm(MFMA).MFMA integrates global exploration via the chimp optimization algorithm with local exploration using the coati optimization algorithm based on the optimal position learning and adaptive weight factor(COA-OLA),complemented by population management through truncation ***,leveraging MFMA,we propose a power optimization approach for MPRM logic circuits that searches for the best polarity configuration to minimize circuit *** results based on Microelectronics Center of North Carolina(MCNC)benchmark circuits demonstrate significant improvements over existing power optimization *** achieves a maximum power saving rate of 72.30%and an average optimization rate of 43.37%;it searches for solutions faster and with higher quality,validating its effectiveness and superiority in power optimization.
This work presents an adaptive tracking guidance method for robotic fishes. The scheme enables robots to suppress external interference and eliminate motion jitter. An adaptive integral surge line-of-sight guidance ru...
详细信息
This work presents an adaptive tracking guidance method for robotic fishes. The scheme enables robots to suppress external interference and eliminate motion jitter. An adaptive integral surge line-of-sight guidance rule is designed to eliminate dynamics interference and sideslip issues. Limited-time yaw and surge speed observers are reported to fit disturbance variables in the model. The approximation values can compensate for the system's control input and improve the robots' tracking ***, this work develops a terminal sliding mode controller and third-order differential processor to determine the rotational torque and reduce the robots' run jitter. Then, Lyapunov's theory proves the uniform ultimate boundedness of the proposed method. Simulation and physical experiments confirm that the technology improves the tracking error convergence speed and stability of robotic fishes.
As Saudi Arabia moves forward with its Vision 2030 initiative to improve the quality of life and services for its people, visual pollution continues to have a negative impact on the environment. However, assessing and...
详细信息
ISBN:
(数字)9798331506995
ISBN:
(纸本)9798331507008
As Saudi Arabia moves forward with its Vision 2030 initiative to improve the quality of life and services for its people, visual pollution continues to have a negative impact on the environment. However, assessing and addressing visual pollution in cities remains a challenging task due to its subjective nature and complexity. One of the main challenges is the lack of powerful and reliable intelligent systems for detecting visual pollution. To tackle this issue, we have invested our efforts in developing a cost-effective intelligent system using advanced technologies like the Internet of Things (IoT) and computer vision. This system will help detect and monitor visual pollution, including items such as water cans, paper, and plastic cups. Our smart system uses sensors like cameras to collect data and then analyzes it to display the information on a user-friendly control panel for administrators to monitor the area under study. The system has been successfully tested under various scenarios and has shown promising accuracy rates, reaching up to 87% in detecting recyclable materials. We believe that there are numerous opportunities to further enhance the performance of future designs.
暂无评论