The majority of the conventional approaches used in current oral cancer screening methods, such as biopsy and visual inspection, result in late-stage detection, high false-positive/negative rates, and higher healthcar...
详细信息
ISBN:
(数字)9798350353648
ISBN:
(纸本)9798350353655
The majority of the conventional approaches used in current oral cancer screening methods, such as biopsy and visual inspection, result in late-stage detection, high false-positive/negative rates, and higher healthcare expenses. These techniques need specialized staff and are labor-intensive and subjective. To improve diagnostic speed and accuracy, the research offers a unique approach that makes use of deep learning methods, particularly Transformer models and Hybrid Neural Networks (HNNs). To enhance input quality, the system incorporates sophisticated image preparation methods such as data augmentation and normalization. While HNNs integrate Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for robust feature extraction and temporal analysis, Transformers use attention techniques to extract contextual information. Its potential for early and accurate oral cancer detection is highlighted by the results, which show a significant improvement in detection accuracy (94% vs. 80-85% in existing systems), sensitivity (90% vs. 70-78%), and specificity (92% vs. 75-82%), along with a reduction in processing time to just 2 minutes.
Pneumonia remains a significant factor in global mortality rates, highlighting the need for prompt and accurate diagnostic methods to improve patient outcomes. While radiographic examination is a standard diagnostic t...
详细信息
ISBN:
(数字)9798350356816
ISBN:
(纸本)9798350356823
Pneumonia remains a significant factor in global mortality rates, highlighting the need for prompt and accurate diagnostic methods to improve patient outcomes. While radiographic examination is a standard diagnostic tool, accurate chest X-ray interpretation might be difficult because of the visual similarities between pneumonia and other respiratory issues. This research explores deep learning techniques for detecting and localizing pneumonia in chest X-ray images. This work has investigated Mask R-CNN’s performance with various backbone architectures. This approach includes comprehensive data preparation, including text removal, image resizing, and employing data augmentation techniques. The study examines different backbone architectures, loss functions, and optimization strategies to find the optimal configuration. The bounding boxes generated by the models identify potential pneumonia infections, and their performance is evaluated using various metrics at IoU thresholds between 0.5 and 0.95. The combined results of the Mask R-CNN model as base model and backbone model as ResNet-101 demonstrates superior performance, with an average IoU of 0.75, precision (88.21%), recall (86.03%), and an F1 score (87.11%). This proposed method not only performs competitively with current models but also provides precise localization through bounding boxes and segmentation masks, potentially enhancing the diagnostic process for radiologists. This research represents a significant advancement in utilizing deep learning for detecting and localizing pneumonia in CXR-images.
The development of Convolutional Neural Networks (CNNs) and the growth of the Internet of Things (IoT) have made smart eyewear a potentially revolutionary platform for visual assistance. This research introduces a new...
详细信息
ISBN:
(数字)9798331540661
ISBN:
(纸本)9798331540678
The development of Convolutional Neural Networks (CNNs) and the growth of the Internet of Things (IoT) have made smart eyewear a potentially revolutionary platform for visual assistance. This research introduces a new method for real-time object detection and navigation assistance using IoT connection and CNNs algorithms. The proposed solution improves users' ability to see and understand their environments by combining a small camera with smart glasses. The smart glasses assist the user by identifying items in their range of vision using CNN-based object recognition algorithms and giving contextual information. Using IoT connection, the system allows easy integration with navigation services, providing users with real-time assistance and direction in new areas. It presents the planned smart eyewear system, including its design, implementation, and assessment. It emphasizes the system's uses in helping people with vision impairments or navigating complicated situations more independently. The experimental findings show that the system is efficient and effective, with reliable visual and navigational help, proving it can be used in the real world.
Detecting respiratory disorders can be improved with real-time diagnostic solutions, where monitoring respiration rates and patterns can act as early indicators for various cardiorespiratory diseases. We present a cos...
详细信息
ISBN:
(数字)9798331530143
ISBN:
(纸本)9798331530150
Detecting respiratory disorders can be improved with real-time diagnostic solutions, where monitoring respiration rates and patterns can act as early indicators for various cardiorespiratory diseases. We present a cost-effective edge-computing method utilizing wearable technology for respiratory disorder detection. Our system employs a wearable device with an IMU sensor for real-time signal transmission to a custom smart-phone app which enables thorough visualization of respiratory signals, continuous monitoring of respiration rates, and rapid alarms for breathing anomalies, alongside ECG functionalities. A novel approach is introduced for respiratory pattern detection that includes a pre-trained AI model for apnea detection and classification of normal, bradypnea, and tachypnea patterns from non-apnea signals. During model building using the Apnea-ECG dataset, the proposed hyper-feature algorithm for apnea detection demonstrates excellent performance, achieving accuracies of 92.33%, 94.89%, and 97.66% for Chest, Abdominal, and Nasal respiration signals, respectively. With an average inference time of 5 ms for respiratory event detection, the classifier achieves outstanding accuracy rates of 91.24%, 92.42%, and 93.26% for these signals on the validation dataset after being implemented and tested at the edge device. Real-time data analysis from 10 subjects further underscores the system's potential for continuous respiratory and cardiac monitoring in real-world scenarios.
Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortalit...
详细信息
ISBN:
(数字)9798350351552
ISBN:
(纸本)9798350351569
Deep learning has revolutionized medical imaging, offering advanced methods for accurate diagnosis and treatment planning. The BCLC staging system is crucial for staging Hepatocellular Carcinoma (HCC), a high-mortality cancer. An automated BCLC staging system could significantly enhance diagnosis and treatment planning efficiency. However, we found that BCLC staging, which is directly related to the size and number of liver tumors, aligns well with the principles of the Multiple Instance Learning (MIL) framework. To effectively achieve this, we proposed a new preprocessing technique called Masked Cropping and Padding(MCP), which addresses the variability in liver volumes and ensures consistent input sizes. This technique preserves the structural integrity of the liver, facilitating more effective learning. Furthermore, we introduced Re ViT, a novel hybrid model that integrates the local feature extraction capabilities of Convolutional Neural Networks (CNNs) with the global context modeling of Vision Transformers (ViTs). Re ViT leverages the strengths of both architectures within the MIL framework, enabling a robust and accurate approach for BCLC staging. We will further explore the trade-off between performance and interpretability by employing TopK Pooling strategies, as our model focuses on the most informative instances within each bag.
Drip saline fluid administration in hospitals can be better monitored and managed with the help of cloud-based technology. Intravenous treatment and postoperative recovery are two instances when drip saline fluid ther...
详细信息
ISBN:
(数字)9798331504403
ISBN:
(纸本)9798331504410
Drip saline fluid administration in hospitals can be better monitored and managed with the help of cloud-based technology. Intravenous treatment and postoperative recovery are two instances when drip saline fluid therapy is essential. The proposed system uses the Internet of Things (IoT) to remotely monitor vital metrics, including fluid flow rate, infused volume, and patient vital signs while delivering saline fluids. Using Raspberry Pi, the system gathers sensor data, processes it, sends it to the cloud, integrates it with the cloud, and triggers abnormal notification alerts. Accurate and timely fluid delivery can significantly improve patient health and reduce the risk of complications when monitored manually. When the system detects any abnormal condition, such as a drop in the predicted flow rate or an unexpected and concerning shift in patient vital signs, it sends a message to the relevant medical personnel. Healthcare providers can better manage their patients’ fluid treatment with accurate and up-to-date information through cloud-based analytics. Insights and suggestions for action are gathered from the data by smart systems. Doctors can detect patterns, predict difficulties, and optimize their patients’ fluid management plans by analyzing data. The system’s remote access features allow doctors to check patients and track their fluid treatment from anywhere. Improved patient outcomes and more efficiency in healthcare settings are the ultimate objectives of this system.
Computer-aided diagnosis systems are increasingly used in the detection and segmentation of abnormalities in medical imaging. However, in many borderline cases, radiologists and physicians need to analyze the images t...
详细信息
Tasks related to vision based action recognition are different human activities from the whole movements of those actions. It also helps predict how that individual will behave in the future by drawing conclusions fro...
详细信息
ISBN:
(数字)9798350355338
ISBN:
(纸本)9798350355345
Tasks related to vision based action recognition are different human activities from the whole movements of those actions. It also helps predict how that individual will behave in the future by drawing conclusions from their present behaviour. It was a subject in past years since it tackles real-world problems including visual surveillance, driverless automobiles, entertainment, etc. A great deal of research has been done in this domain to develop an efficient human action recognizer. It is also expected that more work will be required. Thus, there are a plethora of applications for human action detection, such as video surveillance and patient monitoring. The Convolutional Neural Network (CNN) models are published in this piece. The results demonstrate strategy which outperforms the conventional two-stream CNN technique by at least 8% in terms of accuracy. Robots with wearable exoskeletons are becoming a promising technology to assist human movements in many activities. Real-time activity detection offers helpful data to improve the robot's control support for routine operations. With the help of two rotary encoders included into the exoskeleton robot and the activity signals from an inertial measurement unit (IMU), a real-time activity detection system is implemented in this study. For the purpose of recognizing activities, five deep learning models in real-time and assessed. Consequently, an edge device was used to assess a subset of refined deep learning models in real-time while using eight typical human actions, which include standing, bending, crouching, walking, sit-down, sit-up, and climbing and descending stairs. With the chosen edge device, these eight robot wearers' behaviours are identified in real-time testing with an average accuracy of 97.35%, an inference time of less than 10ms, and an overall latency of. 506 s per recognition
Research on quantum computing is still in its infancy, but it has a lot of potential uses. One topic with potential is machine learning, namely in the field of reinforcement learning. This work examines the integratio...
详细信息
ISBN:
(数字)9798350387988
ISBN:
(纸本)9798350387995
Research on quantum computing is still in its infancy, but it has a lot of potential uses. One topic with potential is machine learning, namely in the field of reinforcement learning. This work examines the integration of parametrized quantum circuits (PQC) into reinforcement learning (RL) algorithms, assessing the potential of quantum-enhanced models to solve classical RL tasks. It closely follows the example found on the TensorFlow website. This paper reviews applications of quantum reinforcement learning (QRL). We examine PQCs in a standard RL scenario, the CartPole-v1 environment from Gym, using TensorFlow Quantum and Cirq, to evaluate the relative performance of quantum versus conventional models. In comparison to conventional deep neural network (ONN) models, PQCs show slower convergence and higher processing needs, even if they are still able to learn the task and perform competitively. After they are fully trained, the quantum models show unique difficulties during the early training stages and reach a performance stability level like classical methods. This study sheds light on the present constraints as well as possible uses of quantum computing in reinforcement learning, particularly in situations with intricate, high-dimensional settings that prove difficult for classical computers to handle effectively. As we look to the future, we suggest that investigating hybrid quantum-classical algorithms, developing quantum hardware, and using quantum RL for increasingly difficult tasks are essential first steps. The study presents findings from both a classical reinforcement learning algorithm and a quantum integrated reinforcement learning algorithm. To provide a reliable comparison between quantum reinforcement algorithms and their classical equivalents, further work remains. This work lays the groundwork for future advances in the field by investigating the viability and use of quantum algorithms in reinforcement learning, even if it is not particularly unique
The detection melanoma is so difficult to identify and is the most severe of all skin diseases, skin cancer. When all other types of skin cancer are compared side by side, melanoma is considered the most deadly and re...
详细信息
The detection melanoma is so difficult to identify and is the most severe of all skin diseases, skin cancer. When all other types of skin cancer are compared side by side, melanoma is considered the most deadly and responsible for most skin cancer fatalities. It originates from the skin cells called melanocytes, which produce the pigment melanin. Most melanomas are black and brown. Computer-assisted technology may detect melanoma by classifying dermoscopic images of melanoma and non-melanoma based on the training set and the added weights to the system, which is based on the Machine learning approach. The automated diagnosis makes it difficult to make an early diagnosis of melanoma. The Deep feedforward Neural Network algorithm's architecture will be changed by utilizing the automatic diagnosis using deep learning, a subsection of machine learning, making early detection feasible. The neural network's layers are cut down to eight, which shortens the detection time and allows for early melanoma diagnosis. The architecture, which derives its name from the Visual Geometry Group, is known as octal architecture (VGG -16). The distinct characteristics of the incoming data will be extracted using the layers of the architecture and used for categorization. More than 1697 photos were employed in the experiment's training set, which led to early detection with 96% accuracy. For training the random forest model 510 images were taken. Testing is also performed with a random forest algorithm and based on accuracy the efficient method is chosen. The application is created using the Python programming language.
暂无评论