In medical diagnostics, detection of bone fracture is very crucial. It require time and accurate treatment of that injuries. Previous methods for bone fracture detection are X-ray in which analyzes the fracture by the...
详细信息
ISBN:
(数字)9798331519582
ISBN:
(纸本)9798331519599
In medical diagnostics, detection of bone fracture is very crucial. It require time and accurate treatment of that injuries. Previous methods for bone fracture detection are X-ray in which analyzes the fracture by the help of radiations. It is time consuming and prone to human error. To address these limitations we used an automated approach for detection of bone fracture is yolov8. It is deep learning model for real time object detection. Its well suited for medical imagining because its architecture give more accuracy and speed. Our results show YOLOv8 achieve high accuracy and speed from the traditional methods. It is also more reliable. Since it is less time consuming and give the consistent results so it can be used in healthcare. It is possible that its efficiency can be enhance, minimize errors. This study shows the potential of deep learning model like YOLOv8 in diagnostics and medical imaging particularly in bone fracture detection
Traditional survey systems struggle with data immutability, privacy protection, and reliable storage. These limitations compromise transparency, security, and data integrity. This paper proposes a decentralized and se...
详细信息
ISBN:
(数字)9798331531935
ISBN:
(纸本)9798331531942
Traditional survey systems struggle with data immutability, privacy protection, and reliable storage. These limitations compromise transparency, security, and data integrity. This paper proposes a decentralized and secure survey platform to address these challenges. Fast Identity Online 2 (FIDO2) passwordless authentication strengthens user verification, backed by public key cryptography. Fluree, a permissioned blockchain based graph database, ensures decentralized storage and minimizes data tampering. Smart codes are designed based on user requirements, while integrated statistical analyses enhance data insights. This approach of integrating these technologies prioritizes transparency, security, and integrity in the data collection process while maintaining a seamless user experience. By fostering trust among stakeholders, it enables reliable, data driven decision-making.
Unsupervised learning enables deep-neural-network (DNN) training without high-quality data. Typical DNN methods for unsupervised image quality enhancement either (i) focus only on spatially uncorrelated noise, (ii) de...
详细信息
ISBN:
(数字)9798331520526
ISBN:
(纸本)9798331520533
Unsupervised learning enables deep-neural-network (DNN) training without high-quality data. Typical DNN methods for unsupervised image quality enhancement either (i) focus only on spatially uncorrelated noise, (ii) demand a training set comprising multiple noisy acquisitions per scene, or (iii) apply only to specific data; these aspects limit their applicability to medical images in clinical applications. Moreover, most such existing methods lack robustness to out-of-distribution (OOD) images observed during deployment. We propose a novel unsupervised DNN learning formulation to enhance a variety of medical images. Our unsupervised DNN training optimizes sets of multistage adversarial perturbations to (i) auto-generate multiple degraded inputs and latent-space encodings for each training image, (ii) adapt to the textural statistics of real-world degradations across medical imaging domains, and (iii) gain robustness to OOD images. This formulation also includes uncertainty modeling and estimation. Results on three publicly available datasets (CT, PET, MRI) show the benefits of our method in image-quality enhancement on in-distribution and OOD images.
Quantum technologies are rapidly advancing as image classification tasks grow more complex due to large image volumes and extensive parameter updates required by traditional machine learning models. Quantum Machine Le...
详细信息
ISBN:
(数字)9798331523893
ISBN:
(纸本)9798331523909
Quantum technologies are rapidly advancing as image classification tasks grow more complex due to large image volumes and extensive parameter updates required by traditional machine learning models. Quantum Machine Learning (QML) offers a promising solution for medical image classification. The parallelization of quantum computing can significantly improve speed and accuracy in disease detection and diagnosis. This paper provides an overview of recent studies on medical image classification through a structured taxonomy, highlighting key contributions, limitations and gaps in current research. It emphasizes moving from simulations to real quantum computers, addressing challenges like noisy qubits and suggests future research to enhance medical image classification using quantum technology.
Traditional machine learning algorithms have paved the way for more sophisticated models mainly in the field of Gen AI. This review compares how Gen AI is used in recommendation systems to traditional AI methods and t...
详细信息
ISBN:
(数字)9798331537555
ISBN:
(纸本)9798331537562
Traditional machine learning algorithms have paved the way for more sophisticated models mainly in the field of Gen AI. This review compares how Gen AI is used in recommendation systems to traditional AI methods and the application of both in various fields. Generative AI has transformed the systems for recommendation by correcting the flaws of conventional machine learning approaches. This review compares the use of Gen AI and conventional AI in RS throughout various fields, with a focus on GANs and VAEs. These generative models indicate their capabilities and challenges involving low data, cold start, and lack of diversity in recommendations. They also show potential limitations for further research. The report outlines recent works to represent how Gen AI enhances RS performance traces key trends, and addresses relevant emerging concerns with reliability and ethics. The results highlight hybrid approaches, promising further developments of the effective and flexible RSs. To conclude, the paper advocates for further research to be performed.
Diabetes is a serious health condition that can result in serious complications if not properly detected or treated. Despite recent developments in machine learning and deep learning, which have enhanced the detection...
详细信息
ISBN:
(数字)9798350357509
ISBN:
(纸本)9798350357516
Diabetes is a serious health condition that can result in serious complications if not properly detected or treated. Despite recent developments in machine learning and deep learning, which have enhanced the detection of diabetes, there are still challenges. It is necessary to overcome challenges such as data imbalance and enhance key performance measures for the creation of reliable predictive models. In the present study, we suggest a semi-supervised learning strategy with the pseudo-labeling technique and a hybrid Bidirectional Long Short-Term Memory-Gated Recurrent Unit model that is tailor-made to overcome data imbalance and optimize overall prediction performance. Additionally, in order to achieve an additional boost in the model’s performance, Random Under-Sampling (RUS) is employed, leading to a significant improvement in the F1 score as well as AUC. Our model achieves an AUC of 0.8297, accuracy of 0.7503, and F1 score of 0.7649. Additionally, we cover how to use explainable AI using SHAP (Shapley Additive Explanations) for interpretation of feature contributions, providing greater transparency in the decision-making of the model.
This research investigates the area of Music Information Retrieval (MIR) and Music Emotion Recognition (MER) in relation to Sinhala songs, an underexplored field in music studies. The purpose of this study is to analy...
详细信息
In the context of modern medicine, where polypharmacy is prevalent, particularly among older adults, the potential for hazardous drug-drug interactions (DDIs) is a significant concern. These interactions can lead to s...
详细信息
Important bug report comments can help developers efficiently fix bugs. This paper proposes a bug report comment ranking model called BRCR based on deep learning models. This paper also proposes a pseudo-labeling appr...
详细信息
Social media websites have provided rich contextual data but its misuse for criminal activities creates lot of problems. This paper seeks to solve the problem of criminal behavioral analysis on social media platforms ...
详细信息
ISBN:
(数字)9798331523923
ISBN:
(纸本)9798331523930
Social media websites have provided rich contextual data but its misuse for criminal activities creates lot of problems. This paper seeks to solve the problem of criminal behavioral analysis on social media platforms using machine learning, deep learning and Natural Language Processing (NLP) methodologies. The goal is to assess the effectiveness of classification algorithms such as SVM, Navier Bayes, Random Forest, Convolutional Neural Network, Recurrent Neural Network, and the Natural Language Processing (NLP) methodology that include sentiment analysis, topic modelling and entity recognition for detecting irregularities. Specifically, this research study discusses about the recent progress in these methods while considering essential problems, including data accessibility, model flexibility, and the topic of ethics.
暂无评论