This paper emphasizes the importance of interdisciplinary collaboration in exploring the concept of robot gender within Human-Robot Interaction (HRI). It draws on a case study of the authors' own collaboration, wh...
详细信息
The degradation of image quality caused by things like light absorption, scattering, and distortion makes object detection in underwater environments a unique challenge. Applications like marine research, environmenta...
详细信息
Knee osteoarthritis (KOA) is a prevalent joint disorder diagnosed using imaging modalities like MRI, CT scans, and X-rays, with X-rays being the most cost-effective. Early detection is crucial for effective management...
详细信息
The uncontrolled growth of skin cells in the epidermis producing the creation of a mass termed a tumor is a dangerous condition known as skin cancer. Current developments in deep learning artificial intelligence have ...
详细信息
The uncontrolled growth of skin cells in the epidermis producing the creation of a mass termed a tumor is a dangerous condition known as skin cancer. Current developments in deep learning artificial intelligence have greatly improved image-based diagnosis. In this study, we included a Skin Lesion Cancer feature extractor Convolutional Neural Network (SLC-CNN) model, which is used for both classification with the SVM classifier and segmentation with XGBoost for skin cancer. In our proposed system, a test image of skin cancer is taken and pre-processed for both classification and segmentation purposes. After applying pre-processing, the test image features are extracted using the SLC-CNN feature extractor, which features are used in SVM to classify the types of skin cancer (Benign and Malignant), and based on the classification result, a trained XGBoost model is called to segment the cancer region. We have tested our system using the dermoscopy image collection from the International Skin Imaging Collaboration (ISIC) and built it in Google Colab to best use the GPU. Our suggested approach has gained a segmentation accuracy of 95.25% and a classification accuracy of 99.6%.
Knee osteoarthritis (KOA) is a prevalent joint disorder diagnosed using imaging modalities like MRI, CT scans, and X-rays, with X-rays being the most cost-effective. Early detection is crucial for effective management...
详细信息
ISBN:
(数字)9798331523893
ISBN:
(纸本)9798331523909
Knee osteoarthritis (KOA) is a prevalent joint disorder diagnosed using imaging modalities like MRI, CT scans, and X-rays, with X-rays being the most cost-effective. Early detection is crucial for effective management. This study presents an automated deep learning approach to detect and classify KOA severity based on the Kellgren-Lawrence (KL) grading system using single posteroanterior standing knee X-ray images. Utilizing the Osteoarthritis Initiative dataset, we employed transfer learning to fine-tune DenseNet-201, enhancing model performance. Additionally, knowledge distillation was applied to reduce computational complexity while maintaining accuracy. Our model achieved over 95% accuracy on both testing and cross-validation datasets, outperforming existing methods. This approach offers a reliable tool for early KOA diagnosis and grading, potentially aiding clinical decision-making
作者:
Agarwal, EkanshZhang, XiongLuo, NingDept. of Engineering
College of Engineering and Computer Science Texas A&M Univ.–Corpus Christi Corpus ChristiTX United States Dept. of Civil
Architectural and Environmental Engineering Missouri Univ. of Science and Technology RollaMO United States
This study focuses on modeling a rigid pavement slab on expansive soil in extreme climates to understand the interaction between weather, pavement, and soil. Lightweight superstructures such as pavements are particula...
详细信息
ISBN:
(数字)9780784485996
This study focuses on modeling a rigid pavement slab on expansive soil in extreme climates to understand the interaction between weather, pavement, and soil. Lightweight superstructures such as pavements are particularly prone to damage due to the differential settlement of expansive soils. In the context of climate change, the occurrence of severe droughts followed by intense rainfall has risen, causing severe impacts on crack initiation and development, and thus infiltration patterns in the structures built on expansive soils. Pavements are typically designed for a limited lifespan, and early failure may occur if climate change is not considered during design. This is especially important in coastal areas when coastal flooding becomes more frequent. The interplay between climates, soils, and pavements leads to a spatial and temporal change in soil moisture and even soil structure, causing significant variations of volume change. Despite the dominant impact of expansive soils on pavement systems, a deep understanding of their role in pavement structural behavior remains challenging to both the researchers and the practitioners. This paper addresses this gap through a comprehensive numerical study using two-dimensional (2D) finite element modeling. We adopted the unsaturated soil constitutive relationship to understand the stress changes during the expansion and shrinkage of expansive soil. We employed four user-defined subroutines in ABAQUS to perform a coupled hydro-mechanical stress analysis. The study uses historical climate events as a reference to assess the impact of climate events on pavements. Mechanical, hydraulic, and soil-vegetation-atmosphere (SVA) boundary conditions are considered. The numerical findings highlight the vulnerability of pavements founded on expansive soils to climate change-induced events and indicate that a coupled hydro-climate-geotechnical analysis is necessary. Unprecedented climatic events lead to more uneven settling of pavements
With the rising incidents of harassment and violence in India, particularly against women, this paper presents a real-time violence detection system using YOLO image detection models (YOLOv7, YOLOv8, and YOLOv9). The ...
详细信息
ISBN:
(数字)9798331515683
ISBN:
(纸本)9798331515690
With the rising incidents of harassment and violence in India, particularly against women, this paper presents a real-time violence detection system using YOLO image detection models (YOLOv7, YOLOv8, and YOLOv9). The models were trained on a carefully curated and manually annotated dataset using Roboflow, ensuring robust detection across diverse scenarios. Transfer learning and hyperparameter tuning were applied to improve accuracy. The system was evaluated using key performance metrics, including mean average precision (mAP), Intersection over Union (IoU), precision, and recall, achieving 80% precision and 50–60% recall. Extensive manual testing on real-world surveillance footage and additional video sources further validated its effectiveness. Results indicate that YOLOv8 outperforms other versions in balancing speed and accuracy. This system has strong potential for deployment in law enforcement, public surveillance, and safety-critical applications.
Mobile apps for taxi-hailing and carpooling have become very popular to tackle city problems like traffic jams, pollution, and high costs. This review of research aims to spot the main trends in this field and look at...
详细信息
ISBN:
(数字)9798331521691
ISBN:
(纸本)9798331521707
Mobile apps for taxi-hailing and carpooling have become very popular to tackle city problems like traffic jams, pollution, and high costs. This review of research aims to spot the main trends in this field and look at different approaches across key areas. We dig into models that don't have a central control using blockchain tech safe options with anonymous IDs and encryption based on traits quick systems to match rides in real-time, ways to manage how well-liked services are to build trust, plans to get more people carpooling, and how ride-sharing affects various groups of users and rules. On top of these current trends, we suggest a new feature of smart contract customization to give ride-sharing platforms more flexibility and the ability to adapt. This customization could allow users and platforms to adjust contracts for specific situations, like changing prices, insurance choices, or extra services. We also support adding real-time ride-matching systems and emergency help options to make users safer and more comfortable. By looking at many studies, we spot promising areas to develop in the future and suggest ways to explore further to improve ride-sharing tech and make it more available to different groups of people.
Natural language processing (NLP) methods can be used to identify phishing websites in addition to static and dynamic features. Phishing sites frequently include certain phrases, misspellings, or misleading text patte...
详细信息
暂无评论