教学课程资源库 更多>>

摘要： The publication of this article unfortunately contained mistakes. The funding section was missing. Please find it below: National Natural Science Foundation of China (grant number: 62077037) and Research and Innovation Grant for Graduate Students, Shanghai University of Sport (Project Number: YJSCX-2023–034). The original article has been corrected. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： career decisions   computer science   Gifted education   science, technology, engineering, and mathematics programs   specialized schools   talent development  

摘要： This study explored factors impacting the decision for gifted females to pursue a career in computer science. The study used a phenomenological approach to delve into the experiences of ten gifted alumnae of The Gatton Academy of Mathematics and Science (Gatton), a residential STEM program, aiming to reveal nuanced insights into factors shaping their career development. Participants were selected based on their initial intentions to pursue careers other than CS before attending Gatton but changing to a CS focus afterward. Semi-structured interviews conducted via Zoom and coded using thematic analysis provided rich data on lived experiences and perspectives of participants. Findings shed light on the multifaceted factors influencing gifted women’s career intentions before attending Gatton, the transformative effects of the residential STEM program on their decisions to pursue CS careers, and the evolution of their perceptions of CS over time. © The Author(s) 2024.

关键词： Brain modeling   Accuracy   Magnetic resonance imaging   Feature extraction   Predictive models   Data models   Computer science   Classification algorithms   Transfer learning   Medical diagnostic imaging   Brain tumor   deep learning   ensemble   glioma   meningioma   MRI   pituitary  

摘要： The article reflects on the classification of brain tumors where several deep learning (DL) approaches are used. Both primary and secondary brain tumors reduce the patient's quality of life, and therefore, any sign of the tumor should be treated immediately for adequate response and survival rates. DL, especially in the diagnosis of brain tumors using MRI and CT scans, has applied its abilities to identify excellent patterns. The proposed ensemble framework begins with the image preprocessing of the brain MRI to enhance the quality of images. These images are then utilized to train seven DL models and all of these models recognize the features related to the tumor. There are four models which are General, Glioma, Meningioma, and Pituitary tumors or No Tumor model, which helps in reaching a joint profitable prediction and concentrating solely on the strength of the estimation and outcome. This is a significant improvement over all the individual models, attaining a 99. 43% accuracy. The data used in this research was gotten from Kaggle website and comprised of 7023 images belonging to four classes. Future work will focus on increasing the dataset size, investigating additional DL architectures, and enhancing real-time detection to improve the accuracy of diagnostic scans and their overall relevance to clinical practice.

关键词： Variational autoencoders (VAEs)   particle swarm optimization (PSO)   generative art   interactive digital installations   artistic expression   deep learning algorithms   algorithmic creativity  

摘要： This article investigates the integration ofVariational Autoencoders (VAEs) and Particle Swarm Optimization (PSO) in the realm of generative art and interactive digital installations. The study focuses on how these advanced algorithms can enhance artistic expression and interactivity, providing novel approaches for generating and optimizing art. Key innovations include the application of VAEs to create diverse and complex art forms, coupled with PSO to fine-tune these generative processes. The research demonstrates that VAEs significantly improve the aesthetic quality and variety of generated artworks, achieving an average aesthetic score of 8.3 out of 10. Integrating PSO further optimizes these results, enhancing the quality of outputs with a final score of 9.0. The study also reveals that this combination improves user engagement and satisfaction, with interactive installations utilizing VAE + PSO achieving a satisfaction score of 9.0, compared to 7.0 for traditional methods. The findings highlight the transformative impact of these algorithms on art generation, showing that while computational resources and time are higher, the artistic and interactive benefits are substantial. This research underscores the potential of combining deep learning and optimization techniques to push the boundaries of digital creativity and offers new perspectives for artists and designers. The article concludes that the synergy of VAEs and PSO represents a significant advancement in generative art and interactive installations, opening new avenues for future exploration and development in the field.

ISBN: (纸本)9783031500718

关键词： Structured Query Language   SQL injection   Databases   Analytical models   Accuracy   Feature extraction   Security   Data models   Deep learning   Computer science   SIDNet   SQLI   cyber security   CNN  

摘要： SQL (Structured Query Language) injection is one of the most prevalent and dangerous forms of cyber-attacks, posing significant threats to database management systems and the overall security of web applications. By exploiting vulnerabilities in web applications, attackers can execute malicious SQL statements, potentially compromising the integrity and confidentiality of critical data. To combat these threats, in this study, we introduce two novel CNN models, SIDNet-1 (SQL Injection-attack Detection Network-1) and SIDNet-2 (SQL Injection-attack Detection Network-2), specifically designed for the classification of SQL injection attacks to bolster web application security. Our comprehensive evaluation includes a comparison of the performance of these customized CNN models against traditional machine learning approaches, highlighting improvements in classification accuracy and reductions in false alarm rates. The proposed models have been experimented with two publicly available dataset SQLI (SQL-Injection) and SQLV2 (SQL-Injection version2). Specifically, SIDNet-1 achieves an impressive accuracy of 98.02% on the SQLI dataset, while SIDNet-2 closely follows with 97.54%. Furthermore, on the SQLIV2 dataset, SIDNet-1 attains 97.77%, and SIDNet-2 achieves 97.83% accuracy respectively.

摘要： In this article the legend of Figures 10 and 12 were inadvertently swapped;the figure should have appeared as shown below. Error histogram for [HC]4 composites In the sentence beginning ‘Figures 8 and 12 show that..’ in this article, the figure citation 12 should have read as 11. The line should read as "Figures 8 and 11 show that the gradient and mu is decreasing over time and the model is learning and getting closer to the minimum of the loss function." R2 value of training, validation and testing data sets for [NHC]4 composites The original article has been corrected. © The Author(s), under exclusive licence to Springer-Verlag France SAS, part of Springer Nature 2024.

关键词： Climate change   Greenhouse gases   Computer architecture   Environmental monitoring   Sustainable development   Carbon emissions   Machine learning   Computer applications   Computer science   Green design   Greenhouse gas emissions   computer science architecture   sustainable environment   review  

摘要： Computer Science Architecture (CSA), encompassing data, application, technology, and business architecture, is a vital tool for addressing climate change challenges. It aims to reduce greenhouse gas emissions from sectors such as stationary energy, transportation, industry, product use, waste, and land use. CSA principles extend to advanced technologies like artificial intelligence (AI), the Internet of Things (IoT), Machine Learning (ML), data centers, blockchain, multi-agent systems, sensors, and smart grids. This review explores CSA's role in mitigating greenhouse gas emissions for a sustainable environment. It analyzes implications, indicators, and methodologies for data, application, technology, and business architecture, highlighting their direct impact on creating an environmentally friendly technological landscape. The study also delves into emerging trends and suggestions for future research, contributing to the discourse on leveraging technology for a greener future.

关键词： Semantic segmentation   Semantics   Training   Annotations   Unsupervised learning   Convolutional neural networks   Computer science   Unsupervised semantic segmentation   self-supervised learning   semantic clustering   pseudo labeling   context-aware embedding  

摘要： Despite the great progress of semantic segmentation with supervised learning, annotating large amounts of pixel-wise labels is, however, very expensive and time-consuming. To this end, Unsupervised Semantic Segmentation(USS) has been proposed to learn semantic segmentation, without any form of annotations. This approach involves dense prediction of semantics which is however challenging due to the unreliable nature of local representations. To solve this problem, we propose a newly context-aware unsupervised semantic segmentation framework, which aims to enhance the unsupervised semantic segmentation by leveraging contextual knowledge within and across images. In particular, we introduce a training strategy based on our Pyramid Semantic Guidance (PSG), which utilizes holistic semantics on pyramid views to guide pixel clustering with a siamese network-based framework. Additionally, we introduce a Context-Aware Embedding (CAE) module to fuse global features with low-level geometrical and appearance representations. We evaluate our method on the COCO-Stuff dataset and achieved competitive results compared to both the convolutional and ViT-based USS methods. Specifically, we attain significant improvements of +4.5% and +5% mIoU for Stuff and all class segmentation respectively, compared to previous approaches that employ unsupervised convolutional backbones.