检索结果-内蒙古大学图书馆

Compression through extraction of learned parameters from images in de-correlated image space

学校读者我要写书评

暂无评论

Iran Journal of computer Science 2024年第2期7卷 259-277页

作者： Hasnat, Abul Halder, Santanu Bhattacharjee, Debotosh Government College of Engineering and Textile Technology West Bengal Berhampore India Government College of Engineering and Leather Technology West Bengal Kolkata India Computer Science and Engineering Jadavpur University Kolkata 700032 India Center for Basic and Applied Science Faculty of Informatics and Management University of Hradec Kralove Rokitanskeho 62 Hradec Kralove 500 03 Czech Republic

Image compression is a class of algorithms that reduces the storage space requirement for a digital image. Lossy image compression techniques achieve higher compression but the visual quality of the decompressed image is degraded many times. Decompressed images lose their visual appeal due to compression artifacts. These compression artifacts are introduced due to the quantization step of the compression phase. We developed a lossy image compression technique that works on the spatial domain and de-correlated color model. For the luminance channel compression, the modified Vector Quantization method is used. In the case of chrominance channels, a feature vector is built for each pixel using the neighborhood statistics and cluster information of the pixel. For all the pixels of the image, using these feature vectors, a training dataset is formed. For the training of an artificial neural network (ANN), a feature vector of a pixel is used as the input and its respective chrominance value is used as the target output. Two training datasets are used to train two ANNs separately—one for the Cb channel and one for the Cr channel. These two trained ANNs are stored as the compressed form for the chrominance channels. During the decompression process, first, the luminance channel is reconstructed. Later, for each chrominance channel, the respective trained ANN predicts the chrominance values for each pixel. Thus, the whole image is reconstructed. The method has been tested on the benchmark images and also color images from the UCID v.2 database. The experimental result shows that the method successfully avoids the blocking artifacts in the reconstructed images. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： JPEG JPEG2000 Lossy image compression Neighborhood Statistics PSNR SSIM Vector quantization

Perceptual Crack Detection for Rendered 3D Textured Meshes

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sarvestani, Armin Shafiee Zhou, Wei Wang, Zhou Dept. of Electrical & Computer Engineering University of Waterloo Canada School of Computer Science and Informatics Cardiff University United Kingdom

Recent years have witnessed many advancements in the applications of 3D textured meshes. As the demand continues to rise, evaluating the perceptual quality of this new type of media content becomes crucial for quality assurance and optimization purposes. Different from traditional image quality assessment, crack is an annoying artifact specific to rendered 3D meshes that severely affects their perceptual quality. In this work, we make one of the first attempts to propose a novel Perceptual Crack Detection (PCD) method for detecting and localizing crack artifacts in rendered meshes. Specifically, motivated by the characteristics of the human visual system (HVS), we adopt contrast and Laplacian measurement modules to characterize crack artifacts and differentiate them from other undesired artifacts. Extensive experiments on large-scale public datasets of 3D textured meshes demonstrate effectiveness and efficiency of the proposed PCD method in correct localization and detection of crack artifacts. Moreover, to quantify the performance of the proposed detection method and validate its effectiveness, we propose a simple yet effective weighting mechanism to incorporate the resulting crack map into classical quality assessment (QA) models, which creates significant performance improvement in predicting the perceptual image quality when tested on public datasets of static 3D textured meshes. A software release of the proposed method is publicly available at: https://***/arshafiee/crack-detection-VVM. © 2024, CC BY.

关键词： Quality assurance

Evaluation Metrics for Automated Typographic Poster Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rebelo, Sérgio M. Merelo, J.J. Bicker, João Machado, Penousal University of Coimbra CISUC/LASI – Centre for Informatics and Systems the University of Coimbra Department of Informatics Engineering Portugal Department of Computer Engineering Automatics and Robotics and CITIC University of Granada Spain

Computational Design approaches facilitate the generation of typographic design, but evaluating these designs remains a challenging task. In this paper, we propose a set of heuristic metrics for typographic design evaluation, focusing on their legibility, which assesses the text visibility, aesthetics, which evaluates the visual quality of the design, and semantic features, which estimate how effectively the design conveys the content semantics. We experiment with a constrained evolutionary approach for generating typographic posters, incorporating the proposed evaluation metrics with varied setups, and treating the legibility metrics as constraints. We also integrate emotion recognition to identify text semantics automatically and analyse the performance of the approach and the visual characteristics *** Codes 68W50 © 2024, CC BY.

关键词： Quality control

Latent Communication in Artificial Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Moschella, Luca GLADIA research lab Department of Computer Science Faculty of Information Engineering Informatics and Statistics Italy

As NNs (Neural Networks) permeate various scientific and industrial domains, understanding the universality and reusability of their representations becomes crucial. At their core, these networks create intermediate neural representations, indicated as latent spaces, of the input data and subsequently leverage them to perform specific downstream tasks. This dissertation focuses on the universality and reusability of neural representations. Do the latent representations crafted by a NN remain exclusive to a particular trained instance, or can they generalize across models, adapting to factors such as randomness during training, model architecture, or even data domain? This adaptive quality introduces the notion of Latent Communication – a phenomenon that describes when representations can be unified or reused across neural spaces. A salient observation from our research is the emergence of similarities in latent representations, even when these originate from distinct or seemingly unrelated NNs. By exploiting a partial correspondence between the two data distributions that establishes a semantic link, we found that these representations can either be projected into a universal representation (Moschella*, Maiorca*, et al., 2023), coined as Relative Representation, or be directly translated from one space to another (Maiorca* et al., 2023). Intriguingly, this holds even when the transformation relating the spaces is unknown (Cannistraci, Moschella, Fumero, et al., 2024) and when the semantic bridge between them is minimal (Cannistraci, Moschella, Maiorca, et al., 2023). Latent Communication allows for a bridge between independently trained NN, irrespective of their training regimen, architecture, or the data modality they were trained on – as long as the data semantic content stays the same (e.g., images and their captions). This holds true for both generation, classification and retrieval downstream tasks;in supervised, weakly supervised, and unsupervised settings;and

关键词： Neural networks

Analyzing the concept of technical debt in the context of agile software development: A systematic literature review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Behutiye, Woubshet Nema Rodriguez, Pilar Oivo, Markku Tosun, Ayşe University of Oulu Oulu Finland Faculty of Computer Engineering and Informatics Istanbul Technical University Turkey

Context: Technical debt (TD) is a metaphor that is used to communicate the consequences of poor software development practices to non-technical stakeholders. In recent years, it has gained significant attention in agile software development (ASD). Objective: The purpose of this study is to analyze and synthesize the state of the art of TD, and its causes, consequences, and management strategies in the context of ASD. Research Method: Using a systematic literature review (SLR), 38 primary studies, out of 346 studies, were identified and analyzed. Results: We found five research areas of interest related to the literature of TD in ASD. Among those areas, "managing TD in ASD" received the highest attention, followed by "architecture in ASD and its relationship with TD". In addition, eight categories regarding the causes and five categories regarding the consequences of incurring TD in ASD were identified. "Focus on quick delivery" and "architectural and design issues" were the most popular causes of incurring TD in ASD. "Reduced productivity", "system degradation" and "increased maintenance cost" were identified as significant consequences of incurring TD in ASD. Additionally, we found 12 strategies for managing TD in the context of ASD, out of which "refactoring" and "enhancing the visibility of TD" were the most significant. Conclusion: The results of this study provide a structured synthesis of TD and its management in the context of ASD as well as potential research areas for further investigation. © 2024, CC BY-NC-ND.

关键词： Software design

A Review of Zero Trust Security Framework (ZTF) for Sustainable and Resilient Smart Cities 23

学校读者我要写书评

暂无评论

A Review of Zero Trust Security Framework (ZTF) for Sustaina...

Proceedings of the 27th Pan-Hellenic Conference on Progress in Computing and informatics

作者： Loukas Xagoraris Dimitrios Kogias Panagiotis Karkazis University of West Attica Greece Department of Informatics and Computer Engineering University of West Attica Greece

ISBN: (纸本)9798400716263

In recent years, cities as they adopt smart technology in an ever-evolving technological environment, face new complex threats and security challenges. Threats that affect the privacy of citizens but often impact critical infrastructure of a smart city, creating sustainability risks. Hence, the cyber security incidents have multiplied, allowing these threats to disrupt the functioning of a smart digitized ecosystem. In addition to these challenges, the smart cities have been developed like a technological complex puzzle with different interconnected sensors and software. This Internet of Things (IoT) – based infrastructure of a smart city includes different smart grid systems which will be studied. This paper highlights the vulnerabilities of a digital ecosystem in a smart city environment and addresses the security and privacy issues regarding the IoT-based infrastructure and cloud computing. We also present future trends on blockchain technology and we focus on the presentation of a zero trust blockchain-security framework (ZTF) which can be developed to mitigate the urban surface area of vulnerability exploitation and security risks.

关键词： Blockchain IoT and Cloud Computing Smart City Resilience Smart City Sustainability

Classification of Arrhythmias 12-Lead ECG Signals Based on 1 Dimensional Convolutional Neural Networks

学校读者我要写书评

暂无评论

Classification of Arrhythmias 12-Lead ECG Signals Based on 1...

Smart Computing, IoT and Machine Learning (SIML), International Conference on

作者： Arief Kurniawan Bayu Aditya Triwibowo Dion Hayu Fandiantoro Department of Computer Engineering Faculty of Intelligent Electrical and Informatics Technology Institut Teknologi Sepuluh Nopember

ISBN: (数字)9798350364101

ISBN: (纸本)9798350364118

Heart disease is the highest cause of death in the world. Arrhythmia is an abnormality in the rhythm of the heartbeat. The heart beats too fast, too slow, or irregularly. Arrhythmias are not always dangerous, e.g., someone who does excessive activity has a faster heart rate. Then, a diagnosis is needed to classify arrhythmias. One method used is ECG (Electrocardiogram) signal analysis. The ECG signal consists of P, QRS Complex, and T waves. The morphology of the QRS is used for arrhythmia classification. Currently, cardiologists analyze ECG signals by observing directly. This method is depending on the level of expertise of the cardiologist. Previous research classified arrhythmias based on the QRS morphology from a single ECG lead. As 12-lead ECG devices have now become standard in ECG examinations because abnormalities can be observed from multiple angles. This study proposes the classification of arrhythmias in 12-lead ECG signals based on the morphology of QRS complex waves using a deep learning 1-dimensional Convolutional Neural Network. The output of deep learning is the classification of arrhythmias into four classes, namely: Normal, Right Bundle Branch Block, Premature Ventricular Contraction, and Atrial Premature Beat. The outcome of the proposed system is that each QRS segment is used as input for deep learning, which can improve classification performance compared to the classification carried out by each lead. The experimental results show the method can be done well, with an average Accuracy, Precision, Sensitivity, and F1-Score were 98.8%, 99.2%, 99.2%, and 99.2%, respectively.

关键词： Deep learning Accuracy Sensitivity Heart beat Arrhythmia Morphology Electrocardiography

Multiclass Imbalance Resampling Techniques for Network Intrusion Detection

学校读者我要写书评

暂无评论

Multiclass Imbalance Resampling Techniques for Network Intru...

International Conference on Smart Computing & Communications (ICSCC)

作者： Zawiyah Saharuna Tohari Ahmad Department of Informatics Institut Teknologi Sepuluh November Surabaya Indonesia Department of Informatics & Computer Engineering Politeknik Negeri Ujung Pandang Makassar Indonesia

ISBN: (数字)9798350363104

ISBN: (纸本)9798350363111

Security datasets often exhibit significant imbalances that can introduce bias during model training, diminish sensitivity to actual attacks, and lead to a substantial number of false negatives, potentially overlooking real threats. This is particularly evident in the highly skewed distribution of the UNSW-NB18 Bot-IoT dataset. To mitigate these issues, this study proposes implementing either Random Oversampling (ROS) or Synthetic Minority Oversampling (SMOTE) in conjunction with five ensemble algorithms to develop models for predicting intrusions in the Internet of Things networks. The results show that incorporating these methods with ensemble learners significantly improves model accuracy by 1 % to 4 % across the four algorithms compared to their absence. In addition, there were dramatic increases in precision, recall, and F1-score, achieving values between 95% and 100%.

关键词： Training Accuracy Sensitivity Network intrusion detection Predictive models Prediction algorithms Ensemble learning Security Internet of Things Random forests

A Communication-Aware and Energy-Efficient Genetic Programming Based Method for Dynamic Resource Allocation in Clouds 28th

学校读者我要写书评

暂无评论

A Communication-Aware and Energy-Efficient Genetic Programm...

28th European Conference on Applications of Evolutionary Computation, EvoApplications 2025, held as part of EvoStar 2025

作者： Fang, Zhengxin Ma, Hui Chen, Gang Hartmann, Sven Chen, Shiping Centre for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Department of Informatics Clausthal University of Technology Clausthal-Zellerfeld Germany CSIRO Data61 Sydney Australia

ISBN: (纸本)9783031900648

Loosely coupled microservices have emerged as a new paradigm for efficiently deploying applications in clouds. However, dynamic resource allocation in clouds introduces significant challenges to microservice application deployment. On the one hand, frequent invocations between microservices may lead to substantial communication overhead if microservices are not allocated properly. On the other hand, the increasing number of microservices in modern applications makes it very challenging to minimize the energy consumption of a cloud data center as it introduces a bi-level optimization problem with an extremely large search space. In this paper, we propose a new communication-aware and energy-efficient genetic programming based method that automatically learns heuristics for dynamic resource allocation to jointly minimize the communication overhead and the energy consumption. Comprehensive experiments using real-world datasets show that our proposed method can evolve effective heuristics that noticeably outperform existing approaches for dynamic microservice deployment in clouds. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Genetic programming