教学课程资源库 更多>>

关键词： Blockchains   Industrial Internet of Things   Computer architecture   Security   Knowledge discovery   Computer science   Cloud computing   Prototypes   Authentication   Analytical models   Blockchain   Industrial Internet of Things (IIoT)   proxy re-encryption   whitelist-based access control   privacy   security  

摘要： The field of Industrial Internet of Things (IIoT) is now being duly recognized as a revolutionary area in industrial automation. With the budding interest of knowledge discovery that helps the businesses in applying technology on a large scale, researchers are now faced with several major security concerns. Blockchain integration is one of the suggested applications of technology that could help secure the data during transmission, storage, and knowledge discovery. Moreover, by integrating smart contracts, a secure architecture could also assimilate accountability during data exchange. Thus, we propose a four-layer security architecture that isolates IIoT devices from user-oriented layers and maintains a record of all IIoT devices registered in the organization to prevent malicious devices from corrupting the database and discovery process. Further, by choosing proof of authority (PoA), we ensure the fair functioning of the Blockchain nodes. Through proxy re-encryption for clients, PoA consensus for Blockchain nodes, and Whitelist-based access control for IIoT Devices, we ensure the legitimacy of all participating nodes. We also implement a prototype using a private Ethereum network with proof of authority consensus and present the time taken for the entire exchange and the gas (ethereum currency) consumed per exchange by the contracts. Also we implemented the secure knowledge discovery to understand the significance of the developed scheme. The results show that the exchange can be implemented in an IIoT environment and work with a reasonable amount of resource consumption.

关键词： Privacy   Protection   Sensitivity   Social networking (online)   Differential privacy   Publishing   Organizations   Data models   Computer science   Training   Social networks   differential privacy   user-perceived sensitivity   personalized privacy protection  

摘要： With the prevalence of online social networks (OSNs), much personal information is collected and maintained by trusted service providers for third-party queries and analyses. Existing works regarding differentially private social network data publication overlook the fact that different users exhibit distinct privacy preferences or sensitivity inclinations. Neglecting these individual nuances may lead to privacy mechanisms that are overly conservative or inadequately protective. Furthermore, the injection of excessive noise into OSN data perceived by users as non-personal or less sensitive can incur additional privacy costs, resulting in lower service quality. This paper introduces a fine-grained, sensitivity-aware personalized edge differential privacy model (SPEDP) for OSNs. Specifically, SPEDP enables each OSN user to individually define the sensitivity level of their social connections, facilitating user-friendly personalized privacy settings. We design a privacy-aware mechanism that operates within a trusted service provider, capable of establishing privacy protection levels based on user-perceived sensitivity settings. Additionally, we propose a sensitivity-aware sampling mechanism to implement SPEDP. To further optimize the privacy mechanism, we explore a privacy threshold optimization strategy aimed at minimizing privacy budget waste. Finally, the personalized privacy protections and utility improvements achieved by the SPEDP mechanism are rigorously validated through theoretical analysis and comprehensive comparative experiments on benchmark datasets.

关键词： Correlation   Representation learning   Correlation coefficient   Training   Reviews   Labeling   Image classification   Computer science   Adaptation models   Standards   Heterogeneous domain adaptation   correlative feature learning   discriminative distribution alignment   pseudo-label selection  

摘要： Heterogeneous domain adaptation seeks to learn an effective classifier or regression model for unlabeled target samples by using the well-labeled source samples but residing in different feature spaces and lying different distributions. Most recent works have concentrated on learning domain-invariant feature representations to minimize the distribution divergence via target pseudo-labels. However, two critical issues need to be further explored: 1) new feature representations should be not only domain-invariant but also category-correlative and discriminative and 2) alleviating the negative transfer caused by the incorrect pseudo-labeling target samples could boost the adaptation performance during the iterative learning process. To address these issues, in this paper, we put forward a novel heterogeneous domain adaptation method to learn category-correlative and discriminative representations, referred to as correlative and discriminative feature learning (CDFL). Specifically, CDFL aims to learn a feature space where class-specific feature correlations between the source and target domains are maximized, the divergences of marginal and conditional distribution between the source and target domains are minimized, and the distances of inter-class distribution are forced to be maximized to ensure the discriminative ability. Meanwhile, a selective pseudo-labeling procedure based on the correlation coefficient and classifier prediction is introduced to boost class-specific feature correlation and discriminative distribution alignment in an iteration way. Extensive experiments certify that CDFL outperforms the State-of-the-Art algorithms on five standard benchmarks.

关键词： Virtual environments  

摘要： The development of the national economy has promoted the development of the tourism industry, and outdoor tourism has gradually become the main leisure and entertainment method for people during holidays. However, the current tourism promotion mechanism only considers tourist preferences, resulting in tourists receiving recommendations. The unique features of the tourist attractions in the destination area are extremely similar to those of previous tourist areas. Therefore, the research is based on the Visual Geometry 19 model, using skip connections and soft threshold functions to improve the Visual Geometry 19 network. A residual network is designed for feature extraction, and panoramic stitching technology is used to construct virtual scenes of tourist attractions. The findings indicated that the residual network designed in the study demonstrated convergence after 50 iterations of training and testing on the tourism map dataset, with an accuracy of scene reconstruction reaching 85%. The designed tourism location image reconstruction could be completed in about 90 seconds, effectively improving the speed of the virtual reconstruction of tourism scenes. The designed tourism attraction promotion mechanism based on virtual reality technology effectively solves the problem of single tourism promotion and improves the experience of national outbound tourism. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Image segmentation   Optical imaging   Retinal vessels   Coherence   Biomedical optical imaging   Data augmentation   Training   Computer science   Feature extraction   Diseases   Cross-attention   data augmentation   data fusion   deep learning (DL)   fundus image  

摘要： Accurate automatic retinal blood vessel segmentation in fundus images plays an important role in the early diagnosis of any ocular disease detection system. However, most of the past literature has yet to attain a superior result primarily due to a lack of sufficient annotated data and the complexity of the vessel structure under challenging background conditions. In this work, we propose the design of a coherence measure-guided data augmentation model, named lambda-coherence measure-guided Cartesian-square ( lambda CMgC2 ), for enriching the existing datasets with synthetic and structurally coherent fundus images thus alleviating the issue of data scarcity. Subsequently, we propose a novel end-to-end convolutional network, called two-path cross-context encoder with probability map-based bandpass decoder (2pCePd-Net) for the segmentation of blood vessels endowed with a novel 2pCd(+) encoder block with CERg skip connection and a novel p<^>BPf -enabled decoder block. The proposed work has been evaluated using four standard datasets, namely, DRIVE, STARE, CHASEDB1, and HRF, and has obtained a benchmark accuracy (Ac) of 97.6%, 98.1%, 98.2%, and 97.7%, respectively. Statistically, our proposed model has further achieved benchmark results across sensitivity (Se), specificity (Sp), F1 , and AUC measures of evaluation as well.

关键词： Intrusion detection   Feature extraction   Software defined networking   Computer science   Information technology   Deep learning   Classification algorithms   Bidirectional long short term memory   Telecommunication traffic   Prediction algorithms   Software-defined networking   deep learning   feature selection   intrusion detection system   enhanced artificial orcas algorithm  

摘要： Software-defined networking (SDN) is a novel network theory that divides the controller from the network devices such as switches and routers. The integrated SDN structure enables the global network organization and tackles the necessity of present data centers. There are great advantages presented by the architecture of SDN, the hazard of novel assaults is a vital issue and can avert the widespread acceptance of SDNs. The controller of SDN is an essential part, and it is a tempting aim for the invaders. If the attacker effectively acquires the SDN controller, it can transmit the traffic depending upon its desires, causing severe loss to the complete system. Mobile users can access crucial actual services over wireless models such as software-defined networks (SDNs) topologies and the Internet of Things (IoTs). Thus, managing power consumption and system and device congestion turns into a main problem for SDN-based IoT applications. Network intrusion detection systems (NIDSs) are significant devices for identifying and protecting the network landscape from anomalous attacks and malicious activity. Currently, deep Learning (DL) has revealed desired outcomes in a diversity of problems like speech, image, text applications, etc. Whereas numerous works used DL for NIDSs, almost all these methods neglect the outcome of the overfitting issue throughout the execution of DL techniques. This study presents a novel Enhancing Software-Defined Networking Security with Deep Learning and Hybrid Feature Selection (ESDNS-DLHFS) technique for consumer platforms. The proposed ESDNS-DLHFS system primarily focuses on protecting data privacy in SDN-assisted IoT platforms. In the ESDNS-DLHFS method, the initial phase of min-max normalization is executed to scale the input data. For the feature selection process, the hybrid crow search arithmetic optimization algorithm (HCSAOA) is utilized to optimally select feature subsets. Next, the deep bidirection- al long short-term memory (Deep BiL

关键词： Text summarization   Generators   Long short term memory   Encoding   Training   Reinforcement learning   Feature extraction   Computer science   Bidirectional control   Accuracy   transductive learning   generative adversarial network   reinforcement learning   DistilBERT  

摘要： Text summarization is crucial in various sectors, such as engineering and healthcare, because it enhances efficiency in terms of time and costs. Current extractive text summarization methods struggle with challenges such as greedy selection, model generalization limitations, and high computational demands. To solve these problems, this research introduces a novel extractive text summarization method that uniquely integrates a Generative Adversarial Network (GAN), Transductive Long Short-Term Memory (TLSTM), and DistilBERT for sentence embedding. Our technique uses GANs, which include generator and discriminator components, with the core design based on TLSTM. TLSTM utilizes transductive learning to improve accuracy by focusing on samples geographically closer to the test data. In our model, the generator considers whether to include a sentence in the summary while the discriminator critically reviews the generated summary. This GAN model reduces greedy sentence selection, enhancing summary coherence and quality. We implement a Reinforcement Learning (RL)-based strategy to address an imbalance caused by more fake than real samples in the discriminator. This RL approach, novel in the context of GANs for summarization, views training as a sequence of interconnected decisions, treating each sample as a unique scenario. The network, acting as the decision-making agent, assigns greater rewards or penalties to the minority class to correct the imbalance. The effectiveness of our model was evaluated using the well-regarded CNN/Daily Mail dataset, achieving ROUGE-1, ROUGE-2, and ROUGE-L scores of 52.45, 26.46, and 44.85, respectively. Compared to existing methods, our results demonstrate a significant improvement in summarization quality and operational efficiency, as measured by the ROUGE metric.

关键词： Layout   Accuracy   Deep learning   Classification algorithms   Cameras   Text analysis   Image analysis   Detectors   Computer science   Complexity theory   DIA   deep learning models   Pashto   SSD  

摘要： The paper explores the layout analysis and classification task of Pashto document images, a field with limited research due to the language's low-resource status. It uses Document Image Analysis (DIA) to detect one-column and two-column text blocks from Pashto documents captured using handheld cameras. A novel dataset containing real-world documents is annotated using bounding boxes to distinguish between one-column and two-column layouts. Layout analysis plays a vital role in Document Image Analysis (DIA) and answers questions about the nature of Document Images integral parts (components). These components are mainly text, graphics, and tabular data. The detection/identification of such elements is initially dependent on the general layout of a document. Textual columns are one of the basic layout structures present in document images. Such textual columns need identification as one-column or two-column before feeding the textual blocks into an Optical Character Recognition (OCR) system. Also, it becomes more crucial if the document images belong to a low-resource language like Pashto. Thus, this work contributes mainly in two aspects. First, it contributes to creating a dataset containing camera-captured document images with one-column and two-column patterns. Second, it proposes a deep learning model to identify/detect one-column and two-column textual blocks in the Pashto text images. The proposed model utilizes a reputed variant of a Faster Region-based Convolutional Neural Network (R-CNN) called single shot detector (SSD). The evaluation was done by examining the test set and a mean average precision (mAP) of 89% is achieved as a baseline.

关键词： Authentication   Public key   Privacy   Security   Protocols   Training   Performance evaluation   Data privacy   Computer science   Artificial intelligence   VANETs   anonymous credentials   decentralization   authentication   privacy preservation  

摘要： In Vehicular Ad-hoc Networks (VANETs), vehicles must authenticate their identities before accessing services. However, existing authentication schemes based on anonymous credentials still face single-point failure in multi-authority scenarios. In addition, in traditional anonymous credential schemes, the public key of credential authority is used directly to verify the credential, which may increase the risk of vehicle privacy being misused. To address these issues, we propose a decentralized threshold credential management system with fine-grained authentication for VANETs. The decentralized credential management architecture is proposed for VANETs with multiple credential authorities, each credential authority consists of multiple credential managers who issue credentials using the threshold mechanism, effectively solving the single-point failure. Based on this architecture, we design a fine-grained, privacy-preserving authentication scheme that allows vehicles to autonomously perform selective attribute disclosure, credential aggregation, and randomization before requesting verification from the Cloud Service Provider, thereby achieving a balance between privacy preservation and authentication efficiency. The security proofs and analysis show that our scheme satisfies the target security properties. Performance evaluations indicate that our scheme enables efficient, flexible credential management and authentication in VANETs while ensuring privacy preservation.

关键词： Semantics   Computational efficiency   Feature extraction   Training   Computational modeling   Biological system modeling   Visualization   Computer science   Web sites   Video on demand   Text-video retrieval   vision-and-language pre-training   CLIP model   consistent learning  

摘要： Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involve transferring text-video pairs to a common embedding space and leveraging cross-modal interactions on specific entities for semantic alignment. Though effective, these paradigms entail prohibitive computational costs, leading to inefficient retrieval. To address this, we propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL), which capitalizes on latent shared semantics across modalities for text-video retrieval. Specifically, we introduce a parameter-free global interaction module to explore coarse-grained alignment. Then, we devise a shared local interaction module that employs several learnable queries to capture latent semantic concepts for learning fine-grained alignment. Furthermore, an Inter-Consistency Loss (ICL) is devised to accomplish the concept alignment between the visual query and corresponding textual query, and an Intra-Diversity Loss (IDL) is developed to repulse the distribution within visual (textual) queries to generate more discriminative concepts. Extensive experiments on five widely used benchmarks (i.e., MSR-VTT, MSVD, DiDeMo, LSMDC, and ActivityNet) substantiate the superior effectiveness and efficiency of the proposed method. Remarkably, our method achieves comparable performance with SOTA as well as being nearly 220 times faster in terms of computational cost. Code is available at: https://***/zchoi/GLSCL