Academic literature on the topic 'InterDataNet'

Radio Frequency Identification (RFID) techniques are considered relevant building blocks for the Internet of Things. The interoperability across different RFID software and hardware infrastructures is a key requirement for achieving effective and wide-scale Internet of Thing deployments. In this context, the EPC Information Service (EPCIS) is a set of standard specifications for sharing RFID-related data (i.e., EPC events) both within and across enterprises. Although the EPCIS specifies a set of HTTP and Web Service interfaces for querying and adding EPC events, interoperability and easiness of use is hindered by the fact that client applications should be aware of the repositories that are authoritative for one or more given queries and links among related events are not explicitly represented in response messages. In this paper we argue that, by leveraging emerging REST and Linked Data paradigms, EPC events can be handled as a graph of globally-addressable information resources that can be navigated, queried, and aggregated through a uniform interface and seamlessly across organization domains. To validate this approach, we have developed a prototype that exposes the EPCIS interfaces as a set of REST APIs. The prototype implementation exploits the information modeling and management capabilities provided by a framework, called InterDataNet (IDN), that we conceived and developed to ease the realization of the Web of Data and Linked Data applications.

Speaker identification is gaining popularity, with notable applications in security, automation, and authentication. For speaker identification, deep-convolutional-network-based approaches, such as SincNet, are used as an alternative to i-vectors. Convolution performed by parameterized sinc functions in SincNet demonstrated superior results in this area. This system optimizes softmax loss, which is integrated in the classification layer that is responsible for making predictions. Since the nature of this loss is only to increase interclass distance, it is not always an optimal design choice for biometric-authentication tasks such as face and speaker recognition. To overcome the aforementioned issues, this study proposes a family of models that improve upon the state-of-the-art SincNet model. Proposed models AF-SincNet, Ensemble-SincNet, and ALL-SincNet serve as a potential successor to the successful SincNet model. The proposed models are compared on a number of speaker-recognition datasets, such as TIMIT and LibriSpeech, with their own unique challenges. Performance improvements are demonstrated compared to competitive baselines. In interdataset evaluation, the best reported model not only consistently outperformed the baselines and current prior models, but also generalized well on unseen and diverse tasks such as Bengali speaker recognition.

Most existing face authentication systems have limitations when facing the challenge raised by presentation attacks, which probably leads to some dangerous activities when using facial unlocking for smart device, facial access to control system, and face scan payment. Accordingly, as a security guarantee to prevent the face authentication from being attacked, the study of face presentation attack detection is developed in this community. In this work, a face presentation attack detector is designed based on residual color texture representation (RCTR). Existing methods lack of effective data preprocessing, and we propose to adopt DW-filter for obtaining residual image, which can effectively improve the detection efficiency. Subsequently, powerful CM texture descriptor is introduced, which performs better than widely used descriptors such as LBP or LPQ. Additionally, representative texture features are extracted from not only RGB space but also more discriminative color spaces such as HSV, YCbCr, and CIE 1976 L∗a∗b (LAB). Meanwhile, the RCTR is fed into the well-designed classifier. Specifically, we compare and analyze the performance of advanced classifiers, among which an ensemble classifier based on a probabilistic voting decision is our optimal choice. Extensive experimental results empirically verify the proposed face presentation attack detector’s superior performance both in the cases of intradataset and interdataset (mismatched training-testing samples) evaluation.

Purpose. Retinal blood vessel image segmentation is an important step in ophthalmological analysis. However, it is difficult to segment small vessels accurately because of low contrast and complex feature information of blood vessels. The objective of this study is to develop an improved retinal blood vessel segmentation structure (WA-Net) to overcome these challenges. Methods. This paper mainly focuses on the width of deep learning. The channels of the ResNet block were broadened to propagate more low-level features, and the identity mapping pathway was slimmed to maintain parameter complexity. A residual atrous spatial pyramid module was used to capture the retinal vessels at various scales. We applied weight normalization to eliminate the impacts of the mini-batch and improve segmentation accuracy. The experiments were performed on the DRIVE and STARE datasets. To show the generalizability of WA-Net, we performed cross-training between datasets. Results. The global accuracy and specificity within datasets were 95.66% and 96.45% and 98.13% and 98.71%, respectively. The accuracy and area under the curve of the interdataset diverged only by 1%∼2% compared with the performance of the corresponding intradataset. Conclusion. All the results show that WA-Net extracts more detailed blood vessels and shows superior performance on retinal blood vessel segmentation tasks.

Recently proposed methods in intrusion detection are iterating on machine learning methods as a potential solution. These novel methods are validated on one or more datasets from a sparse collection of academic intrusion detection datasets. Their recognition as improvements to the state-of-the-art is largely dependent on whether they can demonstrate a reliable increase in classification metrics compared to similar works validated on the same datasets. Whether these increases are meaningful outside of the training/testing datasets is rarely asked and never investigated. This work aims to demonstrate that strong general performance does not typically follow from strong classification on the current intrusion detection datasets. Binary classification models from a range of algorithmic families are trained on the attack classes of CSE-CIC-IDS2018, a state-of-the-art intrusion detection dataset. After establishing baselines for each class at various points of data access, the same trained models are tasked with classifying samples from the corresponding attack classes in CIC-IDS2017, CIC-DoS2017 and CIC-DDoS2019. Contrary to what the baseline results would suggest, the models have rarely learned a generally applicable representation of their attack class. Stability and predictability of generalized model performance are central issues for all methods on all attack classes. Focusing only on the three best-in-class models in terms of interdataset generalization, reveals that for network-centric attack classes (brute force, denial of service and distributed denial of service), general representations can be learned with flat losses in classification performance (precision and recall) below 5%. Other attack classes vary in generalized performance from stark losses in recall (−35%) with intact precision (98+%) for botnets to total degradation of precision and moderate recall loss for Web attack and infiltration models. The core conclusion of this article is a warning to researchers in the field. Expecting results of proposed methods on the test sets of state-of-the-art intrusion detection datasets to translate to generalized performance is likely a serious overestimation. Four proposals to reduce this overestimation are set out as future work directions.

La Web Science si pone l'obiettivo di guidare l'evoluzione del Web fornendo possibili risposte ad aspetti cruciali di questo sistema socio-tecnico quali: identità, privacy, sicurezza, trust e governance. Il Web attuale, inteso come sistema socio-tecnico , non fornisce un meccanismo di collaborazione che possa avvalersi di un adeguato supporto infrastrutturale; il movimento Web of Data si sta muovendo in questa direzione, mediante gli approcci Linked Data ed Open Data. Il presente lavoro si colloca all'interno di InterDataNet, un framework che si propone come soluzione architetturale per consentire ad utenti distribuiti nel tempo e nello spazio di collaborare intorno ad elementi informativi che appartengono ad uno spazio globale di dati distribuito con cui è possibile interagire mediante la metafora dei documenti. In particolare, il presente lavoro si pone l'obiettivo di arricchire l'infrastruttura InterDataNet proponendo una soluzione finalizzata ad un riuso dei dati efficiente ed efficace; tale meccanismo, cui è stato assegnato il nome di IDN Template, rende possibile la descrizione di un modello che definisce un insieme di regole al quale un documento strutturato, sia nel complesso sia in ogni sua singola parte, deve risultare conforme. L'IDN Template fornisce al progettista la possibilità di rendere disponibili a soggetti terzi, informazioni sia riguardo il documento nel complesso, attraverso la descrizione dei vari elementi che vanno a comporne la struttura, sia riguardo le sue singole parti, attraverso la descrizione del formato, della sintassi, dei vincoli strutturali e della semantica dei dati. Il meccanismo abilitato dall'IDN Template, facilita il riuso da parte di progettisti terzi dei dati per i quali sia stato definito un opportuno modello. Come caso d'uso viene analizzato un insieme di Open Data geografici, messi a disposizione dal Comune di Firenze; tali informazioni sono state opportunamente elaborate ed inserite all'interno dell'infrastruttura InterDataNet, modellate mediante il ricorso alla tecnica di modellazione descritta e successivamente rielaborate congiuntamente a dati prodotti da soggetti terzi. I risultati conseguiti hanno rafforzato la convinzione che l'infrastruttura InterDataNet possa fornire una soluzione innovativa per un Web di dati strutturati e riusabili in modo collaborativo, mantenendo la piena compatibilità con gli standard proposti dal Linked Data e dal Semantic Web. -------------------------------------------------------------------------------------- The Web Science aims to drive the evolution of the Web providing possible answers to key aspects of this socio-technical system such as: identity, privacy, security, trust and governance. The current Web, intended as a social-technical system, does not provide a mechanism for collaboration that will maintain a suitable infrastructural support; the Web of Data is moving in that direction through the Linked Data and Open Data approaches. This work is part of the InterDataNet framework (IDN) that wants to be an architectural solution in order to allow users, distributed across time and space, to collaborate around information elements that belong to a global area of distributed data with which is possible to interact through the metaphor of documents. Specifically, this work aims to enrich the IDN infrastructure by proposing a solution aimed at an efficient and effective data reuse; such a mechanism, called IDN Template, makes possible the description of a model that defines a set of rules to which a structured document must comply with, both as a whole and in all its component parts. The IDN Template provides the designer with the ability to make available to third parties details regarding both the document as a whole – through the description of the different elements composing the structure – both in terms of its individual components - through the description of format, syntax, structural constraints and semantics of data. The reuse mechanism enabled by the IDN Template, makes easy to reuse by third parties data for which has been defined a suitable model. As use case, a collection of geographical Open Data made available by the Municipality of Florence, Italy is evaluated; such information, duly processed, was inserted into InterDataNet infrastructure through the use of the template technique and then reprocessed together with data produced by third parties. The results obtained have strengthened the belief that the InterDataNet infrastructure can provide an innovative solution for a web of structured and reusable data in a collaborative manner while maintaining the full compatibility with the standards suggested by Linked Data and Semantic Web.