Assessment of small strain modulus in soil using advanced computational models.

Small-strain shear modulus ([Formula: see text]) of soils is a crucial dynamic parameter that significantly impacts seismic site response analysis and foundation design. [Formula: see text] is susceptible to multiple factors, including soil uniformity coefficient ([Formula: see text]), void ratio (e), mean particle size ([Formula: see text]), and confining stress ([Formula: see text]). This study aims to establish a [Formula: see text] database and suggests three advanced computational models for [Formula: see text] prediction. Nine performance indicators, including four new indices, are employed to calculate and analyze the model's performance. The XGBoost model outperforms the other two models, with all three models achieving [Formula: see text] values exceeding 0.9, RMSE values below 30, MAE values below 25, VAF values surpassing 80%, and ARE values below 50%. Compared to the empirical formula-based traditional prediction models, the model proposed in this study exhibits better performance in IOS, IOA, a20-index, and PI metrics values. The model has higher prediction accuracy and better generalization ability.

Leveraging Deep Learning for IoT Transceiver Identification.

With the increasing demand for Internet of Things (IoT) network applications, the lack of adequate identification and authentication has become a significant security concern. Radio frequency fingerprinting techniques, which utilize regular radio traffic as the identification source, were then proposed to provide a more secured identification approach compared to traditional security methods. Such solutions take hardware-level characteristics as device fingerprints to mitigate the risk of pre-shared key leakage and lower computational complexity. However, the existing studies suffer from problems such as location dependence. In this study, we have proposed a novel scheme for further exploiting the spectrogram and the carrier frequency offset (CFO) as identification sources. A convolutional neural network (CNN) is chosen as the classifier. The scheme addressed the location-dependence problem in the existing identification schemes. Experimental evaluations with data collected in the real world have indicated that the proposed approach can achieve 80% accuracy even if the training and testing data are collected on different days and at different locations, which is 13% higher than state-of-the-art approaches.

Effect of moisture, protein, starch, soluble sugar contents and microstructure on mechanical properties of maize kernels.

The relationships between components contents and mechanical properties of maize kernels were studied. The relationships were analyzed by gray relation analysis (GRA), correlation analysis (CA), and multiple linear regression (MLR). Furthermore, Scanning Electron Microscope (SEM) was utilized for interpreting mechanical properties. The results of GRA and CA indicated that soluble sugar content was not an important factor that can affect mechanical properties compared with the moisture, starch and protein contents. The results of MLR indicated that the regression models can be used to access the hardness, rupture force and apparent elastic modulus (R greater than 0.75), but cannot be used to access rupture energy and viscoelastic parameters. The microstructure observation illustrated that high protein content could increase hardness, rupture force, rupture energy, and elastic properties, while high starch content could increase viscous properties. This study can provide technical references for transportation, processing and harvest processes.

Determination of hardness for maize kernels based on hyperspectral imaging.

In order to realize rapid and non-destructive detection of hardness for maize kernels, a method for quantitative hardness measurement was proposed based on hyperspectral imaging technology. Firstly, the regression model of hardness and moisture content was established. Then, based on reflectance hyperspectral imaging at wavelengths within 399.75-1005.80 nm, the prediction model of the moisture content was studied by the partial least squares regression (PLSR) based on the characteristic wavelengths, which was selected through successive projection algorithm (SPA). Finally, the hardness prediction model was validated by combing the prediction model of moisture content with the regression model of hardness. The coefficient of determination (R2), the root mean square error (RMSE) the ratio of performance-to-deviation (RPD) and the ratio of error range (RER) of hardness prediction were 0.912, 17.76 MPa, 3.41 and 14, respectively. Therefore, this study provided a method for rapid and non-destructive detection of hardness of maize kernels.

No-Reference Screen Content Image Quality Assessment With Unsupervised Domain Adaptation.

In this paper, we quest the capability of transferring the quality of natural scene images to the images that are not acquired by optical cameras (e.g., screen content images, SCIs), rooted in the widely accepted view that the human visual system has adapted and evolved through the perception of natural environment. Here, we develop the first unsupervised domain adaptation based no reference quality assessment method for SCIs, leveraging rich subjective ratings of the natural images (NIs). In general, it is a non-trivial task to directly transfer the quality prediction model from NIs to a new type of content (i.e., SCIs) that holds dramatically different statistical characteristics. Inspired by the transferability of pair-wise relationship, the proposed quality measure operates based on the philosophy of improving the transferability and discriminability simultaneously. In particular, we introduce three types of losses which complementarily and explicitly regularize the feature space of ranking in a progressive manner. Regarding feature discriminatory capability enhancement, we propose a center based loss to rectify the classifier and improve its prediction capability not only for source domain (NI) but also the target domain (SCI). For feature discrepancy minimization, the maximum mean discrepancy (MMD) is imposed on the extracted ranking features of NIs and SCIs. Furthermore, to further enhance the feature diversity, we introduce the correlation penalization between different feature dimensions, leading to the features with lower rank and higher diversity. Experiments show that our method can achieve higher performance on different source-target settings based on a light-weight convolution neural network. The proposed method also sheds light on learning quality assessment measures for unseen application-specific content without the cumbersome and costing subjective evaluations.

FTRLIM: Distributed Instance Matching Framework for Large-Scale Knowledge Graph Fusion.

Instance matching is a key task in knowledge graph fusion, and it is critical to improving the efficiency of instance matching, given the increasing scale of knowledge graphs. Blocking algorithms selecting candidate instance pairs for comparison is one of the effective methods to achieve the goal. In this paper, we propose a novel blocking algorithm named MultiObJ, which constructs indexes for instances based on the Ordered Joint of Multiple Objects' features to limit the number of candidate instance pairs. Based on MultiObJ, we further propose a distributed framework named Follow-the-Regular-Leader Instance Matching (FTRLIM), which matches instances between large-scale knowledge graphs with approximately linear time complexity. FTRLIM has participated in OAEI 2019 and achieved the best matching quality with significantly efficiency. In this research, we construct three data collections based on a real-world large-scale knowledge graph. Experiment results on the constructed data collections and two real-world datasets indicate that MultiObJ and FTRLIM outperform other state-of-the-art methods.

Joint Coding of Local and Global Deep Features in Videos for Visual Search.

Practically, it is more feasible to collect compact visual features rather than the video streams from hundreds of thousands of cameras into the cloud for big data analysis and retrieval. Then the problem becomes which kinds of features should be extracted, compressed and transmitted so as to meet the requirements of various visual tasks. Recently, many studies have indicated that the activations from the convolutional layers in convolutional neural networks (CNNs) can be treated as local deep features describing particular details inside an image region, which are then aggregated (e.g., using Fisher Vectors) as a powerful global descriptor. Combination of local and global features can satisfy those various needs effectively. It has also been validated that, if only local deep features are coded and transmitted to the cloud while the global features are recovered using the decoded local features, the aggregated global features should be lossy and consequently would degrade the overall performance. Therefore, this paper proposes a joint coding framework for local and global deep features (DFJC) extracted from videos. In this framework, we introduce a coding scheme for real-valued local and global deep features with intra-frame lossy coding and inter-frame reference coding. The theoretical analysis is performed to understand how the number of inliers varies with the number of local features. Moreover, the inter-feature correlations are exploited in our framework. That is, local feature coding can be accelerated by making use of the frame types determined with global features, while the lossy global features aggregated with the decoded local features can be used as a reference for global feature coding. Extensive experimental results under three metrics show that our DFJC framework can significantly reduce the bitrate of local and global deep features from videos while maintaining the retrieval performance.

Obfuscatable multi-recipient re-encryption for secure privacy-preserving personal health record services.

BACKGROUND: With the rapid development of cloud computing techniques, it is attractive for personal health record (PHR) service providers to deploy their PHR applications and store the personal health data in the cloud. However, there could be a serious privacy leakage if the cloud-based system is intruded by attackers, which makes it necessary for the PHR service provider to encrypt all patients' health data on cloud servers. OBJECTIVE: Existing techniques are insufficiently secure under circumstances where advanced threats are considered, or being inefficient when many recipients are involved. Therefore, the objectives of our solution are (1) providing a secure implementation of re-encryption in white-box attack contexts and (2) assuring the efficiency of the implementation even in multi-recipient cases. METHODS: We designed the multi-recipient re-encryption functionality by randomness-reusing and protecting the implementation by obfuscation. RESULTS: The proposed solution is secure even in white-box attack contexts. Furthermore, a comparison with other related work shows that the computational cost of the proposed solution is lower. CONCLUSIONS: The proposed technique can serve as a building block for supporting secure, efficient and privacy-preserving personal health record service systems.

Secure Obfuscation for Encrypted Group Signatures.

In recent years, group signature techniques are widely used in constructing privacy-preserving security schemes for various information systems. However, conventional techniques keep the schemes secure only in normal black-box attack contexts. In other words, these schemes suppose that (the implementation of) the group signature generation algorithm is running in a platform that is perfectly protected from various intrusions and attacks. As a complementary to existing studies, how to generate group signatures securely in a more austere security context, such as a white-box attack context, is studied in this paper. We use obfuscation as an approach to acquire a higher level of security. Concretely, we introduce a special group signature functionality-an encrypted group signature, and then provide an obfuscator for the proposed functionality. A series of new security notions for both the functionality and its obfuscator has been introduced. The most important one is the average-case secure virtual black-box property w.r.t. dependent oracles and restricted dependent oracles which captures the requirement of protecting the output of the proposed obfuscator against collision attacks from group members. The security notions fit for many other specialized obfuscators, such as obfuscators for identity-based signatures, threshold signatures and key-insulated signatures. Finally, the correctness and security of the proposed obfuscator have been proven. Thereby, the obfuscated encrypted group signature functionality can be applied to variants of privacy-preserving security schemes and enhance the security level of these schemes.