With the advancements in connected devices, a huge amount of real-time data is being generated. Efficient storage, transmission, and analysation of this real-time big data is important, as it serves a number of purposes ranging from decision making to fault prediction, etc. Alongside this, real-time big data has rigorous utility and privacy requirements, therefore, it is also significantly important to choose the handling strategies meticulously. One of the optimal way to store and transmit data in the form of lossless compression is Huffman coding, which compresses the data into a variable length binary stream. Similarly, in order to protect the privacy of such big data, differential privacy is being used nowadays, which perturbs the data on the basis of privacy budget and sensitivity. Nevertheless, traditional differential privacy mechanisms provide privacy guarantees. However, on the other hand, real-time data cannot be dealt as an ordinary set of records, because it usually has certain underlying patterns and cycles, which can be used for forming a link to a specific individuals private information that can lead to severe privacy leakages (e.g., analysing smart metering data can lead to classification of individuals daily routine). Thus, it is equally important to develop a privacy preservation model, which preserves the privacy on the basis of occurrences and patterns in the data. In this paper, we design a novel Huff-DP mechanism, which selects the optimal privacy budget on the basis of privacy requirement for that specific record. In order to further enhance the budget determination, we propose static, sine, and fuzzy logic based decision algorithms. From the experimental evaluations, it can be concluded that our proposed Huff-DP mechanism provides effective privacy protection alongside reducing the privacy budget computational cost.
相關內容
The object perception capabilities of humans are impressive, and this becomes even more evident when trying to develop solutions with a similar proficiency in autonomous robots. While there have been notable advancements in the technologies for artificial vision and touch, the effective integration of these two sensory modalities in robotic applications still needs to be improved, and several open challenges exist. Taking inspiration from how humans combine visual and haptic perception to perceive object properties and drive the execution of manual tasks, this article summarises the current state of the art of visuo-haptic object perception in robots. Firstly, the biological basis of human multimodal object perception is outlined. Then, the latest advances in sensing technologies and data collection strategies for robots are discussed. Next, an overview of the main computational techniques is presented, highlighting the main challenges of multimodal machine learning and presenting a few representative articles in the areas of robotic object recognition, peripersonal space representation and manipulation. Finally, informed by the latest advancements and open challenges, this article outlines promising new research directions.
Novel view synthesis (NVS) is a challenging task in computer vision that involves synthesizing new views of a scene from a limited set of input images. Neural Radiance Fields (NeRF) have emerged as a powerful approach to address this problem, but they require accurate knowledge of camera \textit{intrinsic} and \textit{extrinsic} parameters. Traditionally, structure-from-motion (SfM) and multi-view stereo (MVS) approaches have been used to extract camera parameters, but these methods can be unreliable and may fail in certain cases. In this paper, we propose a novel technique that leverages unposed images from dynamic datasets, such as the NVIDIA dynamic scenes dataset, to learn camera parameters directly from data. Our approach is highly extensible and can be integrated into existing NeRF architectures with minimal modifications. We demonstrate the effectiveness of our method on a variety of static and dynamic scenes and show that it outperforms traditional SfM and MVS approaches. The code for our method is publicly available at \href{//github.com/redacted/refinerf}{//github.com/redacted/refinerf}. Our approach offers a promising new direction for improving the accuracy and robustness of NVS using NeRF, and we anticipate that it will be a valuable tool for a wide range of applications in computer vision and graphics.
Recently, there has been a growing interest in applying machine learning methods to problems in engineering mechanics. In particular, there has been significant interest in applying deep learning techniques to predicting the mechanical behavior of heterogeneous materials and structures. Researchers have shown that deep learning methods are able to effectively predict mechanical behavior with low error for systems ranging from engineered composites, to geometrically complex metamaterials, to heterogeneous biological tissue. However, there has been comparatively little attention paid to deep learning model calibration, i.e., the match between predicted probabilities of outcomes and the true probabilities of outcomes. In this work, we perform a comprehensive investigation into ML model calibration across seven open access engineering mechanics datasets that cover three distinct types of mechanical problems. Specifically, we evaluate both model and model calibration error for multiple machine learning methods, and investigate the influence of ensemble averaging and post hoc model calibration via temperature scaling. Overall, we find that ensemble averaging of deep neural networks is both an effective and consistent tool for improving model calibration, while temperature scaling has comparatively limited benefits. Looking forward, we anticipate that this investigation will lay the foundation for future work in developing mechanics specific approaches to deep learning model calibration.
Predicting image memorability has attracted interest in various fields. Consequently, prediction accuracy with convolutional neural network (CNN) models has been approaching the empirical upper bound estimated based on human consistency. However, identifying which feature representations embedded in CNN models are responsible for such high prediction accuracy of memorability remains an open question. To tackle this problem, this study sought to identify memorability-related feature representations in CNN models using brain similarity. Specifically, memorability prediction accuracy and brain similarity were examined and assessed by Brain-Score across 16,860 layers in 64 CNN models pretrained for object recognition. A clear tendency was shown in this comprehensive analysis that layers with high memorability prediction accuracy had higher brain similarity with the inferior temporal (IT) cortex, which is the highest stage in the ventral visual pathway. Furthermore, fine-tuning the 64 CNN models revealed that brain similarity with the IT cortex at the penultimate layer was positively correlated with memorability prediction accuracy. This analysis also showed that the best fine-tuned model provided accuracy comparable to the state-of-the-art CNN models developed specifically for memorability prediction. Overall, this study's results indicated that the CNN models' great success in predicting memorability relies on feature representation acquisition similar to the IT cortex. This study advanced our understanding of feature representations and its use for predicting image memorability.
The US Census Bureau will implement a new privacy-preserving disclosure avoidance system (DAS), which includes application of differential privacy, on publicly-released 2020 census data. There are concerns that the DAS may bias small-area and demographically-stratified population counts, which play a critical role in public health research, serving as denominators in estimation of disease/mortality rates. Employing three DAS demonstration products, we quantify errors attributable to reliance on DAS-protected denominators in standard small-area disease mapping models for characterizing health inequities. We conduct simulation studies and real data analyses of inequities in premature mortality at the census tract level in Massachusetts and Georgia. Results show that overall patterns of inequity by racialized group and economic deprivation level are not compromised by the DAS. While early versions of DAS induce errors in mortality rate estimation that are larger for Black than non-Hispanic white populations in Massachusetts, this issue is ameliorated in newer DAS versions.
Artwork recommendation is challenging because it requires understanding how users interact with highly subjective content, the complexity of the concepts embedded within the artwork, and the emotional and cognitive reflections they may trigger in users. In this paper, we focus on efficiently capturing the elements (i.e., latent semantic relationships) of visual art for personalized recommendation. We propose and study recommender systems based on textual and visual feature learning techniques, as well as their combinations. We then perform a small-scale and a large-scale user-centric evaluation of the quality of the recommendations. Our results indicate that textual features compare favourably with visual ones, whereas a fusion of both captures the most suitable hidden semantic relationships for artwork recommendation. Ultimately, this paper contributes to our understanding of how to deliver content that suitably matches the user's interests and how they are perceived.
Time series anomaly detection has applications in a wide range of research fields and applications, including manufacturing and healthcare. The presence of anomalies can indicate novel or unexpected events, such as production faults, system defects, or heart fluttering, and is therefore of particular interest. The large size and complex patterns of time series have led researchers to develop specialised deep learning models for detecting anomalous patterns. This survey focuses on providing structured and comprehensive state-of-the-art time series anomaly detection models through the use of deep learning. It providing a taxonomy based on the factors that divide anomaly detection models into different categories. Aside from describing the basic anomaly detection technique for each category, the advantages and limitations are also discussed. Furthermore, this study includes examples of deep anomaly detection in time series across various application domains in recent years. It finally summarises open issues in research and challenges faced while adopting deep anomaly detection models.
Click-through rate (CTR) prediction plays a critical role in recommender systems and online advertising. The data used in these applications are multi-field categorical data, where each feature belongs to one field. Field information is proved to be important and there are several works considering fields in their models. In this paper, we proposed a novel approach to model the field information effectively and efficiently. The proposed approach is a direct improvement of FwFM, and is named as Field-matrixed Factorization Machines (FmFM, or $FM^2$). We also proposed a new explanation of FM and FwFM within the FmFM framework, and compared it with the FFM. Besides pruning the cross terms, our model supports field-specific variable dimensions of embedding vectors, which acts as soft pruning. We also proposed an efficient way to minimize the dimension while keeping the model performance. The FmFM model can also be optimized further by caching the intermediate vectors, and it only takes thousands of floating-point operations (FLOPs) to make a prediction. Our experiment results show that it can out-perform the FFM, which is more complex. The FmFM model's performance is also comparable to DNN models which require much more FLOPs in runtime.
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.
Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8,730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191