Wangkai Jin

Junyu Liu, Wangkai Jin, Zhenyong He et al.

The emerging trends of Internet-of-Vehicles (IoV) demand centralized servers to collect/process sensitive data with limited computational resources on a single vehicle. Such centralizations of sensitive data demand practical privacy protections. One widely-applied paradigm, Differential Privacy, can provide strong guarantees over sensitive data by adding noises. However, directly applying DP for IoV incurs significant challenges for data utility and effective protection. We observe that the key issue about DP-enabled protection in IoV lies in how to synergistically combine DP with special characteristics of IoV, whose query sequences are usually formed as unbalanced batches due to frequent interactions between centralized servers and edge vehicles. To this end, we propose HUT, a new algorithm to enable High UTility for DP-enabled protection in IoV. Our key insight is to leverage the inherent characteristics in IoV: the unbalanced batches. Our key idea is to aggregate local batches and apply Order Constraints, so that information loss from DP protection can be mitigated. We evaluate the effectiveness of HUT against the state-of-the-art DP protection mechanisms. The results show that HUT can provide much lower information loss by 95.69\% and simultaneously enable strong mathematically-guaranteed protection over sensitive data.

Wangkai Jin, Yicun Duan, Junyu Liu et al.

Emerging Autonomous Vehicles (AV) breed great potentials to exploit data-driven techniques for adaptive and personalized Human-Vehicle Interactions. However, the lack of high-quality and rich data supports limits the opportunities to explore the design space of data-driven techniques, and validate the effectiveness of concrete mechanisms. Our goal is to initialize the efforts to deliver the building block for exploring data-driven Human-Vehicle Interaction designs. To this end, we present BROOK dataset, a multi-modal dataset with facial video records. We first brief our rationales to build BROOK dataset. Then, we elaborate how to build the current version of BROOK dataset via a year-long study, and give an overview of the dataset. Next, we present three example studies using BROOK to justify the applicability of BROOK dataset. We also identify key learning lessons from building BROOK dataset, and discuss about how BROOK dataset can foster an extensive amount of follow-up studies.

Yicun Duan, Junyu Liu, Wangkai Jin et al.

Recent developments of advanced Human-Vehicle Interactions rely on the concept Internet-of-Vehicles (IoV), to achieve large-scale communications and synchronizations of data in practice. The concept of IoV is highly similar to a distributed system, where each vehicle is considered as a node and all nodes are grouped with a centralized server. In this manner, the concerns of data privacy are significant since all vehicles collect, process and share personal statistics (e.g. multi-modal, driving statuses and etc.). Therefore, it's important to understand how modern privacy-preserving techniques suit for IoV. We present the most comprehensive study to characterize modern privacy-preserving techniques for IoV to date. We focus on Differential Privacy (DP), a representative set of mathematically-guaranteed mechanisms for both privacy-preserving processing and sharing on sensitive data. The purpose of our study is to demystify the tradeoffs of deploying DP techniques, in terms of service quality. We first characterize representative privacy-preserving processing mechanisms, enabled by advanced DP approaches. Then we perform a detailed study of an emerging in-vehicle, Deep-Neural-Network-driven application, and study the upsides and downsides of DP for diverse types of data streams. Our study obtains 11 key findings and we highlight FIVE most significant observations from our detailed characterizations. We conclude that there are a large volume of challenges and opportunities for future studies, by enabling privacy-preserving IoV with low overheads for service quality.

Wangkai Jin, Junyu Liu, Jianfeng Ren et al.

The challenges of polyphonic sound event detection (PSED) stem from the detection of multiple overlapping events in a time series. Recent efforts exploit Deep Neural Networks (DNNs) on Time-Frequency Representations (TFRs) of audio clips as model inputs to mitigate such issues. However, existing solutions often rely on a single type of TFR, which causes under-utilization of input features. To this end, we propose a novel PSED framework, which incorporates Multi-Type-Multi-Scale TFRs. Our key insight is that: TFRs, which are of different types or in different scales, can reveal acoustics patterns in a complementary manner, so that the overlapped events can be best extracted by combining different TFRs. Moreover, our framework design applies a novel approach, to adaptively fuse different models and TFRs symbiotically. Hence, the overall performance can be significantly improved. We quantitatively examine the benefits of our framework by using Capsule Neural Networks, a state-of-the-art approach for PSED. The experimental results show that our method achieves a reduction of 7\% in error rate compared with the state-of-the-art solutions on the TUT-SED 2016 dataset.