A number of studies on privacy-preserving data mining have been proposed. Most of them assume that they can separate quasi-identifiers (QIDs) from sensitive attributes. For instance, they assume that address, job, and age are QIDs but are not sensitive attributes and that a disease name is a sensitive attribute but is not a QID. However, all of these attributes can have features that are both sensitive attributes and QIDs in practice. In this paper, we refer to these attributes as sensitive QIDs and we propose novel privacy models, namely, (l1, ..., lq)-diversity and (t1, ..., tq)-closeness, and a method that can treat sensitive QIDs. Our method is composed of two algorithms: An anonymization algorithm and a reconstruction algorithm. The anonymization algorithm, which is conducted by data holders, is simple but effective, whereas the reconstruction algorithm, which is conducted by data analyzers, can be conducted according to each data analyzer's objective. Our proposed method was experimentally evaluated using real data sets.

Mobile crowdsensing, which collects environmental information from mobile phone users, is growing in popularity. These data can be used by companies for marketing surveys or decision making. However, collecting sensing data from other users may violate their privacy. Moreover, the data aggregator and/or the participants of crowdsensing may be untrusted entities. Recent studies have proposed randomized response schemes for anonymized data collection. This kind of data collection can analyze the sensing data of users statistically without precise information about other users' sensing results. However, traditional randomized response schemes and their extensions require a large number of samples to achieve proper estimation. In this paper, we propose a new anonymized data-collection scheme that can estimate data distributions more accurately. Using simulations with synthetic and real datasets, we prove that our proposed method can reduce the mean squared error and the JS divergence by more than 85% as compared with other existing studies.

Word-level sign language recognition (WSLR) is the backbone for continuous sign language recognition (CSLR) that infers glosses from sign videos. Finding the relevant gloss from the sign sequence and detecting explicit boundaries of the glosses from sign videos is a persistent challenge. In this paper, we propose a systematic approach for gloss prediction in WLSR using the Sign2Pose Gloss prediction transformer model. The primary goal of this work is to enhance WLSR’s gloss prediction accuracy with reduced time and computational overhead. The proposed approach uses hand-crafted features rather than automated feature extraction, which is computationally expensive and less accurate. A modified key frame extraction technique is proposed that uses histogram difference and Euclidean distance metrics to select and drop redundant frames. To enhance the model’s generalization ability, pose vector augmentation using perspective transformation along with joint angle rotation is performed. Further, for normalization, we employed YOLOv3 (You Only Look Once) to detect the signing space and track the hand gestures of the signers in the frames. The proposed model experiments on WLASL datasets achieved the top 1% recognition accuracy of 80.9% in WLASL100 and 64.21% in WLASL300. The performance of the proposed model surpasses state-of-the-art approaches. The integration of key frame extraction, augmentation, and pose estimation improved the performance of the proposed gloss prediction model by increasing the model’s precision in locating minor variations in their body posture. We observed that introducing YOLOv3 improved gloss prediction accuracy and helped prevent model overfitting. Overall, the proposed model showed 17% improved performance in the WLASL 100 dataset.