Personalized diagnosis and therapy requires monitoring patient activity using various body sensors. Sensor data generated during personalized exercises or tasks may be too specific or inadequate to be evaluated using supervised methods such as classification. We propose multidimensional motif (MDM) discovery as a means for patient activity monitoring, since such motifs can capture repeating patterns across multiple dimensions of the data, and can serve as conformance indicators. Previous studies pertaining to mining MDMs have proposed approaches that lack the capability of concurrently processing multiple dimensions, thus limiting their utility in online scenarios. In this paper, we propose an efficient real-time approach to MDM discovery in body sensor generated time series data for monitoring performance of patients during therapy. We present two alternative models for MDMs based on motif co-occurrences and temporal ordering among motifs across multiple dimensions, with detailed formulation of the concepts proposed. The proposed method uses an efficient hashing based record to enable speedy update and retrieval of motif sets, and identification of MDMs. Performance evaluation using synthetic and real body sensor data in unsupervised motif discovery tasks shows that the approach is effective for 1) concurrent processing of multidimensional time series information suitable for real-time applications, 2) finding unknown naturally occurring patterns with minimal delay, and 3) tracking similarities among repetitions, possibly during therapy sessions.

Data scarcity and class imbalance are common occurrences in healthcare datasets and have adverse effect on classification performance of machine learning models. Artificial data generation in various applications can be used to handle these challenges. This paper proposes Guided Evolutionary Synthesizer (GES), a tool derived from principles of genetic algorithm, and designed to generate artificial healthcare time series data for improving classification performance of machine learning models. We conducted a series of promising and confirmatory preliminary experiments performance using traditional machine learning and non-residual convolutional neural network models to evaluate the effectiveness of GES synthetic on data classification. Motivated by the preliminary results, we conducted eight detailed experiments using residual neural network (ResNet), which demonstrated the flexibility of GES and effectiveness of GES synthetic data in improving classification performance of deep neural networks. These experiments use GES generated electrocardiogram (ECG) and electroencephalogram (EEG) datasets. Our findings show that models trained with GES synthetic data i) performed better than models trained with regular perturbed data, ii) had better diagnostic performance for both EEG and ECG datasets, iii) achieved better performance with lower training volume for EEG dataset, iv) eased learning biases seen in literature for ECG normal sinus and premature ventricular complex rhythms, and v) had better classification outcomes than comparable related work models trained with similar ECG classes.

Digital watermarking for copyright protection of 3-D meshes cannot be directly applied to point clouds, since we need to derive consistent connectivity information, which might change due to attacks, such as noise addition and cropping. Schemes for point clouds operate only on the geometric data and, hence, are generic and applicable to mesh-based representations of 3-D models. For building generic copyright schemes for 3-D models, this paper presents a robust blind watermarking mechanism for 3-D point-sampled geometry. The basic idea is to find a cluster tree from clusters of 3-D points. Using the cluster tree, watermarks can be embedded and extracted by deriving an order among points at global (intracluster) and local levels (intercluster). The multiple bit watermarks are encoded/decoded inside each cluster based on an extension of the cluster structure-based 3-D quantization index modulation. The encoding mechanism makes the technique robust against uniform affine transformations (rotation, scaling, and transformation), reordering, cropping, simplification, and noise addition attacks. The technique when applied to 3-D meshes also achieves robustness against retriangulation and progressive compression techniques. Customization of the bit-encoding scheme achieves high hiding capacity with embedding rates that are equal to 4 b/point, while maintaining the imperceptibility of the watermark with low distortions. The estimated time complexity is O (n logn), where n is the number of 3-D points.

This paper presents a blind spectral two-way watermarking framework for 3-D models with parametric information. We introduce a spectral geometric watermarking technique based on Dirichlet Manifold Harmonic Transform to alter the geometric shape, while the spectral basis functions are computed from the parametric mesh as the analysis domain. This new geometric method embeds watermarks into small surface patches without introducing discontinuity across the patch boundary, while at the same time is robust against various spatial attacks. By manipulating part of the geometric shape on the intermediate model instead of the original model, this method gains robustness against connectivity changing and cropping attacks. By combining the new geometric method with the existing texture method into the two-way watermarking framework, we can withstand various attacks applied to either geometric mesh or parametric information. Theoretical analysis and experiments show that this new geometric method is robust against the majority of attacks and the two-way watermarking framework helps achieve better robustness.