Feedrate scheduling is crucial for improving productivity and accuracy in robotic milling applications. However, due to the nonlinear relationship between the joint space and task space, how to plan a time-optimal feedrate profile with quick analytical solution while ensuring kinematic control up to the snap level remains quite a challenge. To solve these concerns, a snap-bounded and time-optimal feedrate scheduling model is first presented in this article. For accelerating the solving process of the nonlinear model, a synchronous linearization approach is also introduced to help relax the highly nonlinear constraints in both joint space and task space into linear ones. Thereby, the originally complex feedrate scheduling issue is converted to a finite-state convex optimization problem, and an analytical solution to the feedrate profile could be computed efficiently using a straightforward linear programming algorithm. Finally, comparative simulation and experiment are carried out to verify the effectiveness of the proposed method.

In recent years, fiber-optical distributed acoustic sensing (DAS) has been applied to various large-scale infrastructure monitoring areas in smart cities, leading to a new generation of fiber-optic IoT for ground listening. However, its single-task-focused postprocessing methods cannot achieve real-time efficient ground event recognition and localization concurrently. In this article, a two-level multitask learning (MTL) enhanced smart fiber-optical DAS (sDAS) system is proposed, for the first time, to simultaneously realize ground event recognition and localization. Performances and efficiency of both tasks are significantly improved by sharing knowledge across them. Besides, the imbalanced incremental learning ability for new events is also enhanced in the proposed MTL network. The total computation time for the two tasks is greatly shortened to 0.3 ms for a spatial-temporal sample with 129-m fiber length and 5-s time frame, which equals to a processing time of 0.04 s over a total fiber length of 18.7-km with a spatial sampling interval of 1.29 m, and is even better than the fastest single recognition reported to date. In the field test, such an MTL-enhanced sDAS system indicates excellent feature extraction performance with classification accuracy of up to 99.46% for five events and location error of ±1 m for two core-events at 8/16 different radial distances, which are much better than the DAS systems with multiclassifier and the combined single-task learning methods. Also, the MTL-enhanced sDAS shows strong robustness against environmental noises. Hence, it provides a breakthrough technology for time-efficient multitask processing in smart distributed sensors.

High spatial resolution (HSR) remote sensing image scene classification is a crucial way for land-use interpretation. However, most of the current scene classification methods assume that the training and test sets of remote sensing images follow the same feature distribution. In practical application, this assumption is difficult to guarantee. Domain adaptation (DA) is a machine learning paradigm that can effectively alleviate such problems. However, previous works mostly focused on aligning the global distribution of source domain (SD) and target domain (TD), which lose the inter-subdomain contextual relations between both domains, and ignore the redundancy among features. However, most DA methods usually only use the manually designed measurement criteria to establish the relationship between the SD and the TD, which is insufficient or complicated. In this paper, a weakly pseudo-supervised decorrelated subdomain adaptation (WPS-DSA) framework is proposed for HSR cross-domain land-use classification. In WPS-DSA, a feature extractor based on the subdomain adaptation network is used to extract the inter-subdomain characteristics of both domains. To weaken the influence of the features redundancy among remote sensing images, the switchable whitening module is introduced. In addition, a domain hierarchical sampling mechanism is designed to strengthen the connection between SD and TD in a simple way. Moreover, the WH-SH DA Dataset which is sampled from two typical Chinese cities is constructed to verify the generalization of the proposed framework. The experimental results of the cross-domain tasks on three publicly available HSR datasets and WH-SH DA Dataset display considerable performance and generalization ability of WPS-DSA.

Cardiovascular disease (CVD) is the single leading cause of global mortality and is projected to remain so. Cardiac arrhythmia is a very common type of CVD and may indicate an increased risk of stroke or sudden cardiac death. The ECG is the most widely adopted clinical tool to diagnose and assess the risk of arrhythmia. ECGs measure and display the electrical activity of the heart from the body surface. During patients' hospital visits, however, arrhythmias may not be detected on standard resting ECG machines, since the condition may not be present at that moment in time. While Holter-based portable monitoring solutions offer 24-48 h ECG recording, they lack the capability of providing any real-time feedback for the thousands of heart beats they record, which must be tediously analyzed offline. In this paper, we seek to unite the portability of Holter monitors and the real-time processing capability of state-of-the-art resting ECG machines to provide an assistive diagnosis solution using smartphones. Specifically, we developed two smartphone-based wearable CVD-detection platforms capable of performing real-time ECG acquisition and display, feature extraction, and beat classification. Furthermore, the same statistical summaries available on resting ECG machines are provided.

To date, spike sorting for neural processing in brain-computer interfaces has been performed using off-chip analysis or custom ASIC designs. In this paper, we propose and test the feasibility of performing on-chip, real-time spike sorting on a commercially available and programmable smartdust wireless sensor network mote since such a platform is currently the closest to an implantable chip due to its small size and similar physical and environmental constraints.

Brain-computer interfaces (BCIs) offer tremendous promise for improving the quality of life for disabled individuals. BCIs use spike sorting to identify the source of each neural firing. To date, spike sorting has been performed using off-chip analysis, which requires a wired connection penetrating the skull to a bulky external power/processing unit, or ASIC designs, which lack the programmability to perform different algorithms and upgrades. In this research, we propose and test the feasibility of performing on-chip, real-time spike sorting on a programmable smartdust, including feature extraction, classification, compression, and wireless transmission. A detailed power/performance trade-off analysis using DVFS is presented. Our experimental results show that the execution time and power density meet the requirements to perform real-time spike sorting and wireless transmission on a single neural channel.