Search for: All records

We report threshold voltage (V_TH) control in ultrawide bandgap Al_0.4Ga_0.6N-channel metal oxide semiconductor heterostructure field-effect transistors using a high-temperature (300 °C) anneal of the high-kZrO₂gate-insulator. Annealing switched the polarity of the fixed charges at the ZrO₂/AlGaN interface from +5.5 × 10¹³cm⁻²to −4.2 × 10¹³cm⁻², pinningV_THat ∼ (−12 V), reducing gate leakage by ∼10³, and improving subthreshold swing 2× (116 mV decade⁻¹). It also enabled the gate to repeatedly withstand voltages from −40 to +18 V, allowing the channel to be overdriven doubling the peak currents to ∼0.5 A mm⁻¹.

 

Missing data is a very common challenge in health monitoring systems and one reason for that is that they are largely dependent on different types of sensors. A critical characteristic of the sensor-based prediction systems is their dependency on hardware, which is prone to physical limitations that add another layer of complexity to the algorithmic component of the system. For instance, it might not be realistic to assume that the prediction model has access to all sensors at all times. This can happen in the real-world setup if one or more sensors on a device malfunction or temporarily have to be disabled due to power limitations. The consequence of such a scenario is that the model faces ``missing input data'' from those unavailable sensors at the deployment time, and as a result, the quality of prediction can degrade significantly. While the missing input data is a very well-known problem, to the best of our knowledge, no study has been done to efficiently minimize the performance drop when one or more sensors may be unavailable for a significant amount of time. The sensor failure problem investigated in this paper can be viewed as a spatial missing data problem, which has not been explored to date. In this work, we show that the naive known methods of dealing with missing input data such as zero-filling or mean-filling are not suitable for sensor-based prediction and we propose an algorithm that can reconstruct the missing input data for unavailable sensors. Moreover, we show that on the MobiAct, MotionSense, and MHEALTH activity classification benchmarks, our proposed method can outperform the baselines by large accuracy margins of 8.2%, 15.1%, and 11.6%, respectively. 

Physical activity is a cornerstone of chronic conditions and one of the most critical factors in reducing the risks of cardiovascular diseases, the leading cause of death in the United States. App-based lifestyle interventions have been utilized to promote physical activity in people with or at risk for chronic conditions. However, these mHealth tools have remained largely static and do not adapt to the changing behavior of the user. In a step toward designing adaptive interventions, we propose BeWell24Plus, a framework for monitoring activity and user engagement and developing computational models for outcome prediction and intervention design. In particular, we focus on devising algorithms that combine data about physical activity and engagement with the app to predict future physical activity performance. Knowing in advance how active a person is going to be in the next day can help with designing adaptive interventions that help individuals achieve their physical activity goals. Our technique combines the recent history of a person's physical activity with app engagement metrics such as when, how often, and for how long the app was used to forecast the near future's activity. We formulate the problem of multimodal activity forecasting and propose an LSTM-based realization of our proposed model architecture, which estimates physical activity outcomes in advance by examining the history of app usage and physical activity of the user. We demonstrate the effectiveness of our forecasting approach using data collected with 58 prediabetic people in a 9-month user study. We show that our multimodal forecasting approach outperforms single-modality forecasting by 2.2$ to 11.1% in mean-absolute-error. 

The Current practice of air-fuel ratio control relies on empirical models and traditional PID controllers, which require extensive calibration to maintain the post-catalyst air-fuel ratio close to stoichiometry. In contrast, this work utilizes a physics-based Three-Way Catalyst (TWC) model to develop a model predictive control (MPC) strategy for air-fuel ratio control based on internal TWC oxygen storage dynamics. In this paper, parameters of the physics-based temperature and oxygen storage models of the TWC are identified using vehicle test data for a catalyst aged to 150,000 miles. A linearized oxygen storage model is then developed from the identified nonlinear model, which is shown via simulation to follow the nonlinear model with minimal error during nominal operation. This motivates the development of a Linear MPC (LMPC) framework using the linearized TWC oxygen storage model, reducing the requisite computational effort relative to a nonlinear MPC strategy. In this work, the LMPC utilizing a linearized physics-based TWC model is proven suitable for tracking a desired oxygen storage level by controlling the commanded engine air-fuel ratio, which is also a novel contribution. The offline simulation results show successful tracking performance of the developed LMPC framework. 

Background: Long non-coding RNA plays a vital role in changing the expression profiles of various target genes that lead to cancer development. Thus, identifying prognostic lncRNAs related to different cancers might help in developing cancer therapy. Method: To discover the critical lncRNAs that can identify the origin of different cancers, we propose the use of the state-of-the-art deep learning algorithm concrete autoencoder (CAE) in an unsupervised setting, which efficiently identifies a subset of the most informative features. However, CAE does not identify reproducible features in different runs due to its stochastic nature. We thus propose a multi-run CAE (mrCAE) to identify a stable set of features to address this issue. The assumption is that a feature appearing in multiple runs carries more meaningful information about the data under consideration. The genome-wide lncRNA expression profiles of 12 different types of cancers, with a total of 4768 samples available in The Cancer Genome Atlas (TCGA), were analyzed to discover the key lncRNAs. The lncRNAs identified by multiple runs of CAE were added to a final list of key lncRNAs that are capable of identifying 12 different cancers. Results: Our results showed that mrCAE performs better in feature selection than single-run CAE, standard autoencoder (AE), and other state-of-the-art feature selection techniques. This study revealed a set of top-ranking 128 lncRNAs that could identify the origin of 12 different cancers with an accuracy of 95%. Survival analysis showed that 76 of 128 lncRNAs have the prognostic capability to differentiate high- and low-risk groups of patients with different cancers. Conclusion: The proposed mrCAE, which selects actual features, outperformed the AE even though it selects the latent or pseudo-features. By selecting actual features instead of pseudo-features, mrCAE can be valuable for precision medicine. The identified prognostic lncRNAs can be further studied to develop therapies for different cancers.