Diffuse optical tomography (DOT) leverages near-infrared light propagation through tissue to assess its optical properties and identify abnormalities. DOT image reconstruction is an ill-posed problem due to the highly scattered photons in the medium and the smaller number of measurements compared to the number of unknowns. Limited-angle DOT reduces probe complexity at the cost of increased reconstruction complexity. Reconstructions are thus commonly marred by artifacts and, as a result, it is difficult to obtain an accurate reconstruction of target objects, e.g., malignant lesions. Reconstruction does not always ensure good localization of small lesions. Furthermore, conventional optimization-based reconstruction methods are computationally expensive, rendering them too slow for real-time imaging applications. Our goal is to develop a fast and accurate image reconstruction method using deep learning, where multitask learning ensures accurate lesion localization in addition to improved reconstruction. We apply spatial-wise attention and a distance transform based loss function in a novel multitask learning formulation to improve localization and reconstruction compared to single-task optimized methods. Given the scarcity of real-world sensor-image pairs required for training supervised deep learning models, we leverage physics-based simulation to generate synthetic datasets and use a transfer learning module to align the sensor domain distribution between in silico and real-world data, while taking advantage of cross-domain learning. Applying our method, we find that we can reconstruct and localize lesions faithfully while allowing real-time reconstruction. We also demonstrate that the present algorithm can reconstruct multiple cancer lesions. The results demonstrate that multitask learning provides sharper and more accurate reconstruction.

In this paper, a new switched-mode bidirectional bridgeless AC/DC converter, operating in the discontinuous conduction mode (DCM), for automotive energy harvesting is presented. The simple topology consisting of common source n-MOSFETs allows for direct AC/DC conversion, minimum auxiliary circuits and simple gating patterns, when compared to other AC/DC converters proposed in the literatures. The circuit operation is analyzed and shown that the converter-battery topology can operate as a synthesized variable resistor with regenerative functionality. The circuit is designed for low-power energy harvesting applications; for example, regenerating dissipated power in a vehicle suspension damper by converting vibrational energy into battery charge. Simulation results including various switching waveforms and power conversion efficiency are presented to demonstrate performance of the proposed converter. Experimental results, including power conversion efficiency and resistance synthesis sweep, by connecting the proposed converter to a regenerative vehicle suspension prototype are also included.

This paper proposes a mechatronic suspension system with capabilities of energy regeneration and sky- hook (SK) control incorporated into the mechanism. The system overcomes the tradeoffs between energy consumption and ride comfort in an active suspension system. Central to the concept is development of a coupled switched-mode rectifier (SMR) capable of providing either a positive or negative damping ratio by alternating between regenerative and motoring modes. Using the proposed circuit, an active sky-hook control strategy is utilized to offer continuous damping force that improves the vibration isolation significantly. Simulation results presented demonstrate the directions of power flow in both regenerating and motoring modes to verify performance of the SMR.

The detection of the onset of damage in gear systems is of great importance to industry. In this paper, a new neuro-fuzzy diagnostic system is developed, whereby the strengths of three robust signal processing techniques are integrated. The adopted techniques are: the continuous wavelet transform (amplitude) and beta kurtosis based on the overall residual signal, and the phase modulation by employing the signal average. Three reference functions are proposed as post-processing techniques to enhance the feature characteristics in a way that increases the accuracy of fault detection. Monitoring indexes are derived to facilitate the automatic diagnoses. A constrained-gradient-reliability algorithm is developed to train the fuzzy membership function parameters and rule weights, while the required fuzzy completeness is retained. The system output is set to different monitoring levels by using an optimization procedure to facilitate the decision-making process. The test results demonstrate that the novel neuro-fuzzy system, because of its adaptability and robustness, significantly improves the diagnostic accuracy. It outperforms other related classifiers, such as those based on fuzzy logic and neuro-fuzzy schemes, which adopt different types of rule weights and employ different training algorithms.

Unique phenomena that can arise in linear and nonlinear systems that are dynamically and/or statically coupled have been utilised for vibration suppression. In the linear case, static coupling is established between the oscillatory modes of a plant with a single input and a series of second order controllers. The controlled system is characterised by a plant response that approaches the desired state at the rate of a cosine function. In this investigation the single-degree-of freedom coupling control theory is extended to suppress disturbance induced oscillations of a single flexible link. The suppression action is achieved using the hybrid control method which was developed to supply the suppression action, especially for the multidegree-of freedom case. The resulting control algorithm is implemented experimentally.>