A basic procedure for designing a power inductor is presented. Many papers and textbook chapters offer more sophisticated methods, but it is harder to find a clear outline of a basic design process. Studying and practicing a basic design process is useful for beginners to understand the fundamental tradeoffs in design and to build intuition. For more advanced work, the basic design process is useful as it avoids relying on assumptions that might not be valid with, for example, high-frequency loss effects that are ignored in the development of some more sophisticated methods, or that constrain other methods to narrow, specific cases. Two options are outlined: starting with a saturation constraint, and then checking the core/winding loss balance; or, starting by optimizing the core/winding loss balance, and then checking the saturation constraint.

In this paper, more emphasis has been given to develop various machine learning models using SPPCA and SUBXPCA dimensionality reduction algorithms to increase the classification accuracy. Firstly, Discrete Wavelet Transform (DWT) is applied to EEG signals for extracting the time-frequency domain features of epilepsy such as the energy of each sub-pattern, spike rhythmicity, relative spike amplitude, Dominant Frequency (DF) and Spectral Entropy (SE). The features obtained after performing DWT on an EEG signal are extensive in number, to select the prominent features and to retain their properties, correlation feature sub-pattern-based PCA (SPPCA), and cross sub-pattern correlation-based PCA (SUBXPCA) are used as a dimensionality reduction techniques. To validate the proposed work, performance evaluation parameter such as the accuracy of the time-frequency domain features from different combinations of the dataset has been compared with the latest state-of-the-art works. Simulation results show that the proposed algorithm combined with machine learning classifiers. The best accuracy of 97% for SPPCA is achieved by CatBoost and for SUBXPCA the best accuracy of 98% is achieved by random forest classifier which clearly outperformed the other related works, both in terms of accuracy and computational complexity.

This paper proposes a deep learning-based fast grasp detection method with a small dataset for robotic bin-picking. We consider the problem of grasping stacked up mechanical parts on a planar workspace using a parallel gripper. In this paper, we use a deep neural network to solve the problem with a single depth image. To reduce the computation time, we propose an edge-based algorithm to generate potential grasps. Then, a convolutional neural network (CNN) is applied to evaluate the robustness of all potential grasps for bin-picking. Finally, the proposed method ranks them and the object is grasped by using the grasp with the highest score. In bin-picking experiments, we evaluate the proposed method with a 7-DOF manipulator using textureless mechanical parts with complex shapes. The success ratio of grasping is 97%, and the average computation time of CNN inference is less than 0.23[s] on a laptop PC without a GPU array. In addition, we also confirm that the proposed method can be applied to unseen objects which are not included in the training dataset.

A major gap between few-shot and many-shot learning is the data distribution empirically observed by the model during training. In few-shot learning, the learned model can easily become over-fitted based on the biased distribution formed by only a few training examples, while the ground-truth data distribution is more accurately uncovered in many-shot learning to learn a well-generalized model. In this paper, we propose to calibrate the distribution of these few-sample classes to be more unbiased to alleviate such an over-fitting problem. The distribution calibration is achieved by transferring statistics from the classes with sufficient examples to those few-sample classes. After calibration, an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier. Extensive experiments on three datasets, miniImageNet, tieredImageNet, and CUB, show that a simple linear classifier trained using the features sampled from our calibrated distribution can outperform the state-of-the-art accuracy by a large margin. We also establish a generalization error bound for the proposed distribution-calibration-based few-shot learning, which consists of the distribution assumption error, the distribution approximation error, and the estimation error. This generalization error bound theoretically justifies the effectiveness of the proposed method.

Arabic Natural Language Processing for Qur’anic Research: A Systematic Review

This paper describes ARI robot, the social robot developed by PAL Robotics, highlights its autonomous navigation system framework using Visual SLAM and the potential of combining it with its interaction abilities to achieve safe and robust navigation in human-crowded environments.

It is a new grid scheduling algorithm that uses ratio formula for task scheduling and equal makes optimum use of available research base on criteria such as resource size, speed of communication link and so on

This is a review paper for the analysis and prediction of lung cancer drug resistance. We explore several computational methods, that can provide, biological insights for the analysis, visualization and prediction of lung cancer drug resistance.

We consider the evaluation of the Number of Degrees of Freedom (NDF) of the field radiated by square sources in the far zone. The analysis is performed by employing a Singular-Value Decomposition (SVD) of the radiation operator in the two-dimensional scalar case. To this end, we start the analysis from simple geometries like two parallel strips and angle strips where analytical results can be established. For sufficiently spaced strip sources, the NDF depends only on their total electrical length. Then results for square sources follow on the same line. Finally, the numerical investigation of the case of concentric square sources, leading to an NDF independent on the inner source, opens the way to the discussion of the NDF of a full square source. In this case, it results that it depends only on the source perimeter.

In this article, we consider the scenario where remotely sensed images are collected sequentially in temporal batches, where each batch focuses on images from a particular ecoregion, but different batches can focus on different ecoregions with distinct landscape characteristics. For such a scenario, we study the following questions: (1) How well do DL models trained in homogeneous regions perform when they are transferred to different ecoregions, (2) Does increasing the spatial coverage in the data improve model performance in a given ecoregion (even when the extra data do not come from the ecoregion), and (3) Can a landslide pixel labelling model be incrementally updated with new data, but without access to the old data and without losing performance on the old data (so that researchers can share models obtained from proprietary datasets)? We address these questions by a framework called Task-Specific Model Updates (TSMU). The goal of this framework is to continually update a (landslide) semantic segmentation model with data from new ecoregions without having to revisit data from old ecoregions and without losing performance on them. We conduct extensive experiments on four ecoregions in the United States to address the above questions and establish that data from other ecoregions can help improve the model’s performance on the original ecoregion. In other words, if one has an ecoregion of interest, one could still collect data both inside and outside that region to improve model performance on the ecoregion of interest. Furthermore, if one has many ecoregions of interest, data from all of them are needed.

With the advent of machine learning (ML) applications in daily life, the questions about liability, trust, and interpretability of their outputs are raising, especially for healthcare applications. The black-box nature of ML models is a roadblock for clinical utilization. Therefore, to gain the trust of clinicians and patients, researchers need to provide explanations of how and why the model is making a specific decision. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provide a comprehensive review of explainable and interpretable ML techniques implemented for providing the reasons behind their decisions for various healthcare applications. Along with highlighting various security, safety, and robustness challenges that hinder the trustworthiness of ML we also discussed the ethical issues of healthcare ML and describe how explainable and trustworthy ML can resolve these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

A document by Edern Ollivier . Click on the document to view its contents.

Vital sign (breathing and heartbeat) monitoring is essential for patient care and sleep disease prevention. Most current solutions are based on wearable sensors or cameras; however, the former could affect sleep quality, while the latter often present privacy concerns. To address these shortcomings, we propose Wital, a contactless vital sign monitoring system based on low-cost and widespread commercial off-the-shelf (COTS) Wi-Fi devices. There are two challenges that need to be overcome. First, the torso deformations caused by breathing/heartbeats are weak. How can such deformations be effectively captured? Second, movements such as turning over affect the accuracy of vital sign monitoring. How can such detrimental effects be avoided? For the former, we propose a non-line-of-sight (NLOS) sensing model for modeling the relationship between the energy ratio of line-of-sight (LOS) to NLOS signals and the vital sign monitoring capability using Ricean K theory and use this model to guide the system construction to better capture the deformations caused by breathing/heartbeats. For the latter, we propose a motion segmentation method based on motion regularity detection that accurately distinguishes respiration from other motions, and we remove periods that include movements such as turning over to eliminate detrimental effects. We have implemented and validated Wital on low-cost COTS devices. The experimental results demonstrate the effectiveness of Wital in monitoring vital signs.

Current deep learning approaches to linear prediction coefficient (LPC) estimation for the augmented Kalman filter (AKF) produce bias estimates, due to the use of a whitening filter. This severely degrades the perceived quality and intelligibility of enhanced speech produced by the AKF. In this paper, we propose a deep learning framework that produces clean speech and noise LPC estimates with significantly less bias than previous methods, by avoiding the use of a whitening filter. The proposed framework, called DeepLPC, jointly estimates the clean speech and noise LPC power spectra. The estimated clean speech and noise LPC power spectra are passed through the inverse Fourier transform to form autocorrelation matrices, which are then solved by the Levinson-Durbin recursion to form the LPCs and prediction error variances of the speech and noise for the AKF. The performance of DeepLPC is evaluated on the NOIZEUS and DEMAND Voice Bank datasets using subjective AB listening tests, as well as seven different objective measures (CSIG, CBAK, COVL, PESQ, STOI, SegSNR, and SI-SDR). DeepLPC is compared to six existing deep learning-based methods. Compared to other deep learning approaches to clean speech LPC estimation, DeepLPC produces a lower spectral distortion (SD) level than existing methods, confirming that it exhibits less bias. DeepLPC also produced higher objective scores than any of the competing methods (with an improvement of 0.11 for CSIG, 0.15 for CBAK, 0.14 for COVL, 0.13 for PESQ, 2.66\% for STOI, 1.11 dB for SegSNR, and 1.05 dB for SI-SDR, over the next best method). The enhanced speech produced by DeepLPC was also the most preferred by listeners. By producing less biased clean speech and noise LPC estimates, DeepLPC enables the AKF to produce enhanced speech at a higher quality and intelligibility.

The multimodal Tongue Drive System (mTDS) is an assistive technology for people with tetraplegia that provides an alternative method to interact with a computer by combining tongue control, head gesture, and speech. This multimodality is designed to facilitate the completion of complex computer tasks (e.g. drag-and-drop) that cannot be easily performed by existing uni-modal assistive technologies. Previous studies with able-bodied participants showed promising performance of the mTDS on complex tasks when compared to other input methods such as keyboard and mouse. In this three-session pilot study, the primary objective is to show the feasibility of using mTDS to facilitate human-computer interactions by asking fourteen participants with tetraplegia to complete five computer access tasks with increased level of complexity: maze navigation, center-out tapping, playing bubble shooter and peg solitaire, and sending an email. Speed and accuracy are quantified by key metrics that are found to be generally increasing from the first to third session, indicating the potential existence of a learning phase that could result in improved performance over time.

The synoptic-scale (3 - 7 days) variability is a dominant contributor to the Indian summer monsoon (ISM) seasonal precipitation. An accurate prediction of ISM precipitation by dynamical or statistical models remains a challenge. Here we show that the sea level pressure (SLP) can be used as a proxy to predict the active-break cycle as well as the genesis of low- pressure-systems (LPS), using a deep learning model, namely, convolutional long short-term memory (ConvLSTM) networks. The deep learning model is able to reliably predict the daily SLP anomalies over Central India and the Bay of Bengal at a lead time of 7 days. As the fluctuations in SLP drive the changes in the strength of the atmospheric circulation, the prediction of SLP anomalies is useful in predicting the intensity of ISM. It is demonstrated that the ConvLSTM possesses better prediction skill compared to a conventional numerical weather prediction model, indicating the usefulness of a physics guided deep learning model in medium range weather forecasting.

We demonstrate an RF photonic fractional Hilbert transformer based on an integrated Kerr micro-comb source featuring a record low free spectral range of 49 GHz. By programming and shaping the comb lines according to calculated tap weights for up to 39 wavelengths across the C-band, we achieve tunable bandwidths ranging from 1.2 to 15.3 GHz as well as variable center frequencies from baseband to 9.5 GHz, for both standard integral and arbitrary fractional orders. We experimentally characterize the RF amplitude and phase response of the tunable bandpass and lowpass Hilbert transformers with 90 and 45-degree phase shifts. The experimental results show good agreement with theory, confirming the effectiveness of our approach as a powerful way to implement standard and fractional order Hilbert transformers with broad and variable bandwidths and center frequencies, with high reconfigurability and greatly reduced size and complexity.

A network-based event-triggered control is proposed for the continuous linear system. The primary feature of the proposed event-triggered control is to broadcast the current measurements when a pre-defined condition on input error is satisfied, which can avoid the redundant control updates from the controller to the actuator. Secondly, it provides an augmented system performance by appropriate selection of design parameters. Moreover, a dynamic threshold is introduced in the triggered condition to further improve the trade-off between resource utilization and system performance.