Aiming at recognizing and localizing the object of novel categories by a few reference samples, few-shot object detection is a quite challenging task. Previous works often depend on the fine-tuning process to transfer their model to the novel category and rarely consider the defect of fine-tuning, resulting in many drawbacks. For example, these methods are far from satisfying in the low-shot or episode-based scenarios since the fine-tuning process in object detection requires much time and high-shot support data. To this end, this paper proposes a plug-and-play few-shot object detection (PnP-FSOD) framework that can accurately and directly detect the objects of novel categories without the fine-tuning process. To accomplish the objective, the PnP-FSOD framework contains two parallel techniques to address the core challenges in the few-shot learning, i.e., across-category task and few-annotation support. Concretely, we first propose two simple but effective meta strategies for the box classifier and RPN module to enable the across-category object detection without fine-tuning. Then, we introduce two explicit inferences into the localization process to reduce its dependence on the annotated data, including explicit localization score and semi-explicit box regression. In addition to the PnP-FSOD framework, we propose a novel one-step tuning method that can avoid the defects in fine-tuning. It is noteworthy that the proposed techniques and tuning method are based on the general object detector without other prior methods, so they are easily compatible with the existing FSOD methods. Extensive experiments show that the PnP-FSOD framework has achieved the state-of-the-art few-shot object detection performance without any tuning method. After applying the one-step tuning method, it further shows a significant lead in both efficiency, precision, and recall, under varied few-shot evaluation protocols.

We present a data-driven approach for probabilistic wind power forecasting based on conditional normalizing flow~(CNF). In contrast with the existing, this approach is distribution-free (as for non-parametric and quantile-based approaches) and can directly yield continuous probability densities, hence avoiding quantile crossing. It relies on a base distribution and a set of bijective mappings. Both the shape parameters of the base distribution and the bijective mappings are approximated with neural networks. Spline-based conditional normalizing flow is considered owing to its universal approximation capability. Over the training phase, the model sequentially maps input examples onto samples of base distribution, where parameters are estimated through maximum likelihood. To issue probabilistic forecasts, one eventually map samples of the base distribution into samples of a desired distribution. Case studies based on open datasets validate the effectiveness of the proposed model, and allows us to discuss its advantages and caveats with respect to the state of the art. Code will be released upon publication.

Linear regression can be applied to time series data to extract model parameters such as the effective force and friction constant matrices of the system. Even highly nonlinear systems can be analyzed by linear regression, if the total amount of data is broken up into shorter “time windows”, so that the dynamics is considered to be piece-wise linear. Traditionally, linear regression has been performed on the equation of motion itself (which approach we refer to as LRX). There has been surprisingly little published on the accuracy and reliability of LRX as applied to time series data. Here we show that linear regression can also be applied to the time correlation function of the dynamical observables (which approach we refer to as LRC), and that this approach is better justified within the context of statistical physics, namely, Zwanzig-Mori theory. We test LRC against LRX on a simple system of two damped harmonic oscillators driven by Gaussian random noise. We find that LRC allows one to improve the signal to noise ratio in a way that is not possible within LRX. Linear regression using time correlation functions (LRC) thus appears to be not only better justified theoretically, but it is more accurate and more versatile than LRX.

The sudden short-circuit is considered the gold-standard parameter measurement method for wound-field synchronous machines (WFSMs) as it enables the recording of the characteristic quantities in near-to-real conditions. However, the test needs huge pieces of equipment, but even worse, it reduces the lifetime of the electrical components by up to 10 years due to the high winding overhang mechanical forces. The DC-Decay tests are low-power alternatives to obtain the characteristic quantities without damaging the machinery. To allow wider use of this method, there are a couple of challenges left that are tackled by this paper. The two main open challenges are, firstly, the number of measurements needed to reach a particular precision, and secondly, a comparison of the DC-Decay with the sudden short-circuit test to allow the validation against the gold standard. More detailed, this paper explores the main challenges associated with the practical use of the DC decay method, which is a non-conventional and detailed-level approach to characterize WFSMs. We provide replies and recommendations regarding the number of measurements, suggesting the minimum number of recorded tests needed to obtain the equivalent diagram with a given accuracy, which has been further validated with an experimental case study. Moreover, the potential enhancement and precision of the parameter identification algorithm are studied in detail. Finally, the equivalent parameters of the DC decay method are compared to the gold standard, which concludes on what the characterization means in terms of predicting accurate transient short-circuit currents for WFSMs.

Smart grid is an essential concept in the transformation of the electricity sector into an intelligent digitalized energy network that can deliver optimal energy from the source to the consumers. Smart grids being self-sufficient systems are constructed through the integration of information, telecommunication, and advanced power technologies with the existing electricity systems. Artificial Intelligence (AI) is an important technology driver in smart grids. The application of AI techniques in smart grid is becoming more apparent because the traditional modelling optimization and control techniques have their own limitations. Machine Learning (ML) being a sub-set of AI enables intelligent decision-making and response to sudden changes in the customer energy demands, unexpected disruption of power supply, sudden variations in renewable energy output or any other catastrophic events in a smart grid. This paper presents the comparison among some of the state-of-the-art ML algorithms for predicting smart grid stability. The dataset that has been selected contains results from simulations of smart grid stability. Enhanced ML algorithms such as Support Vector Machine (SVM), Logistic Regression, K-Nearest Neighbour (KNN), Naïve Bayes (NB), Decision Tree (DT), Random Forest (RF), Stochastic Gradient Descent (SGD) classifier, XGBoost and Gradient Boosting classifiers have been implemented to forecast smart grid stability. A comparative analysis among the different ML models has been performed based on the following evaluation metrics such as accuracy, precision, recall, F1-score, AUC-ROC, and AUC-PR curves. The test results that have been obtained have been quite promising with the XGBoost classifier outperforming all the other models with an accuracy of 97.5%, recall of 98.4%, precision of 97.6%, F1-score of 97.9%, AUC-ROC of 99.8% and AUC-PR of 99.9%.

A new state observer-based current balancing method for Modular Multilevel Converters with Interleaved half-bridge Sub-Modules (ISM-MMC) is presented in this paper. The developed observer allows estimating currents through interleaved half-bridge legs in each submodule of ISM-MMC basing only on arm current and submodule’s capacitor voltage measurements. Then, the interleaved current balancing control uses the estimated currents to reduce the interleaved currents imbalance caused by upstream control actions. This technique minimizes the number of required current sensors in ISM-MMC, thereby reducing the converter’s cost, weight, and volume. Capabilities of the proposed interleaved currents sensorless balancing control has been tested against standard parameter tolerances of the composing passive elements. The feasibility of the proposed method is verified by extensive simulation and experimental tests.

We present a new algorithm for coordinating the motion of multiple extruders to increase throughput in fused filament fabrication (FFF)/fused deposition modelling (FDM) additive manufacturing. Platforms based on FFF are commonly available and advantageous to several industries, but are limited by slow fabrication time and could be could be significantly improved through efficient use of multiple extruders. We propose the coordinated toolpath planning problem for systems of extruders mounted as end-effectors on robot arms with the objective of maximising utilization and avoiding collisions. Building on the idea of dependency graphs introduced in our earlier work, we develop a planning and control framework that precomputes a set of multi-layer toolpath segments from the input model and efficiently assigns them to individual extruders such that executed toolpaths are collision-free. Our method overcomes key limitations of existing methods, including utilization loss from workspace partitioning, precomputed toolpaths subject to collisions with the partially fabricated object, and wasted motion resulting from strict layer-by-layer fabrication. We report simulation results that show a major increase in utilization compared to single- and multi-extruder methods, and favorable fabrication results using commodity hardware that demonstrate the feasibility of our method in practice.

Recently, the method that learns networks layer by layer has attracted increasing interest for its ease of analysis. For the method, the main challenge lies in deriving an optimization target for each layer by inversely propagating the global target of the network. The target propagation is an ill-posed problem, due to involving the inversion of nonlinear activations from low-dimensional to high-dimensional spaces. To address the problem, the existing solution is to learn an auxiliary network to specially propagate the target. However, the network lacks stability, and moreover, it leads to higher complexity for network learning. In the letter, we show that target propagation could be achieved by modeling the network’s each layer with compressed sensing, without the need of auxiliary networks. Experiments show that the proposed method could achieve better performance than the auxiliary network-based method.

With the rapid development of intelligent vehicles and Advanced Driver-Assistance Systems (ADAS), a new trend is that mixed levels of human driver engagements will be involved in the transportation system. Therefore, necessary visual guidance for drivers is vitally important under this situation to prevent potential risks. To advance the development of visual guidance systems, we introduce a novel vision-cloud data fusion methodology, integrating camera image and Digital Twin information from the cloud to help intelligent vehicles make better decisions. Target vehicle bounding box is drawn and matched with the help of the object detector (running on the ego-vehicle) and position information (received from the cloud). The best matching result, a 79.2% accuracy under 0.7 intersection over union threshold, is obtained with depth images served as an additional feature source. A case study on lane change prediction is conducted to show the effectiveness of the proposed data fusion methodology. In the case study, a multi-layer perceptron algorithm is proposed with modified lane change prediction approaches. Human-in-the-loop simulation results obtained from the Unity game engine reveal that the proposed model can improve highway driving performance significantly in terms of safety, comfort, and environmental sustainability.

This paper provides a solution for a linear command governor (CG) that employs invariant and constraint-admissible ellipsoid. The motivation is to substitute the typical polyhedral set used in almost all CG schemes with the ellipsoidal one, which is much easier to construct. However the price for this offline computational efficiency is that the size of the feasible set can be relatively small, and the online computational burden is heavier than that of polyhedral set based CGs. The proposed solution overcomes these two weaknesses and offers a very attractive alternative to polyhedral set based CG. Two numerical examples with comparison to earlier solutions from the literature illustrate the effectiveness of the proposed algorithm.

Qualitative research experiment to gather descriptive data on the NEAT algorithm's performance in an environment with variability. Individual research performed for my AP Research paper. The experiment was conducted using Python and the NEAT-Python library. The research conducted was for the sake of doing research in the field of AI in computer science and is rather outdated.

This paper shows that using synthetic images for violence detection is a feasible option for training deep models, they aid in quick convergence and perform better.

This brief proposes a low power mixed-signal foreground calibration algorithm of a pipeline ADC, using a digitally controlled re-configurable switched capacitor multiplying DAC (MDAC) gain controller. The proposed calibration technique forces the front-end stage MDAC gain towards its ideal value to achieve the ideal ADC output linearity. In this paper, a feedback mechanism has been employed to nullify the effect of change in MDAC gain from its ideal value by sensing a digital backend unit response. The proposed technique has been verified in 0.18 um CMOS process using the cadence virtuoso tool by simulating an 11- bit pipeline ADC which contains a 1.5-bit nonideal pipeline stage followed by a 10-bit linear back-end ADC (BE-ADC). Simulation results demonstrate the recovery of the lost linearity of a 11 bit pipeline ADC post calibration.

Development of transistors for advanced low noise amplifiers requires better understanding of mechanisms governing the charge carrier transport in correlation with the noise performance. In this paper, we report on study of the carrier velocity in InGaAs/InP high-electron-mobility transistors (HEMTs) found via geometrical magnetoresistance in the wide range of the drain fields, up to 2 kV/cm, at cryogenic temperature of 2 K. We observed, for the first time experimentally, the velocity peaks with peak velocity and corresponding field decreasing significantly with the transverse field. The low-field mobility and peak velocity are found to be up to 65000 cm2/Vs and 1.2x106 cm/s, respectively. Extrapolations to the lower transverse fields show that the peak velocity can be as high as 2.7x107 cm/s. The corresponding intrinsic transit frequency can be up to 172 GHz at the gate length of 250 nm. We demonstrated, for the first time, that the low-field mobility and peak velocity reveal opposite dependencies on the transverse field, indicating the difference in carrier transport mechanisms dominating at low- and high-fields. Therefore, the peak velocity is an appropriate parameter for characterization and development of the low noise HEMTs, complementary to the low-field mobility. The results of the research clarify the ways of the further development of the HEMTs for advanced applications.

The cellular internet-of-things wireless network is a promising solution to provide massive connectivity for machine- type devices. However, designing grant-free random access (GF- RA) protocols to manage such connections is challenging, since they must operate in interference-aware scenarios with sporadic device activation patterns and a shortage of mutually orthogonal resources. Supervised machine learning models have provided efficient solutions for activity detection, non-coherent data detection, and non-orthogonal preamble design in scenarios with massive connectivity. Considering these promising results, in this paper, we develop two deep learning (DL) sparse support recovery algorithms to detect active devices in mMTC random access. The DL algorithms, developed to deploy GF-RA protocols, are based on the deep multilayer perceptron and the convolutional neural network models. Unlike previous works, we investigate the impact of the type of sequences for preamble design on the activity detection accuracy. Our results reveal that preambles based on the Zadoff-Chu sequences, which present good correlation properties, achieve better activity detection accuracy with the proposed algorithms than random sequences. Besides, we demonstrate that our DL algorithms achieve activity detection accuracy comparable to state-of-the-art techniques with extremely low computational complexity.

Unsupervised blind motion deblurring is still a challenging topic due to the inherent ill-posed properties, and lacking of paired data and accurate quality assessment method. Besides, virtually all the current studies suffer from large chromatic aberration between the latent and original images, which will directly cause the loss of image details. However, how to model and quantify the chromatic aberration appropriately are difficult issues urgent to be solved. In this paper, we propose a general unsupervised color retention network termed CRNet for blind motion deblurring, which can be easily extended to other tasks suffering from chromatic aberration. New concepts of blur offset estimation and adaptive blur correction are introduced, so that more detailed information can be retained to improve the deblurring task. Specifically, CRNet firstly learns a mapping from the blurry image to motion offset, rather than directly from the blurry image to latent image as previous work. With obtained motion offset, an adaptive blur correction operation is then performed on the original blurry image to obtain the latent image, thereby retaining the color information of image to the greatest extent. A new pyramid global blur feature perception module is also designed to further retain the color information and extract more blur information. To assess the color retention ability for image deblurring, we present a new chromatic aberration quantization metric termed Color-Sensitive Error (CSE) in line with human perception, which can be applied to both the cases with/without paired data. Extensive experiments demonstrated the effectiveness of our CRNet for the color retention in unsupervised deblurring.

Accepted and published version of this work can be accessed by  https://doi.org/10.1016/j.sna.2022.113752 . This paper introduces a new method for improved  integrated angle sensing in the foldable robot joints (hinges), using low-cost inkjet printed sensors and a novel physical intelligence based compensation approach. Silver nanoparticle angle sensors are inkjet printed on a flexible PET substrate as a hinge material and implemented as pairs of compression and tension side folding individuals into a rigid experimental setup. Resulting combined signals improved the individual sensor responses due to their compensating physical characteristics, and gave the far best performances in the existing literature in terms of linearity, sensor life-time, static and cyclic drift, hysteresis and dynamic dependency. Proposed approach is promising for eliminating the major limitations on the printed sensor use in flexible hinges and paving the way to reliable, fully soft and easy-to-fabricate all-integrated foldable robots.

A document by Sabah Suhail . Click on the document to view its contents.