This paper proposes a fixture-free 2D sewing system using a dual-arm manipulator, i.e., the seam lines of the top and bottom fabric parts are the same. The proposed 2D sewing system sews two stacked fabric parts together along a desired seam line printed on the top fabric part without the use of a fixture. In the proposed system, the set of aligned and stacked fabric parts is held by the end-effectors of the dual-arm manipulator in coordination. The dual-arm manipulator controls the motion of the fabric parts on the flat sewing table stitch by stitch in coordination, while keeping the manipulated fabric parts flat using the internal force applied to the set of fabric parts. A novel vision-based seam line tracking control is proposed to control the motion of the set of fabric parts along the printed seam line on the top fabric part. The convergence of the tracking error is analyzed for sewing along both straight and curved seam lines and is shown to be specified by the control parameters. Sewing experiments show that the tracking error converges to zero as analyzed. The sewing experiments also show that the newly proposed trajectory generation method, which synchronizes the coordinated motion of the manipulators and the motion of the sewing needle, is essential for achieving accurate sewing.

Explainable artificial intelligence (XAI) elucidates the decision-making process of complex AI models and is important in building trust in model predictions. XAI explanations themselves require evaluation as to accuracy and reasonableness and in the context of use of the underlying AI model. This review details the evaluation of XAI in cardiac AI applications and has found that, of the studies examined, 37% evaluated XAI quality using literature results, 11% used clinicians as domain-experts, 11% used proxies or statistical analysis, with the remaining 43% not assessing the XAI used at all. We aim to inspire additional studies within healthcare, urging researchers not only to apply XAI methods but to systematically assess the resulting explanations, as a step towards developing trustworthy and safe models.

This paper presents a comprehensive survey of Quantum Multi-Agent Reinforcement Learning (QMARL), a nascent field at the intersection of quantum computing and multi-agent systems. The survey begins by introducing the fundamentals of quantum computing, highlighting its potential to revolutionize computational capabilities. We then delve into the principles of multi-agent reinforcement learning (MARL), examining how quantum computing can enhance learning efficiency and decision-making processes in complex environments. The core of the survey focuses on the current state of QMARL, reviewing existing literature, methodologies, and case studies that demonstrate the integration of quantum algorithms with MARL frameworks. The paper also addresses the unique challenges and opportunities presented by quantum technologies in multi-agent systems, such as quantum entanglement and superposition, and their implications for agent coordination and learning dynamics. Additionally, the survey explores the practical applications of QMARL in various domains, including cybersecurity, finance, and robotics, underscoring its transformative potential. The paper concludes by identifying key research gaps and proposing future directions for the development of QMARL. This includes the need for scalable quantum algorithms, the exploration of quantum-resistant strategies in adversarial settings, and the integration of quantum principles in agent communication and collaboration. Overall, this survey serves as a foundational guide for researchers and practitioners interested in the emerging field of QMARL, offering insights into its current achievements and future possibilities.

As a machine learning approach, domain adaptation methods are widely applied in cross-scenario fault diagnosis. However, the target domain may need more annotated data, posing challenges to the performance of domain adaptation methods.

We find that traditional GNNs are not well suited to learning on utility-scale power distribution graphs due to typical attributes of power distribution systems such as: their large size and low density, their heterophilic nature, and the long paths between nodes along which information must travel. Herein we outline a novel inductive GNN architecture which has been optimized for learning on power distribution graphs and which can pass information efficiently across the graph. We also demonstrate the performance of this algorithm by applying it to ComEd’s data as part of a practical use-case, and we benchmark our algorithm’s performance on this data versus other well-known GNN architectures. Submitted to IEEE PES General Meeting 2024

Can the smart radio environment paradigm measurably enhance the performance of contemporary urban macrocells? In this study, we explore the impact of reconfigurable intelligent surfaces (RISs) on a real-world sub-6 GHz MIMO channel. A rooftop-mounted macrocell antenna has been adapted to enable frequency domain channel measurements to be ascertained. A nature-inspired beam search algorithm has been employed to maximize channel gain at user positions, revealing a potential 50% increase in channel capacity in certain circumstances. Analysis reveals, however, that the spatial characteristics of the channel can be adversely affected through the introduction of a RIS in these settings. The RIS prototype schematics, Gerber files, and source code have been made available to aid in future experimental efforts of the wireless research community.

Force/torque sensing on hand-held tools enables control of applied forces, which is often essential in both tele-robotics and remote guidance of people. However, existing force sensors are either bulky, complex, or have insufficient load rating. This paper presents a novel force sensing modality based on differential magnetic field readings in a collection of sensor modules placed around a tool or device. The instrumentation is easy to install and low profile, but nonetheless achieves good performance. A detailed mathematical model and optimization-based design procedure are also introduced. The modeling, simulation, and optimization of the force sensor are described and then used in the electrical and mechanical design and integration of the sensor into an ultrasound probe. Through a neural network-based nonlinear calibration, the sensor achieves average root-mean-square test errors of 0.41 N and 0.027 Nm compared to an off-the-shelf ATI Nano25 sensor, which are 0.80% and 1.16% of the full-scale range respectively. The sensor has an average noise power spectral density of less than 0.0001 N/sqrt(Hz), and a 95% confidence interval resolution of 0.063 N and 0.0086 Nm. The practical readout rate is 1.3 kHz over USB serial and it can also operate over Bluetooth or Wi-Fi. This sensor can enable instrumentation of manual tools to improve the performance and transparency of teleoperated or autonomous systems.

 Assisted and automated driving (AAD) systems heavily rely on data collected from perception sensors, such as cameras. While prior research has explored the quality of camera data via traditional and well-established image quality assessment (IQA) metrics (e.g. PSNR, SSIM, BRISQUE) or have considered when noisy/degraded data affects perception algorithms (e.g. deep neural network (DNN) based object detection), there are no works that approach the holistic relationship between IQA and DNN performance. This work proposes that traditional IQA metrics, designed to evaluate digital image quality according to human visual perception, can help to predict the sensor data degradation level that perception algorithms can tolerate before performance deterioration occurs. Consequently, a correlation analysis was conducted between 17 selected IQA metrics (with and without reference) and DNN average precision. The evaluated data was increasingly compressed to generate degradation and artefacts. Notably, the experimental results show that several IQA metrics had a strong positive correlation (exceeding correlation scores of 0.7) with average precision, with IW-SSIM and DSS having very high correlation (> 0.9). Interestingly, the results show that re-training BRISQUE on compressed data causes an exceptionally high positive correlation (> 0.97), making it very suitable for predicting the performance of DNN object detectors. By effectively relating traditional image quality metrics to DNN performance, this research offers a series of significant tools to understand and predict perception degradation based on the quality of data, thus resulting in a significant impact on the development of automated driving systems.Â

Ulcerative colitis is a chronic disease characterized by bleeding and ulcers in the colon. Currently, the gastroenterologist reviews the colonoscopy video to assess the disease severity using an endoscopic score. This task is time-consuming and does not consider the size and the number of lesions. Consequently, automatic detection methods were proposed enabling fine-grained assessment of lesion severity. However, they depend on the quality of the training set, and its specificity to the application context. To suit the local clinical setup, we opted for an internal training dataset containing only rough bounding box annotations around lesions. Color information is the primary indicator used by specialists to recognize the lesions. Thus, we propose to use linear models in suitable color spaces to detect lesions. We introduce an efficient sampling scheme for exploring the set of linear classifiers and removing trivial models i.e. those showing zero false negative or positive ratio. Using bounding boxes leads to ex- aggerated false negative/positive ratios due to mislabeled pixels, especially in the corners, resulting in decreased modelsâ\euro™ accuracy. Therefore, we propose to evaluate the model sensitivity on the annotation level instead of the pixel level. Our sampling strategy can eliminate up to 25% of trivial models. Despite the limited annotationsâ\euro™ quality, the detectors achieved good performance (93% specificity/89% sensitivity for bleeding and 57% specificity/83% sensitivity for ulcers). The best models exhibit low variability when tested on a small subset of endoscopic images. However, the inter-patient model performance was variable suggesting that appearance normalization is critical in this context.

This study endeavors to establish an simple, robust, and transparent forecasting framework that is easily deployable, computationally efficient, and adaptable across the various sectors constituting distributed integrated energy systems. Accordingly, a probabilistic day-ahead forecasting framework and its application are presented. A personalized standard load profile (PSLP) is then applied to electricity and heat demand, as well as PV generation. Furthermore, it is extended to incorporate a quantile personalized standard load profile employing quantile regression. Using a PCHIP interpolation, the empirical cumulative distribution function is approximated from the non-parametric approach and the probability density function derived. Furthermore, it is shown how discrete convolution can be used to determine the joint probability density function of the distributed net load. A case study was conducted at a commercial logistics facility that utilized a decentralized energy system to showcase the forecasting framework and its application for optimization in the presence of uncertainty. This involved using the net load and its probability density functions for uncertainty-based optimization.

Non-autoregressive text-to-speech (TTS) has recently received a lot of atten-tion due to its reliability and fast reasoning. Despite its outstanding achieve-ment, non-autoregressive speech synthesis still faces some critical challenges. A major issue is that non-autoregressive methods necessitate an external toolkit to align the speech with the transcript, thus substantially complicat-ing the process of building the model. Besides, non-autoregressive methods suffer from the one-to-many mapping issue, where the same transcript may correspond to speech in numerous styles. This problem may harm the ex-pressiveness of the generated speech because the model tends to provide output with an average style. To address the above issues, this paper pro-poses a cooperative learning strategy for non-autoregressive speech synthe-sis. Specifically, the suggested method employs both an autoregressive and a non-autoregressive TTS model during the training procedure. The autore-gressive model is trained as a partner at each iteration, providing essential alignment information and also the prosody embedding of the speech to the non-autoregressive model. After receiving the above useful knowledge, the non-autoregressive model can be further trained without relying on external alignment tools. Meanwhile, the prosody embedding from the autoregressive model and the pitch information from the raw audio can be utilised together to alleviate the one-to-many mapping problem. Experimental results demon-strate that our approach can produce comparable speech to the most popular FastSpeech 2 model while drastically reducing the complexity of constructing a non-autoregressive TTS model.

An accurate assessment of a mission system’s performance, called Mission Impact Assessment (MIA), can effectively identify and counteract any issues in the current system to avoid potential risks or vulnerabilities that may cause mission failure. Although the importance of MIA research has been recognized to mitigate the system’s potential risk for more than a decade, little research has shown a comprehensive MIA framework with experimental validation showing the inference performance of the MIA tools under realistic attack-defense interactions. To fill this gap, we propose an interdependent mission impact assessment (MIA), called iMIA, that can adequately capture the inter-relationships of the key components in a mission system and environment and accurately infer a mission outcome (i.e., success or failure) under uncertainty.  In the proposed iMIA, we first consider Subjective Bayesian Networks to evaluate how successfully a given system introduces impacts on mission success under uncertainty due to a lack of evidence.  In addition, we consider strategic attack-defense interactions based on a hypergame theory in which the attacker and defender can take actions under their perceived uncertainty.  Our extensive experiments showed the outperformance of our proposed MIA up to 70% and 25% over the performance of the baseline and the state-of-the-art Bayesian Network-based counterparts, respectively, in terms of inference accuracy in mission performance (e.g., mission outcomes, such as mission success or failure).  We also provide in-depth sensitivity analyses to identify the key system components that should be considered more carefully to avoid mission failure.

This study presents design guidelines for a high-k dielectric Superjunction Schottky barrier diode (SBD) to further enhance the already impressive unipolar power figure of merit (PFOM) of Ultra-wide bandgap (UWBG) materials. We employed analytical modeling to optimize the device parameters, accounting for the appropriate dielectric and semiconductor dimensions including the aspect ratio and the dielectric constant of the highk material. Our findings reveal that device performance is intimately linked to structural dimensions and the dielectric constant of the insulator. Specifically, we observed that the dielectric superjunction SBD exhibits behavior akin to a conventional SBD, where the effective doping density in the drift layer decreases by a factor dependent on semiconductor and dielectric width, aspect ratio and the dielectric constant of the insulator. We discuss optimal design guidelines for achieving a 10 kV β-Ga2O3 SBD with a PFOM of 50 GW/cm2, a significant improvement over the conventional unipolar PFOM of 34 GW/cm2 for β-Ga2O3. Additionally, we conducted a comparative analysis of the switching energies between the superjunction Schottky barrier diode and a conventional Schottky barrier diode.We provide design guidelines to minimize switching energies for a desired PFOM in β-Ga2O3 SBDs. This underscores the immense potential of such structures in advancing vertical power electronics to unprecedented levels of performance.

With the continuous evolution of wireless communication and the explosive growth in data traffic, decentralized spectrum sensing has become essential for the optimal utilization of wireless resources. In this direction, we propose an over-the-air aggregation-based Federated Learning (FL) for a technology recognition model that can identify signals from multiple Radio Access Technologies (RATs), including Wi-Fi, Long Term Evolution (LTE), 5G New Radio (NR), Cellular Vehicle-to-Everything PC5 (C-V2X PC5), and Intelligent Transport Systems G5 (ITS-G5). In the proposed FL-based technology recognition framework, we consider edge network elements as clients to train local models and a central server to create the global model. In each client, a Convolutional Neural Network (CNN)-based model is trained from Inphase and Quadrature (IQ) samples collected from a certain combination of RATs. The possible combination of RATs considered in the clients is selected based on the capabilities of the real-world network elements that can be used as a client. The FL framework involves a process where multiple clients periodically send updates derived from local data to a central server, which then integrates these contributions to enhance a shared global model. This method ensures that the system stays current with the evolving real-world environment while also minimizing bandwidth required for training data transfer and allowing for the maintenance of personalized local models on each clientâ\euro™s end.

Intelligent control technology and intelligent information integration technology are the two core technologies of intelligent control system. In this paper, intelligent control and intelligent system are studied from two perspectives: multi-agent integration and neural network intelligent control technology. The multi-agent oriented research aims to provide an architecture suitable for information integration of distributed intelligent control systems. The research of neural network aims to deeply study the theory and technology of neural control, an important branch of intelligent control. The main conclusions of this paper are as follows: In the aspect of multi-layer forward neural network learning algorithm, the weight learning and structure learning methods of multi-layer forward neural network are studied. A heuristic genetic algorithm for sample division and a composite structure learning method are proposed. The sample division heuristic genetic algorithm uses the sample division method to construct the initial genetic population, and combines the subspace division for heuristic search. Several algebraic properties of sample set classes and their training are presented and proved.

The paper aims to try to push the current conecpt about reduced switch count Multi-level inverter (RSC-MLI) for battery sotage systems. They can be used to reduce the count of Mosefts used in Home storage systems(HSS); However, it would require precise Voltage measuring instruments and a complexer code to control the switching of Mosfets. To smooth the on /off step function, one can also use an inductor. The research sparked interest during Covid phase when the prices of certain Mosfets increased 20 folds.Â

To assess the performance of orthomode transducers (OMTs), the back-to-back (BTB) configuration is analyzed in simple fundamentals for accurate results and clear physical insight. The axial rotation of an OMT in the BTB measurement setup is investigated, and clear facts are highlighted. Furthermore, terminating OMTâ\euro™s Common Port with a short circuit load is proposed as a low-cost and accurate evaluation technique based on detailed analysis. The presented techniques have the advantage of using only power measurements without anechoic chambers. A full-wave simulation of a published OMT operating at V-band (55 - 65) GHz is used to validate these analyses.

We report a dual-polarization radio frequency (RF) channelizer based on microcombs. With the tailored mismatch between the FSRs of the active and passive MRRs, wideband RF spectra can be channelized into multiple segments featuring digital-compatible bandwidths via the Vernier effect. Due to the use of dual-polarization states, the number of channelized spectral segments, and thus the RF instantaneous bandwidth (with a certain spectral resolution), can be doubled. In our experiments, we used 20 microcomb lines with ~ 49 GHz FSR to achieve 20 channels for each polarization, with high RF spectra slicing resolutions at 144 MHz (TE) and 163 MHz (TM), respectively; achieving an instantaneous RF operation bandwidth of 3.1 GHz (TE) and 2.2 GHz (TM). Our approach paves the path towards monolithically integrated photonic RF receivers (the key componentsâ\euro”active and passive MRRs are all fabricated on the same platform) with reduced complexity, size, and unprecedented performance, which is important for wide RF applications with digital-compatible signal detection.