This letter provides a simulation study on calibration of a 3D LiDAR with respect to a camera, with point-topoint and point-on-plane correspondences for calibration constraints, by extending our previously proposed 2D LiDAR calibration methods. The calibration performance is examined in terms of vertical scan view and resolution, especially in narrow/sparse scan space, in the presence of sensor noise. It contributes to a guidance on a use of various sensors and dataset depending on contexts and applications with different scan view and resolution, and an understanding of the effect of the different constraints on calibration. As a result, the combination of the point and plane constraints yields better performance than either of them.

Spatial synchronization in roadside scenarios is essential for integrating data from multiple sensors at different locations. Current methods using cascading spatial transformation (CST) often lead to cumulative errors in large-scale deployments. Manual camera calibration is insufficient and requires extensive manual work, and existing methods are limited to controlled or single-view scenarios. To address these challenges, our research introduces a parallel spatial transformation (PST)-based framework for large-scale, multi-view, multi-sensor scenarios. PST parallelizes sensor coordinate system transformation, reducing cumulative errors. We incorporate deep learning for precise roadside monocular global localization, reducing manual work. Additionally, we use geolocation cues and an optimization algorithm for improved synchronization accuracy. Our framework has been tested in real-world scenarios, outperforming CST-based methods. It significantly enhances large-scale roadside multi-perspective, multi-sensor spatial synchronization, reducing deployment costs.

 In this paper, we delve into the historical and enduring algebraic conundrum known as the Two Couriers Problem, originally posed by the French mathematician Clairaut in 1746. Over the centuries, this problem has persisted, finding its way into numerous textbooks, journals, and mathematical discussions. One of the remarkable aspects of the Two Couriers Problem is its inherent connection to division by zero, a mathematical operation that has intrigued scholars for generations. Division by zero, a concept laden with complexity and ambiguity, has sparked diverse mathematical approaches. Conventional mathematics regards division by zero as an indeterminate or undefined result. However, alternative methodologies have emerged over time. Transmathematics defines division by zero as either nullity or explicitly positive or negative infinity, offering a different perspective. Saitoh simplifies division by zero as zero, challenging traditional conventions, while Barukˇci´c explores the possibility of defining it as either unity or explicitly positive or implicitly negative infinity. Amidst these varied approaches, the central question persists: which method offers the most effective solution to the enigma of division by zero? To answer this question, we propose utilizing the Two Couriers Problem as an objective benchmark. By subjecting these different mathematical approaches to this historical problem, we aim to rigorously evaluate their efficacy and determine which one stands out as the most viable solution. This paper seeks to unravel the complexities of division by zero through a systematic analysis, utilizing the Two Couriers Problem as a guiding light. By doing so, we endeavor to shed new insights on this age-old mathematical puzzle and contribute valuable perspectives to the ongoing discourse surrounding division by zero and its diverse interpretationÂ

The high penetration and uneven distribution of single-phase rooftop PVs and load demands in power systems may lead to unbalanced active powers, adversely impacting power quality and system reliability. This paper introduces a strategy based on multi-agent deep reinforcement learning to address these unbalanced active powers. The approach involves deploying single-phase battery systems throughout the LV residential distribution system, subsidized by the utility. Initially, the unbalanced active powers are framed as a Markov game, which is then addressed using a multi-agent deep deterministic policy gradient algorithm. The strategy relies on local measurements, with agents' experiences centrally shared during training for cooperative tasks. Notably, information about the phase connections of the battery systems becomes unnecessary. The strategy learns from historical data, gradually mastering the process. Real data from rooftop PVs and demands in a four-wire LV residential distribution system validate the effectiveness of the proposed approach. Acting as adaptive agents, the battery systems collaboratively operate by adjusting active powers to minimize neutral current at the point of common connection.

The combination of Deep Learning techniques and Raman spectroscopy shows great potential offering precise and prompt identification of pathogenic bacteria in clinical settings. However, the traditional closed-set classification approaches assume that all test samples belong to one of the known pathogens, and their applicability is limited since the clinical environment is inherently unpredictable and dynamic, unknown or emerging pathogens may not be included in the available catalogs. We demonstrate that the current state-of-the-art Neural Networks identifying pathogens through Raman spectra are vulnerable to unknown inputs, resulting in an uncontrollable false positive rate. To address this issue, first, we developed a novel ensemble of ResNet architectures combined with the attention mechanism which outperforms existing closed-world methods, achieving an accuracy of 87.8±0.1% compared to the best available modelâ\euro™s accuracy of 86.7 ± 0.4%. Second, through the integration of feature regularization by the Objectosphere loss function, our model achieves both high accuracy in identifying known pathogens from the catalog and effectively separates unknown samples drastically reducing the false positive rate. Finally, the proposed feature regularization method during training significantly enhances the performance of out-ofdistribution detectors during the inference phase improving the reliability of the detection of unknown classes. Our novel algorithm for Raman spectroscopy enables the detection of unknown, uncatalogued, and emerging pathogens providing the flexibility to adapt to future pathogens that may emerge, and has the potential to improve the reliability of Raman-based solutions in dynamic operating environments where accuracy is critical, such as public safety applications.Â

The minimum noise figure of an electrical amplifier is Fe=1. E. Desurvire's traditional optical noise Fpnf of an optical amplifier has the minimum value Fpnf=2. If Fpnf is a noise figure then power, gain and Fe need to be redefined. Fpnf is in conflict with physics and Fe. The correct optical noise figure Fo,IQ, observable in coherent I&Q receivers, has the minimum Fo,IQ=1 and is compatible with Fe. In the derivation of the consistent unified noise figure FIQ for all frequencies, from Fe and Fo,IQ, thermal noise energy is needed. Its usual simplified expression kT is now replaced by Nyquist's correct result. This holds also in a unified homodyne noise figure FI, against which H. Haus' unified noise figure Ffas is discussed.

Hate speech targets different social groups such as race and gender, and poses a significant threat to social harmony. Researchers are increasingly motivated to devise efficient techniques to improve automatic hate speech detection on social media platforms. However, current models are usually evaluated without considering hate speech targets and fail when the targets are unseen in the training data. In this study, we examine target (domain) shifts of hate speech and propose, \emph{Tad}, an adaptation framework for neural models that adopts domain-aware networks to improve cross-domain hate speech detection. Tad features a hate knowledge lexicon infusion network, a domain-specific network, and a weighting network. We demonstrate that incorporating Tad improves the performance of leading neural models in hate speech detection when tested on unseen domains. Specifically, Tad yields improvements of up to 8$.1\%$ and an average of $2.4\%$ in macro F1-scores. Moreover, we identify data quality and quantity as vital factors to address performance gaps between models tested on seen and unseen domains. Our results reveal that excessive knowledge infusion may result in a decrease in performance such as for \textsl{Religion}. In addition, we find trade-offs in cross-domain hate speech detection. For example, weighted loss for heavily imbalanced data generally improves performance.

In this paper, an robot parallel evolution design algorithm is proposed, based on the idea of module network, and the learning method is verified and tested as well. The learning method of collision avoidance, approach and wall switching behavior of evolutionary robots based on neural network method is optimized. The evolutionary robot can autonomously realize the behaviors of collision avoidance, movement, replication and attack. In the simulation environment of this paper, the obstacles in the environment are represented by a randomly generated rectangular region with the largest side length. The shape and location of obstacles are evenly distributed. The simulated environment has an approach target but no obstacles, and these approach targets are placed randomly and scattered in the environment. The formation of behavior is integrated with basic behaviors such as collision avoidance and approach, so that the robot is gradually enhanced based on the growth of neural network.

This paper introduces the Subspace Rotation Algorithm (SRA) for training the Restricted Hopfield Network (RHN) as an auto-associative memory. SRA is a gradient-free subspace tracking method based on Singular Value Decomposition (SVD) to update the weight matrix. Despite having slightly worse time complexity than Back-propagation (BP) theoretically, in practice, SRA completes training faster since it requires fewer iterations to converge. Comparative analysis with BP for training RHN reveals that SRA consistently reaches the optimal solution, whereas BP fails to achieve comparable performance if the weight initialization is not within the appropriate basin of attraction. Experiments involving the memorization of 10, 50, and 100 patterns from the MNIST dataset show that RHN trained with SRA exhibits better robustness to noisy and corrupted patterns compared to RHN trained with BP. These findings suggest that SRA offers a more reliable and effective method for training RHNs in applications needing high tolerance to input distortions.

Coded aperture snapshot spectral imager (CASSI) can recover three-dimensional hyperspectral images (HSIs) from two-dimensional compressive measurements. Recently, deep unfolding approaches were shown impressive reconstruction performance among various algorithms. Existing deep unfolding methods usually employ linear projection methods to guide the iterative learning process. However, the linear projections do not include trainable parameters and ignore the essential characteristics of HSI. This paper proposes a novel learning-based deep estimation-enhancement unfolding (DEEU) framework to improve the HSI reconstruction. The deep estimation-enhancement (DEE) module is used to guide the iterative learning process of the network based on the prior information of the CASSI system, and then exploits the intrinsic features of the reconstructed HSI in both spectral and spatial dimensions. In addition, a multi-prior ensemble learning module is proposed to further improve the reconstruction performance without increasing runtime. As with most of deep unfolding methods, we plug a convolutional neural network as a denoiser in each stage of the DEEU framework, which finally forms the proposed DEEU-Net. Comprehensive experiments on both simulation and real datasets demonstrate that the effectiveness of our DEEU framework, and our DEEU-Net can achieve both high reconstruction quality and speed, outperforming the state-of-the-art methods.

The Cognitive Agents and Interaction Lab (CAIL) at the University of Dhaka has strategically developed a focused High-Performance Computing (HPC) facility, underpinning its niche in artificial intelligence (AI) research, with a special emphasis â\euro” but not limited to â\euro” deep and reinforcement learning within the context of multi-agent systems. This technical report outlines the HPC resources at CAIL, highlighting a number of advanced GPUs that drive our research forward. The facility, supported by multiple grants, exemplifies a model for small-scale, high-impact computational research environments. We detail how these resources empower our team to achieve significant strides in AI, despite the challenges of scale, and set a precedent for innovation in the field.

This paper explores the experimental localization of single and multiple ground RF transmitters using both traditional localization and machine learning algorithms. For the localization of a single transmitter, the setup is evaluated in two unlicensed frequency bands with and without interference. A threshold approach is proposed to improve accuracy in the presence of interference. To localize multiple transmitters, the RSSI data are divided into clusters by a k-means clustering algorithm and fed into a localization algorithm. These experimental results are preceded by an analysis phase where the UAV flight path and data collection are simulated using the QuaDRiGa channel model.

Most single image super resolution (SISR) methods are developed on synthetic low resolution (LR) and  high resolution (HR) image pairs, which are simulated by a  predetermined degradation operation, such as bicubic  downsampling. However, these methods only learn the  inverse process of the predetermined operation, which fails to super resolve the real-world LR images, whose true  formulation deviates from the predetermined operation. To  address this, we propose a novel SR framework named  hardware-aware super-resolution (HASR) network that first extracts hardware information, particularly the camera degradation information. The LR images are then super resolved by integrating the extracted information. To  evaluate the performance of HASR network, we build a dataset named Real-Micron from real-world micron-scale  patterns. The paired LR and HR images are captured by  changing the objectives and registered using a developed  registration algorithm. Transfer learning is implemented  during the training of Real-Micron dataset due to the lack  of amount of data. Experiments demonstrate that by  integrating the degradation information, our proposed  network achieves state-of-the-art performance for the blind  SR task on both synthetic and real-world datasets. Impact Statementâ\euro” The proposed HASR method has  significant impact on various areas, such as enhancing the  accurate inspection of manufactured products for quality  control and enhancing the resolution of medical images to  enable more accurate diagnosis and healthcare. Current SR solutions neglect the uniqueness of each imaging system,  hence cannot produce accurate HR images across the  different systems. Taking advantage of the known hardware information, HASR can differentiate low?resolution images across different imaging systems and  produce HR images that are closer to the real-world  scenario. Given sufficient training images, the proposed  HASR method can overcome the physical optical limitation  and generate higher quality images. The proposed method  improves the overall performance by about 0.2 dB and 0.5  dB on the synthetic and the real-world datasets,  respectively. Â

On-chip integration of two-dimensional (2D) materials with unique structures and distinctive properties endow integrated devices with new functionalities and improved performance. With a high flexibility in modifying its properties and a strong compatibility with various integrated platforms, graphene oxide (GO) becomes an attractive 2D material for implementing functional hybrid integrated devices. Here, we demonstrate novel functionalities that go beyond the capabilities of conventional photonic integrated circuits, by harnessing the photo-thermal effects in 2D GO films integrated onto them. These include all-optical control and switching, optical power limiting, and non-reciprocal light transmission. The 2D layered GO films are on-chip integrated with precise control of their thicknesses and sizes. Benefitting from the broadband response of 2D GO films, all the three functionalities feature a very wide operational bandwidth. By fitting the experimental results with theory, we also extract the changes in material properties induced by the photo-thermal effects, which reveal interesting insights about 2D GO films. These results highlight the versatility of 2D GO films in implementing functional integrated photonic devices for a range of applications.Â

This paper addresses the distributed optimal coordination problem for a network of heterogeneous agents. To the best of our knowledge, few works where the control design requires no information regarding agents dynamics can be found in the literature. Compared to these works in which agents are only allowed to be of relative degree one, this paper extends the results for networks that are mixtures of agents with different relative degrees. The main goal is that all agents' outputs globally converge to the minimizer of the global cost function. We introduce a novel distributed two-layer control policy to do so. The top layer searches for the minimizer and generates reference signals for the bottom layer. The top layer is identical for all agents. The bottom layer provides each agent with an adaptive controller, enabling the agent to track its associated reference signal. Local cost functions are assumed to be strictly convex and have smooth gradients. The proposed control policy is fully distributed, meaning agents only depend on their own and their neighbors' information to reach a consensus on the global minimizer. Numerical simulations validate the theoretical results.

In wireless communication systems, the asynchronization of the oscillators in the transmitter and the receiver along with the Doppler shift due to relative movement may lead to the presence of carrier frequency offset (CFO) in the received signals. Estimation of CFO is crucial for subsequent processing such as coherent demodulation. In this brief, we demonstrate the utilization of deep learning for CFO estimation by employing a residual network (ResNet) to learn and extract signal features from the raw in-phase (I) and quadrature (Q) components of the signals. We use multiple modulation schemes in the training set to make the trained model adaptable to multiple modulations or even new signals. In comparison to the commonly used traditional CFO estimation methods, our proposed IQ-ResNet method exhibits superior performance across various scenarios including different oversampling ratios, various signal lengths, and different channels.

A document by Vahdaneh Kiani . Click on the document to view its contents.

OpenAIâ\euro™s continuous efforts to push our knowledge and build on it for natural language processing have led to the development of GPT-4, the highly acclaimed successor of GPT-3. Built upon the Generative Pretrained Transformer architecture (GPT), it showcases significant advancements in natural language processing, as it now incorporates image handling capabilities alongside its vast data and computational resources. This article delves into a comprehensive comparison between GPT-3 and GPT-4 exploring their similarities, differences, cost of implementation etc. Through a comprehensive analysis of their conversational abilities, accuracy, creativity, and reliability, this article offers valuable insights into the distinctive features and performance enhancements of GPT-4 over its predecessor. As the latest iteration of OpenAIâ\euro™s language models, GPT-4 promises to redefine the landscape of natural language processing and unlock new possibilities in various domains.Â