Search

Melody stuck in your head, also known as "earworm", is tough to get rid of, unless you listen to it again or sing it out loud. But what if you can not find the name of that song? It must be an intolerable feeling. Recognizing a song name base on humming sound is not an easy task for a human being and should be done by machines. However, there is no research paper published about hum tune recognition. Adapting from Hum2Song Zalo AI Challenge 2021 - a competition about querying the name of a song by user's giving humming tune, which is similar to Google's Hum to Search. This paper covers details about the pre-processed data from the original type (mp3) to usable form for training and inference. In training an embedding model for the feature extraction phase, we ran experiments with some states of the art, such as ResNet, VGG, AlexNet, MobileNetV2. And for the inference phase, we use the Faiss module to effectively search for a song that matched the sequence of humming sound. The result comes at nearly 94\% in MRR@10 metric on the public test set, along with the top 1 result on the public leaderboard.

Primordial black holes (PBHs) are the natural candidate of dark matter (DM) as they only interact gravitationally and can evade any experiments on earth. In the standard semiclassical calculation of Hawking radiation, PBHs with mass below $10^{15}\rm g$ evaporated by now and therefore cannot be DM. However, the recently-discovered quantum memory burden effect can significantly suppress the evaporation of PBHs after the half-decay time. This quantum effect could open up a new mass window below $10^{10} \rm g$ where PBHs can still exist today and be DM. In this paper, we compute the gravitational wave (GW) signals associated with the formation of PBHs in this new mass window. We consider two formation scenarios: PBHs formed from inflationary perturbation and PBHs formed from collapse of Fermi-balls in a first-order phase transition (FOPT). GWs produced from these two scenarios have distinct features and, while the GW from inflation peaks at high frequency, the GW from FOPT peaks at lower frequency that can be within the reach of future experiments., Comment: 20 pages, 4 figures, 1 table

Feature Selection (FS) under domain adaptation (DA) is a critical task in machine learning, especially when dealing with limited target data. However, existing methods lack the capability to guarantee the reliability of FS under DA. In this paper, we introduce a novel statistical method to statistically test FS reliability under DA, named SFS-DA (statistical FS-DA). The key strength of SFS-DA lies in its ability to control the false positive rate (FPR) below a pre-specified level $\alpha$ (e.g., 0.05) while maximizing the true positive rate. Compared to the literature on statistical FS, SFS-DA presents a unique challenge in addressing the effect of DA to ensure the validity of the inference on FS results. We overcome this challenge by leveraging the Selective Inference (SI) framework. Specifically, by carefully examining the FS process under DA whose operations can be characterized by linear and quadratic inequalities, we prove that achieving FPR control in SFS-DA is indeed possible. Furthermore, we enhance the true detection rate by introducing a more strategic approach. Experiments conducted on both synthetic and real-world datasets robustly support our theoretical results, showcasing the superior performance of the proposed SFS-DA method.

Large Language Models (LLMs) have shown remarkable capabilities, but their inherent probabilistic nature often leads to inconsistency and inaccuracy in complex problem-solving tasks. This paper introduces DANA (Domain-Aware Neurosymbolic Agent), an architecture that addresses these issues by integrating domain-specific knowledge with neurosymbolic approaches. We begin by analyzing current AI architectures, including AutoGPT, LangChain ReAct and OpenAI's ChatGPT, through a neurosymbolic lens, highlighting how their reliance on probabilistic inference contributes to inconsistent outputs. In response, DANA captures and applies domain expertise in both natural-language and symbolic forms, enabling more deterministic and reliable problem-solving behaviors. We implement a variant of DANA using Hierarchical Task Plans (HTPs) in the open-source OpenSSA framework. This implementation achieves over 90\% accuracy on the FinanceBench financial-analysis benchmark, significantly outperforming current LLM-based systems in both consistency and accuracy. Application of DANA in physical industries such as semiconductor shows that its flexible architecture for incorporating knowledge is effective in mitigating the probabilistic limitations of LLMs and has potential in tackling complex, real-world problems that require reliability and precision.

This paper presents a Multimodal Ambient Context-enriched Intelligence Platform (MACeIP) for Smart Cities, a comprehensive system designed to enhance urban management and citizen engagement. Our platform integrates advanced technologies, including Internet of Things (IoT) sensors, edge and cloud computing, and Multimodal AI, to create a responsive and intelligent urban ecosystem. Key components include Interactive Hubs for citizen interaction, an extensive IoT sensor network, intelligent public asset management, a pedestrian monitoring system, a City Planning Portal, and a Cloud Computing System. We demonstrate the prototype of MACeIP in several cities, focusing on Fredericton, New Brunswick. This work contributes to innovative city development by offering a scalable, efficient, and user-centric approach to urban intelligence and management., Comment: 4 pages, 6 figures, IEEE/IEIE ICCE-Asia 2024

The sixth-generation (6G) non-terrestrial networks (NTNs) are crucial for real-time monitoring in critical applications like disaster relief. However, limited bandwidth, latency, rain attenuation, long propagation delays, and co-channel interference pose challenges to efficient satellite communication. Therefore, semantic communication (SC) has emerged as a promising solution to improve transmission efficiency and address these issues. In this paper, we explore the potential of SC as a bandwidth-efficient, latency-minimizing strategy specifically suited to 6G satellite communications. While existing SC methods have demonstrated efficacy in direct satellite-terrestrial transmissions, they encounter limitations in satellite networks due to distortion accumulation across gateway hop-relays. Additionally, certain ground users (GUs) experience poor signal-to-noise ratios (SNR), making direct satellite communication challenging. To address these issues, we propose a novel framework that optimizes gateway hop-relay selection for GUs with low SNR and integrates gateway-based denoising mechanisms to ensure high-quality-of-service (QoS) in satellite-based SC networks. This approach directly mitigates distortion, leading to significant improvements in satellite service performance by delivering customized services tailored to the unique signal conditions of each GU. Our findings represent a critical advancement in reliable and efficient data transmission from the Earth observation satellites, thereby enabling fast and effective responses to urgent events. Simulation results demonstrate that our proposed strategy significantly enhances overall network performance, outperforming conventional methods by offering tailored communication services based on specific GU conditions., Comment: 13 pages, 8 figures, 2 tables

Earth observation satellites generate large amounts of real-time data for monitoring and managing time-critical events such as disaster relief missions. This presents a major challenge for satellite-to-ground communications operating under limited bandwidth capacities. This paper explores semantic communication (SC) as a potential alternative to traditional communication methods. The rationality for adopting SC is its inherent ability to reduce communication costs and make spectrum efficient for 6G non-terrestrial networks (6G-NTNs). We focus on the critical satellite imagery downlink communications latency optimization for Earth observation through SC techniques. We formulate the latency minimization problem with SC quality-of-service (SC-QoS) constraints and address this problem with a meta-heuristic discrete whale optimization algorithm (DWOA) and a one-to-one matching game. The proposed approach for captured image processing and transmission includes the integration of joint semantic and channel encoding to ensure downlink sum-rate optimization and latency minimization. Empirical results from experiments demonstrate the efficiency of the proposed framework for latency optimization while preserving high-quality data transmission when compared to baselines., Comment: Accepted in GLOBECOM 2024

Recent advancements in deep learning have significantly improved visual quality inspection and predictive maintenance within industrial settings. However, deploying these technologies on low-resource edge devices poses substantial challenges due to their high computational demands and the inherent complexity of Explainable AI (XAI) methods. This paper addresses these challenges by introducing a novel XAI-integrated Visual Quality Inspection framework that optimizes the deployment of semantic segmentation models on low-resource edge devices. Our framework incorporates XAI and the Large Vision Language Model to deliver human-centered interpretability through visual and textual explanations to end-users. This is crucial for end-user trust and model interpretability. We outline a comprehensive methodology consisting of six fundamental modules: base model fine-tuning, XAI-based explanation generation, evaluation of XAI approaches, XAI-guided data augmentation, development of an edge-compatible model, and the generation of understandable visual and textual explanations. Through XAI-guided data augmentation, the enhanced model incorporating domain expert knowledge with visual and textual explanations is successfully deployed on mobile devices to support end-users in real-world scenarios. Experimental results showcase the effectiveness of the proposed framework, with the mobile model achieving competitive accuracy while significantly reducing model size. This approach paves the way for the broader adoption of reliable and interpretable AI tools in critical industrial applications, where decisions must be both rapid and justifiable. Our code for this work can be found at https://github.com/Analytics-Everywhere-Lab/vqixai., Comment: 29 pages, preprint submitted to Information Fusion journal

Several forms for constructing novel physics-informed neural-networks (PINN) for the solution of partial-differential-algebraic equations based on derivative operator splitting are proposed, using the nonlinear Kirchhoff rod as a prototype for demonstration. The open-source DeepXDE is likely the most well documented framework with many examples. Yet, we encountered some pathological problems and proposed novel methods to resolve them. Among these novel methods are the PDE forms, which evolve from the lower-level form with fewer unknown dependent variables to higher-level form with more dependent variables, in addition to those from lower-level forms. Traditionally, the highest-level form, the balance-of-momenta form, is the starting point for (hand) deriving the lowest-level form through a tedious (and error prone) process of successive substitutions. The next step in a finite element method is to discretize the lowest-level form upon forming a weak form and linearization with appropriate interpolation functions, followed by their implementation in a code and testing. The time-consuming tedium in all of these steps could be bypassed by applying the proposed novel PINN directly to the highest-level form. We developed a script based on JAX. While our JAX script did not show the pathological problems of DDE-T (DDE with TensorFlow backend), it is slower than DDE-T. That DDE-T itself being more efficient in higher-level form than in lower-level form makes working directly with higher-level form even more attractive in addition to the advantages mentioned further above. Since coming up with an appropriate learning-rate schedule for a good solution is more art than science, we systematically codified in detail our experience running optimization through a normalization/standardization of the network-training process so readers can reproduce our results., Comment: 61 pages, 52 figures

Semantic communication, notable for ensuring quality of service by jointly optimizing source and channel coding, effectively extracts data semantics, reduces transmission length, and mitigates channel noise. However, most studies overlook multi-user scenarios and resource availability, limiting real-world application. This paper addresses this gap by focusing on downlink communication from a base station to multiple users with varying computing capacities. Users employ variants of Swin transformer models for source decoding and a simple architecture for channel decoding. We propose a novel training regimen, incorporating transfer learning and knowledge distillation to improve low-computing users' performance. Extensive simulations validate the proposed methods., Comment: 5 pages, 5 figures

Face recognition is a very important topic in data science and biometric security research areas. It has multiple applications in military, finance, and retail, to name a few. In this paper, the novel hypergraph Laplacian Eigenmaps will be proposed and combine with the k nearest-neighbor method and/or with the kernel ridge regression method to solve the face recognition problem. Experimental results illustrate that the accuracy of the combination of the novel hypergraph Laplacian Eigenmaps and one specific classification system is similar to the accuracy of the combination of the old symmetric normalized hypergraph Laplacian Eigenmaps method and one specific classification system.

This paper addresses the inverse scattering problem in the domain Omega. The input data, measured outside Omega, involve the waves generated by the interaction of plane waves with various directions and unknown scatterers fully occluded inside Omega. The output of this problem is the spatially dielectric constant of these scatterers. Our approach to solving this problem consists of two primary stages. Initially, we eliminate the unknown dielectric constant from the governing equation, resulting in a system of partial differential equations. Subsequently, we develop the Carleman contraction mapping method to effectively tackle this system. It is noteworthy to highlight this method's robustness. It does not request a precise initial guess of the true solution, and its computational cost is not expensive. Some numerical examples are presented.

We study dark matter production from mediator decays in scenarios with an epoch of early matter domination. Particles that mediate interactions between dark matter and the standard model particles are kinematically accessible to the thermal bath as long as their mass is below the reheating temperature of the Universe after inflation. Decay of on-shell mediators can then lead to copious production of dark matter during early matter domination or a preceding radiation-dominated phase. In particular, for mediators that are charged under the standard model, it can exceed the standard freeze-in channel due to inverse annihilations at much lower temperatures (often by many orders of magnitude). The requirement to obtain the correct relic abundance severely constrains the parameter space for dark matter masses above a few TeV., Comment: 19 pages, 4 figures; published version

LangXAI is a framework that integrates Explainable Artificial Intelligence (XAI) with advanced vision models to generate textual explanations for visual recognition tasks. Despite XAI advancements, an understanding gap persists for end-users with limited domain knowledge in artificial intelligence and computer vision. LangXAI addresses this by furnishing text-based explanations for classification, object detection, and semantic segmentation model outputs to end-users. Preliminary results demonstrate LangXAI's enhanced plausibility, with high BERTScore across tasks, fostering a more transparent and reliable AI framework on vision tasks for end-users.

Krylov methods have reappeared recently, connecting physically sensible notions of complexity with quantum chaos and quantum gravity. In these developments, the Hamiltonian and the Liouvillian are tridiagonalized so that Schrodinger/Heisenberg time evolution is expressed in the Krylov basis. In the context of Schrodinger evolution, this tridiagonalization has been carried out in Random Matrix Theory. We extend these developments to Heisenberg time evolution, describing how the Liouvillian can be tridiagonalized as well until the end of Krylov space. We numerically verify the analytical formulas both for Gaussian and non-Gaussian matrix models., Comment: 20 pages, 5 figuress; v2: typos corrected, references added

We investigate the stability and softness of nuclei against quadrupole, octupole, and hexadecapole deformation. By applying the spherical Skyrme-force Hartree-Fock Bardeen-Cooper-Schrieffer quasi-particle random phase approximation, we diagnose ground-state deformation when imaginary solutions are obtained, i.e., the spherical ground state {\em collapses}. We also calculate the multipole polarizability in spherical nuclei with no collapse, as a measure of softness. This numerically light and theoretically sound method is found able to capture deformation patterns across the nuclide chart. The connection between the intrinsic shape of nuclei and the dynamics of their low-lying collective states is established and the role of shell structure is discussed., Comment: 8 pages, 8 figures, accepted for publication in Physical Review C

We consider logistic regression including two sets of discrete or categorical covariates that are missing at random (MAR) separately or simultaneously. We examine the asymptotic properties of two multiple imputation (MI) estimators, given in the study of Lee at al. (2023), for the parameters of the logistic regression model with both sets of discrete or categorical covariates that are MAR separately or simultaneously. The proposed estimated asymptotic variances of the two MI estimators address a limitation observed with Rubin's type estimated variances, which lead to underestimate the variances of the two MI estimators (Rubin, 1987). Simulation results demonstrate that our two proposed MI methods outperform the complete-case, semiparametric inverse probability weighting, random forest MI using chained equations, and stochastic approximation of expectation-maximization methods. To illustrate the methodology's practical application, we provide a real data example from a survey conducted in the Feng Chia night market in Taichung City, Taiwan.

Background: Photoacoustic Microscopy (PAM) integrates optical and acoustic imaging, offering enhanced penetration depth for detecting optical-absorbing components in tissues. Nonetheless, challenges arise in scanning large areas with high spatial resolution. With speed limitations imposed by laser pulse repetition rates, the potential role of computational methods is highlighted in accelerating PAM imaging. Purpose: We are proposing a novel and highly adaptable DiffPam algorithm that utilizes diffusion models for speeding up the photoacoustic imaging process. Method: We leveraged a diffusion model trained exclusively on natural images, comparing its performance with an in-domain trained U-Net model using a dataset focused on PAM images of mice brain microvasculature. Results: Our findings indicate that DiffPam achieves comparable performance to a dedicated U-Net model, without the need for a large dataset or training a deep learning model. The study also introduces the efficacy of shortened diffusion processes for reducing computing time without compromising accuracy. Conclusion: This study underscores the significance of DiffPam as a practical algorithm for reconstructing undersampled PAM images, particularly for researchers with limited AI expertise and computational resources., Comment: 10 pages, 7 figures

Multi-access Edge Computing (MEC) addresses computational and battery limitations in devices by allowing them to offload computation tasks. To overcome the difficulties in establishing line-of-sight connections, integrating unmanned aerial vehicles (UAVs) has proven beneficial, offering enhanced data exchange, rapid deployment, and mobility. The utilization of reconfigurable intelligent surfaces (RIS), specifically simultaneously transmitting and reflecting RIS (STAR-RIS) technology, further extends coverage capabilities and introduces flexibility in MEC. This study explores the integration of UAV and STAR-RIS to facilitate communication between IoT devices and an MEC server. The formulated problem aims to minimize energy consumption for IoT devices and aerial STAR-RIS by jointly optimizing task offloading, aerial STAR-RIS trajectory, amplitude and phase shift coefficients, and transmit power. Given the non-convexity of the problem and the dynamic environment, solving it directly within a polynomial time frame is challenging. Therefore, deep reinforcement learning (DRL), particularly proximal policy optimization (PPO), is introduced for its sample efficiency and stability. Simulation results illustrate the effectiveness of the proposed system compared to benchmark schemes in the literature.

This study investigates the compatibility of the electroweak sector of particle physics with quantum gravity, under the assumption that the conventional S-matrix positivity bounds can be extended to gravitational context. It focuses on constraints implied by these bounds to the weak couplings of the Weinberg-Salam model coupled to gravity, analyzed through forward-limit of various $2\rightarrow 2$ scatterings, including $HH \rightarrow HH, H\gamma \rightarrow H\gamma, \gamma\gamma\rightarrow\gamma\gamma$. These constraints suggest possible extensions to the magnetic Weak Gravity Conjecture, relating gauge couplings with the EFT cutoff scale., Comment: 5 pages, 3 figures, Contribution to: Windows on the Universe [https://inspirehep.net/conferences/2652810]

This paper aims to determine the initial conditions for quasi-linear hyperbolic equations that include nonlocal elements. We suggest a method where we approximate the solution of the hyperbolic equation by truncating its Fourier series in the time domain with a polynomial-exponential basis. This truncation effectively removes the time variable, transforming the problem into a system of quasi-linear elliptic equations. We refer to this technique as the "time dimensional reduction method." To numerically solve this system comprehensively without the need for an accurate initial estimate, we used the newly developed Carleman contraction principle. We show the efficiency of our method through various numerical examples. The time dimensional reduction method stands out not only for its precise solutions but also for its remarkable speed in computation.

In this talk, we present the program Lilith, a python package for constraining new physics from Higgs measurements. We discuss the usage of signal strength results in the latest published version of Lilith, which allows for constraining deviations from SM Higgs couplings through coupling modifiers. Moreover, we discuss the on-going development to include Higgs STXS data and SMEFT parametrizations in Lilith with the aim of performing global fits of the ATLAS and CMS data. As we point out, detailed information on Standard Model uncertainties and their correlations is important to enable the proper reuse of the experimental results., Comment: content unchanged, citation and references made more explicit

A Network Intrusion Detection System (NIDS) is a tool that identifies potential threats to a network. Recently, different flow-based NIDS designs utilizing Machine Learning (ML) algorithms have been proposed as solutions to detect intrusions efficiently. However, conventional ML-based classifiers have not seen widespread adoption in the real world due to their poor domain adaptation capability. In this research, our goal is to explore the possibility of using sequences of flows to improve the domain adaptation capability of network intrusion detection systems. Our proposal employs natural language processing techniques and Bidirectional Encoder Representations from Transformers framework, which is an effective technique for modeling data with respect to its context. Early empirical results show that our approach has improved domain adaptation capability compared to previous approaches. The proposed approach provides a new research method for building a robust intrusion detection system.

Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose training performance heavily relies on data availability. Existing studies often make unrealistic assumptions of a readily accessible data source, where in practice, data is mainly created on the client side. Due to privacy and security concerns, the transmission of data is restricted, which is necessary for conventional centralized training schemes. To address this challenge, we explore semantic communication in a federated learning (FL) setting that utilizes client data without leaking privacy. Additionally, we design our system to tackle the communication overhead by reducing the quantity of information delivered in each global round. In this way, we can save significant bandwidth for resource-limited devices and reduce overall network traffic. Finally, we introduce a mechanism to aggregate the global model from clients, called FedLol. Extensive simulation results demonstrate the effectiveness of our proposed technique compared to baseline methods., Comment: 5 pages, 3 figures

We propose a globally convergent computational technique for the nonlinear inverse problem of reconstructing the zero-order coefficient in a parabolic equation using partial boundary data. This technique is called the "reduced dimensional method". Initially, we use the polynomial-exponential basis to approximate the inverse problem as a system of 1D nonlinear equations. We then employ a Picard iteration based on the quasi-reversibility method and a Carleman weight function. We will rigorously prove that the sequence derived from this iteration converges to the accurate solution for that 1D system without requesting a good initial guess of the true solution. The key tool for the proof is a Carleman estimate. We will also show some numerical examples.

The Rotar central limit theorem is a remarkable theorem in the non-classical version since it does not use the condition of asymptotic infinitesimality for the independent individual summands, unlike the theorems named Lindeberg's and Lindeberg-Feller's in the classical version. The Rotar central limit theorem generalizes the classical Lindeberg-Feller central limit theorem since the Rotar condition is weaker than Lindeberg's. The main aim of this paper is to introduce the Rotar central limit theorem for sums of a random number of independent (not necessarily identically distributed) random variables and the conditions for its validity. The order of approximation in this theorem is also considered in this paper., Comment: 15 pages