Search

The rapid expansion of edge devices and Internet-of-Things (IoT) continues to heighten the demand for data transport under limited spectrum resources. The goal-oriented communications (GO-COM), unlike traditional communication systems designed for bit-level accuracy, prioritizes more critical information for specific application goals at the receiver. To improve the efficiency of generative learning models for GO-COM, this work introduces a novel noise-restricted diffusion-based GO-COM (Diff-GO$^\text{n}$) framework for reducing bandwidth overhead while preserving the media quality at the receiver. Specifically, we propose an innovative Noise-Restricted Forward Diffusion (NR-FD) framework to accelerate model training and reduce the computation burden for diffusion-based GO-COMs by leveraging a pre-sampled pseudo-random noise bank (NB). Moreover, we design an early stopping criterion for improving computational efficiency and convergence speed, allowing high-quality generation in fewer training steps. Our experimental results demonstrate superior perceptual quality of data transmission at a reduced bandwidth usage and lower computation, making Diff-GO$^\text{n}$ well-suited for real-time communications and downstream applications., Comment: Submitted to IEEE International Conference on Communications (ICC) 2025

Topology and superconductivity, two distinct phenomena offer unique insight into quantum properties and their applications in quantum technologies, spintronics, and sustainable energy technologies if system can be found where they coexist. Tin (Sn) plays a pivotal role here as an element due to its two structural phases, $\alpha$-Sn and $\beta$-Sn, exhibiting topological characteristics ($\alpha$-Sn) and superconductivity ($\beta$-Sn). In this study we show how precise control of $\alpha$ and $\beta$ phases of Sn thin films can be achieved by using molecular beam epitaxy grown buffer layers with systematic control over the lattice parameter. The resulting Sn films showed either $\beta$-Sn or $\alpha$-Sn phases as the lattice constant of the buffer layer was varied from 6.10 A to 6.48 A, covering the range between GaSb (closely matched to InAs) and InSb. The crystal structures of the $\alpha$- and $\beta$-Sn films were characterized by x-ray diffraction and confirmed by Raman spectroscopy and scanning transmission electron microscopy. The smooth and continuous surface morphology of the Sn films was validated using atomic force microscopy. The characteristics of $\alpha$- and $\beta$-Sn phases were further verified using electrical transport measurements by observing resistance drop near 3.7 K for superconductivity of the $\beta$-Sn phase and Shubnikov-de Haas oscillations for the $\alpha$-Sn phase. Density functional theory calculations showed that the stability of the Sn phases is highly dependent on lattice strain, with $\alpha$-Sn being more stable under tensile strain and $\beta$-Sn becoming favorable under compressive strain, which is in good agreement with experimental observations. Hence, this study sheds light on controlling Sn phases through lattice engineering, enabling innovative applications in quantum technologies and beyond.

This paper presents a novel high-speed hardware algorithm for the modulus operation for FPGA implementation. The proposed algorithm use only addition, subtraction, logical, and bit shift operations, avoiding the complexities and hardware costs associated with multiplication and division. It demonstrates consistent performance across operand sizes ranging from 32-bit to 2048-bit, addressing scalability challenges in cryptographic applications. Implemented in Verilog HDL and tested on a Xilinx Zynq-7000 family FPGA, the algorithm shows a predictable linear scaling of cycle count with bit length difference (BLD), described by the equation $y=2x+2$, where $y$ represents the cycle count and $x$ represents the BLD. The application of this algorithm in prime number calculation up to 500,000 shows its practical utility and performance advantages. Comprehensive evaluations reveal efficient resource utilization, robust timing performance, and effective power management, making it suitable for high-performance and resource-constrained platforms. The results indicate that the proposed algorithm significantly improves the efficiency of modular arithmetic operations, with potential implications for cryptographic protocols and secure computing.

We propose Deep-Motion-Net: an end-to-end graph neural network (GNN) architecture that enables 3D (volumetric) organ shape reconstruction from a single in-treatment kV planar X-ray image acquired at any arbitrary projection angle. Estimating and compensating for true anatomical motion during radiotherapy is essential for improving the delivery of planned radiation dose to target volumes while sparing organs-at-risk, and thereby improving the therapeutic ratio. Achieving this using only limited imaging available during irradiation and without the use of surrogate signals or invasive fiducial markers is attractive. The proposed model learns the mesh regression from a patient-specific template and deep features extracted from kV images at arbitrary projection angles. A 2D-CNN encoder extracts image features, and four feature pooling networks fuse these features to the 3D template organ mesh. A ResNet-based graph attention network then deforms the feature-encoded mesh. The model is trained using synthetically generated organ motion instances and corresponding kV images. The latter is generated by deforming a reference CT volume aligned with the template mesh, creating digitally reconstructed radiographs (DRRs) at required projection angles, and DRR-to-kV style transferring with a conditional CycleGAN model. The overall framework was tested quantitatively on synthetic respiratory motion scenarios and qualitatively on in-treatment images acquired over full scan series for liver cancer patients. Overall mean prediction errors for synthetic motion test datasets were 0.16$\pm$0.13 mm, 0.18$\pm$0.19 mm, 0.22$\pm$0.34 mm, and 0.12$\pm$0.11 mm. Mean peak prediction errors were 1.39 mm, 1.99 mm, 3.29 mm, and 1.16 mm.

The exponential growth of scientific literature has resulted in information overload, challenging researchers to effectively synthesize relevant publications. This paper explores the integration of traditional reference management software with advanced computational techniques, including Large Language Models and Retrieval-Augmented Generation. We introduce PyZoBot, an AI-driven platform developed in Python, incorporating Zoteros reference management with OpenAIs sophisticated LLMs. PyZoBot streamlines knowledge extraction and synthesis from extensive human-curated scientific literature databases. It demonstrates proficiency in handling complex natural language queries, integrating data from multiple sources, and meticulously presenting references to uphold research integrity and facilitate further exploration. By leveraging LLMs, RAG, and human expertise through a curated library, PyZoBot offers an effective solution to manage information overload and keep pace with rapid scientific advancements. The development of such AI-enhanced tools promises significant improvements in research efficiency and effectiveness across various disciplines., Comment: 10 pages, 2 figures. The code is provided in github and the link to the repository is provided at the end of the publication

To characterize radio frequency (RF) signal power distribution in wireless communication systems, the radiomap is a useful tool for resource allocation and network management. Usually, a dense radiomap is reconstructed from sparse observations collected by deployed sensors or mobile devices. To leverage both physical principles of radio propagation models and data statistics from sparse observations, this work introduces a novel task-incentivized generative learning model, namely TiRE-GAN, for radiomap estimation. Specifically, we first introduce a radio depth map to capture the overall pattern of radio propagation and shadowing effects, following which a task-driven incentive network is proposed to provide feedback for radiomap compensation depending on downstream tasks. Our experimental results demonstrate the power of the radio depth map to capture radio propagation information, and the efficiency of the proposed TiRE-GAN for radiomap estimation.

Many students in introductory programming courses fare poorly in the code writing tasks of the final summative assessment. Such tasks are designed to assess whether novices have developed the analytical skills to translate from the given problem domain to coding. In the past researchers have used instruments such as code-explain and found that the extent of cognitive depth reached in these tasks correlated well with code writing ability. However, the need for manual marking and personalized interviews used for identifying cognitive difficulties limited the study to a small group of stragglers. To extend this work to larger groups, we have devised several question types with varying cognitive demands collectively called Algorithmic Reasoning Tasks (ARTs), which do not require manual marking. These tasks require levels of reasoning which can define a learning trajectory. This paper describes these instruments and the machine learning models used for validating them. We have used the data collected in an introductory programming course in the penultimate week of the semester which required attempting ART type instruments and code writing. Our preliminary research suggests ART type instruments can be combined with specific machine learning models to act as an effective learning trajectory and early prediction of code-writing skills., Comment: Preprint. Accepted to the 19th International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE 2024). Final version to be published by SCITEPRESS, http://www.scitepress.org

The latest advances in artificial intelligence (AI) present many unprecedented opportunities to achieve much improved bandwidth saving in communications. Unlike conventional communication systems focusing on packet transport, rich datasets and AI makes it possible to efficiently transfer only the information most critical to the goals of message recipients. One of the most exciting advances in generative AI known as diffusion model presents a unique opportunity for designing ultra-fast communication systems well beyond language-based messages. This work presents an ultra-efficient communication design by utilizing generative AI-based on diffusion models as a specific example of the general goal-oriented communication framework. To better control the regenerated message at the receiver output, our diffusion system design includes a local regeneration module with finite dimensional noise latent. The critical significance of noise latent control and sharing residing on our Diff-GO is the ability to introduce the concept of "local generative feedback" (Local-GF), which enables the transmitter to monitor the quality and gauge the quality or accuracy of the message recovery at the semantic system receiver. To this end, we propose a new low-dimensional noise space for the training of diffusion models, which significantly reduces the communication overhead and achieves satisfactory message recovery performance. Our experimental results demonstrate that the proposed noise space and the diffusion-based generative model achieve ultra-high spectrum efficiency and accurate recovery of transmitted image signals. By trading off computation for bandwidth efficiency (C4BE), this new framework provides an important avenue to achieve exceptional computation-bandwidth tradeoff., Comment: Submitted to IEEE International Conference on Communications (ICC) 2024

Academic researchers face challenges keeping up with exponentially growing published findings in their field. Performing comprehensive literature reviews to synthesize knowledge is time-consuming and labor-intensive using manual approaches. Recent advances in artificial intelligence provide promising solutions, yet many require coding expertise, limiting accessibility. KNIMEZoBot represents an innovative integration of Zotero, OpenAI, and the KNIME visual programming platform to automate literature review tasks for users with no coding experience. By leveraging KNIME's intuitive graphical interface, researchers can create workflows to search their Zotero libraries and utilize OpenAI models to extract key information without coding. Users simply provide API keys and configure settings through a user-friendly interface in a locally stored copy of the workflow. KNIMEZoBot then allows asking natural language questions via a chatbot and retrieves relevant passages from papers to generate synthesized answers. This system has significant potential to expedite literature reviews for researchers unfamiliar with coding by automating retrieval and analysis of publications in personal Zotero libraries. KNIMEZoBot demonstrates how thoughtfully designed AI tools can expand accessibility and accelerate knowledge building across diverse research domains.

Most enterprise applications use logging as a mechanism to diagnose anomalies, which could help with reducing system downtime. Anomaly detection using software execution logs has been explored in several prior studies, using both classical and deep neural network-based machine learning models. In recent years, the research has largely focused in using variations of sequence-based deep neural networks (e.g., Long-Short Term Memory and Transformer-based models) for log-based anomaly detection on open-source data. However, they have not been applied in industrial datasets, as often. In addition, the studied open-source datasets are typically very large in size with logging statements that do not change much over time, which may not be the case with a dataset from an industrial service that is relatively new. In this paper, we evaluate several state-of-the-art anomaly detection models on an industrial dataset from our research partner, which is much smaller and loosely structured than most large scale open-source benchmark datasets. Results show that while all models are capable of detecting anomalies, certain models are better suited for less-structured datasets. We also see that model effectiveness changes when a common data leak associated with a random train-test split in some prior work is removed. A qualitative study of the defects' characteristics identified by the developers on the industrial dataset further shows strengths and weaknesses of the models in detecting different types of anomalies. Finally, we explore the effect of limited training data by gradually increasing the training set size, to evaluate if the model effectiveness does depend on the training set size., Comment: 12 pages, 14 figures. Submitted to QRS 2023 - 23rd IEEE International Conference on Software Quality, Reliability and Security

Among applications of deep learning (DL) involving low cost sensors, remote image classification involves a physical channel that separates edge sensors and cloud classifiers. Traditional DL models must be divided between an encoder for the sensor and the decoder + classifier at the edge server. An important challenge is to effectively train such distributed models when the connecting channels have limited rate/capacity. Our goal is to optimize DL models such that the encoder latent requires low channel bandwidth while still delivers feature information for high classification accuracy. This work proposes a three-step joint learning strategy to guide encoders to extract features that are compact, discriminative, and amenable to common augmentations/transformations. We optimize latent dimension through an initial screening phase before end-to-end (E2E) training. To obtain an adjustable bit rate via a single pre-deployed encoder, we apply entropy-based quantization and/or manual truncation on the latent representations. Tests show that our proposed method achieves accuracy improvement of up to 1.5% on CIFAR-10 and 3% on CIFAR-100 over conventional E2E cross-entropy training.

Recent advances of generative learning models are accompanied by the growing interest in federated learning (FL) based on generative adversarial network (GAN) models. In the context of FL, GAN can capture the underlying client data structure, and regenerate samples resembling the original data distribution without compromising the private raw data. Although most existing GAN-based FL works focus on training a global model, Personalized FL (PFL) sometimes can be more effective in view of client data heterogeneity in terms of distinct data sample distributions, feature spaces, and labels. To cope with client heterogeneity in GAN-based FL, we propose a novel GAN sharing and aggregation strategy for PFL. The proposed PFL-GAN addresses the client heterogeneity in different scenarios. More specially, we first learn the similarity among clients and then develop an weighted collaborative data aggregation. The empirical results through the rigorous experimentation on several well-known datasets demonstrate the effectiveness of PFL-GAN.

To satisfy the broad applications and insatiable hunger for deploying low latency multimedia data classification and data privacy in a cloud-based setting, federated learning (FL) has emerged as an important learning paradigm. For the practical cases involving limited computational power and only unlabeled data in many wireless communications applications, this work investigates FL paradigm in a resource-constrained and label-missing environment. Specifically, we propose a novel framework of UFed-GAN: Unsupervised Federated Generative Adversarial Network, which can capture user-side data distribution without local classification training. We also analyze the convergence and privacy of the proposed UFed-GAN. Our experimental results demonstrate the strong potential of UFed-GAN in addressing limited computational resources and unlabeled data while preserving privacy.

Intracellular lasers are emerging as powerful biosensors for multiplexed tracking and precision sensing of cells and their microenvironment. This sensing capacity is enabled by quantifying their narrow-linewidth emission spectra, which is presently challenging to do at high speeds. In this work, we demonstrate rapid snapshot hyperspectral imaging of intracellular lasers. Using integral field mapping with a microlens array and a diffraction grating, we obtain images of the spatial and spectral intensity distribution from a single camera acquisition. We demonstrate widefield hyperspectral imaging over a 3$\times$3 mm$^2$ field of view and volumetric imaging over 250$\times$250$\times$800 $\mu$m$^3$ volumes with a spatial resolution of 5 $\mu$m and a spectral resolution of less than 0.8 nm. We evaluate the performance and outline the challenges and strengths of snapshot methods in the context of characterising the emission from intracellular lasers. This method offers new opportunities for a diverse range of applications, including high-throughput and long-term biosensing with intracellular lasers., Comment: 15 pages, 6 figures

We develop an automated video colorization framework that minimizes the flickering of colors across frames. If we apply image colorization techniques to successive frames of a video, they treat each frame as a separate colorization task. Thus, they do not necessarily maintain the colors of a scene consistently across subsequent frames. The proposed solution includes a novel deep recurrent encoder-decoder architecture which is capable of maintaining temporal and contextual coherence between consecutive frames of a video. We use a high-level semantic feature extractor to automatically identify the context of a scenario including objects, with a custom fusion layer that combines the spatial and temporal features of a frame sequence. We demonstrate experimental results, qualitatively showing that recurrent neural networks can be successfully used to improve color consistency in video colorization.

Federated Learning (FL) has emerged as an effective learning paradigm for distributed computation owing to its strong potential in capturing underlying data statistics while preserving data privacy. However, in cases of practical data heterogeneity among FL clients, existing FL frameworks still exhibit deficiency in capturing the overall feature properties of local client data that exhibit disparate distributions. In response, generative adversarial networks (GANs) have recently been exploited in FL to address data heterogeneity since GANs can be integrated for data regeneration without exposing original raw data. Despite some successes, existing GAN-related FL frameworks often incur heavy communication cost and also elicit other privacy concerns, which limit their applications in real scenarios. To this end, this work proposes a novel FL framework that requires only partial GAN model sharing. Named as PS-FedGAN, this new framework enhances the GAN releasing and training mechanism to address heterogeneous data distributions across clients and to strengthen privacy preservation at reduced communication cost, especially over wireless networks. Our analysis demonstrates the convergence and privacy benefits of the proposed PS-FEdGAN framework. Through experimental results based on several well-known benchmark datasets, our proposed PS-FedGAN shows great promise to tackle FL under non-IID client data distributions, while securing data privacy and lowering communication overhead.

Sb thin films have attracted wide interests due to their tunable band structure, topological phases, and remarkable electronic properties. We successfully grow epitaxial Sb thin films on a closely lattice-matched GaSb(001) surface by molecular beam epitaxy. We find a novel anisotropic directional dependence of their structural, morphological, and electronic properties. The origin of the anisotropic features is elucidated using first-principles density functional theory (DFT) calculations. The growth regime of crystalline and amorphous Sb thin films was determined by mapping the surface reconstruction phase diagram of the GaSb(001) surface under Sb$_2$ flux, with confirmation of structural characterizations. Crystalline Sb thin films show a rhombohedral crystal structure along the rhombohedral (104) surface orientation parallel to the cubic (001) surface orientation of the GaSb substrate. At this coherent interface, Sb atoms are aligned with the GaSb lattice along the [1-10] crystallographic direction but are not aligned well along the [110] crystallographic direction, which results in anisotropic features in reflection high-energy electron diffraction patterns, surface morphology, and transport properties. Our DFT calculations show that the anisotropic features originate from the GaSb surface, where Sb atoms align with the Ga and Sb atoms on the reconstructed surface. The formation energy calculations confirm that the stability of the experimentally observed structures. Our results provide optimal film growth conditions for further studies of novel properties of Bi$_{1-x}$Sb$_x$ thin films with similar lattice parameters and an identical crystal structure as well as functional heterostructures of them with III-V semiconductor layers along the (001) surface orientation, supported by a theoretical understanding of the anisotropic film orientation.