Search

The pressure swing adsorption (PSA) process is one of the widely utilized techniques for air separation. Operating on the Skarstrom cycle, the porous adsorbent columns of a PSA system alternate between adsorption and desorption phases to selectively enrich the desired component in a gas mixture. The current work presents a robust and generalizable digital twin CFD model of a PSA system that can significantly help in design and device characterization. Using an axisymmetric representation, the digital twin accurately mimics all the key components of an air separation plant, including the air reservoir, adsorbent columns, product buffer tank, pressure regulator, solenoidal valves, and mesh filters. The model simulates the flow and adsorption processes in the system by solving the conservation equations for mass, momentum, energy, and species, along with the equation for adsorption kinetics. The cyclic operation of the PSA plants, typically controlled by solenoid valves, is emulated by dynamically modifying the boundary conditions of different subdomains. Such an integrated approach is shown here to closely replicate the performance of an in-house PSA pilot setup producing oxygen in terms of purity and pressure transience. Also, both the numerical and the experimental results yield an optimum performance for the same process parameters, such as pressurization time (26 s), purge time (2 s), and equalization time (4 s). The proposed numerical model is versatile and can be adapted to various industrial applications of PSA technology, such as hydrogen purification and carbon capture. Thus, it offers a cost-effective tool for designing and optimizing PSA systems.

State-of-the-art methods for backpropagation-free learning employ local error feedback to direct iterative optimisation via gradient descent. In this study, we examine the more restrictive setting where retrograde communication from neuronal outputs is unavailable for pre-synaptic weight optimisation. To address this challenge, we propose Forward Projection (FP). This novel randomised closed-form training method requires only a single forward pass over the entire dataset for model fitting, without retrograde communication. Target values for pre-activation membrane potentials are generated layer-wise via nonlinear projections of pre-synaptic inputs and the labels. Local loss functions are optimised over pre-synaptic inputs using closed-form regression, without feedback from neuronal outputs or downstream layers. Interpretability is a key advantage of FP training; membrane potentials of hidden neurons in FP-trained networks encode information which is interpretable layer-wise as label predictions. We demonstrate the effectiveness of FP across four biomedical datasets. In few-shot learning tasks, FP yielded more generalisable models than those optimised via backpropagation. In large-sample tasks, FP-based models achieve generalisation comparable to gradient descent-based local learning methods while requiring only a single forward propagation step, achieving significant speed up for training. Interpretation functions defined on local neuronal activity in FP-based models successfully identified clinically salient features for diagnosis in two biomedical datasets. Forward Projection is a computationally efficient machine learning approach that yields interpretable neural network models without retrograde communication of neuronal activity during training., Comment: 26 pages, 5 figures

Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope restrict the applicability of Multi-Modal Large Language Models (MM-LLMs) on these data streams. Traditional Retrieval-Augmented Generation (RAG) systems address knowledge limitations of these models, but suffer from slow preprocessing, making them unsuitable for real-time analysis. We propose StreamingRAG, a novel RAG framework designed for streaming data. StreamingRAG constructs evolving knowledge graphs capturing scene-object-entity relationships in real-time. The knowledge graph achieves temporal-aware scene representations using MM-LLMs and enables timely responses for specific events or user queries. StreamingRAG addresses limitations in existing methods, achieving significant improvements in real-time analysis (5-6x faster throughput), contextual accuracy (through a temporal knowledge graph), and reduced resource consumption (using lightweight models by 2-3x)., Comment: Accepted and Presented at AI4Sys, HPDC 2024

We study the consequences of new long-range forces between neutrinos on cosmic scales. If these forces are a few orders of magnitude stronger than gravity, they can induce perturbation instability in the non-relativistic cosmic neutrino background in the late time universe. As a result, the cosmic neutrino background may form nonlinear bound states instead of free-streaming. The implications of the formation of nonlinear neutrino bound states include enhancing matter perturbations and triggering star formation. Based on existing measurements of the matter power spectrum and reionization history, we place new constraints on long-range forces between neutrinos with ranges lying in $1 \text{ kpc}\lesssim m_\phi^{-1} \lesssim 10 \text{ Mpc}$., Comment: 15 pages, 5 figures

Millicharged particles are generic in theories of dark sectors. A cosmic or local abundance of them may be produced by the early universe, stellar environments, or the decay or annihilation of dark matter/dark energy. Furthermore, if such particles are light, these production channels result in a background of millicharged radiation. We show that light-shining-through-wall experiments employing superconducting RF cavities can also be used as ``direct deflection" experiments to search for this relativistic background. The millicharged plasma is first subjected to an oscillating electromagnetic field of a driven cavity, which causes charge separation in the form of charge and current perturbations. In turn, these perturbations can propagate outwards and resonantly excite electromagnetic fields in a well-shielded cavity placed nearby, enabling detection. We estimate that future versions of the existing Dark SRF experiment can probe orders of magnitude of currently unexplored parameter space, including millicharges produced from the Sun, the cosmic neutrino background, or other mechanisms that generate a thermal abundance with energy density as small as $\sim 10^{-4}$ that of the cosmic microwave background., Comment: 31 pages, 8 figures

We present Noise Adaptor, a novel method for constructing competitive low-latency spiking neural networks (SNNs) by converting noise-injected, low-bit artificial neural networks (ANNs). This approach builds on existing ANN-to-SNN conversion techniques but offers several key improvements: (1) By injecting noise during quantized ANN training, Noise Adaptor better accounts for the dynamic differences between ANNs and SNNs, significantly enhancing SNN accuracy. (2) Unlike previous methods, Noise Adaptor does not require the application of run-time noise correction techniques in SNNs, thereby avoiding modifications to the spiking neuron model and control flow during inference. (3) Our method extends the capability of handling deeper architectures, achieving successful conversions of activation-quantized ResNet-101 and ResNet-152 to SNNs. We demonstrate the effectiveness of our method on CIFAR-10 and ImageNet, achieving competitive performance. The code will be made available as open-source.

Analog in-memory computing (AIMC) has emerged as a promising solution to overcome the von Neumann bottleneck, accelerating neural network computations and improving computational efficiency. While AIMC has demonstrated success with architectures such as CNNs, MLPs, and RNNs, deploying transformer-based models using AIMC presents unique challenges. Transformers are expected to handle diverse downstream tasks and adapt to new user data or instructions after deployment, which requires more flexible approaches to suit AIMC constraints. In this paper, we propose a novel method for deploying pre-trained transformer models onto AIMC hardware. Unlike traditional approaches requiring hardware-aware training, our technique allows direct deployment without the need for retraining the original model. Instead, we utilize lightweight, low-rank adapters -- compact modules stored in digital cores -- to adapt the model to hardware constraints. We validate our approach on MobileBERT, demonstrating accuracy on par with, or even exceeding, a traditional hardware-aware training approach. Our method is particularly appealing in multi-task scenarios, as it enables a single analog model to be reused across multiple tasks. Moreover, it supports on-chip adaptation to new hardware constraints and tasks without updating analog weights, providing a flexible and versatile solution for real-world AI applications. Code is available.

The rapid advancement of large language models (LLMs) has enabled the ability to effectively analyze and generate code nearly instantaneously, resulting in their widespread adoption in software development. Following this advancement, researchers and companies have begun integrating LLMs across the hardware design and verification process. However, these highly potent LLMs can also induce new attack scenarios upon security vulnerabilities across the hardware development process. One such attack vector that has not been explored is intellectual property (IP) piracy. Given that this attack can manifest as rewriting hardware designs to evade piracy detection, it is essential to thoroughly evaluate LLM capabilities in performing this task and assess the mitigation abilities of current IP piracy detection tools. Therefore, in this work, we propose LLMPirate, the first LLM-based technique able to generate pirated variations of circuit designs that successfully evade detection across multiple state-of-the-art piracy detection tools. We devise three solutions to overcome challenges related to integration of LLMs for hardware circuit designs, scalability to large circuits, and effectiveness, resulting in an end-to-end automated, efficient, and practical formulation. We perform an extensive experimental evaluation of LLMPirate using eight LLMs of varying sizes and capabilities and assess their performance in pirating various circuit designs against four state-of-the-art, widely-used piracy detection tools. Our experiments demonstrate that LLMPirate is able to consistently evade detection on 100% of tested circuits across every detection tool. Additionally, we showcase the ramifications of LLMPirate using case studies on IBEX and MOR1KX processors and a GPS module, that we successfully pirate. We envision that our work motivates and fosters the development of better IP piracy detection tools., Comment: Accepted by NDSS Symposium 2025

There are strong arguments that quantum mechanics may be nonlinear in its dynamics. A discovery of nonlinearity would hint at a novel understanding of the interplay between gravity and quantum field theory, for example. As such, experiments searching for potential nonlinear effects in the electromagnetic sector are important. Here we outline such an experiment, consisting of a stream of random bits (which were generated using Rigetti's Aspen-M-3 chip) as input to an RF signal generator coupled to a cryogenic detector. Projective measurements of the qubit state, which is originally prepared in an equal superposition, serve as the random binary output of a signal generator. Thereafter, spectral analysis of the RF detector would yield a detectable excess signal predicted to arise from such a nonlinear effect. A comparison between the projective measurements of the quantum bits vs the classical baseline showed no power excess. This sets a new limit on the electromagnetic nonlinearity parameter $|\epsilon| \lessapprox 1.15 \times 10^{-12}$, at a 90.0% confidence level. This is the most stringent limit on nonlinear quantum mechanics thus far and an improvement by nearly a factor of 50 over the previous experimental limit.

Bayesian Neural Networks (BNNs) provide superior estimates of uncertainty by generating an ensemble of predictive distributions. However, inference via ensembling is resource-intensive, requiring additional entropy sources to generate stochasticity which increases resource consumption. We introduce Bayes2IMC, an in-memory computing (IMC) architecture designed for binary Bayesian neural networks that leverage nanoscale device stochasticity to generate desired distributions. Our novel approach utilizes Phase-Change Memory (PCM) to harness inherent noise characteristics, enabling the creation of a binary neural network. This design eliminates the necessity for a pre-neuron Analog-to-Digital Converter (ADC), significantly improving power and area efficiency. We also develop a hardware-software co-optimized correction method applied solely on the logits in the final layer to reduce device-induced accuracy variations across deployments on hardware. Additionally, we devise a simple compensation technique that ensures no drop in classification accuracy despite conductance drift of PCM. We validate the effectiveness of our approach on the CIFAR-10 dataset with a VGGBinaryConnect model, achieving accuracy metrics comparable to ideal software implementations as well as results reported in the literature using other technologies. Finally, we present a complete core architecture and compare its projected power, performance, and area efficiency against an equivalent SRAM baseline, showing a $3.8$ to $9.6 \times$ improvement in total efficiency (in GOPS/W/mm$^2$) and a $2.2 $ to $5.6 \times$ improvement in power efficiency (in GOPS/W). In addition, the projected hardware performance of Bayes2IMC surpasses that of most of the BNN architectures based on memristive devices reported in the literature, and achieves up to $20\%$ higher power efficiency compared to the state-of-the-art., Comment: Accepted for publication in IEEE Transactions On Circuits and Systems I: Regular Papers

Bayesian Neural Networks (BNNs) provide principled estimates of model and data uncertainty by encoding parameters as distributions. This makes them key enablers for reliable AI that can be deployed on safety critical edge systems. These systems can be made resource efficient by restricting synapses to two synaptic states $\{-1,+1\}$ and using a memristive in-memory computing (IMC) paradigm. However, BNNs pose an additional challenge -- they require multiple instantiations for ensembling, consuming extra resources in terms of energy and area. In this work, we propose a novel sparsity-aware optimization for Bayesian Binary Neural Network (BBNN) accelerators that exploits the inherent BBNN sampling sparsity -- most of the network is made up of synapses that have a high probability of being fixed at $\pm1$ and require no sampling. The optimization scheme proposed here exploits the sampling sparsity that exists both among layers, i.e only a few layers of the network contain a majority of the probabilistic synapses, as well as the parameters i.e., a tiny fraction of parameters in these layers require sampling, reducing total sampled parameter count further by up to $86\%$. We demonstrate no loss in accuracy or uncertainty quantification performance for a VGGBinaryConnect network on CIFAR-100 dataset mapped on a custom sparsity-aware phase change memory (PCM) based IMC simulator. We also develop a simple drift compensation technique to demonstrate robustness to drift-induced degradation. Finally, we project latency, energy, and area for sparsity-aware BNN implementation in both pipelined and non-pipelined modes. With sparsity-aware implementation, we estimate upto $5.3 \times$ reduction in area and $8.8\times$ reduction in energy compared to a non-sparsity-aware implementation. Our approach also results in $2.9 \times $ more power efficiency compared to the state-of-the-art BNN accelerator.

Inspired by biological processes, neuromorphic computing leverages spiking neural networks (SNNs) to perform inference tasks, offering significant efficiency gains for workloads involving sequential data. Recent advances in hardware and software have shown that embedding a small payload within each spike exchanged between spiking neurons can enhance inference accuracy without increasing energy consumption. To scale neuromorphic computing to larger workloads, split computing - where an SNN is partitioned across two devices - is a promising solution. In such architectures, the device hosting the initial layers must transmit information about the spikes generated by its output neurons to the second device. This establishes a trade-off between the benefits of multi-level spikes, which carry additional payload information, and the communication resources required for transmitting extra bits between devices. This paper presents the first comprehensive study of a neuromorphic wireless split computing architecture that employs multi-level SNNs. We propose digital and analog modulation schemes for an orthogonal frequency division multiplexing (OFDM) radio interface to enable efficient communication. Simulation and experimental results using software-defined radios reveal performance improvements achieved by multi-level SNN models and provide insights into the optimal payload size as a function of the connection quality between the transmitter and receiver.

Precision therapy for liver cancer necessitates accurately delineating liver sub-regions to protect healthy tissue while targeting tumors, which is essential for reducing recurrence and improving survival rates. However, the segmentation of hepatic segments, known as Couinaud segmentation, is challenging due to indistinct sub-region boundaries and the need for extensive annotated datasets. This study introduces LiverFormer, a novel Couinaud segmentation model that effectively integrates global context with low-level local features based on a 3D hybrid CNN-Transformer architecture. Additionally, a registration-based data augmentation strategy is equipped to enhance the segmentation performance with limited labeled data. Evaluated on CT images from 123 patients, LiverFormer demonstrated high accuracy and strong concordance with expert annotations across various metrics, allowing for enhanced treatment planning for surgery and radiation therapy. It has great potential to reduces complications and minimizes potential damages to surrounding tissue, leading to improved outcomes for patients undergoing complex liver cancer treatments.

Sequence models have demonstrated the ability to perform tasks like channel equalization and symbol detection by automatically adapting to current channel conditions. This is done without requiring any explicit optimization and by leveraging not only short pilot sequences but also contextual information such as long-term channel statistics. The operating principle underlying automatic adaptation is in-context learning (ICL), an emerging property of sequence models. Prior art adopted transformer-based sequence models, which, however, have a computational complexity scaling quadratically with the context length due to batch processing. Recently, state-space models (SSMs) have emerged as a more efficient alternative, affording a linear inference complexity in the context size. This work explores the potential of SSMs for ICL-based equalization in cell-free massive MIMO systems. Results show that selective SSMs achieve comparable performance to transformer-based models while requiring approximately eight times fewer parameters and five times fewer floating-point operations.

Hardware-level memory vulnerabilities severely threaten computing systems. However, hardware patching is inefficient or difficult postfabrication. We investigate the effectiveness of hardware fuzzing in detecting hardware memory vulnerabilities and highlight challenges and potential future research directions to enhance hardware fuzzing for memory safety.

Microarchitectural attacks represent a challenging and persistent threat to modern processors, exploiting inherent design vulnerabilities in processors to leak sensitive information or compromise systems. Of particular concern is the susceptibility of Speculative Execution, a fundamental part of performance enhancement, to such attacks. We introduce Specure, a novel pre-silicon verification method composing hardware fuzzing with Information Flow Tracking (IFT) to address speculative execution leakages. Integrating IFT enables two significant and non-trivial enhancements over the existing fuzzing approaches: i) automatic detection of microarchitectural information leakages vulnerabilities without golden model and ii) a novel Leakage Path coverage metric for efficient vulnerability detection. Specure identifies previously overlooked speculative execution vulnerabilities on the RISC-V BOOM processor and explores the vulnerability search space 6.45x faster than existing fuzzing techniques. Moreover, Specure detected known vulnerabilities 20x faster.

Spiking Neural Networks (SNNs) have emerged as a promising approach to improve the energy efficiency of machine learning models, as they naturally implement event-driven computations while avoiding expensive multiplication operations. In this paper, we develop a hardware-software co-optimisation strategy to port software-trained deep neural networks (DNN) to reduced-precision spiking models demonstrating fast and accurate inference in a novel event-driven CMOS reconfigurable spiking inference accelerator. Experimental results show that a reduced-precision Resnet-18 and VGG-11 SNN models achieves classification accuracy within 1% of the baseline full-precision DNN model within 8 spike timesteps. We also demonstrate an FPGA prototype implementation of the spiking inference accelerator with a throughput of 38.4 giga operations per second (GOPS) consuming 1.54 Watts on PYNQ-Z2 FPGA. This corresponds to 0.6 GOPS per processing element and 2.25,GOPS/DSP slice, which is 2x and 4.5x higher utilisation efficiency respectively compared to the state-of-the-art. Our co-optimisation strategy can be employed to develop deep reduced precision SNN models and port them to resource-efficient event-driven hardware accelerators for edge applications.

Deep reinforcement learning (DRL) has shown success in diverse domains such as robotics, computer games, and recommendation systems. However, like any other software system, DRL-based software systems are susceptible to faults that pose unique challenges for debugging and diagnosing. These faults often result in unexpected behavior without explicit failures and error messages, making debugging difficult and time-consuming. Therefore, automating the monitoring and diagnosis of DRL systems is crucial to alleviate the burden on developers. In this paper, we propose RLExplorer, the first fault diagnosis approach for DRL-based software systems. RLExplorer automatically monitors training traces and runs diagnosis routines based on properties of the DRL learning dynamics to detect the occurrence of DRL-specific faults. It then logs the results of these diagnoses as warnings that cover theoretical concepts, recommended practices, and potential solutions to the identified faults. We conducted two sets of evaluations to assess RLExplorer. Our first evaluation of faulty DRL samples from Stack Overflow revealed that our approach can effectively diagnose real faults in 83% of the cases. Our second evaluation of RLExplorer with 15 DRL experts/developers showed that (1) RLExplorer could identify 3.6 times more defects than manual debugging and (2) RLExplorer is easily integrated into DRL applications., Comment: Accepted for publication in The International Conference on Software Maintenance and Evolution (ICSME 2024)

Optimizing framerate for a given bitrate-spatial resolution pair in adaptive video streaming is essential to maintain perceptual quality while considering decoding complexity. Low framerates at low bitrates reduce compression artifacts and decrease decoding energy. We propose a novel method, Decoding-complexity aware Framerate Prediction (DECODRA), which employs a Variable Framerate Pareto-front approach to predict an optimized framerate that minimizes decoding energy under quality degradation constraints. DECODRA dynamically adjusts the framerate based on current bitrate and spatial resolution, balancing trade-offs between framerate, perceptual quality, and decoding complexity. Extensive experimentation with the Inter-4K dataset demonstrates DECODRA's effectiveness, yielding an average decoding energy reduction of up to 13.45%, with minimal VMAF reduction of 0.33 points at a low-quality degradation threshold, compared to the default 60 fps encoding. Even at an aggressive threshold, DECODRA achieves significant energy savings of 13.45% while only reducing VMAF by 2.11 points. In this way, DECODRA extends mobile device battery life and reduces the energy footprint of streaming services by providing a more energy-efficient video streaming pipeline., Comment: Accepted at IEEE International Conference on Visual Communications and Image Processing (VCIP) 2024

Light, weakly coupled bosonic particles such as axions can mediate long range monopole-dipole interactions between matter and spins. We propose a new experimental method using atom interferometry to detect such a force on a freely falling atom exerted by the spin of electrons. The intrinsic advantages of atom interferometry, such as the freely falling nature of the atom and the well-defined response of the atom to external magnetic fields, should enable the proposed method to overcome systematic effects induced by vibrations, magnetic fields, and gravity. This approach is most suited to probe forces with a range $\gtrsim$~10~cm. With current technology, our proposed setup could potentially extend probes of such forces by an order of magnitude beyond present laboratory limits., Comment: 10 pages, 5 figures

While there has been progress towards aligning Large Language Models (LLMs) with human values and ensuring safe behaviour at inference time, safety guards can easily be removed when fine tuned on unsafe and harmful datasets. While this setting has been treated extensively, another popular training paradigm, learning from unsafe feedback with reinforcement learning, has previously been unexplored. This is concerning due to the widespread deployment of feedback collection systems. We address this gap by providing an analysis of learning settings where feedback is harmful, i.e. that unsafe samples are preferred over safe ones despite model developers goal to maintain safety. We find that safety-aligned LLMs easily explore unsafe action spaces via generating harmful text and optimize for reward that violates safety constraints indicating that current safety guards are not enough to prevent learning from unsafe feedback. In order to protect against this vulnerability, we adapt a number of both "implict" and "explicit" harmful fine-tuning defences to evaluate whether they are effective as learning constraints in an RLHF setting finding that no method is generally effective pointing to the need for more defence research. We end the paper with the observation that some defences work by performing "harmless reward hacking" for which we provide a theoretical explanation drawn from the theory of Constrained Markov Decision Processes and provide some direction for future defence development.

With the increasing frequency of high impact low probability events, electricity markets are experiencing significant price spikes more often. This paper proposes a novel social equity driven optimal power flow framework to mitigate the adverse effects of price events that lead to such price spikes. The framework integrates social welfare optimization with socioeconomic considerations by including a socioeconomic score that quantifies the energy burden and socioeconomic status of consumers. By incorporating both supply cost and consumer satisfaction, the model aims to achieve a balanced and fair distribution of resources during price events, while considering resource scarcity and possible load curtailment. The proposed framework is tested for convergence on modified versions of the PJM 5-bus system and IEEE 24-bus reliability test system, discussing its potential effectiveness in enhancing social equity and optimizing power flow under system security constraints. Sensitivity analysis further highlights the impact of socioeconomic score on social welfare, providing insights for future improvements., Comment: Published in proceedings of the 2024 56th North American Power Symposium (NAPS)

Learning-based methods have proven useful at generating complex motions for robots, including humanoids. Reinforcement learning (RL) has been used to learn locomotion policies, some of which leverage a periodic reward formulation. This work extends the periodic reward formulation of locomotion to skateboarding for the REEM-C robot. Brax/MJX is used to implement the RL problem to achieve fast training. Initial results in simulation are presented with hardware experiments in progress.

This paper introduces a novel Soft Acoustic Curvature (SAC) sensor. SAC incorporates integrated audio components and features an acoustic channel within a flexible structure. A reference acoustic wave, generated by a speaker at one end of the channel, propagates and is received by a microphone at the other channel's end. Our previous study revealed that acoustic wave energy dissipation varies with acoustic channel deformation, leading us to design a novel channel capable of large deformation due to bending. We then use Machine Learning (ML) models to establish a complex mapping between channel deformations and sound modulation. Various sound frequencies and ML models were evaluated to enhance curvature detection accuracy. The sensor, constructed using soft material and 3D printing, was validated experimentally, with curvature measurement errors remaining within 3.5 m-1 for a range of 0 to 60 m-1 curvatures. These results demonstrate the effectiveness of the proposed method for estimating curvatures. With its flexible structure, the SAC sensor holds potential for applications in soft robotics, including shape measurement for continuum manipulators, soft grippers, and wearable devices., Comment: To appear in Robotics and Automation Letter

This paper introduces Xpikeformer, a hybrid analog-digital hardware architecture designed to accelerate spiking neural network (SNN)-based transformer models. By combining the energy efficiency and temporal dynamics of SNNs with the powerful sequence modeling capabilities of transformers, Xpikeformer leverages mixed analog-digital computing techniques to enhance performance and energy efficiency. The architecture integrates analog in-memory computing (AIMC) for feedforward and fully connected layers, and a stochastic spiking attention (SSA) engine for efficient attention mechanisms. We detail the design, implementation, and evaluation of Xpikeformer, demonstrating significant improvements in energy consumption and computational efficiency. Through an image classification task and a wireless communication symbol detection task, we show that Xpikeformer can achieve software-comparable inference accuracy. Energy evaluations reveal that Xpikeformer achieves up to a $17.8$--$19.2\times$ reduction in energy consumption compared to state-of-the-art digital ANN transformers and up to a $5.9$--$6.8\times$ reduction compared to fully digital SNN transformers. Xpikeformer also achieves a $12.0\times$ speedup compared to the GPU implementation of spiking transformers.

We present a comprehensive theoretical framework governing the dynamics of droplets in acoustic fields, applicable to all droplet sizes, from the Rayleigh limit (D<

In the field of object detection, domain generalisation (DG) aims to ensure robust performance across diverse and unseen target domains by learning the robust domain-invariant features corresponding to the objects of interest across multiple source domains. While there are many approaches established for performing DG for the task of classification, there has been a very little focus on object detection. In this paper, we propose a domain penalisation (DP) framework for the task of object detection, where the data is assumed to be sampled from multiple source domains and tested on completely unseen test domains. We assign penalisation weights to each domain, with the values updated based on the detection networks performance on the respective source domains. By prioritising the domains that needs more attention, our approach effectively balances the training process. We evaluate our solution on the GWHD 2021 dataset, a component of the WiLDS benchmark and we compare against ERM and GroupDRO as these are primarily loss function based. Our extensive experimental results reveals that the proposed approach improves the accuracy by 0.3 percent and 0.5 percent on validation and test out-of-distribution (OOD) sets, respectively for FasterRCNN. We also compare the performance of our approach on FCOS detector and show that our approach improves the baseline OOD performance over the existing approaches by 1.3 percent and 1.4 percent on validation and test sets, respectively. This study underscores the potential of performance based domain penalisation in enhancing the generalisation ability of object detection models across diverse environments.

We investigate the potential of self-supervision in improving the accuracy of deep learning models trained to classify melanoma patches. Various self-supervision techniques such as rotation prediction, missing patch prediction, and corruption removal were implemented and assessed for their impact on the convolutional neural network's performance. Preliminary results suggest a positive influence of self-supervision methods on the model's accuracy. The study notably demonstrates the efficacy of the corruption removal method in enhancing model performance. Despite observable improvements, we conclude that the self-supervised models have considerable potential for further enhancement, achievable through training over more epochs or expanding the dataset. We suggest exploring other self-supervision methods like Bootstrap Your Own Latent (BYOL) and contrastive learning in future research, emphasizing the cost-benefit trade-off due to their resource-intensive nature. The findings underline the promise of self-supervision in augmenting melanoma detection capabilities of deep learning models.

This paper describes the development of a counterfactual Root Cause Analysis diagnosis approach for an industrial multivariate time series environment. It drives the attention toward the Point of Incipient Failure, which is the moment in time when the anomalous behavior is first observed, and where the root cause is assumed to be found before the issue propagates. The paper presents the elementary but essential concepts of the solution and illustrates them experimentally on a simulated setting. Finally, it discusses avenues of improvement for the maturity of the causal technology to meet the robustness challenges of increasingly complex environments in the industry., Comment: Accepted for the Causal Inference for Time Series Data Workshop at the 40th Conference on Uncertainty in Artificial Intelligence (CI4TS 2024)

Radiation therapy (RT) is one of the most effective treatments for cancer, and its success relies on the accurate delineation of targets. However, target delineation is a comprehensive medical decision that currently relies purely on manual processes by human experts. Manual delineation is time-consuming, laborious, and subject to interobserver variations. Although the advancements in artificial intelligence (AI) techniques have significantly enhanced the auto-contouring of normal tissues, accurate delineation of RT target volumes remains a challenge. In this study, we propose a visual language model-based RT target volume auto-delineation network termed Radformer. The Radformer utilizes a hierarichal vision transformer as the backbone and incorporates large language models to extract text-rich features from clinical data. We introduce a visual language attention module (VLAM) for integrating visual and linguistic features for language-aware visual encoding (LAVE). The Radformer has been evaluated on a dataset comprising 2985 patients with head-and-neck cancer who underwent RT. Metrics, including the Dice similarity coefficient (DSC), intersection over union (IOU), and 95th percentile Hausdorff distance (HD95), were used to evaluate the performance of the model quantitatively. Our results demonstrate that the Radformer has superior segmentation performance compared to other state-of-the-art models, validating its potential for adoption in RT practice.

The need to reduce the environmental impact of inorganic electronic systems is pressing. Although the field of organic electronics provides a potential solution to this issue, research and optimization is still majorly carried out on glass or plastic substrates. Additionally, the fabrication of organic devices requiring transparent electrodes is fraught with complex techniques and expensive materials which limit widespread implementation and sustainability goals. Here, we show that the quasi-fractal lignocellulose structures extracted from natural leaves can be successfully modified to be used as biodegradable substrates as well as electrodes for optoelectronic applications. Chemically coating the microstructures of these leaf skeletons with metals results in quasi-transparent, flexible electrodes having sheet resistances below 1 ohm/sq. and a concomitant current carrying capacity as high as 6 A over a 2.5*2.5 cm2 leaf electrode, all while maintaining broadband optical transmittance values of around 80%., Comment: 4 pages, 6 figures, IEEE International conference publication

Dark matter may exist today in the form of ultraheavy composite bound states. Collisions between such dark matter states can release intense bursts of radiation that includes gamma-rays among the final products. Thus, indirect-detection signals of dark matter may include unconventional gamma-ray bursts. Such bursts may have been missed not necessarily because of their low arriving gamma-ray fluxes, but rather their briefness and rareness. We point out that intense bursts whose non-detection thus far are due to the latter can be detected in the near future with existing and planned facilities. In particular, we propose that, with slight experimental adjustments and suitable data analyses, imaging atmospheric Cherenkov telescopes (IACTs) and Pulsed All-sky Near-infrared and Optical Search for Extra-Terrestrial Intelligence (PANOSETI) are promising tools for detecting such rare, brief, but intense bursts. We also show that if we assume these bursts originate from collisions of dark matter states, IACTs and PANOSETI can probe a large dark matter parameter space beyond existing limits. Additionally, we present a concrete model of dark matter that produces bursts potentially detectable in these instruments., Comment: 34 pages, 5 figures, journal version

Acoustic Soft Tactile (AST) skin is a novel sensing technology which derives tactile information from the modulation of acoustic waves travelling through the skin's embedded acoustic channels. A generalisable data-driven calibration model maps the acoustic modulations to the corresponding tactile information in the form of contact forces with their contact locations and contact geometries. AST skin technology has been highlighted for its easy customisation. As a case study, this paper discusses the possibility of using AST skin on a custom-built robotic end effector finger for strawberry handling. The paper delves into the design, prototyping, and calibration method to sensorise the end effector finger with AST skin. A real-time force-controlled gripping experiment is conducted with the sensorised finger to handle strawberries by their peduncle. The finger could successfully grip the strawberry peduncle by maintaining a preset force of 2 N with a maximum Mean Absolute Error (MAE) of 0.31 N over multiple peduncle diameters and strawberry weight classes. Moreover, this study sets confidence in the usability of AST skin in generating real-time tactile feedback for robot manipulation tasks., Comment: TAROS 2024