Search

This work presents Fair4Free, a novel generative model to generate synthetic fair data using data-free distillation in the latent space. Fair4Free can work on the situation when the data is private or inaccessible. In our approach, we first train a teacher model to create fair representation and then distil the knowledge to a student model (using a smaller architecture). The process of distilling the student model is data-free, i.e. the student model does not have access to the training dataset while distilling. After the distillation, we use the distilled model to generate fair synthetic samples. Our extensive experiments show that our synthetic samples outperform state-of-the-art models in all three criteria (fairness, utility and synthetic quality) with a performance increase of 5% for fairness, 8% for utility and 12% in synthetic quality for both tabular and image datasets.

Rapid urbanization in megacities around the world, like Dhaka, has caused numerous transportation challenges that need to be addressed. Emerging technologies of deep learning and artificial intelligence can help us solve these problems to move towards Intelligent Transportation Systems (ITS) in the city. The government of Bangladesh recognizes the integration of ITS to ensure smart mobility as a vital step towards the development plan "Smart Bangladesh Vision 2041", but faces challenges in understanding ITS, its effects, and directions to implement. A vehicle detection system can pave the way to understanding traffic congestion, finding mobility patterns, and ensuring traffic surveillance. So, this paper proposes a fine-tuned object detector, the YOLOv9 model to detect native vehicles trained on a Bangladesh-based dataset. Results show that the fine-tuned YOLOv9 model achieved a mean Average Precision (mAP) of 0.934 at the Intersection over Union (IoU) threshold of 0.5, achieving state-of-the-art performance over past studies on Bangladesh-based datasets, shown through a comparison. Later, by suggesting the model to be deployed on CCTVs (closed circuit television) on the roads, a conceptual technique is proposed to process the vehicle detection model output data in a graph structure creating a vehicle detection system in the city. Finally, applications of such vehicle detection system are discussed showing a framework on how it can solve further ITS research questions, to provide a rationale for policymakers to implement the proposed vehicle detection system in the city., Comment: 16 pages, 10 figures

Arabic, with its rich diversity of dialects, remains significantly underrepresented in Large Language Models, particularly in dialectal variations. We address this gap by introducing seven synthetic datasets in dialects alongside Modern Standard Arabic (MSA), created using Machine Translation (MT) combined with human post-editing. We present AraDiCE, a benchmark for Arabic Dialect and Cultural Evaluation. We evaluate LLMs on dialect comprehension and generation, focusing specifically on low-resource Arabic dialects. Additionally, we introduce the first-ever fine-grained benchmark designed to evaluate cultural awareness across the Gulf, Egypt, and Levant regions, providing a novel dimension to LLM evaluation. Our findings demonstrate that while Arabic-specific models like Jais and AceGPT outperform multilingual models on dialectal tasks, significant challenges persist in dialect identification, generation, and translation. This work contributes $\approx$45K post-edited samples, a cultural benchmark, and highlights the importance of tailored training to improve LLM performance in capturing the nuances of diverse Arabic dialects and cultural contexts. We have released the dialectal translation models and benchmarks developed in this study (https://huggingface.co/datasets/QCRI/AraDiCE)., Comment: Benchmarking, Culturally Informed, Large Language Models, Arabic NLP, LLMs, Arabic Dialect, Dialectal Benchmarking

With the increasing popularity of daily information sharing and acquisition on the Internet, this paper introduces an innovative approach for intent classification in Bangla language, focusing on social media posts where individuals share their thoughts and opinions. The proposed method leverages multimodal data with particular emphasis on authorship identification, aiming to understand the underlying purpose behind textual content, especially in the context of varied user-generated posts on social media. Current methods often face challenges in low-resource languages like Bangla, particularly when author traits intricately link with intent, as observed in social media posts. To address this, we present the Multimodal-based Author Bangla Intent Classification (MABIC) framework, utilizing text and images to gain deeper insights into the conveyed intentions. We have created a dataset named "Uddessho," comprising 3,048 instances sourced from social media. Our methodology comprises two approaches for classifying textual intent and multimodal author intent, incorporating early fusion and late fusion techniques. In our experiments, the unimodal approach achieved an accuracy of 64.53% in interpreting Bangla textual intent. In contrast, our multimodal approach significantly outperformed traditional unimodal methods, achieving an accuracy of 76.19%. This represents an improvement of 11.66%. To our best knowledge, this is the first research work on multimodal-based author intent classification for low-resource Bangla language social media posts., Comment: Accepted for publication in "18th International Conference on Information Technology and Applications (ICITA 2024)"

The automation of guitar tablature generation from video inputs holds significant promise for enhancing music education, transcription accuracy, and performance analysis. Existing methods face challenges with consistency and completeness, particularly in detecting fretboards and accurately identifying notes. To address these issues, this paper introduces an advanced approach leveraging deep learning, specifically YOLO models for real-time fretboard detection, and Fourier Transform-based audio analysis for precise note identification. Experimental results demonstrate substantial improvements in detection accuracy and robustness compared to traditional techniques. This paper outlines the development, implementation, and evaluation of these methodologies, aiming to revolutionize guitar instruction by automating the creation of guitar tabs from video recordings.

In this paper, we present a novel approach to the development and deployment of an autonomous mosquito breeding place detector rover with the object and obstacle detection capabilities to control mosquitoes. Mosquito-borne diseases continue to pose significant health threats globally, with conventional control methods proving slow and inefficient. Amidst rising concerns over the rapid spread of these diseases, there is an urgent need for innovative and efficient strategies to manage mosquito populations and prevent disease transmission. To mitigate the limitations of manual labor and traditional methods, our rover employs autonomous control strategies. Leveraging our own custom dataset, the rover can autonomously navigate along a pre-defined path, identifying and mitigating potential breeding grounds with precision. It then proceeds to eliminate these breeding grounds by spraying a chemical agent, effectively eradicating mosquito habitats. Our project demonstrates the effectiveness that is absent in traditional ways of controlling and safeguarding public health. The code for this project is available on GitHub at - https://github.com/faiyazabdullah/MosquitoMiner, Comment: Accepted - 2024 IEEE Region 10 Symposium (TENSYMP 2024)

Artificial Intelligence (AI) has paved the way for revolutionary decision-making processes, which if harnessed appropriately, can contribute to advancements in various sectors, from healthcare to economics. However, its black box nature presents significant ethical challenges related to bias and transparency. AI applications are hugely impacted by biases, presenting inconsistent and unreliable findings, leading to significant costs and consequences, highlighting and perpetuating inequalities and unequal access to resources. Hence, developing safe, reliable, ethical, and Trustworthy AI systems is essential. Our team of researchers working with Trustworthy and Responsible AI, part of the Transdisciplinary Scholarship Initiative within the University of Calgary, conducts research on Trustworthy and Responsible AI, including fairness, bias mitigation, reproducibility, generalization, interpretability, and authenticity. In this paper, we review and discuss the intricacies of AI biases, definitions, methods of detection and mitigation, and metrics for evaluating bias. We also discuss open challenges with regard to the trustworthiness and widespread application of AI across diverse domains of human-centric decision making, as well as guidelines to foster Responsible and Trustworthy AI models., Comment: 44 pages, 2 figures

Data Fairness is a crucial topic due to the recent wide usage of AI powered applications. Most of the real-world data is filled with human or machine biases and when those data are being used to train AI models, there is a chance that the model will reflect the bias in the training data. Existing bias-mitigating generative methods based on GANs, Diffusion models need in-processing fairness objectives and fail to consider computational overhead while choosing computationally-heavy architectures, which may lead to high computational demands, instability and poor optimization performance. To mitigate this issue, in this work, we present a fair data generation technique based on knowledge distillation, where we use a small architecture to distill the fair representation in the latent space. The idea of fair latent space distillation enables more flexible and stable training of Fair Generative Models (FGMs). We first learn a syntax-agnostic (for any data type) fair representation of the data, followed by distillation in the latent space into a smaller model. After distillation, we use the distilled fair latent space to generate high-fidelity fair synthetic data. While distilling, we employ quality loss (for fair distillation) and utility loss (for data utility) to ensure that the fairness and data utility characteristics remain in the distilled latent space. Our approaches show a 5%, 5% and 10% rise in performance in fairness, synthetic sample quality and data utility, respectively, than the state-of-the-art fair generative model.

In this work, we introduce LightCNN, a minimalist Convolutional Neural Network (CNN) architecture designed for Parkinson's disease (PD) classification using EEG data. LightCNN's strength lies in its simplicity, utilizing just a single convolutional layer. Embracing Leonardo da Vinci's principle that "simplicity is the ultimate sophistication," LightCNN demonstrates that complexity is not required to achieve outstanding results. We benchmarked LightCNN against several state-of-the-art deep learning models known for their effectiveness in EEG-based PD classification. Remarkably, LightCNN outperformed all these complex architectures, with a 2.3% improvement in recall, a 4.6% increase in precision, a 0.1% edge in AUC, a 4% boost in F1-score, and a 3.3% higher accuracy compared to the closest competitor. Furthermore, LightCNN identifies known pathological brain rhythms associated with PD and effectively captures clinically relevant neurophysiological changes in EEG. Its simplicity and interpretability make it ideal for deployment in resource-constrained environments, such as mobile or embedded systems for EEG analysis. In conclusion, LightCNN represents a significant step forward in efficient EEG-based PD classification, demonstrating that a well-designed, lightweight model can achieve superior performance over more complex architectures. This work underscores the potential for minimalist models to meet the needs of modern healthcare applications, particularly where resources are limited., Comment: 10 pages, 5 figures

Language models have achieved remarkable success in various natural language processing tasks. However, their application to time series data, a crucial component in many domains, remains limited. This paper proposes LiPCoT (Linear Predictive Coding based Tokenizer for time series), a novel tokenizer that encodes time series data into a sequence of tokens, enabling self-supervised learning of time series using existing Language model architectures such as BERT. Unlike traditional time series tokenizers that rely heavily on CNN encoder for time series feature generation, LiPCoT employs stochastic modeling through linear predictive coding to create a latent space for time series providing a compact yet rich representation of the inherent stochastic nature of the data. Furthermore, LiPCoT is computationally efficient and can effectively handle time series data with varying sampling rates and lengths, overcoming common limitations of existing time series tokenizers. In this proof-of-concept work, we present the effectiveness of LiPCoT in classifying Parkinson's disease (PD) using an EEG dataset from 46 participants. In particular, we utilize LiPCoT to encode EEG data into a small vocabulary of tokens and then use BERT for self-supervised learning and the downstream task of PD classification. We benchmark our approach against several state-of-the-art CNN-based deep learning architectures for PD detection. Our results reveal that BERT models utilizing self-supervised learning outperformed the best-performing existing method by 7.1% in precision, 2.3% in recall, 5.5% in accuracy, 4% in AUC, and 5% in F1-score highlighting the potential for self-supervised learning even on small datasets. Our work will inform future foundational models for time series, particularly for self-supervised learning., Comment: 17 pages, 5 figures

Many socio-economical critical domains (such as sustainability, public health, and disasters) are characterized by highly complex and dynamic systems, requiring data and model-driven simulations to support decision-making. Due to a large number of unknowns, decision-makers usually need to generate ensembles of stochastic scenarios, requiring hundreds or thousands of individual simulation instances, each with different parameter settings corresponding to distinct scenarios, As the number of model parameters increases, the number of potential timelines one can simulate increases exponentially. Consequently, simulation ensembles are inherently sparse, even when they are extremely large. This necessitates a platform for (a) deciding which simulation instances to execute and (b) given a large simulation ensemble, enabling decision-makers to explore the resulting alternative timelines, by extracting and visualizing consistent, yet diverse timelines from continuous-coupled simulation ensembles. In this article, we present DataStorm-EM platform for data- and model-driven simulation ensemble management, optimization, analysis, and exploration, describe underlying challenges and present our solution.

We investigate coherent quantum control of a nitrogen vacancy (NV) center in diamond with microwave fields generated from a nanoscale magnet that is proximal to the NV center. Our results show remarkable coherent control with high contrast Rabi oscillations using nearfield microwaves from shape anisotropic nanomagnets of lateral dimensions down to 200 nm x 180 nm, driven remotely by surface acoustic wave (SAW) excitation that is at least 400 times and potentially 4 orders of magnitude more energy efficient than generating microwaves with an antenna. Furthermore, we show that varying the acoustic power driving such nanomagnets can achieve control over Rabi frequency. We also report spin-lattice relaxation time T1 is 103 +/-0.5 micro-seconds, the spin-spin relaxation time T2 is 1.23+/-0.29 micro-seconds, and the Ramsey coherence time T2* is 218+/-27 nanoseconds measured using microwave pulses generated by such nanomagnets. The use of the nanoscale magnets to implement highly localized and energy efficient coherent quantum control can replace thermally noisy microwave circuits and demonstrate a path to scalable quantum computing and sensing with NV-defects in diamond and other spin qubits.

Diffusion Probabilistic Models (DPMs) suffer from inefficient inference due to their slow sampling and high memory consumption, which limits their applicability to various medical imaging applications. In this work, we propose a novel conditional diffusion modeling framework (LDSeg) for medical image segmentation, utilizing the learned inherent low-dimensional latent shape manifolds of the target objects and the embeddings of the source image with an end-to-end framework. Conditional diffusion in latent space not only ensures accurate image segmentation for multiple interacting objects, but also tackles the fundamental issues of traditional DPM-based segmentation methods: (1) high memory consumption, (2) time-consuming sampling process, and (3) unnatural noise injection in the forward and reverse processes. The end-to-end training strategy enables robust representation learning in the latent space related to segmentation features, ensuring significantly faster sampling from the posterior distribution for segmentation generation in the inference phase. Our experiments demonstrate that LDSeg achieved state-of-the-art segmentation accuracy on three medical image datasets with different imaging modalities. In addition, we showed that our proposed model was significantly more robust to noise compared to traditional deterministic segmentation models. The code is available at https://github.com/FahimZaman/LDSeg.git., Comment: 10 pages, 10 figures, journal article

1 ps timing resolution is the entry point to signature based searches relying on secondary/tertiary vertices and particle identification. We describe a preliminary design for PSEC5, an 8-channel 40 GS/s waveform-sampling ASIC in the TSMC 65 nm process targetting 1 ps resolution at 20 mW power per channel. Each channel consists of four fast and one slow switched capacitor arrays (SCA), allowing ps time resolution combined with a long effective buffer. Each fast SCA is 1.6 ns long and has a nominal sampling rate of 40 GS/s. The slow SCA is 204.8 ns long and samples at 5 GS/s. Recording of the analog data for each channel is triggered by a fast discriminator capable of multiple triggering during the window of the slow SCA. To achieve a large dynamic range, low leakage, and high bandwidth, the SCA sampling switches are implemented as 2.5 V nMOSFETs controlled by 1.2 V shift registers. Stored analog data are digitized by an external ADC at 10 bits or better. Specifications on operational parameters include a 4 GHz analog bandwidth and a dead time of 20 microseconds, corresponding to a 50 kHz readout rate, determined by the choice of the external ADC., Comment: 16th Pisa Meeting on Advanced Detectors

Absence of tamper-proof cattle identification technology was a significant problem preventing insurance companies from providing livestock insurance. This lack of technology had devastating financial consequences for marginal farmers as they did not have the opportunity to claim compensation for any unexpected events such as the accidental death of cattle in Bangladesh. Using machine learning and deep learning algorithms, we have solved the bottleneck of cattle identification by developing and introducing a muzzle-based cattle identification system. The uniqueness of cattle muzzles has been scientifically established, which resembles human fingerprints. This is the fundamental premise that prompted us to develop a cattle identification system that extracts the uniqueness of cattle muzzles. For this purpose, we collected 32,374 images from 826 cattle. Contrast-limited adaptive histogram equalization (CLAHE) with sharpening filters was applied in the preprocessing steps to remove noise from images. We used the YOLO algorithm for cattle muzzle detection in the image and the FaceNet architecture to learn unified embeddings from muzzle images using squared $L_2$ distances. Our system performs with an accuracy of $96.489\%$, $F_1$ score of $97.334\%$, and a true positive rate (tpr) of $87.993\%$ at a remarkably low false positive rate (fpr) of $0.098\%$. This reliable and efficient system for identifying cattle can significantly advance livestock insurance and precision farming., Comment: In claimed novel augmentation techniques, there are some mistakes in equations that convey wrong result, which should not be

Those experiencing strokes, traumatic brain injuries, and drug complications can often end up hospitalized and diagnosed with coma or locked-in syndrome. Such mental impediments can permanently alter the neurological pathways in work and significantly decrease the quality of life (QoL). It is critical to translate brain signals into images to gain a deeper understanding of the thoughts of a comatose patient. Traditionally, brain signals collected by an EEG could only be translated into text, but with the novel method of an open-source model available on GitHub, DreamDiffusion can be used to convert brain waves into images directly. DreamDiffusion works by extracting features from EEG signals and then using the features to create images through StableDiffusion. Upon this, we made further improvements that could make StableDiffusion the forerunner technology in waves to media translation. In our study, we begin by modifying the existing DreamDiffusion codebase so that it does not require any prior setup, avoiding any confusing steps needed to run the model from GitHub. For many researchers, the incomplete setup process, errors in the existing code, and a lack of directions made it nearly impossible to run, not even considering the model's performance. We brought the code into Google Colab so users could run and evaluate problems cell-by-cell, eliminating the specific file and repository dependencies. We also provided the original training data file so users do not need to purchase the necessary computing power to train the model from the given dataset. The second change is utilizing the mutability of the code and optimizing the model so it can be used to generate images from other given inputs, such as sleep data. Additionally, the affordability of EEG technology allows for global dissemination and creates the opportunity for those who want to work on the shared DreamDiffusion model.

Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks, can easily be specified to align well with our intended goal: -1 reward every time step with termination upon reaching the goal state, called minimum-time tasks. Despite this simplicity, such formulations are often overlooked in favor of dense rewards due to their perceived difficulty and lack of informativeness. Our studies contrast the two reward paradigms, revealing that the minimum-time task specification not only facilitates learning higher-quality policies but can also surpass dense-reward-based policies on their own performance metrics. Crucially, we also identify the goal-hit rate of the initial policy as a robust early indicator for learning success in such sparse feedback settings. Finally, using four distinct real-robotic platforms, we show that it is possible to learn pixel-based policies from scratch within two to three hours using constant negative rewards., Comment: In Proceedings of Reinforcement Learning Conference 2024. For a video demo, see https://youtu.be/a6zlVUuKzBc

The Skipper CCD-in-CMOS Parallel Read-Out Circuit V2 (SPROCKET2) is designed to enable high frame rate readout of Skipper CCD-in-CMOS image sensors. The SPROCKET2 pixel is fabricated in a 65 nm CMOS process and occupies a 60$\mu$m $\times$ 60$\mu$m footprint. SPROCKET2 is intended to be heterogeneously integrated with a pixelated Skipper CCD-in-CMOS sensor, such that one readout pixel is connected to a multiplexed array of 16 active image sensor pixels, to match their spatial geometry. Our design benefits from the Skipper CCD-in-CMOS sensor's non-destructive readout capability to achieve exceptionally low noise through multi-sampling and averaging while optimizing for total power consumption. The pixel readout utilizes correlated double sampling to minimize 1/f noise and includes "pile-up" of ten successive samples in the analog domain before digitizing at a rate of 66.7 ksps. Measurement results of in-pixel serial SAR ADC show DNL and INL of ~0. 44 LSB and 0.58 LBS respectively. A large area array of 20,000 SPROCKET2 ADC pixels (multiplexed 1:16 to 320,000 sensor pixels) is currently under test. By reading out data over a 10 Gbps optical link, this pixel design enables a frame rate of $\sim$ 4 kfps for large sensing areas with minimal sensing deadtime. In the highest gain mode, the pixelated ADC has an input-referred resolution of 10$\mu$V with a simulated power consumption of 50$\mu$W. The pixel operates with constant current draw to minimize power-rail crosstalk., Comment: IEEE NSS MIC RTSD 2024