Search

Chest X-rays (X-ray images) have been proven to be effective for the diagnosis of chest diseases, including Pneumonia, Lung Opacity, and COVID-19. However, relying on traditional medical methods for diagnosis from X-ray images is prone to delays and inaccuracies because the medical personnel who evaluate the X-ray images may have preconceived biases. For this reason, researchers have proposed the use of deep learning-based techniques to facilitate the diagnosis process. The preeminent method is the use of sophisticated Convolutional Neural Networks (CNNs). In this paper, we propose a novel detection model named \textbf{AttCDCNet} for the task of X-ray image diagnosis, enhancing the popular DenseNet121 model by adding an attention block to help the model focus on the most relevant regions, using focal loss as a loss function to overcome the imbalance of the dataset problem, and utilizing depth-wise convolution to reduce the parameters to make the model lighter. Through extensive experimental evaluations, the proposed model demonstrates exceptional performance, showing better results than the original DenseNet121. The proposed model achieved an accuracy, precision and recall of 94.94%, 95.14% and 94.53%, respectively, on the COVID-19 Radiography Dataset.

The original compass state, created by superposing four coherent states, yields anisotropic sub-Planck structures and demonstrates enhanced sensitivity to perturbations, offering advantages for quantum sensing. We propose two variants of this compass state by simultaneously applying photon addition and subtraction in different orders: one with addition first and one with subtraction first to the state. Our variants display sub-Planck structures and improved sensitivity to displacements, with photon addition and subtraction influencing these characteristics. In our cases, adding photons increases the average photon number, while photon subtraction lowers it in the first case and has no effect in the second. Furthermore, an increment in the added number of photons uniformly reduces the size of sub-Planck structures, whereas increasing the number of photons subtracted from the state causes these sub-Planck structures to expand in size; higher photon addition improves sensitivity, while photon subtraction decreases it. Remarkably, under optimal parameters, our specific variants achieve isotropic sub-Planck structures and provide isotropic enhanced sensitivity across all directions, surpassing compass states., Comment: 14 pages, and 9 figures

Otoscopy is a diagnostic procedure to examine the ear canal and eardrum using an otoscope. It identifies conditions like infections, foreign bodies, ear drum perforations and ear abnormalities. We propose a novel resource efficient deep learning and transformer based framework, Sumotosima (Summarizer for otoscopic images), an end-to-end pipeline for classification followed by summarization. Our framework works on combination of triplet and cross-entropy losses. Additionally, we use Knowledge Enhanced Multimodal BART whose input is fused textual and image embedding. The objective is to provide summaries that are well-suited for patients, ensuring clarity and efficiency in understanding otoscopic images. Given the lack of existing datasets, we have curated our own OCASD (Otoscopic Classification And Summary Dataset), which includes 500 images with 5 unique categories annotated with their class and summaries by Otolaryngologists. Sumotosima achieved a result of 98.03%, which is 7.00%, 3.10%, 3.01% higher than K-Nearest Neighbors, Random Forest and Support Vector Machines, respectively, in classification tasks. For summarization, Sumotosima outperformed GPT-4o and LLaVA by 88.53% and 107.57% in ROUGE scores, respectively. We have made our code and dataset publicly available at https://github.com/anas2908/Sumotosima, Comment: Work in Progress

Recent studies have revealed that, during the inference on generative AI models such as transformer, the importance of different weights exhibits substantial context-dependent variations. This naturally manifests a promising potential of adaptively configuring weight quantization to improve the generative AI inference efficiency. Although configurable weight quantization can readily leverage the hardware support of variable-precision arithmetics in modern GPU and AI accelerators, little prior research has studied how one could exploit variable weight quantization to proportionally improve the AI model memory access speed and energy efficiency. Motivated by the rapidly maturing CXL ecosystem, this work develops a CXL-based design solution to fill this gap. The key is to allow CXL memory controllers play an active role in supporting and exploiting runtime configurable weight quantization. Using transformer as a representative generative AI model, we carried out experiments that well demonstrate the effectiveness of the proposed design solution.

Predicting a trip's travel time is essential for route planning and navigation applications. The majority of research is based on international data that does not apply to Pakistan's road conditions. We designed a complete pipeline for mining trajectories from sensors data. On this data, we employed state-of-the-art approaches, including a shallow artificial neural network, a deep multi-layered perceptron, and a long-short-term memory, to explore the issue of travel time prediction on frequent routes. The experimental results demonstrate an average prediction error ranging from 30 seconds to 1.2 minutes on trips lasting 10 minutes to 60 minutes on six most frequent routes in regions of Islamabad, Pakistan., Comment: N/A

Harnessing the potential of large language models (LLMs) like ChatGPT can help address social challenges through inclusive, ethical, and sustainable means. In this paper, we investigate the extent to which ChatGPT can annotate data for social computing tasks, aiming to reduce the complexity and cost of undertaking web research. To evaluate ChatGPT's potential, we re-annotate seven datasets using ChatGPT, covering topics related to pressing social issues like COVID-19 misinformation, social bot deception, cyberbully, clickbait news, and the Russo-Ukrainian War. Our findings demonstrate that ChatGPT exhibits promise in handling these data annotation tasks, albeit with some challenges. Across the seven datasets, ChatGPT achieves an average annotation F1-score of 72.00%. Its performance excels in clickbait news annotation, correctly labeling 89.66% of the data. However, we also observe significant variations in performance across individual labels. Our study reveals predictable patterns in ChatGPT's annotation performance. Thus, we propose GPT-Rater, a tool to predict if ChatGPT can correctly label data for a given annotation task. Researchers can use this to identify where ChatGPT might be suitable for their annotation requirements. We show that GPT-Rater effectively predicts ChatGPT's performance. It performs best on a clickbait headlines dataset by achieving an average F1-score of 95.00%. We believe that this research opens new avenues for analysis and can reduce barriers to engaging in social computing research., Comment: Extended version of accepted short paper to ASONAM 2024. arXiv admin note: text overlap with arXiv:2304.10145

Threads, a new microblogging platform from Meta, was launched in July 2023. In contrast to prior new platforms, Threads was borne out of an existing parent platform, Instagram, for which all users must already possess an account. This offers a unique opportunity to study platform evolution, to understand how one existing platform can support the "birth" of another. With this in mind, this paper provides an initial exploration of Threads, contrasting it with its parent, Instagram. We compare user behaviour within and across the two social media platforms, focusing on posting frequency, content preferences, and engagement patterns. Utilising a temporal analysis framework, we identify consistent daily posting trends on the parent platform and uncover contrasting behaviours when comparing intra-platform and cross-platform activities. Our findings reveal that Threads engages more with political and AI-related topics, compared to Instagram which focuses more on lifestyle and fashion topics. Our analysis also shows that user activities align more closely on weekends across both platforms. Engagement analysis suggests that users prefer to post about topics that garner more likes and that topic consistency is maintained when users transition from Instagram to Threads. Our research provides insights into user behaviour and offers a basis for future studies on Threads.

Low-code platforms (latest reincarnation of the long tradition of model-driven engineering approaches) have the potential of saving us countless hours of repetitive boilerplate coding tasks. However, as software systems grow in complexity, low-code platforms need to adapt as well. Notably, nowadays this implies adapting to the modeling and generation of smart software. At the same time, if we want to broaden the userbase of this type of tools, we should also be able to provide more open source alternatives that help potential users avoid vendor lock-ins and give them the freedom to explore low-code development approaches (even adapting the tool to better fit their needs). To fulfil these needs, we are building BESSER, an open source low-code platform for developing (smart) software. BESSER offers various forms (i.e., notations) for system and domain specification (e.g. UML for technical users and chatbots for business users) together with a number of generators. Both types of components can be extended and are open to contributions from the community., Comment: Accepted in Exploring Modeling Methods for Systems Analysis and Development (EMSAD 2024) conference

Containerization has emerged as a revolutionary technology in the software development and deployment industry. Containers offer a portable and lightweight solution that allows for packaging applications and their dependencies systematically and efficiently. In addition, containers offer faster deployment and near-native performance with isolation and security drawbacks compared to Virtual Machines. To address the security issues, scanning tools that scan containers for preexisting vulnerabilities have been developed, but they suffer from false positives. Moreover, using different scanning tools to scan the same container provides different results, which leads to inconsistencies and confusion. Limited work has been done to address these issues. This paper provides a fully functional and extensible framework named LUCID that can reduce false positives and inconsistencies provided by multiple scanning tools. We use a database-centric approach and perform query-based analysis, to pinpoint the causes for inconsistencies. Our results show that our framework can reduce inconsistencies by 70%. The framework has been tested on both Intel64/AMD64 and ARM architecture. We also create a Dynamic Classification component that can successfully classify and predict the different severity levels with an accuracy of 84%. We believe this paper will raise awareness regarding security in container technologies and enable container scanning companies to improve their tool to provide better and more consistent results., Comment: 13 pages, 15 figures, 8 tables

Quantum computers (QC) could harbor the potential to significantly advance materials simulations, particularly at the atomistic scale involving strongly correlated fermionic systems where an accurate description of quantum many-body effects scales unfavorably with size. While a full-scale treatment of condensed matter systems with currently available noisy quantum computers remains elusive, quantum embedding schemes like dynamical mean-field theory (DMFT) allow the mapping of an effective, reduced subspace Hamiltonian to available devices to improve the accuracy of ab initio calculations such as density functional theory (DFT). Here, we report on the development of a hybrid quantum-classical DFT+DMFT simulation framework which relies on a quantum impurity solver based on the Lehmann representation of the impurity Green's function. Hardware experiments with up to 14 qubits on the IBM Quantum system are conducted, using advanced error mitigation methods and a novel calibration scheme for an improved zero-noise extrapolation to effectively reduce adverse effects from inherent noise on current quantum devices. We showcase the utility of our quantum DFT+DMFT workflow by assessing the correlation effects on the electronic structure of a real material, Ca2CuO2Cl2, and by carefully benchmarking our quantum results with respect to exact reference solutions and experimental spectroscopy measurements., Comment: 25 pages, 6 figures, supplementary information

Phishing is an increasingly sophisticated form of cyberattack that is inflicting huge financial damage to corporations throughout the globe while also jeopardizing individuals' privacy. Attackers are constantly devising new methods of launching such assaults and detecting them has become a daunting task. Many different techniques have been suggested, each with its own pros and cons. While machine learning-based techniques have been most successful in identifying such attacks, they continue to fall short in terms of performance and generalizability. This paper proposes a comprehensive methodology for detecting phishing websites. The goal is to design a system that is capable of accurately distinguishing phishing websites from legitimate ones and provides generalized performance over a broad variety of datasets. A combination of feature selection, greedy algorithm, cross-validation, and deep learning methods have been utilized to construct a sophisticated stacking ensemble classifier. Extensive experimentation on four different phishing datasets was conducted to evaluate the performance of the proposed technique. The proposed algorithm outperformed the other existing phishing detection models obtaining accuracy of 97.49%, 98.23%, 97.48%, and 98.20% on dataset-1 (UCI Phishing Websites Dataset), dataset-2 (Phishing Dataset for Machine Learning: Feature Evaluation), dataset-3 (Phishing Websites Dataset), and dataset-4 (Web page phishing detection), respectively. The high accuracy values obtained across all datasets imply the models' generalizability and effectiveness in the accurate identification of phishing websites.

Channel estimation (CE) is one of the critical signal-processing tasks of the wireless physical layer (PHY). Recent deep learning (DL) based CE have outperformed statistical approaches such as least-square-based CE (LS) and linear minimum mean square error-based CE (LMMSE). However, existing CE approaches have not yet been realized on system-on-chip (SoC). The first contribution of this paper is to efficiently implement the existing state-of-the-art CE algorithms on Zynq SoC (ZSoC), comprising of ARM processor and field programmable gate array (FPGA), via hardware-software co-design and fixed point analysis. We validate the superiority of DL-based CE and LMMSE over LS for various signal-to-noise ratios (SNR) and wireless channels in terms of mean square error (MSE) and bit error rate (BER). We also highlight the high complexity, execution time, and power consumption of DL-based CE and LMMSE approaches. To address this, we propose a novel compute-efficient LS-augmented interpolated deep neural network (LSiDNN) based CE algorithm and realize it on ZSoC. The proposed LSiDNN offers 88-90% lower execution time and 38-85% lower resource utilization than state-of-the-art DL-based CE for identical MSE and BER. LSiDNN offers significantly lower MSE and BER than LMMSE, and the gain improves with increased mobility between transceivers. It offers 75% lower execution time and 90-94% lower resource utilization than LMMSE.