检索结果-内蒙古大学图书馆

Mitigating Translationese in Low-resource Languages: The Storyboard Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Kuwanto, Garry Urua, Eno-Abasi Amuok, Priscilla Muhammad, Shamsuddeen Hassan Aremu, Anuoluwapo Otiende, Verrah Nanyanga, Loice Nyoike, Teresiah Akpan, Aniefon Udouboh, Nsima Archibong, Idongesit Moses, Idara Ige, Ifeoluwatayo Ajibade, Benjamin Awokoya, Olumide Abdulmumin, Idris Aliyu, Saminu Mohammad Iro, Ruqayya Ahmad, Ibrahim Said Smith, Deontae Michaels, Praise-EL Adelani, David Ifeoluwa Wijaya, Derry Tanti Andy, Anietie Department of Computer Science Boston University United States University of Uyo Nigeria Imperial College London United Kingdom Rochester Institute of Technology United States Data Science for Social Impact Research Group University of Pretoria South Africa Bayero University Kano Nigeria Institute for Experiential AI Northeastern University United States Department of Electrical Engineering and Computer Science Howard University United States University College London United Kingdom Monash University Indonesia Indonesia Masakhane

Low-resource languages often face challenges in acquiring high-quality language data due to the reliance on translation-based methods, which can introduce the translationese effect. This phenomenon results in translated sentences that lack fluency and naturalness in the target language. In this paper, we propose a novel approach for data collection by leveraging storyboards to elicit more fluent and natural sentences. Our method involves presenting native speakers with visual stimuli in the form of storyboards and collecting their descriptions without direct exposure to the source text. We conducted a comprehensive evaluation comparing our storyboard-based approach with traditional text translation-based methods in terms of accuracy and fluency. Human annotators and quantitative metrics were used to assess translation quality. The results indicate a preference for text translation in terms of accuracy, while our method demonstrates worse accuracy but better fluency in the language focused. © 2024, CC BY.

关键词： Translation (languages)

The Power of Bamboo: On the Post-Compromise Security for Searchable Symmetric Encryption

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Tianyang Xu, Peng Picek, Stjepan Luo, Bo Susilo, Willy Jin, Hai Liang, Kaitai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Cluster and Grid Computing Lab School of Computer Science and Technology China Huazhong University of Science and Technology Wuhan430074 China Digital Security Group Radboud University Nijmegen Netherlands Department of EECS Institute of Information Sciences The University of Kansas LawrenceKS United States Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 CD Netherlands

Dynamic searchable symmetric encryption (DSSE) enables users to delegate the keyword search over dynamically updated encrypted databases to an honest-but-curious server without losing keyword privacy. This paper studies a new and practical security risk to DSSE, namely, secret key compromise (e.g., a user’s secret key is leaked or stolen), which threatens all the security guarantees offered by existing DSSE schemes. To address this open problem, we introduce the notion of searchable encryption with key-update (SEKU) that provides users with the option of non-interactive key updates. We further define the notion of post-compromise secure with respect to leakage functions to study whether DSSE schemes can still provide data security after the client’s secret key is compromised. We demonstrate that post-compromise security is achievable with a proposed protocol called "Bamboo". Interestingly, the leakage functions of Bamboo satisfy the requirements for both forward and backward security. We conduct a performance evaluation of Bamboo using a real-world dataset and compare its runtime efficiency with the existing forward-and-backward secure DSSE schemes. The result shows that Bamboo provides strong security with better or comparable performance. © 2024, CC BY.

关键词： Bamboo

Deep learning for macular fovea detection based on ultra-widefield fundus images 2

学校读者我要写书评

暂无评论

Deep learning for macular fovea detection based on ultra-wid...

2nd International Conference on Electrical, Electronics, and Information engineering, EEIE 2023

作者： Wang, Mini Han Huang, Lina Hou, Guanghui Yang, Jie Xing, Lumin Yuan, Qiting Chong, Kelvin Kam-Lung Lin, Zhiyuan Zeng, Peijin Fang, Xiaoxiao Yao, Xiaoping Li, Qingqian Liu, Jiang Lin, Chen Department of Ophthalmology & Visual Sciences Faculty of Medicine Chinese University of Hong Kong Hong Kong999077 Hong Kong The faculty of Data Science City University of Macau 999078 China Zhuhai People's Hospital Zhuhai Hospital Affiliated with Jinan University Zhuhai519000 China The Department of AI and big data application Zhuhai Institute of Advanced Technology Chinese Academy of Sciences Zhuhai519000 China Perspective Technology Group Zhuhai519000 China Jinan University Affiliated Shenzhen Eye Hospital Shenzhen518000 China Aier Eye Hospital of Zhuhai Zhuhai519000 China College of Artificial Intelligence Chongqing Industry & Trade Polytechnic Chongqing408000 China The First Affiliated Hospital Shandong First Medical University Shandong Provincial Qianfoshan Hospital Jinan250014 China Business School Hong Kong University of Science and Technology Hong Kong999077 Hong Kong Company Ltd. Guangdong Shenzhen518000 China School of Computer Beijing Institute of Technology Zhuhai Zhuhai519000 China Union Hospital of Fujian Medical University Fuzhou353000 China Department of Ophthalmology People's Hospital of Yantian District Shenzhen518000 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518000 China Department of Ophthalmology Shenzhen People's Hospital Shenzhen518000 China

ISBN: (纸本)9781510672840

Macula fovea detection is a crucial molecular biological prerequisite for screening and diagnosing macular diseases. Without early detection and proper treatment, any abnormality involving the macula may lead to blindness. However, with the ophthalmologist shortage and time-consuming artificial evaluation, neither the accuracy nor effectiveness of the diagnosis process could be guaranteed. In this project, we proposed a light-weighted deep learning model based on ultra-widefield fundus (UWF) images for macula fovea detection tasks. This study collected 2300 ultra-widefield fundus images from Shenzhen Aier Eye Hospital in China. A light-weighted method based on a U-shape network (Unet) and Fully Convolution Network (FCN) approach is implemented on 1800 (before amplifying process) training fundus images, 400 (before amplifying process) validation images, and 100 test images. Three professional ophthalmologists were invited to mark the fovea. A method from the anatomy perspective is investigated. This approach is derived from the spatial relationship between the macula fovea and optic disc center in UWF. A set of parameters of this method is set based on the experience of ophthalmologists and verified to be effective. The ultra-widefield swept-source optical coherence tomography (UWF-OCT) approach is the grounded method. Through a comparison of proposed methods, we conclude that the proposed light-weighted Unet method outperformed other methods on macula fovea detection tasks. © 2024 SPIE.

关键词： Convolution

Fractional-order Modified Windkessel Model of the Human Arterial Vascular System

学校读者我要写书评

暂无评论

Fractional-order Modified Windkessel Model of the Human Arte...

IEEE Biomedical Circuits and Systems (BIOCAS)

作者： Mohamed A. Bahloul Yasser Aboelkassem Zehor Belkhatir Taous-Meriem Laleg-Kirati Electrical Engineering Department College of Engineering Alfaisal University Riyadh Kingdom of Saudi Arabia College of Innovation and Technology University of Michigan-Flint MI USA Michigan Institute for Data Science University of Michigan Ann Arbor MI USA Digital Health & Biomedical Engineering Group and the School of Electronics and Computer Science University of Southampton Southampton UK Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology (KAUST) Makkah Saudi Arabia National Institute for Research in Digital Science and Technology Paris-Saclay France

This paper explores fractional-order derivatives to model the apparent arterial compliance dynamics in human vascular aging subjects. The proposed model employs fractional-order capacitor (FOC) elements that combine complex and frequency-dependence characteristics of proximal and distal arterial compliances. The FOC modeling approach accounted for both resistive and capacitive properties. The mathematical derivation has been combined into a global arterial lumped parameter representation forming a novel fractional-order modified arterial Windkessel representation. The model is then validated using aortic pressure and flow rate data acquired from human subjects at different ages. The results show that the FOC model is an accurate and flexible approach that can estimate arterial compliance dynamics and central blood pressure distribution while maintaining a low model complexity.

关键词：

Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer's dementia recognition from spontaneous speech

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Rohanian, Morteza Hough, Julian Purver, Matthew Cognitive Science Group School of Electronic Engineering and Computer Science Queen Mary University of London Department of Knowledge Technologies Jožef Stefan Institute

This paper is a submission to the Alzheimer's Dementia Recognition through Spontaneous Speech (ADReSS) challenge, which aims to develop methods that can assist in the automated prediction of severity of Alzheimer's Disease from speech data. We focus on acoustic and natural language features for cognitive impairment detection in spontaneous speech in the context of Alzheimer's Disease Diagnosis and the mini-mental state examination (MMSE) score prediction. We proposed a model that obtains unimodal decisions from different LSTMs, one for each modality of text and audio, and then combines them using a gating mechanism for the final prediction. We focused on sequential modelling of text and audio and investigated whether the disfluencies present in individuals' speech relate to the extent of their cognitive impairment. Our results show that the proposed classification and regression schemes obtain very promising results on both development and test sets. This suggests Alzheimer's Disease can be detected successfully with sequence modeling of the speech data of medical sessions. © 2021, CC BY.

关键词： Neurodegenerative diseases

Alzheimer's dementia recognition using acoustic, lexical, disfluency and speech pause features robust to noisy inputs

学校读者我要写书评

暂无评论

arXiv 2021年

We present two multimodal fusion-based deep learning models that consume ASR transcribed speech and acoustic data simultaneously to classify whether a speaker in a structured diagnostic task has Alzheimer's Disease and to what degree, evaluating the ADReSSo challenge 2021 data. Our best model, a BiLSTM with highway layers using words, word probabilities, disfluency features, pause information, and a variety of acoustic features, achieves an accuracy of 84% and RSME error prediction of 4.26 on MMSE cognitive scores. While predicting cognitive decline is more challenging, our models show improvement using the multimodal approach and word probabilities, disfluency, and pause information over word-only models. We show considerable gains for AD classification using multimodal fusion and gating, which can effectively deal with noisy inputs from acoustic features and ASR hypotheses. © 2021, CC BY.

关键词： Neurodegenerative diseases

Learning Fair Representations through Uniformly Distributed Sensitive Attributes

学校读者我要写书评

暂无评论

Learning Fair Representations through Uniformly Distributed ...

Secure and Trustworthy Machine Learning (SaTML), IEEE Conference on

作者： Patrik Joslin Kenfack Adín Ramírez Rivera Adil Mehmood Khan Manuel Mazzara Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia Department of Informatics Digital Signal Processing and Image Analysis (DSB) group University of Oslo Oslo Norway School of Computer Science University of Hull Hull UK Institute of Software Development and Engineering Innopolis University Innopolis Russia

Machine Learning (ML) models trained on biased data can reproduce and even amplify these biases. Since such models are deployed to make decisions that can affect people's lives, ensuring their fairness is critical. One approach to mitigate possible unfairness of ML models is to map the input data into a less-biased new space by means of training the model on fair representations. Several methods based on adversarial learning have been proposed to learn fair representation by fooling an adversary in predicting the sensitive attribute (e.g., gender or race). However, adversarial-based learning can be too difficult to optimize in practice; besides, it penalizes the utility of the representation. Hence, in this research effort we train bias-free representations from the input data by inducing a uniform distribution over the sensitive attributes in the latent space. In particular, we propose a probabilistic framework that learns these representations by enforcing the correct reconstruction of the original data, plus the prediction of the attributes of interest while eliminating the possibility of predicting the sensitive ones. Our method leverages the inability of Deep Neural Networks (DNNs) to generalize when trained on a noisy label space to regularize the latent space. We use a network head that predicts a noisy version of the sensitive attributes in order to increase the uncertainty of their predictions at test time. Our experiments in two datasets demonstrated that the proposed model significantly improves fairness while maintaining the prediction accuracy of downstream tasks.

关键词：

A Reliable Method to Estimate the Bispectral Index Value Using a Single Frontal EEG Channel for Intra and Inter Subject Variability

学校读者我要写书评

暂无评论

A Reliable Method to Estimate the Bispectral Index Value Usi...

2023 IEEE International Symposium on Medical Measurements and Applications, MeMeA 2023

作者： Shahbakhti, Mohammad Beiramvand, Matin Krycinska, Roza Nasiri, Erfan Chen, Wei Sole-Casals, Jordi Wierzchon, Michal Broniec-Wojcik, Anna Augustyniak, Piotr Marozas, Vaidotas Biomedical Engineering Institute Kaunas University of Technology Kaunas Lithuania Tampere University Faculty of Information Technology and Communication Tempere Finland Jagiellonian University Medical College Doctoral School in Medical and Health Sciences Krakow Poland Jagiellonian University Collegium Medicum Department of Interdisciplinary Intensive Care Krakow Poland Allameh Tabataba'i University Faculty of Statistics Mathematics and Computer Tehran Iran Fudan University Center for Intelligent Medical Electronics School of Information Science and Technology Shanghai China University of Vic-Central University of Catalonia Data and Signal Processing Research Group Vic Spain Institute of Psychology Jagiellonian University Krakow Poland Agh University of Science and Technology Department of Biocybernetics and Biomedical Engineering Krakow Poland

ISBN: (纸本)9781665493840

Objective: Monitoring the depth of anesthesia (DoA) plays an important role for administering the drug injection during a surgery, i.e., preventing undesired awareness and inordinate anesthetic depth. Although the bispectral index (BIS) monitor is the golden standard system for the DoA monitoring, it is still not affordable for the developing countries. Alternatively, a low-cost electroencephalogram (EEG) headband can be used. The objective of this paper is to present a new algorithm for estimating the BIS values using a single frontal EEG channel. Method: In the first step, the EEG signal is filtered for the elimination of artifacts and is split into its sub-bands. In the second step, several linear and nonlinear features are extracted from each sub-band and fed to a random forest regression model in order to estimate the BIS. The performance of the proposed algorithm is assessed using EEG data recorded from twenty-four subjects during the general anesthesia and is validated in terms of correlation coefficient (CC) and absolute error (AE) between the reference and estimated BIS values. Results: The proposed algorithm achieved the mean CC of 0.83 and AE of 6.5 for intra subject variability and mean CC of 0.87 and AE of 5.5 for inter subject variability. Significance: Given the similar results for both intra and inter subject variability, the proposed algorithm has the potential to be used in the real-world scenario. © 2023 IEEE.

关键词： Electroencephalography

Nondestructive Chicken Egg Fertility Detection Using CNN-Transfer Learning Algorithms

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Saifullah, Shoffan Drezewski, Rafal Yudhana, Anton Pranolo, Andri Kaswijanti, Wilis Suryotomo, Andiko Putro Putra, Seno Aji Khaliduzzaman, Alin Prabuwono, Anton Satria Japkowicz, Nathalie Institute of Computer Science AGH University of Krakow Krakow30-059 Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta55281 Indonesia Center of Knowledge Engineering and Data Science Department of Electrical Engineering and Informatics Universitas Negeri Malang Malang65145 Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia College of Computer and Information Hohai University Nanjing211100 China Department of Informatics Faculty of Industrial Technology Universitas Ahmad Dahlan Yogyakarta55166 Indonesia Faculty of Agricultural Engineering and Technology Sylhet Agricultural University Sylhet3100 Bangladesh Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science American University WashingtonDC20016 United States

This study explored the application of CNN-Transfer Learning for nondestructive chicken egg fertility detection for precise poultry hatchery practices. Four models, VGG16, ResNet50, InceptionNet, and MobileNet, were trained and evaluated on a dataset (200 single egg images) using augmented images (rotation, flip, scale, translation, and reflection). The training results demonstrated that all models achieved high accuracy, indicating their ability to learn and classify chicken eggs’ fertility. However, variations in accuracy and performance were observed when these models were evaluated on the testing datasets. The InceptionNet exhibited the best overall performance, accurately classifying fertile and non-fertile eggs. It demonstrated excellent performance in all parameters of the evaluation metrics for both training and testing datasets. When evaluated on the testing datasets, it achieved an accuracy of 0.98, a sensitivity of 1 for detecting fertile eggs, and a specificity of 0.96 for identifying non-fertile eggs. The higher performance is attributed to its unique architecture, efficiently capturing features at different scales, which leads to improved accuracy and robustness. Further optimization and fine-tuning of the models might be necessary to address the limitations in accurately detecting fertile and non-fertile eggs using other models. This study highlighted the potential of CNN-transfer learning for nondestructive fertility detection and emphasized the need for further research to enhance the models’ capabilities and to ensure accurate *** Codes CS-Class: 68T07, 68T45, 68U10, ICT-Class: 94A08 © 2023, CC BY-SA.

关键词： Image classification