检索结果-内蒙古大学图书馆

A Trustable LSTM-Autoencoder Network for Cyberbullying Detection on Social Media Using Synthetic Data

学校读者我要写书评

暂无评论

A Trustable LSTM-Autoencoder Network for Cyberbullying Detec...

IEEE International Conference on Big Data

作者： Mst Shapna Akter Hossain Shahriar Alfredo Cuzzocrea Fan Wu Juanjose Rodriguez-Cardenas Department of Intelligent Systems and Robotics University of West Florida USA Center of Cybersecurity University of West Florida USA iDEA Lab University of Calabria Rende Italy Dept. of Computer Science Tuskegee University Tuskegee USA Dept. of Information Technology Kennesaw State University Georgia USA

Social media cyberbullying has a detrimental effect on human life. As online social networking grows daily, the amount of hate speech also increases. Such terrible content can cause depression and actions related to suicide. This paper proposes a trustable LSTM-Autoencoder Network for cyberbullying detection on social media using synthetic data. We have demonstrated a cutting-edge method to address data availability difficulties by producing machine-translated data. However, several languages such as Hindi and Bangla still lack adequate investigations due to a lack of datasets. We carried out experimental identification of aggressive comments on Hindi, Bangla, and English datasets using the proposed model and traditional models, including Long Short-Term Memory (LSTM), Bidirectional Long ShortTerm Memory (BiLSTM), LSTM-Autoencoder, Word2vec, Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-trained Transformer 2 (GPT-2) models. We employed evaluation metrics such as f1-score, accuracy, precision, and recall to assess the models’ performance. Our proposed model outperformed all the models on all datasets, achieving the highest accuracy of 95%. Our model achieves state-of-the-art results among all the previous works on the dataset we used in this paper.

关键词：

The Partner Modelling Questionnaire: A validated self-report measure of perceptions toward machines as dialogue partners

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Doyle, Philip R. Gessinger, Iona Edwards, Justin Clark, Leigh Dumbleton, Odile Garaialde, Diego Rough, Daniel Bleakley, Anna Branigan, Holly P. Cowan, Benjamin R. School of Information and Communication Studies University College Dublin Ireland Learning and Educational Technology Research Lab University of Oulu Finland Computational Foundry Swansea University United Kingdom School of Computer Science University College Dublin Ireland School of Science and Engineering University of Dundee United Kingdom Psychology Department University of Edinburgh United Kingdom

Recent work has looked to understand user perceptions of speech agent capabilities as dialogue partners (termed partner models), and how this affects user interaction. Yet, partner model effects are currently inferred from language production as no metrics are available to quantify these subjective perceptions more directly. Through three phases of work, we develop and validate the Partner Modelling Questionnaire (PMQ): an 18-item self-report semantic differential scale designed to reliably measure people’s partner models of non-embodied speech interfaces. Through confirmatory factor analysis, we confirm that the PMQ scale consists of three factors: communicative competence and dependability, human-likeness in communication, and communicative flexibility. Our studies show that the measure consistently demonstrates good internal reliability, strong test-retest reliability over 4- and 12-week intervals, and predictable convergent/divergent validity. Based on our findings, we discuss the multidimensional nature of partner models, whilst identifying key future research avenues that the development of the PMQ facilitates. Notably, this includes the need to identify the activation, sensitivity, and dynamism of partner models in speech interface interaction. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

A Dynamic Programming Framework for Optimal Planning of Redundant Robots Along Prescribed Paths With Kineto-Dynamic Constraints

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ferrentino, Enrico Savino, Heitor J. Franchi, Antonio Chiacchio, Pasquale University of Salerno SA Fisciano84084 Italy Ambev Robotics Lab Anheuser-Busch InBev SP Jacareí12334-480 Brazil The Robotics and Mechatronics Laboratory Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede7522NH Netherlands The Department of Computer Control and Management Engineering Sapienza University of Rome Rome00185 Italy

Offline optimal planning of trajectories for redundant robots along prescribed task space paths is usually broken down into two consecutive processes: first, the task space path is inverted to obtain a joint space path, then, the latter is parametrized with a time law. If the two processes are separated, they cannot optimize the same objective function, ultimately providing sub-optimal results. In this paper, a unified approach is presented where dynamic programming is the underlying optimization technique. Its flexibility allows accommodating arbitrary constraints and objective functions, thus providing a generic framework for optimal planning of real systems. To demonstrate its applicability to a real world scenario, the framework is instantiated for time-optimality on Franka Emika's Panda robot. The well-known issues associated with the execution of non-smooth trajectories on a real controller are partially addressed at planning level, through the enforcement of constraints, and partially through post-processing of the optimal solution. The experiments show that the proposed framework is able to effectively exploit kinematic redundancy to optimize the performance index defined at planning level and generate feasible trajectories that can be executed on real hardware with satisfactory results. Note to Practitioners-The common planning algorithms which consolidated over the years for generating trajectories for non-redundant robots are not adequate to fully exploit the more advanced capabilities offered by redundant robots. This is especially true in performance-demanding tasks, as for robots employed on assembly lines in manufacturing industries, repeatedly performing the same activity. Once the assembly line engineer has defined the tool path in the task space, our planning algorithm unifies inverse kinematics and time parametrization so as to bring the manipulator at its physical limits to achieve specific efficiency goals, being execution time the most typical

关键词： Robot programming

ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hamed, Injy Habash, Nizar Abdennadher, Slim Vu, Ngoc Thang Computational Approaches to Modeling Language Lab New York University Abu Dhabi United Arab Emirates Institute for Natural Language Processing University of Stuttgart Germany Computer Science Department The German University in Cairo Germany

We present our work on collecting ArzEnST, a code-switched Egyptian Arabic - English Speech Translation Corpus. This corpus is an extension of the ArzEn speech corpus, which was collected through informal interviews with bilingual speakers. In this work, we collect translations in both directions, monolingual Egyptian Arabic and monolingual English, forming a three-way speech translation corpus. We make the translation guidelines and corpus publicly available. We also report results for baseline systems for machine translation and speech translation tasks. We believe this is a valuable resource that can motivate and facilitate further research studying the code-switching phenomenon from a linguistic perspective and can be used to train and evaluate NLP systems. © 2022, CC BY.

关键词： Codes (symbols)

Towards identifying possible fault-tolerant advantage of quantum linear system algorithms in terms of space, time and energy

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tu, Yue Dubynskyi, Mark Mohammadisiahroudi, Mohammadhossein Riashchentceva, Ekaterina Cheng, Jinglei Ryashchentsev, Dmitry Terlaky, Tamás Liu, Junyu Department of Computer Science The University of Pittsburgh PittsburghPA15260 United States Department of Computational and Applied Mathematics The University of Chicago ChicagoIL60637 United States Mason Experimental Geometry Lab FairfaxVA22030 United States Department of Industrial and Systems Engineering Lehigh University BethlehemPA18015 United States The University of Portland PortlandOR97203 United States Charles Schwab Corporation WestlakeTX76262 United States

Quantum computing, a prominent non-Von Neumann paradigm beyond Moore’s law, can offer superpolynomial speedups for certain problems. Yet its advantages in efficiency for tasks like machine learning remain under investigation, and quantum noise complicates resource estimations and classical comparisons. We provide a detailed estimation of space, time, and energy resources for fault-tolerant superconducting devices running the Harrow-Hassidim-Lloyd (HHL) algorithm, a quantum linear system solver relevant to linear algebra and machine learning. Excluding memory and data transfer, possible quantum advantages over the classical conjugate gradient method could emerge at N ≈ 233 ∼ 248 or even lower, requiring O(105) physical qubits, O(1012 ∼ 1013) Joules, and O(106) seconds under surface code fault-tolerance with three types of magic state distillation (15-1, 116-12, 225-1). Key parameters include condition number, sparsity, and precision κ,s ≈ O(10 ∼ 100), ϵ ∼ 0.01, and physical error 10−5. Our resource estimator adjusts N,κ,s,ϵ, providing a map of quantum-classical boundaries and revealing where a practical quantum advantage may arise. Our work quantitatively determine how advanced a fault-tolerant quantum computer should be to achieve possible, significant benefits on problems related to real-world. Copyright © 2025, The Authors. All rights reserved.

关键词： Quantum computers

Multimodal information structuring with single-layer soft skins and high-density electrical impedance tomography

学校读者我要写书评

暂无评论

science robotics 2025年第103期10卷 eadq2303页

作者： David Hardman Thomas George Thuruthel Fumiya Iida Bio-Inspired Robotics Lab University of Cambridge Cambridge UK. Department of Computer Science University College London London UK.

The human skin can reliably capture a wide range of multimodal data over a large surface while providing a soft interface. Artificial technologies using microelectromechanical systems (MEMS) can emulate these biological functions but present numerous challenges in fabrication, delamination due to soft-rigid interfaces, and electrical interference. To address these difficulties, we present a single-layer multimodal sensory skin made using only a highly sensitive hydrogel membrane. Using electrical impedance tomography techniques, we accessed up to 863,040 conductive pathways across the membrane, allowing us to identify at least six distinct types of multimodal stimuli, including human touch, damage, multipoint insulated presses, and local heating. Through comprehensive physical testing, we demonstrate that the highly redundant and coupled sensory information from these pathways can be structured using data-driven techniques, selecting which pathways should be monitored for efficient multimodal perception. To demonstrate our approach's versatility, we cast the hydrogel into the shape and size of an adult human hand. Using our information structuring strategy, we demonstrate the hand's ability to predict environmental conditions, localize human touch, and generate proprioceptive data. Our framework addresses the challenge of physically extracting meaningful information in multimodal soft sensing, opening new directions for the information-led design of single-layer skins in sensitive systems.

关键词：

Optimizing Moving Target Defense For Cyber Anomaly Detection

学校读者我要写书评

暂无评论

Optimizing Moving Target Defense For Cyber Anomaly Detection

computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： M. Vubangsi Auwalu Saleh Mubarak Jameel Yayah Chadi Altrjman Manika Manwal Satya Prakash Yadav Fadi Al-Turjman AI Engineering Dep’t Research Center for AI and IoT AI and Robotics Institute Near East University Mersin Turkey Computational Materials Science Lab HTTTC Bambili University of Bamenda Bambili NWR Cameroon Waterloo University Canada Computer Science and Engineering GraphicEra Hill University Dehradun India Affiliated to AKTU G.L. Bajaj Institute of Technology and Management (GLBITM) Greater Noida India Faculty of Engineering University of Kyrenia Mersin Turkey

In this research, we evaluate the effectiveness of different MTD techniques on the transformer-based cyber anomaly detection models trained on the KDD Cup’99 Dataset, a publicly available dataset commonly used for evaluating intrusion detection systems. We explore the trade-offs between security and performance when using MTD techniques for cyber anomaly detection and investigate how MTD techniques can be combined with other cybersecurity techniques to improve the overall security of the system. We evaluate their performance using standard metrics such as accuracy and FI score, as well as measures of robustness against adversarial attacks. Our results show that MTD techniques can significantly improve the security of the anomaly detection model, with some techniques being more effective than others depending on the model architecture. We also find that there are trade-offs between security and performance, with some MTD techniques leading to a reduction in model accuracy or an increase in computation time. However, we demonstrate that these tradeoffs can be mitigated by optimizing the MTD parameters for the specific model architecture.

关键词：

Privacy-preserving federated prediction of pain intensity change based on multi-center survey data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Das, Supratim Rafie, Mahdie Kammer, Paula Skou, Søren T. Grønne, Dorte T. Roos, Ewa M. Hajek, André König, Hans-Helmut Ullah, Md Shihab Probul, Niklas Baumbach, Jan Baumbach, Linda Institute for Computational Systems Biology University of Hamburg Albert-Einstein-Ring 8-10 Hamburg22761 Germany Department of Health Economics and Health Services Research University Medical Center Hamburg-Eppendorf Martinistraße 52 Hamburg20246 Germany Center for Muscle and Joint Health Department of Sports Science and Clinical Biomechanics University of Southern Denmark Campusvej 55 Odense5230 Denmark The Research and Implementation Unit PROgrez Department of Physiotherapy and Occupational Therapy Næstved-Slagelse-Ringsted Hospitals Fælledvej 2C Slagelse4200 Denmark Computational Biomedicine Lab Department of Mathematics and Computer Science University of Southern Denmark Odense Denmark

Background: Patient-reported survey data are used to train prognostic models aimed at improving healthcare. However, such data are typically available multi-centric and, for privacy reasons, cannot easily be centralized in one data repository. Models trained locally are less accurate, robust, and generalizable. We present and apply privacy-preserving federated machine learning techniques for prognostic model building, where local survey data never leaves the legally safe harbors of the medical centers. Methods: We used centralized, local, and federated learning techniques on two healthcare datasets (GLA:D® data from the five health regions of Denmark and international SHARE data of 27 countries) to predict two different health outcomes. We compared linear regression, random forest regression, and random forest classification models trained on local data with those trained on the entire data in a centralized and in a federated fashion. Results: In GLA:D® data, federated linear regression (R2 0.34, RMSE 18.2) and federated random forest regression (R2 0.34, RMSE 18.3) models outperform their local counterparts (i.e., R2 0.32, RMSE 18.6, R2 0.30, RMSE 18.8) with statistical significance. We also found that centralized models (R2 0.34, RMSE 18.2, R2 0.32, RMSE 18.5, respectively) did not perform significantly better than the federated models. In SHARE, the federated model (AC 0.78, AUROC: 0.71) and centralized model (AC 0.84, AUROC: 0.66) perform significantly better than the local models (AC: 0.74, AUROC: 0.69). Conclusion: Federated learning enables the training of prognostic models from multi-center surveys without compromising privacy and with only minimal or no compromise regarding model performance. © 2024, CC BY.

关键词： Differential privacy

Towards Virtual Clinical Trials of Radiology AI with Conditional Generative Modeling

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Killeen, Benjamin D. Wan, Bohua Kulkarni, Aditya V. Drenkow, Nathan Oberst, Michael Yi, Paul H. Unberath, Mathias Department of Computer Science Johns Hopkins University BaltimoreMD21218 United States Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Malone Center for Healthcare in Engineering Johns Hopkins University BaltimoreMD21218 United States Department of Radiology St. Jude Children’s Research Hospital 262 Danny Thomas Place MemphisTN38105-3678 United States Applied Physics Laboratory Johns Hopkins University LaurelMD20723 United States

Artificial intelligence and machine learning (AI/ML) are poised to transform healthcare by enabling personalized and efficient patient care through data-driven insights. Although radiology is at the forefront of AI/ML adoption, in practice, the potential of AI/ML models is often overshadowed by severe failures to generalize: AI/ML models can have performance degradation of up to 20% when transitioning from controlled test environments to clinical use by radiologists. This mismatch in advertised and observed AI/ML performance raises concerns that radiologists will be misled by incorrect AI/ML predictions in practice and/or grow to distrust AI/ML, rendering these promising technologies practically ineffectual. Exhaustive clinical trials of AI/ML models throughout the development cycle on abundant and diverse data is thus critical to anticipate AI/ML model degradation when encountering varied data samples. Achieving these goals in practice, however, is challenging due to the high costs of collecting the necessary diverse data samples and the corresponding annotations. To overcome these limitations, we introduce a novel conditional generative AI model designed for virtual clinical trials (VCTs) of radiology AI/ML, capable of realistically synthesizing full-body CT images of patients with specified attributes. By learning the joint distribution of images and anatomical structures, and operating on latent representations for memory efficiency, our model enables precise replication of real-world patient populations with unprecedented detail at this scale. We demonstrate meaningful evaluation of radiology AI models through VCTs powered by our synthetic CT study populations, revealing model degradation and facilitating algorithmic auditing for bias-inducing data attributes. Our generative AI approach to VCTs is a promising avenue towards a scalable solution to assess model robustness, mitigate biases, and safeguard patient care by enabling simpler testing and evaluation of A

关键词： computerized tomography