检索结果-内蒙古大学图书馆

Detecting Euphemisms with Literal Descriptions and Visual Imagery

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kesen, Ilker Erdem, Aykut Erdem, Erkut Calixto, Iacer Koç University KUIS AI Center Turkey Koç University Computer Engineering Department Turkey Hacettepe University Computer Engineering Department Turkey Amsterdam UMC University of Amsterdam Department of Medical Informatics Netherlands Amsterdam Public Health Methodology & Mental Health Amsterdam Netherlands

This paper describes our two-stage system1 for the Euphemism Detection shared task hosted by the 3rd Workshop on Figurative Language Processing in conjunction with EMNLP 2022. Euphemisms tone down expressions about sensitive or unpleasant issues like addiction and death. The ambiguous nature of euphemistic words or expressions makes it challenging to detect their actual meaning within a context. In the first stage, we seek to mitigate this ambiguity by incorporating literal descriptions into input text prompts to our baseline model. It turns out that this kind of direct supervision yields remarkable performance improvement. In the second stage, we integrate visual supervision into our system using visual imageries, two sets of images generated by a text-to-image model by taking terms and descriptions as input. Our experiments demonstrate that visual supervision also gives a statistically significant performance boost. Our system achieved the second place with an F1 score of 87.2%, only about 0.9% worse than the best submission. © 2022, CC BY.

关键词：

Pattern Detection in Heart Sound Signal Based on Android Application 3

学校读者我要写书评

暂无评论

Pattern Detection in Heart Sound Signal Based on Android App...

3rd International Conference on computer and informatics engineering, IC2IE 2020

作者： Oktivasari, Prihatin Vallian, Fikri Riandini Polikteknik Negeri Jakarta Department of Informatics and Computer Engineering Depok Indonesia Politeknik Negeri Jakarta Department of Electrical Engineering Depok Indonesia

ISBN: (纸本)9781728182476

The heart sound detector using an android-based electronic stethoscope is a development of an acoustic stethoscope. This tool converts the sound of the heartbeat into an electrical signal by wirelessly displaying the first heart sound signal S1 (Lub), and the second heart sound signal S2 (Dub) on the android application. A low-cost electronic stethoscope consisting of a condenser microphone that converts the sound of the heartbeat captured by the stethoscope into a heartbeat signal, a signal conditioning circuit that corrects the detected signal. The output signal from the conditioner circuit is processed by the ADC on the Arduino, which will then be sent to Android using Bluetooth. The open source software used to display heart rate detection results is Android Studio. S1 and S2 heart sound signal patterns have been recorded in real-time with intervals of 2-3 seconds duration, and no time delay. The resulting signals can be saved as graphs and WAV files. © 2020 IEEE.

关键词： Bluetooth

Radiation-constrained algorithms for wireless energy transfer in ad hoc networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Nikoletseas, Sotiris Raptis, Theofanis P. Raptopoulos, Christoforos Department of Computer Engineering and Informatics University of Patras Greece Computer Technology Institute and Press "Diophantus" Greece

We study the problem of efficiently charging a set of rechargeable nodes using a set of wireless chargers, under safety constraints on the electromagnetic radiation incurred. In particular, we define a new charging model that greatly differs from existing models in that it takes into account real technology restrictions of the chargers and nodes of the network, mainly regarding energy limitations. Our model also introduces non-linear constraints (in the time domain), that radically change the nature of the computational problems we consider. In this charging model, we present and study the Low Radiation Efficient Charging Problem (LREC), in which we wish to optimize the amount of "useful" energy transferred from chargers to nodes (under constraints on the maximum level of imposed radiation). We present several fundamental properties of this problem and provide indications of its hardness. Finally, we propose an iterative local improvement heuristic for LREC, which runs in polynomial time and we evaluate its performance via simulation. Our algorithm decouples the computation of the objective function from the computation of the maximum radiation and also does not depend on the exact formula used for the computation of the electromagnetic radiation in each point of the network, achieving good trade-offs between charging efficiency and radiation control;it also exhibits good energy balance properties. We provide extensive simulation results supporting our claims and theoretical results. © 2021, CC BY-NC-ND.

关键词： Ad hoc networks

Investigating Efficacy of Perplexity in Detecting LLM-Generated Code

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Jinwei Zhang, He Yang, Yanjin Cheng, Zeru Lyu, Jun Liu, Bohan Zhou, Xin Yang, Lanxin Bacchelli, Alberto Chiam, Yin Kia Chiew, Thiam Kian State Key Laboratory of Novel Software Technology Software Institute Nanjing University Nanjing210008 China Department of Informatics University of Zürich Zürich8006 Switzerland Department of Software Engineering Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur50603 Malaysia

Large language model-generated code (LLMgCode) has become increasingly prevalent in software development. Many studies report that LLMgCode has more quality and security issues than human-authored code (HaCode). It is common for LLMgCode to mix with HaCode in a code change, while the change is signed by only human developers, without being carefully checked. Many automated methods have been proposed to detect LLMgCode from HaCode, in which the perplexity-based method (PERPLEXITY for short) is the state-of-the-art method. However, the efficacy evaluation of PERPLEXITY has focused on the detection accuracy. In this article, we are interested in whether PERPLEXITY is good enough in a wider range of realistic evaluation settings. To this end, we devise a large-scale dataset that includes 11,664 HaCode snippets and 13,164 LLMgCode snippets, and based on that, we carry out a family of experiments to compare PERPLEXITY against feature-based and pre-training-based methods from three perspectives: (1) detection accuracy in terms of programming language, degree of difficulty, and scale of solution, (2) generalization capability, and (3) inference efficiency. The experimental results show that PERPLEXITY has the best generalization capability while it has low accuracy and efficiency in most cases. Based on the experimental results and detection mechanism of PERPLEXITY, we discuss implications into both the strengths and limitations of PERPLEXITY, e.g., PERPLEXITY is unsuitable for high-level programming languages while it has good interpretability. As the first large-scale investigation on detecting LLMgCode from HaCode, this article provides a wide range of evidence for future improvement. Copyright © 2024, The Authors. All rights reserved.

关键词： High level languages

Automatic melanoma detection using discrete cosine transform features and metadata on dermoscopic images

学校读者我要写书评

暂无评论

Journal of King Saud University - computer and Information Sciences 2024年第2期36卷

作者： Yousefi, Shamim Najjar-Ghabel, Samad Danehchin, Ramin Band, Shahab S. Hsu, Chung-Chian Mosavi, Amir Department of Computer Engineering University of Mohaghegh Ardabili Ardabil Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan John von Neumann Faculty of Informatics Budapest Hungary Ludovika University of Public Service Budapest Hungary

Machine learning contributes in improving the accuracy of melanoma detection. There are extensive studies in classic and deep learning-based approaches for melanoma detection in the literature. Still, they are not accurate or require high learning data. This paper proposes a hybrid mechanism for automated melanoma detection on dermoscopic images based on Discrete Cosine Transform features and metadata. It is composed of three steps. First, extra information/artifacts are deleted;the remaining pixels are standardized for accurate processing. Second, the reliability of the mechanism is improved by the Radon transform, extra data is removed using the Top-hat filter, and the detection rate is increased by Discrete Wavelet Transform and Discrete Cosine Transform. Then, the number of features is reduced by Locality Sensitive Discriminant Analysis. The third step divides the images into learning and test ones to create image-based models using learning data. Finally, the best model is selected based on test data and improved by a metadata-based model. Simulation results show that the decision tree provides the most practical image-based model by improving accuracy and sensitivity. Besides, the comparison results demonstrate that our model improves the F-Value to detect melanoma superior to other approaches. © 2024 The Author(s)

关键词： Artificial intelligence Big data Data science Dermoscopic image Discrete cosine transform features Machine learning Melanoma detection Metadata

On the Evaluation of Access-point Handovers for UAVs in Long-distance Missions

学校读者我要写书评

暂无评论

On the Evaluation of Access-point Handovers for UAVs in Long...

2021 International Conference on Unmanned Aircraft Systems, ICUAS 2021

作者： Fagundes, Leonardo A. Souza, Vitor Barbosa Brandao, Alexandre S. Núcleo de Especialização em Robótica Federal University of Viçosa Department of Electrical Engineering and Graduate Program on Computer Science Viçosa Brazil Federal University of Viçosa Graduate Program on Computer Science Department of Informatics Viçosa Brazil

ISBN: (纸本)9780738131153

Unmanned Aerial Vehicle (UAV) systems are being increasingly used in a broad range of applications requiring extensive communications either to interconnect the UAVs with each other or to connect them with Ground Control Stations (GCS). Due to the complexity and difficulty of performing long distance experiments with these robots, simulation becomes a viable and necessary alternative. However, focusing either on the modeling of UAV operations or communication dynamics, available simulation tools are not able to capture the complex interdependencies between these two aspects, especially in applications where extensive communications are required. The main contribution of this work is the modeling and implementation of strategies for enhancing connectivity of a UAV performing long-distance navigation tasks, taking into account applications' requirements. The proposed strategies aim at assessing the impact of frequent handovers between wireless access points in terms of packet loss and available bandwidth. The first strategy prioritizes maintaining a connection until the signal-to-noise ratio (SNR) observed by the robot reaches a predefined threshold. For this, it is assumed that the data to be transmitted is small enough so that the robot may change its modulation to obtain smaller bandwidths while improving connection time. The second one prioritizes bandwidth availability, thus, it always searches for a network that is able to offer data rates higher than a minimum threshold. A hybrid model is validated by considering the characteristics of each individual strategy. The capabilities of the simulation tool designed for this work are illustrated through some case-study scenarios. © 2021 IEEE.

关键词： Unmanned aerial vehicles (UAV)

Fistula Condition Monitoring System by the Noise Changes Dynamics

学校读者我要写书评

暂无评论

Fistula Condition Monitoring System by the Noise Changes Dyn...

International Conference on Industrial engineering, Applications and Manufacturing (ICIEAM)

作者： N. I. Yumagulov D. A. Fedorov D. V. Topolsky Dep. for Education in Physics and Mathematics Nizhnevartovsk State University Nizhnevartovsk Russia Department of Informatics and Computer Engineering Surgut State University Surgut Russia Department of Electronic Computing Machines South Ural State University (NRU) Chelyabinsk Russia

The paper presents an automated system for collecting and processing data for diagnosing the condition of an arteriovenous fistula. In the fistula, due to increased blood flow, characteristic noises and vibrations of the vessel walls occur. Using the data acquisition device, the acoustic noise of the arteriovenous fistula is recorded. The system processes and analyzes the measured data, evaluates the main indicators of the fistula condition. Changing the main indicators allows you to evaluate the dynamics of changes in the fistula condition. The developed system can be used for remote, long-term and continuous diagnostics of blood vessels in patients on hemodialysis.

关键词：

SLIFER: Investigating Performance and Robustness of Malware Detection Pipelines

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ponte, Andrea Trizna, Dmitrijs Demetrio, Luca Biggio, Battista Ogbu, Ivan Tesfai Roli, Fabio Department of Informatics Bioengineering Robotics and Systems Engineering University of Genova Viale Causa 13 Genova16145 Italy Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 Rome00185 Italy Department of Electrical and Electronic Engineering University of Cagliari Via Marengo 3 Cagliari09123 Italy Rina Consulting S.p.A. Via Antonio Cecchi 6 Genova16129 Italy

As a result of decades of research, Windows malware detection is approached through a plethora of techniques. However, there is an ongoing mismatch between academia – which pursues an optimal performances in terms of detection rate and low false alarms – and the requirements of real-world scenarios. In particular, academia focuses on combining static and dynamic analysis within a single or ensemble of models, falling into several pitfalls like (i) firing dynamic analysis without considering the computational burden it requires;(ii) discarding impossible-to-analyze samples;and (iii) analyzing robustness against adversarial attacks without considering that malware detectors are complemented with more non-machine-learning components. Thus, in this paper we bridge these gaps, by investigating the properties of malware detectors built with multiple and different types of analysis. To do so, we develop SLIFER, a Windows malware detection pipeline sequentially leveraging both static and dynamic analysis, interrupting computations as soon as one module triggers an alarm, requiring dynamic analysis only when needed. Contrary to the state of the art, we investigate how to deal with samples that impede analyzes, showing how much they impact performances, concluding that it is better to flag them as legitimate to not drastically increase false alarms. Lastly, we perform a robustness evaluation of SLIFER. Counter-intuitively, the injection of new content is either blocked more by signatures than dynamic analysis, due to byte artifacts created by the attack, or it is able to avoid detection from signatures, as they rely on constraints on file size disrupted by attacks. As far as we know, we are the first to investigate the properties of sequential malware detectors, shedding light on their behavior in real production environment. Copyright © 2024, The Authors. All rights reserved.

关键词： Malware

3D point cloud for objects and scenes classification, recognition, segmentation, and reconstruction: A review

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Elharrouss, Omar Hassine, Kawther Zayyan, Ayman Chatri, Zakariyae Al-Maadeed, Somaya Abualsaud, Khalid Department of Computer Science and Engineering Qatar University Doha Qatar Higher School of Communications of Tunis University of Carthage Tunis Tunisia Department of Informatics Faculty of Sciences Dhar-Mahraz University of Sidi Mohamed Ben Ab-dellah Fez Morocco

Three-dimensional (3D) point cloud analysis has become one of the attractive subjects in realistic imaging and machine visions due to its simplicity, flexibility and powerful capacity of visualization. Actually, the representation of scenes and build- ings using 3D shapes and formats leveraged many applications among which automatic driving, scenes and objects reconstruction, etc. Nevertheless, working with this emerging type of data has been a challenging task for objects representation, scenes recognition, segmentation, and reconstruction. In this regard, a significant effort has recently been devoted to developing novel strategies, using different techniques such as deep learning models. To that end, we present in this paper a comprehensive review of existing tasks on 3D point cloud: a well-defined taxonomy of existing techniques is performed based on the nature of the adopted algorithms, application scenarios, and main objectives. Various tasks performed on 3D point could data are investigated, including objects and scenes detection, recognition, segmentation, and reconstruction. In addition, we introduce a list of used datasets, discuss respective evaluation metrics, and compare the performance of existing solutions to better inform the state-of-the-art and identify their limitations and strengths. Lastly, we elaborate on current challenges facing the subject of technology and future trends attracting considerable interest, which could be a starting point for upcoming research studies. © 2023, CC BY.

关键词： Deep learning