检索结果-内蒙古大学图书馆

A Simplified Method to Identify the Sarcastic Elements of Bahasa Indonesia in Youtube Comments

学校读者我要写书评

暂无评论

A Simplified Method to Identify the Sarcastic Elements of Ba...

International Conference of Information and Communication Technology (ICoICT)

作者： Wilbert Wijaya I Made Murwantara Aditya Rama Mitra Undergraduate Programme Universitas Pelita Harapan Tangerang Indonesia Informatics Dept. Universitas Pelita Harapan Tangerang Indonesia Faculty of Computer Science Universitas Pelita Harapan Tangerang Indonesia

ISBN: (数字)9781728161426

ISBN: (纸本)9781728161433

Comments on Youtube media provide feedback to the content owner of how their video influence audience. However, some comments may have intention to convey readers not to the original goals of the video content. Moreover, the sarcasm statements may also provide misleading information that possibly put the conversation into a hatred comments. This paper presents a simplified method to identify sarcasm within comments in a youtube video channel, which enable the channel or video owner to identify and remove or eliminate some comments that may arise hatred between the audience. To identify sarcasm comments, we use Naïve Bayes to find out which statements may have sarcasm elements. Our approach, specifically, designed to detect and explicate the elements of sarcastic words or statements in Bahasa Indonesia. To demonstrate our approach, an Indonesian political Youtube Channel comments for the range of 7 months prior to the 2019 Indonesian Presidential election has been collected and analysed. Our result shows that Naïve Bayes identified 79% of sarcasm within the comments, with accuracy 0,802, precision 1.0 and recall 0,651.

关键词： Testing YouTube Training Voting Predictive models informatics Media

Robust Assessment of ECG Signal Quality for Wearable Devices 7

学校读者我要写书评

暂无评论

Robust Assessment of ECG Signal Quality for Wearable Devices

7th IEEE International Conference on Healthcare informatics, ICHI 2019

作者： Shi, Yuanbo Zhang, Zhengbo Han, Ning Li, Peiyao Yang, Zhicheng Yuan, Qian Du, Yongsheng Lan, Ke Zheng, Jiewen Cao, Desen Chinese PLA General Hospital Dept. of Biomedical Engineering Beijing China University of California Dept. of Computer Science DavisCA United States Beijing Haisi Ruige Technology Co. Ltd. Beijing China Dept. of Biomedical Engineering and Medical Device Research and Development and Evaluation Center Chinese PLA General Hospital China

ISBN: (纸本)9781538691380

With the fast development of mobile health technology, wearable device provides continuous monitoring in a low-cost and convenient way, which is a promising solution for personalized medicine. However, the signal quality issue limits its wide adoption. In our study, we proposed a robust electrocardiogram (ECG) signal quality assessment algorithm. The algorithm has been validated in real clinical scenario with excellent performance. © 2019 IEEE.

关键词： Electrocardiograms

Measuring affective states from technical debt: A psychoempirical software engineering experiment

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Olsson, Jesper Risfelt, Erik Besker, Terese Martini, Antonio Torkar, Richard Chalmers and University of Gothenburg Dept. of Computer Science and Engineering GöteborgSE-412 96 Sweden Wallenberg Research Centre at Stellenbosch University Stellenbosch South Africa University of Oslo Dept. of Informatics OsloN-0373 Norway

Software engineering is a human activity. Despite this, human aspects are under-represented in technical debt research, perhaps because they are challenging to evaluate. This study's objective was to investigate the relationship between technical debt and affective states (feelings, emotions, and moods) from software practitioners. Forty participants (N = 40) from twelve companies took part in a mixed-methods approach, consisting of a repeated-measures (r = 5) experiment (n = 200), a survey, and semi-structured interviews. The statistical analysis shows that different design smells (strong indicators of technical debt) negatively or positively impact affective states. From the qualitative data, it is clear that technical debt activates a substantial portion of the emotional spectrum and is psychologically taxing. Further, the practitioners' reactions to technical debt appear to fall in different levels of maturity. We argue that human aspects in technical debt are important factors to consider, as they may result in, e.g., procrastination, apprehension, and burnout. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

High-throughput segmentation of unmyelinated axons by deep learning

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Plebani, Emanuele Biscola, Natalia P. Havton, Leif A. Rajwa, Bartek Shemonti, Abida Sanjana Jaffey, Deborah Powley, Terry Keast, Janet R. Lu, Kun-Han Dundar, M. Murat Dept. of Computer & Information Sciences Indiana University - Purdue University IndianapolisIN46202 United States Dept. of Neurology Icahn School of Medicine at Mount Sinai New YorkNY10029 United States Dept. of Neuroscience Icahn School of Medicine at Mount Sinai New YorkNY10029 United States James J. Peters Department of Veterans Affairs Medical Center BronxNY10468 United States Bindley Bioscience Center Purdue University West LafayetteIN47906 United States Dept. of Computer Science Purdue University West LafayetteIN47906 United States Dept. of Psychological Sciences Purdue University West LafayetteIN47907 United States Dept. of Anatomy and Physiology The University of Melbourne MelbourneVIC3010 Australia Weldon School of Biomedical Engineering Purdue University West LafayetteIN47907 United States

Axonal characterizations of connectomes in healthy and disease phenotypes are surprisingly incomplete and biased because unmyelinated axons, the most prevalent type of fibers in the nervous system, have largely been ignored as their quantitative assessment quickly becomes unmanageable as the number of axons increases. Herein, we introduce the first prototype of a high-throughput processing pipeline for automated segmentation of unmyelinated fibers. Our team has used transmission electron microscopy images of vagus and pelvic nerves in rats. All unmyelinated axons in these images are individually annotated and used as labeled data to train and validate a deep instance segmentation network. We investigate the effect of different training strategies on the overall segmentation accuracy of the network. We extensively validate the segmentation algorithm as a stand-alone segmentation tool as well as in an expert-in-the-loop hybrid segmentation setting with preliminary, albeit remarkably encouraging results. Our algorithm achieves an instance-level F1 score of between 0.7 and 0.9 on various test images in the stand-alone mode and reduces expert annotation labor by 80% in the hybrid setting. We hope that this new high-throughput segmentation pipeline will enable quick and accurate characterization of unmyelinated fibers at scale and become instrumental in significantly advancing our understanding of connectomes in both the peripheral and the central nervous systems. © 2021, CC BY.

关键词： Fibers

Generalisability of fetal ultrasound deep learning models to low-resource imaging settings in five African countries

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sendra-Balcells, Carla Campello, Víctor M. Torrents-Barrena, Jordina Ahmed, Yahya Ali Elattar, Mustafa Ohene-Botwe, Benard Nyangulu, Pempho Stones, William Ammar, Mohammed Benamer, Lamya Nawal Kisembo, Harriet Nalubega Sereke, Senai Goitom Wanyonyi, Sikolia Z. Temmerman, Marleen Gratacós, Eduard Bonet, Elisenda Eixarch, Elisenda Mikolaj, Kamil Tolsgaard, Martin Grønnebæk Lekadir, Karim Dept. de Matemàtiques i Informàtica Universitat de Barcelona Barcelona Spain HP Inc. Barcelona Spain Obstetrics and Gynecology Dept. School of Medicine Suez University Egypt Medical Imaging and Image Processing Center of Informatics Science Nile University Egypt Research & Development Division Intixel Egypt Dept. of Radiography School of Biomedical & Allied Health Sciences College of Health Sciences University of Ghana Ghana Division of Midwifery and Radiography School of Health & Psychological Sciences University of London London United Kingdom Kamuzu University of Health Sciences Blantyre Malawi Dept. of Electrical Engineering Systems Laboratory of Engineering System and Telecommunication University of M’Hamed Bougara Boumerdes Algiers Algeria Obstetrics and Gynecology Dept. School of Medicine Algiers University Algeria Dept. of Radiology Mulago National Referral and Teaching Hospital Kampala Uganda Dept. of Radiology and Radiotherapy School of Medicine Makerere University College of Health Sciences Kampala Uganda Dept. of Obstetrics and Gynaecology Aga Khan University Hospital 3rd Parklands Avenue Nairobi Kenya Centre of Excellence in Women and Child Health Aga Khan University Nairobi Kenya BCNatal Fetal Medicine Research Center Hospital Clínic and Hospital Sant Joan de Déu Universitat de Barcelona Barcelona Spain Barcelona Spain Barcelona Spain Barcelona Tech Universitat Politècnica de Catalunya Barcelona Spain Copenhagen Academy for Medical Education and Simulation Dept. of Obstetrics Rigshospitalet Denmark

Most artificial intelligence (AI) research and innovations have concentrated in high-income countries, where imaging data, IT infrastructures and clinical expertise are plentiful. However, slower progress has been made in limited-resource environments where medical imaging is needed. For example, in Sub-Saharan Africa, the rate of perinatal mortality is very high due to limited access to antenatal screening. In these countries, AI models could be implemented to help clinicians acquire fetal ultrasound planes for the diagnosis of fetal abnormalities. So far, deep learning models have been proposed to identify standard fetal planes, but there is no evidence of their ability to generalise in centres with low resources, i.e. with limited access to high-end ultrasound equipment and ultrasound data. This work investigates for the first time different strategies to reduce the domain-shift effect arising from a fetal plane classification model trained on one clinical centre with high-resource settings and transferred to a new centre with low-resource settings. To that end, a classifier trained with 1,792 patients from Spain is first evaluated on a new centre in Denmark in optimal conditions with 1,008 patients and is later optimised to reach the same performance in five African centres (Egypt, Algeria, Uganda, Ghana and Malawi) with 25 patients each. The results show that a transfer learning approach for domain adaptation can be a solution to integrate small-size African samples with existing large-scale databases in developed countries. In particular, the model can be re-aligned and optimised to boost the performance on African populations by increasing the recall to 0.92±0.04 and at the same time maintaining a high precision across centres. This framework shows promise for building new AI models generalisable across clinical centres with limited data acquired in challenging and heterogeneous conditions and calls for further research to develop new solutions for the usabil

关键词： Ultrasonic imaging

Evaluating deep transfer learning for whole-brain cognitive decoding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Thomas, Armin W. Lindenberger, Ulman Samek, Wojciech Müller, Klaus-Robert Machine Learning Group Dept. of Computer Science and Electrical Engineering Technische Universität Berlin Berlin Germany Center for Lifespan Psychology Max Planck Institute for Human Development Berlin Germany Stanford Data Science Stanford University StanfordCA United States Dept. of Psychology Stanford University StanfordCA United States Max Planck UCL Centre for Computational Psychiatry and Ageing Research Berlin Germany Dept. of Artificial Intelligence Fraunhofer Heinrich Hertz Institute Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Dept. of Artificial Intelligence Korea University Seoul Korea Republic of Max Planck Institute for Informatics Saarbrücken Germany

Research in many fields has shown that transfer learning (TL) is well-suited to improve the performance of deep learning (DL) models in datasets with small numbers of samples. This empirical success has triggered interest in the application of TL to cognitive decoding analyses with functional neuroimaging data. Here, we systematically evaluate TL for the application of DL models to the decoding of cognitive states (e.g., viewing images of faces or houses) from whole-brain functional Magnetic Resonance Imaging (fMRI) data. We first pre-train two DL architectures on a large, public fMRI dataset and subsequently evaluate their performance in an independent experimental task and a fully independent dataset. The pre-trained models consistently achieve higher decoding accuracies and generally require less training time and data than model variants that were not pre-trained, clearly underlining the benefits of pre-training. We demonstrate that these benefits arise from the ability of the pre-trained models to reuse many of their learned features when training with new data, providing deeper insights into the mechanisms giving rise to the benefits of pre-training. Yet, we also surface nuanced challenges for whole-brain cognitive decoding with DL models when interpreting the decoding decisions of the pre-trained models, as these have learned to utilize the fMRI data in unforeseen and counterintuitive ways to identify individual cognitive states. © 2021, CC BY.

关键词： Decoding

A Prototype of a Fully-Implantable Charge-Balanced Artificial Sensory Stimulator for Bi-directional Brain-computer-Interface (BD-BCI)

学校读者我要写书评

暂无评论

A Prototype of a Fully-Implantable Charge-Balanced Artificia...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Won J. Sohn Po T. Wang Spencer Kellis Richard A. Andersen Charles Y. Liu Payam Heydari Zoran Nenadic An H. Do Dept. of Neurology UCI Irvine CA Dept. of Biomedical Engineering University of California Irvine (UCI) Irvine CA Div. of Biology and Biological Engineering CALTECH Pasadena CA Dept. of Neurological Surgery University of Southern California Los Angeles CA Dept. of Electrical Engineering and Computer Science UCI Irvine CA

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Bi-directional brain-computer interfaces (BD-BCI) to restore movement and sensation must achieve concurrent operation of recording and decoding of motor commands from the brain and stimulating the brain with somatosensory feedback. Previously we developed and validated a benchtop prototype of a fully implantable BCI system for motor decoding. Here, a prototype artificial sensory stimulator was integrated into the benchtop system to develop a prototype of a fully-implantable BD-BCI. The artificial sensory stimulator incorporates an active charge balancing mechanism based on pulse-width modulation to ensure safe stimulation for chronically interfaced electrodes to prevent damage to brain tissue and electrodes. The feasibility of the BD-BCI system's active charge balancing was tested in phantom brain tissue. With the charge-balancing, the removal of the residual charges on an electrode was evident. This is a critical milestone toward fully-implantable BD-BCI systems.

关键词： Electrodes Voltage measurement Robot sensing systems Decoding Threshold voltage Steady-state Prototypes

Analyzing cooperative monitoring and dissemination of critical mobile events by VANETs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Andrade, Everaldo Santos, Aldri Maciel Jr, Paulo D. Matos, Fernando Dept. of Computer Science Federal University of Paraíba Brazil NR2 Federal University of Paraná Brazil Academic Unit of Informatics Federal Institute of Paraíba Brazil

The treatment of mobile and simultaneous critical urban events requires effective actions by the appropriate authorities. Additionally it implies communication challenges in the speed and accuracy of their occurrence by the entities, as well as dealing with the dynamics and speed in these environments. Cooperative solutions with shared resources that address these challenges become a real option in helping to handle these events. This paper presents an evaluation of dynamic monitoring and collaborative dissemination supported by vehicular groups. It aims to analyze the impact of multiple mobile and fixed events in an urban environment on information propagation, considering barriers imposed by the events and the environment. Differently from other studies in the literature, this work takes into account both fixed and mobile events, as well as simultaneous events. NS3 results show that the evaluated system monitored at least 87% and 51.5% of the time for mobile and fixed events respectively, and delivered information over 77% and 50% of the time for those events, with average delay remains close to 0.3s in most scenarios. The results also reveal that a more continuous monitoring of the mobile events is highly dependent on the orientation of the vehicles. The main contribution of this work consists of the performance analysis of both fixed and mobile simultaneous events to support studies on how moving events impact on the dissemination and delivery of real-time data, and thus encouraging the development of new data dissemination protocols for VANETs. Copyright © 2020, The Authors. All rights reserved.

关键词： Information dissemination

Cloud Network Slicing: A Systematic Mapping Study from Scientific Publications

学校读者我要写书评

暂无评论

arXiv 2020年

作者： de Almeida, Leandro C. Maciel, Paulo Ditarso Verdi, Fábio L. Academic Unit of Informatics Federal Institute of Paraíba João Pessoa-PB Brazil Dept. of Computer Science Federal University of São Carlos Sorocaba-SP Brazil

—Cloud Network Slicing is a new research area that brings together cloud computing and network slicing in an end-to-end environment. In this context, understanding the existing scientific contributions and gaps is crucial to driving new research in this field. This article presents a complete quantitative analysis of scientific publications on the Cloud Network Slicing, based on a systematic mapping study. The results indicate the situation of the last ten years in the research area, presenting data such as industry involvement, most cited articles, most active researchers, publications over the years, main places of publication, as well as well-developed areas and gaps. Future guidelines for scientific research are also discussed. Copyright © 2020, The Authors. All rights reserved.

关键词： Mapping