2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)最新文献_第5页

Forecasting Winter Precipitation based on Weather Sensors Data in Apache Spark 基于Apache Spark气象传感器数据的冬季降水预报

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555553

Andreas Kanavos, T. Panagiotakopoulos, Gerasimos Vonitsanos, M. Maragoudakis, Y. Kiouvrekis

引用次数: 2

Robustness of Compressed Deep Neural Networks with Adversarial Training 具有对抗训练的压缩深度神经网络的鲁棒性

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555552

Yunchun Zhang, Chengjie Li, Wangwang Wang, Yuting Zhong, Xin Zhang, Yu-lin Zhang

{"title":"Robustness of Compressed Deep Neural Networks with Adversarial Training","authors":"Yunchun Zhang, Chengjie Li, Wangwang Wang, Yuting Zhong, Xin Zhang, Yu-lin Zhang","doi":"10.1109/IISA52424.2021.9555552","DOIUrl":"https://doi.org/10.1109/IISA52424.2021.9555552","url":null,"abstract":"Deep learning models are not applicable on edge computing devices. Consequently, compressed deep learning models gain momentum recently. Meanwhile, adversarial attacks targeting conventional deep neural networks (DNNs) and compressed DNNs are flouring nowadays. This paper firstly surveys the current compressing techniques, including pruning, distillation, quantization and weights sharing. Then, two iterative adversarial attacks, including I-FGSM (Iterative-Fast Gradient Sign Method) and PGD (Project Gradient Descent), are introduced. Three scenarios are built to test each DNN’s robustness against adversarial attacks. Besides, each DNN is trained with samples generated by different adversarial attacks and is then compressed under different pruning rate and tested under different attacks. The experimental results prove firstly that when a DNN is compressed with pruning rate lower than 70.0% is safe and with tiny accuracy decline. Second, iterative adversarial attacks are effective and cause dramatic performance degradation. Third, adversarial training helps to secure the compressed DNNs while lowering transferability of adversarial samples constructed by different attack algorithms.","PeriodicalId":437496,"journal":{"name":"2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124254982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Look at Service Meshes 查看服务网格

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555536

Arne Koschel, Marvin Bertram, R. Bischof, Kevin Schulze, Marc Schaaf, Irina Astrova

引用次数: 5

CNN-based stress and emotion recognition in ambulatory settings 在门诊环境中基于cnn的压力和情绪识别

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555508

Leonidas Liakopoulos, Nikolaos Stagakis, E. Zacharaki, K. Moustakas

{"title":"CNN-based stress and emotion recognition in ambulatory settings","authors":"Leonidas Liakopoulos, Nikolaos Stagakis, E. Zacharaki, K. Moustakas","doi":"10.1109/IISA52424.2021.9555508","DOIUrl":"https://doi.org/10.1109/IISA52424.2021.9555508","url":null,"abstract":"Stress has been recognized as a major contributor in a number of mental, psychological or physical conditions which reduce the quality of human life. The monitoring of affective states through readily available wearables and unobtrusive sensors can allow to recognize early signs of stress and burn-out, thereby develop prevention policies to combat psychosocial risks. This study analyzes data from diverse sensing modalities with signal processing techniques and advanced machine learning approaches in order to unobtrusively recognize stress and negative emotions. We investigate the performance of - easy to obtain in ambulatory settings - heart rate signal and juxtapose it against multi-modal information from electrophysiological signals, facial expression features and body posture. For the former, we introduce 2D spectrograms into a convolutional neural network (CNN) and use the obtained activation maps as frequency patterns differentiating stressful conditions. For the rest of the sensors, we compare different classifiers (SVM, KNN, Random Forest, Neural Networks) and data fusion schemes. In addition, a second phase assessment is conceptualized for emotion recognition reflected in facial expressions using images from a smartphone’s camera. Our CNN implementation in Android platform enables near real-time estimation of the instantaneous emotional expressions, which, when combined with stress-indicators, can help elucidating the relationship between stress and negative affective states.","PeriodicalId":437496,"journal":{"name":"2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116908627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7

Transfer Learning in sEMG-based Gesture Recognition 基于表面肌电信号的手势识别中的迁移学习

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555555

Panagiotis Tsinganos, Jan Cornelis, Bruno Cornelis, B. Jansen, A. Skodras

{"title":"Transfer Learning in sEMG-based Gesture Recognition","authors":"Panagiotis Tsinganos, Jan Cornelis, Bruno Cornelis, B. Jansen, A. Skodras","doi":"10.1109/IISA52424.2021.9555555","DOIUrl":"https://doi.org/10.1109/IISA52424.2021.9555555","url":null,"abstract":"The latest advancements in the field of deep learning and biomedical engineering have allowed for the development of myoelectric interfaces based on deep neural networks. A longstanding problem of these interfaces is that the models cannot easily be applied to new users due to the high variability and stochastic nature of the electromyography signals. Further training a new model for every new subject requires the collection of large volumes of data. Therefore, this work proposes a transfer learning (TL) scheme which allows reusing the knowledge of a pre-existing model for a new user. Firstly, a convolutional neural network (CNN) is trained on an initial dataset using the data of multiple subjects. Then, the weights of this model are fine-tuned for a new target subject. The approach is evaluated on the Ninapro datasets DB2 and DB7. The experimentation included three different CNN models and eight preprocessing alternatives. The results showed that the success of the TL method depends on how the data are preprocessed. Specifically, the biggest accuracy improvement (+5.14%) is achieved when only the first 20% of the signal duration is used.","PeriodicalId":437496,"journal":{"name":"2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115157612","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Cloud Computing: Serverless 云计算:无服务器

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555534

Arne Koschel, Samuel Klassen, Kerim Jdiya, Marc Schaaf, Irina Astrova

引用次数: 2

Evaluation of Public Funding Processes by Mining Event Logs 通过挖掘事件日志来评估公共资助过程

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555573

Aimilia Zisimou, Ioanna Kalaitzoglou, Georgia Theodoropoulou, Alexandros Bousdekis, G. Miaoulis

{"title":"Evaluation of Public Funding Processes by Mining Event Logs","authors":"Aimilia Zisimou, Ioanna Kalaitzoglou, Georgia Theodoropoulou, Alexandros Bousdekis, G. Miaoulis","doi":"10.1109/IISA52424.2021.9555573","DOIUrl":"https://doi.org/10.1109/IISA52424.2021.9555573","url":null,"abstract":"The European Structural and Investment Funds (ESIF) are financial tools set up to invest in job creation and a sustainable and healthy European economy and environment. The criticality of these processes in terms of the time constraints, the large budgets, and the heterogeneity of the funded projects pose significant challenges to their management and evaluation. On the other hand, the emergence of Process Intelligence opens the door to new ways of managing public funding processes that ensure increased efficiency. In this paper, we propose a process mining based approach for analyzing delays, bottlenecks, and variations in process execution, thus setting the priorities for process improvements in the domain of public funding programs. We applied the proposed approach in the administrative verification of expenditure of the Partnership Agreement for the Development Framework (PA)). The results show that process mining is able to provide significant insights regarding delays, bottlenecks, and variations in process execution, thus setting the priorities for process improvement.","PeriodicalId":437496,"journal":{"name":"2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129427148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Near-Far Problem as a Function of Analog to Digital Converter Resolution in Software Defined Radio Tactical Network 软件定义无线电战术网络中模数转换器分辨率的远近问题

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555577

Kashif Shahzad, M. Zeeshan, M. U. Farooq, S. Khan

{"title":"Near-Far Problem as a Function of Analog to Digital Converter Resolution in Software Defined Radio Tactical Network","authors":"Kashif Shahzad, M. Zeeshan, M. U. Farooq, S. Khan","doi":"10.1109/IISA52424.2021.9555577","DOIUrl":"https://doi.org/10.1109/IISA52424.2021.9555577","url":null,"abstract":"Software-defined radios (SDR) based tactical networks have great significance in hostile scenarios primarily due to their ease of deployment and reconfiguration capabilities. These implementations are without the requirement of any permanent immovable infrastructure which makes them feasible for various law enforcement deployments. These self-healing and self-forming networks can operate over a significantly wide range with the help of various waveforms. This paper discusses a temporal domain issue faced in SDR tactical networks which arise due to different geographical distances between communicating nodes. This is referred to as a near-far problem and it is critical as it affects the performance of the network. This paper also proposes a hypothetical solution utilizing the reduced analog to digital converter (ADC) resolution that can cater to this problem. The proposed scheme is validated by simulations which proposes the concept of frequency selective gains to be used instead of operating on time domain-based Automatic Gain Controllers (AGC). The concept is proposed for the state-of-the-art hybrid narrowband wideband receiver; however, the entire discussion is valid for any TDMA/FDMA-based SDR networks.","PeriodicalId":437496,"journal":{"name":"2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)","volume":"354 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134059583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating Integrated Assessment Modelling in Support of the Paris Agreement: The I2AM PARIS Platform 整合综合评估模型以支持《巴黎协定》:I2AM巴黎平台

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/IISA52424.2021.9555502

A. Nikas, Stavros Skalidakis, Alevgul H. Sorman, Ester Galende-Sánchez, K. Koasidis, Filippos Serepas, D. V. D. Ven, Jorge Moreno, Anastasios Karamaneas, Themistoklis Koutsellis, E. Kanellou, H. Doukas

{"title":"Integrating Integrated Assessment Modelling in Support of the Paris Agreement: The I2AM PARIS Platform","authors":"A. Nikas, Stavros Skalidakis, Alevgul H. Sorman, Ester Galende-Sánchez, K. Koasidis, Filippos Serepas, D. V. D. Ven, Jorge Moreno, Anastasios Karamaneas, Themistoklis Koutsellis, E. Kanellou, H. Doukas","doi":"10.1109/IISA52424.2021.9555502","DOIUrl":"https://doi.org/10.1109/IISA52424.2021.9555502","url":null,"abstract":"Calls “to do science differently” and democratise the research process have proliferated in the last decades, especially in the context of climate science and policy support. This new arena demands more participatory procedures to expand the knowledge-making beyond researchers and experts. One way that science has started to interact with society has been the increasing number of online platforms that have emerged as alternative forums, providing the opportunity for engaging a variety of tools, models, results, and preferences. This study presents I2 AM PARIS, a platform dedicated to delivering on comprehensive and comprehensible scientific information in support of climate policymaking. It does so by bringing the climate-economy modelling community together in a common workspace, with shared protocols, data exchange formats, and nomenclature, and by making the used and produced information accessible to and digestible by all stakeholders. To this end stakeholders, who lie at the heart of the platform, have co-designed the presentation of the platform in order to respond to pertinent questions in the climate debate co-created with stakeholders and the scientific processes together. Oriented on documenting detailed capabilities of integrated assessment models, providing access to input datasets and assumptions driving them, and offering ad hoc visualisation and databases of their outputs, I2 AM PARIS emphasises transparency, reproducibility, inclusivity, plurality, and comprehensibility.","PeriodicalId":437496,"journal":{"name":"2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133420663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

[Front matter] (前页)

2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Pub Date : 2021-07-12 DOI: 10.1109/iisa52424.2021.9555560

引用次数: 0