2018 IEEE Symposium Series on Computational Intelligence (SSCI)最新文献_第4页

Hybrid Deep Learning Model for Stock Price Prediction 股票价格预测的混合深度学习模型

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628641

M. Hossain, Rezaul Karim, R. Thulasiram, Neil D. B. Bruce, Yang Wang

引用次数: 45

Understanding the Biological Underpinning of Auditory Perception for Vowel Sounds Using a Type-2 Fuzzy Neural Network 利用2型模糊神经网络理解元音听觉感知的生物学基础

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628942

Mousumi Laha, A. Konar, P. Rakshit, S. Chaki, A. Nagar

{"title":"Understanding the Biological Underpinning of Auditory Perception for Vowel Sounds Using a Type-2 Fuzzy Neural Network","authors":"Mousumi Laha, A. Konar, P. Rakshit, S. Chaki, A. Nagar","doi":"10.1109/SSCI.2018.8628942","DOIUrl":"https://doi.org/10.1109/SSCI.2018.8628942","url":null,"abstract":"The temporal lobe in the human brain is responsible for low-level audio perception, whereas the pre-frontal lobe takes active role in interpreting the audio information. This paper introduces a novel approach to understand the interrelation between the temporal and the pre-frontal lobes of the brain in interpreting vowel sounds. The inter-relation is ascertained by two approaches. The first approach computes correlation measure between the direct brain signals of the said two lobes. The higher the correlation coefficient, the better is the interrelation between the activated lobes. The second approach aims at developing a feature-level mapping between the temporal and the prefrontal lobe brain activations. The motivation of the second approach lies in examining the uniformity in the learnt neural weights after convergence for the same vowel audio stimulus irrespective of the diurnal variations in the brain signals. Although any traditional mapping functions could be utilized to undertake the temporal to prefrontal mapping, we used a type-2 fuzzy neural network to serve the purpose. Experiments undertaken confirm that the weights of the proposed type-2 fuzzy neural net converges faster than its type-1 counterpart and back-propagation neural network. The faster convergence of weights represent that the proposed type-2 fuzzy neural network captures better audio perceptual ability than the rest. The proposed work is expected to find applications in the early detection of disorder in auditory perceptual-ability, usually referred to as Dyslexia.","PeriodicalId":235735,"journal":{"name":"2018 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114614139","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: 2

Human Pose Detection Through Searching in 3D Database With 2D Extracted Skeletons 利用提取的二维骨架在三维数据库中搜索人体姿态检测

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628776

D. Blok, Jacob Pettigrew, T. Schiphorst, Herbert H. Tsang

引用次数: 2

Decision-Making using the Hesitant Fuzzy Sets COMET Method: An Empirical Study of the Electric City Buses Selection 基于犹豫模糊集COMET方法的决策——城市电动客车选择的实证研究

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628864

W. Sałabun, Artur Karczmarczyk, J. Wątróbski

引用次数: 25

Forward Noise Adjustment Scheme for Data Augmentation 数据增强的前向噪声调整方案

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628917

Francisco J. Moreno-Barea, Fiammetta Strazzera, J. M. Jerez, D. Urda, L. Franco

引用次数: 101

Singlish SenticNet: A Concept-Based Sentiment Resource for Singapore English 新加坡英语SenticNet:一个基于概念的新加坡英语情感资源

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628796

Danyuan Ho, Diyana Hamzah, Soujanya Poria, E. Cambria

引用次数: 6

Efficient Classification of Supercomputer Failures Using Neuromorphic Computing 基于神经形态计算的超级计算机故障高效分类

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628946

Prasanna Date, C. Carothers, J. Hendler, M. Magdon-Ismail

{"title":"Efficient Classification of Supercomputer Failures Using Neuromorphic Computing","authors":"Prasanna Date, C. Carothers, J. Hendler, M. Magdon-Ismail","doi":"10.1109/SSCI.2018.8628946","DOIUrl":"https://doi.org/10.1109/SSCI.2018.8628946","url":null,"abstract":"Today’s petascale supercomputers are comprised of ten’s of thousands of compute nodes. Failures on these massive machines are a growing problem as the time for a single compute node to fail is shrinking. Ideally, the job scheduler would like the capability to predict node failures ahead of time in order to minimize the impact of node failures on overall job throughput. However, due to the tight power constraints of future systems, the online modeling of real-time error data must be accomplished using as little power as possible. To this end, the IBM TrueNorth Neurosynaptic System is used to create a Spiking Neural Network (SNN) model of supercomputer failure data and the classification accuracy of this model is compared to other Machine Learning (ML) and Deep Learning (DL) techniques. It is observed that the TrueNorth failure classification model yields a training accuracy of 99.41%, validation accuracy of 98.12% and testing accuracy of 99.80% and outperforms other machine learning and deep learning approaches. Moreover, the TrueNorth SNN consumes five orders of magnitude less power than the other ML/DL approaches during the testing phase. Additionally, it is observed that all ML/DL approaches investigated as part of this study are able to produce accurate models of the supercomputer system failure data.","PeriodicalId":235735,"journal":{"name":"2018 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116340209","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: 16

Enabling Field Force Operational Sustainability: A Big Bang-Big Crunch Type-2 Fuzzy Logic System for Goal-Driven Simulation 实现野战部队作战可持续性:用于目标驱动仿真的大爆炸-大挤压2型模糊逻辑系统

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628901

Emmanuel Ferreyra, H. Hagras, M. Kern, G. Owusu

引用次数: 2

Hierarchical Reinforcement Learning for Playing a Dynamic Dungeon Crawler Game 基于层次强化学习的动态地下城爬行游戏

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628914

R. Niel, M. Wiering

{"title":"Hierarchical Reinforcement Learning for Playing a Dynamic Dungeon Crawler Game","authors":"R. Niel, M. Wiering","doi":"10.1109/SSCI.2018.8628914","DOIUrl":"https://doi.org/10.1109/SSCI.2018.8628914","url":null,"abstract":"This paper describes a novel hierarchical reinforcement learning (HRL) algorithm for training an autonomous agent to play a dungeon crawler game. As opposed to most previous HRL frameworks, the proposed HRL system does not contain complex actions that take multiple time steps. Instead there is a hierarchy of behaviours which can either execute an action or delegate the decision to a sub-behaviour lower in the hierarchy. The actions or sub-behaviours are chosen by learning the estimated cumulative reward. Since each action only takes one time step and the system starts at the top of the hierarchy at every time step, the system is able to dynamically react to changes in its environment. The developed dungeon crawler game requires the agent to take keys, open doors, and go to the exit while evading or fighting with enemy units. Based on these tasks, behaviours are constructed and trained with a combination of multi-layer perceptrons and Q-learning. The system also uses a kind of multi-bjective learning that allows multiple parts of the hierarchy to simultaneously learn from a chosen action using their own reward function. The performance of the system is compared to an agent using MaxQ-learning that shares a similar overall design. The results show that the proposed dynamic HRL (dHRL) system yields much higher scores and win rates in different game levels and is able to learn to perform very well with only 500 training games.","PeriodicalId":235735,"journal":{"name":"2018 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126131280","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

An immune based dynamic risk control system 基于免疫的动态风险控制系统

2018 IEEE Symposium Series on Computational Intelligence (SSCI) Pub Date : 2018-11-01 DOI: 10.1109/SSCI.2018.8628904

Ping Lin, Jin Yang, Tao Li, Lei Ai

{"title":"An immune based dynamic risk control system","authors":"Ping Lin, Jin Yang, Tao Li, Lei Ai","doi":"10.1109/SSCI.2018.8628904","DOIUrl":"https://doi.org/10.1109/SSCI.2018.8628904","url":null,"abstract":"Global network security is facing more and more serious challenges. Existing traditional network security defense tools (e.g. firewalls, intrusion prevention systems) cannot actively adjust defense strategies and conduct targeted defenses according to change of current network environment threats (e.g. attack intensity, attack type, etc.), which has greater passiveness and blindness. Inspired by artificial immunity, this paper proposes an immune-based dynamic risk control system. The system consists of intrusion detection module, risk assessment and dynamic risk control module. The system obtains the current system environment’s risk level through intrusion detection and risk assessment module, selects the targeted defense strategy from the strategy knowledge database according to the risk level, implements positive and active defense strategies, and then controls targeted risks of different types and levels to prevent the spread of the attack. Compared with the classic intrusion prevention system, of which once the rules are set, it will remain unchanged and cannot be dynamically adjusted, the system adopts different control strategies for different risk of network, and the control strategy can be flexibly and dynamically adjusted according to the change of network threat. The extended active and passive control methods enhance the systems capability to handle different types of attacks and the risk level. Thus, it is flexible, active and targeted to control the risk of network security.","PeriodicalId":235735,"journal":{"name":"2018 IEEE Symposium Series on Computational Intelligence (SSCI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125061375","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