2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA)最新文献_第5页

Evolving long-term dependency rules in lifelong learning models 在终身学习模式中发展长期依赖规则

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7802999

Muhammad Taimoor Khan, Sonam Yar, S. Khalid, Furqan Aziz

{"title":"Evolving long-term dependency rules in lifelong learning models","authors":"Muhammad Taimoor Khan, Sonam Yar, S. Khalid, Furqan Aziz","doi":"10.1109/ICKEA.2016.7802999","DOIUrl":"https://doi.org/10.1109/ICKEA.2016.7802999","url":null,"abstract":"Topic models are extensively used for text analysis to extract prominent concepts as topics in a large collection of documents about a subject domain. They are extended with different approaches to suit various application areas. Automatic knowledge-based topic models are recently introduced to specifically meet the processing needs of large-scale data having many subject domains. The model automatically learns rules across all domains and uses them to improve the results of the current domain by purposefully grouping words into topics to better represent the underlying concept. The existing models apply thresholds on evaluation criteria to learn rules; however, being automatic it may learn wrong, irrelevant or inconsistent rules as well. In this research article the proposed model learns rules and monitors their contributions towards the quality of results. As the model learns new rules, the existing rules undergo refinement and detachment procedures to retain reliable rules only. Experimental results on user reviews from Amazon.com shows improvement in the quality of topics by using fewer rules which advocates the quality of rules and help avoid performance bottleneck at high experience.","PeriodicalId":241850,"journal":{"name":"2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126514513","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: 6

A quality evaluation model for Android system based on forum text mining 基于论坛文本挖掘的Android系统质量评价模型

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7803004

Cangzhou Yuan, You Yue, S. Wei, Naiyu Yin

引用次数: 0

Does information uncertainty moderate the impact of investors' emotion on stock prices? 信息不确定性是否会缓和投资者情绪对股价的影响?

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7802984

Fang-Ming Hsu, Chien-Ho Liao

{"title":"Does information uncertainty moderate the impact of investors' emotion on stock prices?","authors":"Fang-Ming Hsu, Chien-Ho Liao","doi":"10.1109/ICKEA.2016.7802984","DOIUrl":"https://doi.org/10.1109/ICKEA.2016.7802984","url":null,"abstract":"Prior studies point out information uncertainty (IU) of a stock comes from investors' overconfidence. However, overconfidence is hard to be measured. After our collections and reviews of prior studies regarding IU, we propose stock returns are affected by investors' sentiment, and this relation is moderated by IU. We use SentimentAnalyzer system, a text mining technology, to analyze the posts in a stock forum on The Motley Fool financial website to investigate the psychology of investors, and verify our hypotheses by structural equation modeling (SEM) in weekly, monthly and quarterly intervals. Our findings demonstrate that investors' sentiment positively affects the stock returns only in short-term (weekly) interval, and this relation is also affected by IU in short time. Therefore, we proposed two suggestions. In buyer side, the investors who prefer high risks and returns can choose stocks with high IU (small company size or higher volatility in prices and volumes) and good reviews in forums as their targets in next week, and avoid the stocks with bad reviews. In contrast, in seller side, investors can choose the stocks with bad reviews as their next-week targets, too.","PeriodicalId":241850,"journal":{"name":"2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134272118","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

Event scheduling with soft constraints and on-demand re-optimization 带有软约束和按需重新优化的事件调度

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7802993

Patrick Hosein, Steffan Boodhoo

{"title":"Event scheduling with soft constraints and on-demand re-optimization","authors":"Patrick Hosein, Steffan Boodhoo","doi":"10.1109/ICKEA.2016.7802993","DOIUrl":"https://doi.org/10.1109/ICKEA.2016.7802993","url":null,"abstract":"With the increased use of today's information technologies, more people are using electronic calendaring systems, such as Outlook, to schedule everyday events. This includes work related items such as meetings as well as personal items such as birthdays and their kids' events. There have been no significant changes to this process. People enter their personal event items on their calendars. If someone needs to schedule a meeting, they will view available time slots of all potential attendees and choose an appropriate date and time. There are two weaknesses in this process that we address. Firstly, the value of an event to a person is not specified and hence when scheduling a meeting, one simply assumes that any slot that is marked busy is unavailable for the meeting. However, a busy slot could be for something that is not as important as the meeting to be scheduled. The second weakness is that once a meeting is scheduled, the chosen time slots are not changed unless the organizer decides to do so for some specific reason. However, the optimal time slot for the meeting may change over time. In this paper, we propose a framework that addresses these issues and illustrate its value through simulations.","PeriodicalId":241850,"journal":{"name":"2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133917944","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

Application interface for gesture recognition with Kinect sensor 使用Kinect传感器进行手势识别的应用程序界面

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7803000

Dardan Maraj, A. Maraj, Adhurim Hajzeraj

引用次数: 8

Dynamic OOBNs applied to water management in dams 动态oobn在水坝水管理中的应用

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7803030

M. Flores, A. Nicholson, R. F. Ropero

引用次数: 1

E-commerce business strategy analysis and inspiration: Taking Taobao as an example 电子商务经营策略分析与启示:以淘宝为例

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7802995

Chen Gong

引用次数: 5

WSLA extensions for managing composite semantic Web Services 用于管理复合语义Web服务的WSLA扩展

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7802988

Islam Elgedawy

{"title":"WSLA extensions for managing composite semantic Web Services","authors":"Islam Elgedawy","doi":"10.1109/ICKEA.2016.7802988","DOIUrl":"https://doi.org/10.1109/ICKEA.2016.7802988","url":null,"abstract":"Managing Service Level Agreement (SLA) for composite semantic web services is a very complex process, as it involves many complex tasks such as components discovery, provisioning, monitoring, recovery, and coordination. Indeed, managing all these tasks manually is a very cumbersome operation, nevertheless it is time consuming and prone to errors. To overcome such problems, automated SLA management for composite semantic web services is needed. This requires the SLA of the composite service to be described in a machine-understandable format such that it can be understood and processed by the automated SLA management tool. Currently, there is no SLA description language for composite semantic web services, but there exists an SLA description language for atomic web services, known as the Web Service Level Agreement (WSLA). Hence, in this paper, we aim to extend the WSLA language to describe composite semantic web services' SLAs, then we show how we can automatically generate the components' SLAs from the composite semantic web services' SLAs; adopting the CRECENT framework that we previously proposed for managing composite web services.","PeriodicalId":241850,"journal":{"name":"2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA)","volume":"386 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131934485","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: 1

A performance-satisfied and affection-aware MapReduce allocation scheme for intelligent information applications 面向智能信息应用的性能满意且情感感知的MapReduce分配方案

2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA) Pub Date : 2016-09-01 DOI: 10.1109/ICKEA.2016.7802990

Jenn-Wei Lin, A. Selvi, Joesph Arul

{"title":"A performance-satisfied and affection-aware MapReduce allocation scheme for intelligent information applications","authors":"Jenn-Wei Lin, A. Selvi, Joesph Arul","doi":"10.1109/ICKEA.2016.7802990","DOIUrl":"https://doi.org/10.1109/ICKEA.2016.7802990","url":null,"abstract":"Intelligent information applications (e.g. healthcare, business data mining, etc.) usually involve the processing of a huge amount of data. MapReduce can speed up the execution of the application (job) with big data by dividing the job into a number of concurrently running map and reduce tasks in cloud computing systems. With many MapReduce jobs in the systems, it is required to efficiently allocate computing resources for the tasks of such jobs. If not, the performance requirements (e.g. execution deadlines) of some jobs cannot be met. Several deadline-constrained MapReduce schedulers have been proposed, but they do not consider the following factors: 1) affection on existing tasks, and 2) the tradeoff between the number of tasks allocated and the total allocation cost. To take into consideration the above three factors in the MapReduce scheduling, we transform the task allocation problem into a well-known network graph problem: minimum cost flow (MCF) to solve our concerned task allocation problem. Finally, the performance analysis is done to demonstrate the effectiveness of our proposed MapReduce scheduler.","PeriodicalId":241850,"journal":{"name":"2016 IEEE International Conference on Knowledge Engineering and Applications (ICKEA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125995172","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: 1