| 1. |
- Jarke, Matthias, et al.
(författare)
-
Data-centric intelligent information integration : from concepts to automation
- 2014
-
Ingår i: Journal of Intelligent Information Systems. - : Springer. - 0925-9902 .- 1573-7675. ; 43:3, s. 437-462
-
Tidskriftsartikel (refereegranskat)abstract
- Intelligent integration of information continues to challenge database research for over 35 years. While data integration processes of all kinds are now reasonably well understood and widely used in practice, the growth and heterogeneity of data requires much higher degrees of automation to limit the need for human specialist work. This requires deeper insights in data-centric approaches of Enterprise Information Integration which focus on the semantics of information integration. Recent formalizations and algorithms enable both significant improvement in schema integration, and in its automated transformation to efficient data-level integration, in a wide variety of architectural settings such as data warehouses or peer-to-peer databases. In addition to giving a short overview of developments in this field for the past 20 years, this paper focuses particularly on the challenges posed by heterogeneity in data models.
|
|
| 2. |
- Kastrati, Muhamet, et al.
(författare)
-
Leveraging distant supervision and deep learning for twitter sentiment and emotion classification
- 2024
-
Ingår i: Journal of Intelligent Information Systems. - : Springer. - 0925-9902 .- 1573-7675.
-
Tidskriftsartikel (refereegranskat)abstract
- Nowadays, various applications across industries, healthcare, and security have begun adopting automatic sentiment analysis and emotion detection in short texts, such as posts from social media. Twitter stands out as one of the most popular online social media platforms due to its easy, unique, and advanced accessibility using the API. On the other hand, supervised learning is the most widely used paradigm for tasks involving sentiment polarity and fine-grained emotion detection in short and informal texts, such as Twitter posts. However, supervised learning models are data-hungry and heavily reliant on abundant labeled data, which remains a challenge. This study aims to address this challenge by creating a large-scale real-world dataset of 17.5 million tweets. A distant supervision approach relying on emojis available in tweets is applied to label tweets corresponding to Ekman’s six basic emotions. Additionally, we conducted a series of experiments using various conventional machine learning models and deep learning, including transformer-based models, on our dataset to establish baseline results. The experimental results and an extensive ablation analysis on the dataset showed that BiLSTM with FastText and an attention mechanism outperforms other models in both classification tasks, achieving an F1-score of 70.92% for sentiment classification and 54.85% for emotion detection.
|
|
| 3. |
- Lambrix, Patrick, et al.
(författare)
-
Querying documents using content, structure and properties
- 2000
-
Ingår i: Journal of Intelligent Information Systems. - 0925-9902 .- 1573-7675. ; 15:3, s. 287-307
-
Tidskriftsartikel (refereegranskat)abstract
- Much information is nowadays stored electronically in document bases. Users retrieve information from these document bases by browsing and querying. While a large number of tools are available nowadays, not much work has been done on tools that support queries involving all the characteristics of documents as well as the use of domain knowledge during the search for information. In this paper we propose a query language that allows for querying documents using content information, information about the logical structure of the documents as well as information about properties of the documents. Domain knowledge is taken into account during the search as well. We also present an architecture for a system supporting such a language and we describe a prototype implementation together with test results.
|
|
| 4. |
- Leifler, Ola, et al.
(författare)
-
Message classification as a basis for studying command and control communication : an evaluation of machine learning approaches
- 2012
-
Ingår i: Journal of Intelligent Information Systems. - Berlin : Springer. - 0925-9902 .- 1573-7675. ; 38:2, s. 299-320
-
Tidskriftsartikel (refereegranskat)abstract
- In military command and control, success relies on being able to perform key functions such as communicating intent. Most staff functions are carried out using standard means of text communication. Exactly how members of staff perform their duties, who they communicate with and how, and how they could perform better, is an area of active research. In command and control research, there is not yet a single model which explains all actions undertaken by members of staff well enough to prescribe a set of procedures for how to perform functions in command and control. In this context, we have studied whether automated classification approaches can be applied to textual communication to assist researchers who study command teams and analyze their actions. Specifically, we report the results from evaluating machine leaning with respect to two metrics of classification performance: (1) the precision of finding a known transition between two activities in a work process, and (2) the precision of classifying messages similarly to human researchers that search for critical episodes in a workflow. The results indicate that classification based on text only provides higher precision results with respect to both metrics when compared to other machine learning approaches, and that the precision of classifying messages using text-based classification in already classified datasets was approximately 50%. We present the implications that these results have for the design of support systems based on machine learning, and outline how to practically use text classification for analyzing team communications by demonstrating a specific prototype support tool for workflow analysis.
|
|
| 5. |
- Minock, Michael, 1967-
(författare)
-
Describing and deriving certain answers over partial databases
- 2010
-
Ingår i: Journal of Intelligent Information Systems. - : Springer Netherlands. - 0925-9902 .- 1573-7675. ; 35:2, s. 245-260
-
Tidskriftsartikel (refereegranskat)abstract
- Although there has been much work in recent years on answering queries using views, there has been less work on deriving answers from partial databases. That is given a partial database state D V , materialized via the view V, what queries can be asked over D V that can be answered with certainty using only the instance of the partial database and standard query evaluation mechanisms. We define these as the derivable answers and show several special cases in which we can compute and intensionally describe them.
|
|
| 6. |
- Xu, Cheng, et al.
(författare)
-
Scalable Validation of Industrial Equipment using a Functional DSMS
- 2017
-
Ingår i: Journal of Intelligent Information Systems. - : Springer. - 0925-9902 .- 1573-7675. ; 48:3, s. 553-577
-
Tidskriftsartikel (refereegranskat)abstract
- A stream validation system called SVALI is developed in order to continuouslyvalidate data streams from industrial equipment. The functional data model of SVALI allows the user to dene meta-data and queries about the equipment in terms of types and functions. The two system functions model-andvalidate and learn-and-validate provide such validation functionality. The experiments show that parallel stream processing enables SVALI to scale very well with respect to response time and system throughput. The paper is based on a real world application for wheel loader slippage detection at Volvo Construction Equipment.
|
|
| 7. |
|
|
| 8. |
|
|
