| 1. |
- Abraham, Doney, et al.
(författare)
-
Security and Privacy issues in IoT based Smart Grids : A case study in a digital substation
- 2022. - 1
-
Ingår i: Holistic Approach for Decision Making Towards Designing Smart Cities. - Switzerland : Springer. - 9783030855659 - 9783030855666 ; , s. 57-74
-
Bokkapitel (refereegranskat)abstract
- Smart Grid is one of the increasingly used critical infrastruc- ture that is essential for the functioning of a country. This coupled with Internet of Things (IoT) has huge potentials in several areas such as re- mote monitoring and managing of electricity distribution, traffic signs, traffic congestion, parking spaces, road warnings and even early detection of power influxes as a result of natural disasters, safety failures, equip- ment failures or carelessness. Despite the advantages of Smart Grids, there are security threats, privacy concerns and still open challenges re- lated to these issues in Smart Grids. This chapter seeks to provide a review of the security and privacy perspectives inherent in IoT enabled Smart Grids. Firstly the chapter explores the functionalities of Smart Grids as opposed to a traditional grid. Next the chapter provides an overview of Smart Grid architectures followed by positioning IoT con- cept into Smart Grid with a focus on architectures. Then, the proposed approach for identifying threats and attacks in IoT enabled Smart Grid, namely the security pyramid is presented. Lastly, we work on identifying the possible threats and attacks in the digital substation use case.
|
|
| 2. |
- Dalipi, Fisnik, et al.
(författare)
-
A machine learning approach to increase energy efficiency in district heating systems
- 2015
-
Ingår i: Environmental Engineering and Computer Application. - Hong kong : CRC Press. - 9781138028074 - 9781315685380 ; , s. 223-226
-
Konferensbidrag (refereegranskat)abstract
- Heat demand prediction is an important part of increasing system efficiency within district heating. To achieve this efficiency, the energy provider companies need to estimate how much energy is re quired to satisfy the market demand. In this paper, we propose a method to investigate the application of online ma chine learning algorithm to achieve energy efficiency and optimization in District Heating (DH) systems by predicting the heat demand on the consumer side. To accomplish this, we are planning to use operational data from a Norwegian company (EffektivEnergi AS, Hamar) for a group of buildings that are connected to DH in other places.
|
|
| 3. |
- Dalipi, Fisnik, et al.
(författare)
-
Data-Driven Machine Learning Model in District Heating System for Heat Load Prediction : A Comparison Study
- 2016
-
Ingår i: Applied Computational Intelligence and Soft Computing. - : Hindawi Limited. - 1687-9724 .- 1687-9732.
-
Tidskriftsartikel (refereegranskat)abstract
- We present our data-driven supervised machine-learning (ML) model to predict heat load for buildings in a district heating system (DHS). Even though ML has been used as an approach to heat load prediction in literature, it is hard to select an approach that will qualify as a solution for our case as existing solutions are quite problem specific. For that reason, we compared and evaluated three ML algorithms within a framework on operational data from a DH system in order to generate the required prediction model. The algorithms examined are Support Vector Regression (SVR), Partial Least Square (PLS), and random forest (RF). We use the data collected from buildings at several locations for a period of 29 weeks. Concerning the accuracy of predicting the heat load, we evaluate the performance of the proposed algorithms using mean absolute error (MAE), mean absolute percentage error (MAPE), and correlation coefficient. In order to determine which algorithm had the best accuracy, we conducted performance comparison among these ML algorithms. The comparison of the algorithms indicates that, for DH heat load prediction, SVR method presented in this paper is the most efficient one out of the three also compared to other methods found in the literature.
|
|
| 4. |
- Dalipi, Fisnik, et al.
(författare)
-
Enhancing the Learner’s Performance Analysis Using SMEUS Semantic E-learning System and Business Intelligence Technologies
- 2015
-
Ingår i: Learning and Collaboration Technologies. LCT 2015. - Los Angeles : Springer. - 9783319206080 - 9783319206097 ; , s. 208-217
-
Konferensbidrag (refereegranskat)abstract
- Ontologies represent an efficient way of semantic web application on e-learning and offer great opportunity by bringing great advantages to e-learning systems. Nevertheless, despite the many advantages that we get from using ontologies, in terms of structuring the data, there are still many unresolved problems related to the difficulties about getting proper information about a learner’s behavior. Consequently, there is a need of developing tools that enable analysis of the learner’s interaction with the e-learning environment. In this paper, we propose a framework for the application of Business Intelligence (BI) and OLAP technologies in SMEUS e-learning environment. Hence, on one hand, the proposed framework will enable and support the decision-making by answering some questions related to learner’s performance, and on the other hand, will present a case study model for implementing these technologies into a semantic e-learning environment.
|
|
| 5. |
- Dalipi, Fisnik, et al.
(författare)
-
The impact of environmental factors to skiing injuries : Bayesian regularization neural network model for predicting skiing injuries
- 2015
-
Ingår i: 2015 6th International Conference on Computing, Communication and Networking Technologies (ICCCNT). - : IEEE. - 9781479979844 - 9781479979837 ; , s. 1-6
-
Konferensbidrag (refereegranskat)abstract
- Skiing is a winter sport that is found very attractive to many people. Nevertheless, this sport is considered among high-risk sports due to the potential danger of severe injury or death. This is because of variable weather and terrain conditions, obstacles including other skiers, high speeds, trees, etc. Artificial Neural Networks have many applications in predicting the occurrence of various accident severities. In this article, we study the impact of the environmental factors to potential risk factor assessment in skiing. Hence, we apply the Bayesian Regularization Back Propagation neural network (BRBP) to predict the number of severe injuries in skiing, based on the data obtained from our prototype ski-injury registration system, the estimated bindings of environmental conditions, and the potential risk for resulting number of personal injuries. Through comparing with Levenberg Marquardt Back Propagation (LMBP), in terms of prediction accuracy, our experimental results show that BRBP has better performance by achieving higher predictive accuracy.
|
|
| 6. |
- Dalipi, Fisnik, et al.
(författare)
-
User Interface Evaluation of a Ski Injuries Management System
- 2017
-
Ingår i: Advances in Human Factors in Sports and Outdoor Recreation. - Orlando, USA : Springer. - 9783319419527 - 9783319419534 ; , s. 213-222
-
Konferensbidrag (refereegranskat)abstract
- Although many technological devices and solutions to enhance the skiing experience are now available for skiers, skiing sometimes could turn to be potentially dangerous. The speed of movement, environment unpredictability, and variable weather conditions, among others, can contribute to some of the most common skiing injuries that skiers incur. In this paper, we conduct an interface prototype evaluation of a ski injury registration system architecture that is already developed. This system will improve the communication from the ski resort to the medical center, in case an injury has occurred. The results of the interface evaluation indicate that the ski patrollers showed very positive attitude and experience with this prototype. Furthermore, the post-task and SUS (System Usability Scale) question results showed very high score for all participants, indicating that locating the body parts and the right injury was very easy using the interface.
|
|
| 7. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
A General Framework for Text Document Classification Using SEMCON and ACVSR
- 2015
-
Ingår i: Human Interface and the Management of Information. Information and Knowledge Design. - Cham : Springer. - 9783319206110 - 9783319206127 ; , s. 310-319
-
Konferensbidrag (refereegranskat)abstract
- The text document classification employs either text based approach or semantic based approach to index and retrieve text documents. The former uses keywords and therefore provides limited capabilities to capture and exploit the conceptualization involved in user information needs and content meanings. The latter aims to solve these limitations using content meanings, rather than keywords. More formally, the semantic based approach uses the domain ontology to exploit the content meanings of a particular domain. This approach however has some drawbacks. It lacks enrichment of ontology concepts with new lexical resources and evaluation of the importance indicated by weights of those concepts. Therefore to address these issues, this paper proposes a new ontology based text document classification framework. The proposed framework incorporates a newly developed objective metric calledSEMCON to enrich the domain ontology with new concepts by combining contextual as well as semantic information of a term within a text document. The framework also introduces a new approach to automatically estimate the importance of ontology concepts which is indicated by the weights of these concepts, and to enhance the concept vector space model using automatically estimated weights.
|
|
| 8. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
A Hybrid Concept Learning Approach to Ontology Enrichment
- 2018
-
Ingår i: Innovations, Developments, and Applications of Semantic Web and Information Systems. - : IGI Global. - 9781522550426 - 1522550429 - 9781522550433 ; , s. 85-119
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- The wide use of ontology in different applications has resulted in a plethora of automatic approaches for population and enrichment of an ontology. Ontology enrichment is an iterative process where the existing ontology is continuously updated with new concepts. A key aspect in ontology enrichment process is the concept learning approach. A learning approach can be a linguistic-based, statistical-based, or hybrid-based that employs both linguistic as well as statistical-based learning approaches. This chapter presents a concept enrichment model that combines contextual and semantic information of terms. The proposed model called SEMCON employs a hybrid concept learning approach utilizing functionalities from statistical and linguistic ontology learning techniques. The model introduced for the first time two statistical features that have shown to improve the overall score ranking of highly relevant terms for concept enrichment. The chapter also gives some recommendations and possible future research directions based on the discussion in following sections.
|
|
| 9. |
- Kastrati, Zenun, 1984-, et al.
(författare)
-
An improved concept vector space model for ontology based classification
- 2015
-
Ingår i: 2015 11th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS). - : IEEE. ; , s. 240-245
-
Konferensbidrag (refereegranskat)abstract
- This paper proposes an improved concept vector space (ICVS) model which takes into account the importance of ontology concepts. Concept importance shows how important a concept is in an ontology. This is reflected by the number of relations a concept has to other concepts. Concept importance is computed automatically by converting the ontology into a graph initially and then employing one of the Markov based algorithms. Concept importance is then aggregated with concept relevance which is computed using the frequency of concept occurrences in the dataset. In order to demonstrate the applicability of our proposed model and to validate its efficacy, we conducted experiments on document classification using concept based vector space model. The dataset used in this paper consists of 348 documents from the funding domain. The results show that the proposed model yields higher classification accuracy comparing to traditional concept vector space (CVS) model, ultimately giving better document classification performance. We also used different classifiers in order to check for the classification accuracy. We tested CVS and ICVS on Naive Bayes and Decision Tree classifiers and the results show that the classification performance in terms of F1 measure is improved when ICVS is used on both classifiers.
|
|
| 10. |
- Kastrati, Zenun, et al.
(författare)
-
Analysis of Online Social Networks Posts to Investigate Suspects Using SEMCON
- 2015
-
Ingår i: Social Computing and Social Media. SCSM 2015. - Los Angeles : Springer. - 9783319203669 ; , s. 148-157
-
Konferensbidrag (refereegranskat)abstract
- Analysing users’ behaviour and social activity for investigating suspects is an area of great interest nowadays, particularly investigating the activities of users on Online Social Networks (OSNs) for crimes. The criminal activity analysis provides a useful source of information for law enforcement and intelligence agencies across the globe. Current approaches dealing with the social criminal activity analysis mainly rely on the contextual analysis of data using only co-occurrence of terms appearing in a document to find the relationship between criminal activities in a network. In this paper, we propose a model for automated social network analysis in order to assist law enforcement and intelligence agencies to predict whether a user is a possible suspect or not. The model uses web crawlers suited to retrieve users’ data such as posts, feeds, comments, etc., and exploits them semantically and contextually using an ontology enhancement objective metric SEMCON. The output of the model is a probability value of a user being a suspect which is computed by finding the similarity between the terms obtained from the SEMCON and the concepts of criminal ontology. An experiment on analysing the public information of 20 Facebook users is conducted to evaluate the proposed model.
|
|
