Change search
Link to record
Permanent link

Direct link
BETA
Alternative names
Publications (10 of 12) Show all publications
Kusetogullari, H., Yavariabdi, A., Cheddad, A., Grahn, H. & Johan, H. (2019). ARDIS: A Swedish Historical Handwritten Digit Dataset. Neural computing & applications (Print)
Open this publication in new window or tab >>ARDIS: A Swedish Historical Handwritten Digit Dataset
Show others...
2019 (English)In: Neural computing & applications (Print), ISSN 0941-0643, E-ISSN 1433-3058Article in journal (Refereed) Epub ahead of print
Abstract [en]

This paper introduces a new image-based handwrittenhistorical digit dataset named ARDIS (Arkiv DigitalSweden). The images in ARDIS dataset are extractedfrom 15,000 Swedish church records which were writtenby different priests with various handwriting styles in thenineteenth and twentieth centuries. The constructed datasetconsists of three single digit datasets and one digit stringsdataset. The digit strings dataset includes 10,000 samplesin Red-Green-Blue (RGB) color space, whereas, the otherdatasets contain 7,600 single digit images in different colorspaces. An extensive analysis of machine learning methodson several digit datasets is examined. Additionally, correlationbetween ARDIS and existing digit datasets ModifiedNational Institute of Standards and Technology (MNIST)and United States Postal Service (USPS) is investigated. Experimental results show that machine learning algorithms,including deep learning methods, provide low recognitionaccuracy as they face difficulties when trained on existingdatasets and tested on ARDIS dataset. Accordingly, ConvolutionalNeural Network (CNN) trained on MNIST andUSPS and tested on ARDIS provide the highest accuracies 58.80% and 35.44%, respectively. Consequently, the resultsreveal that machine learning methods trained on existingdatasets can have difficulties to recognize digits effectivelyon our dataset which proves that ARDIS dataset hasunique characteristics. This dataset is publicly available forthe research community to further advance handwritten digitrecognition algorithms.

Place, publisher, year, edition, pages
Springer Nature Switzerland, 2019
Keywords
Handwritten digit recognition, ARDIS dataset, Machine learning methods, Benchmark
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:bth-17741 (URN)10.1007/s00521-019-04163-3 (DOI)
Funder
Knowledge Foundation, 20140032
Available from: 2019-03-27 Created: 2019-03-27 Last updated: 2019-05-02Bibliographically approved
Dasari, S. K., Cheddad, A. & Andersson, P. (2019). Random Forest Surrogate Models to Support Design Space Exploration in Aerospace Use-case. In: IFIP Advances in Information and Communication Technology: . Paper presented at 15th International Conference on Artificial Intelligence Applications and Innovations (AIAI'19)At: Crete, Greece. Springer-Verlag New York, 559
Open this publication in new window or tab >>Random Forest Surrogate Models to Support Design Space Exploration in Aerospace Use-case
2019 (English)In: IFIP Advances in Information and Communication Technology, Springer-Verlag New York, 2019, Vol. 559Conference paper, Published paper (Refereed)
Abstract [en]

In engineering, design analyses of complex products rely on computer simulated experiments. However, high-fidelity simulations can take significant time to compute. It is impractical to explore design space by only conducting simulations because of time constraints. Hence, surrogate modelling is used to approximate the original simulations. Since simulations are expensive to conduct, generally, the sample size is limited in aerospace engineering applications. This limited sample size, and also non-linearity and high dimensionality of data make it difficult to generate accurate and robust surrogate models. The aim of this paper is to explore the applicability of Random Forests (RF) to construct surrogate models to support design space exploration. RF generates meta-models or ensembles of decision trees, and it is capable of fitting highly non-linear data given quite small samples. To investigate the applicability of RF, this paper presents an approach to construct surrogate models using RF. This approach includes hyperparameter tuning to improve the performance of the RF's model, to extract design parameters' importance and \textit{if-then} rules from the RF's models for better understanding of design space. To demonstrate the approach using RF, quantitative experiments are conducted with datasets of Turbine Rear Structure use-case from an aerospace industry and results are presented.

Place, publisher, year, edition, pages
Springer-Verlag New York, 2019
Series
IFIP Advances in Information and Communication Technology ; 559
Keywords
machine learning, random forests, hyperparameter tuning, surrogate model, meta-models, engineering design, aerospace
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-17743 (URN)10.1007/978-3-030-19823-7_45 (DOI)978-3-030-19822-0 (ISBN)
Conference
15th International Conference on Artificial Intelligence Applications and Innovations (AIAI'19)At: Crete, Greece
Available from: 2019-03-27 Created: 2019-03-27 Last updated: 2019-06-13Bibliographically approved
Bouhennache, R., Bouden, T., Taleb-Ahmed, A. & Cheddad, A. (2018). A new spectral index for the extraction of built-up land features from Landsat 8 satellite imagery. Geocarto International
Open this publication in new window or tab >>A new spectral index for the extraction of built-up land features from Landsat 8 satellite imagery
2018 (English)In: Geocarto International, ISSN 1010-6049, E-ISSN 1752-0762Article in journal (Refereed) Epub ahead of print
Abstract [en]

Extracting built-up areas from remote sensing data like Landsat 8 satellite is a challenge. We have investigated it by proposing a new index referred as Built-up Land Features Extraction Index (BLFEI). The BLFEI index takes advantage of its simplicity and good separability between the four major component of urban system, namely built-up, barren, vegetation and water. The histogram overlap method and the Spectral Discrimination Index (SDI) are used to study separability. BLFEI index uses the two bands of infrared shortwaves, the red and green bands of the visible spectrum. OLI imagery of Algiers, Algeria, was used to extract built-up areas through BLFEI and some new previously developed built-up indices used for comparison. The water areas are masked out leading to Otsu’s thresholding algorithm to automatically find the optimal value for extracting built-up land from waterless regions. BLFEI, the new index improved the separability by 25% and the accuracy by 5%.

Place, publisher, year, edition, pages
Taylor & Francis Group, 2018
Keywords
Built-up land, Extraction, Index, Landsat 8, Spectral
National Category
Computer Sciences Information Systems Computer Vision and Robotics (Autonomous Systems)
Identifiers
urn:nbn:se:bth-16866 (URN)10.1080/10106049.2018.1497094 (DOI)
Note

open access

Available from: 2018-08-14 Created: 2018-08-14 Last updated: 2018-09-27Bibliographically approved
Akser, M., Bridges, B., Campo, G., Cheddad, A., Curran, K., Fitzpatrick, L., . . . Roman, L. (2018). SceneMaker: Creative technology for digital storytelling. In: Brooks A.L.,Brooks E. (Ed.), Lect. Notes Inst. Comput. Sci. Soc. Informatics Telecommun. Eng.: . Paper presented at 5th International Conference on Arts and Technology, ArtsIT 2016 and 1st International Conference on Design, Learning and Innovation, DLI, Esbjerg, May 2016 (pp. 29-38). Springer Verlag, 196
Open this publication in new window or tab >>SceneMaker: Creative technology for digital storytelling
Show others...
2018 (English)In: Lect. Notes Inst. Comput. Sci. Soc. Informatics Telecommun. Eng. / [ed] Brooks A.L.,Brooks E., Springer Verlag , 2018, Vol. 196, p. 29-38Conference paper, Published paper (Refereed)
Abstract [en]

The School of Creative Arts & Technologies at Ulster University (Magee) has brought together the subject of computing with creative technologies, cinematic arts (film), drama, dance, music and design in terms of research and education. We propose here the development of a flagship computer software platform, SceneMaker, acting as a digital laboratory workbench for integrating and experimenting with the computer processing of new theories and methods in these multidisciplinary fields. We discuss the architecture of SceneMaker and relevant technologies for processing within its component modules. SceneMaker will enable the automated production of multimodal animated scenes from film and drama scripts or screenplays. SceneMaker will highlight affective or emotional content in digital storytelling with particular focus on character body posture, facial expressions, speech, non-speech audio, scene composition, timing, lighting, music and cinematography. Applications of SceneMaker include automated simulation of productions and education and training of actors, screenwriters and directors. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2017.

Place, publisher, year, edition, pages
Springer Verlag, 2018
Series
Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, ISSN 1867-8211
Keywords
3D visualisation, Affective computing, Artificial intelligence (AI), Cinematography, Computer graphics, Dance, Design, Digital storytelling, Drama, Film, Music technology, Natural language processing, SceneMaker, Speech processing, Storyboards, Arts computing, Audio acoustics, Computation theory, Computer games, Films, Human computer interaction, Natural language processing systems, Three dimensional computer graphics, Music technologies, Engineering education
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-14086 (URN)10.1007/978-3-319-55834-9_4 (DOI)000425355100004 ()2-s2.0-85015959988 (Scopus ID)9783319558332 (ISBN)
Conference
5th International Conference on Arts and Technology, ArtsIT 2016 and 1st International Conference on Design, Learning and Innovation, DLI, Esbjerg, May 2016
Available from: 2017-04-06 Created: 2017-04-06 Last updated: 2019-01-11Bibliographically approved
Ola, S., Andreas, K., Mark, C., Keith, H., Emma, I., Jim, D., . . . Juni, P. (2017). E-Science technologies in a workflow for personalized medicine using cancer screening as a case study. JAMIA Journal of the American Medical Informatics Association, 24(5), 950-957
Open this publication in new window or tab >>E-Science technologies in a workflow for personalized medicine using cancer screening as a case study
Show others...
2017 (English)In: JAMIA Journal of the American Medical Informatics Association, ISSN 1067-5027, E-ISSN 1527-974X, Vol. 24, no 5, p. 950-957Article in journal (Refereed) Published
Abstract [en]

Objective: We provide an e-Science perspective on the workflow from risk factor discovery and classification of disease to evaluation of personalized intervention programs. As case studies, we use personalized prostate and breast cancer screenings.

Materials and Methods: We describe an e-Science initiative in Sweden, e-Science for Cancer Prevention and Control (eCPC), which supports biomarker discovery and offers decision support for personalized intervention strategies. The generic eCPC contribution is a workflow with 4 nodes applied iteratively, and the concept of e-Science signifies systematic use of tools from the mathematical, statistical, data, and computer sciences.

Results: The eCPC workflow is illustrated through 2 case studies. For prostate cancer, an in-house personalized screening tool, the Stockholm-3 model (S3M), is presented as an alternative to prostate-specific antigen testing alone. S3M is evaluated in a trial setting and plans for rollout in the population are discussed. For breast cancer, new biomarkers based on breast density and molecular profiles are developed and the US multicenter Women Informed to Screen Depending on Measures (WISDOM) trial is referred to for evaluation. While current eCPC data management uses a traditional data warehouse model, we discuss eCPC-developed features of a coherent data integration platform.

Discussion and Conclusion: E-Science tools are a key part of an evidence-based process for personalized medicine. This paper provides a structured workflow from data and models to evaluation of new personalized intervention strategies. The importance of multidisciplinary collaboration is emphasized. Importantly, the generic concepts of the suggested eCPC workflow are transferrable to other disease domains, although each disease will require tailored solutions.

Place, publisher, year, edition, pages
Oxford University Press, 2017
Keywords
e-Science, cancer, personalized screening, data integration, modeling, simulation
National Category
Radiology, Nuclear Medicine and Medical Imaging Cancer and Oncology
Identifiers
urn:nbn:se:bth-14124 (URN)10.1093/jamia/ocx038 (DOI)000409183600011 ()
Funder
Swedish Research Council
Available from: 2017-04-24 Created: 2017-04-24 Last updated: 2017-11-03Bibliographically approved
Cheddad, A., Kusetogullari, H. & Grahn, H. (2017). Object recognition using shape growth pattern. In: Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis, ISPA: . Paper presented at 10th International Symposium on Image and Signal Processing and Analysis (ISPA), Ljubljana (pp. 47-52). IEEE Computer Society Digital Library, Article ID 8073567.
Open this publication in new window or tab >>Object recognition using shape growth pattern
2017 (English)In: Proceedings of the 10th International Symposium on Image and Signal Processing and Analysis, ISPA, IEEE Computer Society Digital Library, 2017, p. 47-52, article id 8073567Conference paper, Published paper (Refereed)
Abstract [en]

This paper proposes a preprocessing stage to augment the bank of features that one can retrieve from binary images to help increase the accuracy of pattern recognition algorithms. To this end, by applying successive dilations to a given shape, we can capture a new dimension of its vital characteristics which we term hereafter: the shape growth pattern (SGP). This work investigates the feasibility of such a notion and also builds upon our prior work on structure preserving dilation using Delaunay triangulation. Experiments on two public data sets are conducted, including comparisons to existing algorithms. We deployed two renowned machine learning methods into the classification process (i.e., convolutional neural network-CNN- and random forests-RF-) since they perform well in pattern recognition tasks. The results show a clear improvement of the proposed approach's classification accuracy (especially for data sets with limited training samples) as well as robustness against noise when compared to existing methods.

Place, publisher, year, edition, pages
IEEE Computer Society Digital Library, 2017
Keywords
Binary image dilations, convolutional neural network, machine learning, pattern recognition, shape growth pattern
National Category
Computer Systems Signal Processing
Identifiers
urn:nbn:se:bth-15416 (URN)10.1109/ISPA.2017.8073567 (DOI)000442428600009 ()978-1-5090-4011-7 (ISBN)
Conference
10th International Symposium on Image and Signal Processing and Analysis (ISPA), Ljubljana
Projects
Scalable resource efficient systems for big data analytics
Available from: 2017-11-01 Created: 2017-11-01 Last updated: 2018-09-06Bibliographically approved
Devagiri, V. M. & Cheddad, A. (2017). Splicing Forgery Detection and the Impact of Image Resolution. In: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTERS AND ARTIFICIAL INTELLIGENCE - ECAI 2017: . Paper presented at 9th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Targoviste, ROMANIA. IEEE
Open this publication in new window or tab >>Splicing Forgery Detection and the Impact of Image Resolution
2017 (English)In: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTERS AND ARTIFICIAL INTELLIGENCE - ECAI 2017, IEEE , 2017Conference paper, Published paper (Refereed)
Abstract [en]

With the development of the Internet, and the increase in the online storage space, there has been an explosion in the volume of videos and images circulating online. An important part of the digital forensics' tasks is to scrutinise part of these images to make important decisions. Digital tampering of images can impede reliability of these decisions. Through this paper we attempt to improve the detection rate of splicing forgery. We also examine how well the examined splicing forgery detection algorithm works on low-resolution images. In this paper, the aim is to enhance the accuracy of an existing algorithm. One tailed Wilcoxon signed rank test was utilised to compare the performance of the different algorithms.

Place, publisher, year, edition, pages
IEEE, 2017
Series
International Conference on Electronics Computers and Artificial Intelligence, ISSN 2378-7147
Keywords
Image Processing, Splicing Forgery, Machine Learning, Image Resolution
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-15979 (URN)000425865900047 ()978-1-5090-6458-8 (ISBN)
Conference
9th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Targoviste, ROMANIA
Available from: 2018-03-23 Created: 2018-03-23 Last updated: 2018-03-27Bibliographically approved
Cheddad, A. (2017). Structure Preserving Binary Image Morphing using Delaunay Triangulation. Pattern Recognition Letters, 85, 8-14
Open this publication in new window or tab >>Structure Preserving Binary Image Morphing using Delaunay Triangulation
2017 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 85, p. 8-14Article in journal (Refereed) Published
Abstract [en]

Mathematical morphology has been of a great significance to several scientific fields. Dilation, as one of the fundamental operations, has been very much reliant on the common methods based on the set theory and on using specific shaped structuring elements to morph binary blobs. We hypothesised that by performing morphological dilation while exploiting geometry relationship between dot patterns, one can gain some advantages. The Delaunay triangulation was our choice to examine the feasibility of such hypothesis due to its favourable geometric properties. We compared our proposed algorithm to existing methods and it becomes apparent that Delaunay based dilation has the potential to emerge as a powerful tool in preserving objects structure and elucidating the influence of noise. Additionally, defining a structuring element is no longer needed in the proposed method and the dilation is adaptive to the topology of the dot patterns. We assessed the property of object structure preservation by using common measurement metrics. We also demonstrated such property through handwritten digit classification using HOG descriptors extracted from dilated images of different approaches and trained using Support Vector Machines. The confusion matrix shows that our algorithm has the best accuracy estimate in 80% of the cases. In both experiments, our approach shows a consistent improved performance over other methods which advocates for the suitability of the proposed method.

Place, publisher, year, edition, pages
Elsevier, 2017
Keywords
Binary image; Delaunay triangulation; Dilation; Distance transform; Mathematical morphology; Pattern recognition; Set theory; Structuring element
National Category
Signal Processing Computer Vision and Robotics (Autonomous Systems) Media and Communication Technology
Identifiers
urn:nbn:se:bth-13576 (URN)10.1016/j.patrec.2016.11.010 (DOI)000390661600002 ()
Funder
Knowledge Foundation, 20140032
Available from: 2016-12-12 Created: 2016-12-12 Last updated: 2018-01-13Bibliographically approved
Brik, B., Lagraa, N., Abderrahmane, L. & Cheddad, A. (2016). DDGP: Distributed Data Gathering Protocol for vehicular networks. Vehicular Communications, 4, 15-29
Open this publication in new window or tab >>DDGP: Distributed Data Gathering Protocol for vehicular networks
2016 (English)In: Vehicular Communications, ISSN 2214-2096, Vol. 4, p. 15-29Article in journal (Refereed) Published
Abstract [en]

Vehicular Ad-Hoc Network (VANet) is an emerging research area, it offers a wide range of applications including safety, road traffic efficiency, and infotainment applications. Recently researchers are studying the possibility of making use of deployed VANet applications for data collection. In this case, vehicles are considered as mobile collectors that gather both real time and delay tolerant data and deliver them to interested entities. In this paper, we propose a novel Distributed Data Gathering Protocol (DDGP) for the collection of delay tolerant as well as real time data in both urban and highway environments. The main contribution of DDGP is a new medium access technique that enables vehicles to access the channel in a distributed way based on their location information. In addition, DDGP implements a new aggregation scheme, which deletes redundant, expired, and undesired data. We provide an analytical proof of correctness of DDGP, in addition to the performance evaluation through an extensive set of simulation experiments. Our results indicate that DDGP enhances the efficiency and the reliability of the data collection process by outperforming existing schemes in terms of several criteria such as delay and message overhead, aggregation ratio, and data retransmission rate. (C) 2016 Elsevier Inc. All rights reserved.

Place, publisher, year, edition, pages
Elsevier, 2016
Keywords
VANet; Data Collection; DDGP; VL-CSMA
National Category
Media and Communication Technology
Identifiers
urn:nbn:se:bth-11894 (URN)10.1016/j.vehcom.2016.01.001 (DOI)000378959400002 ()
Available from: 2016-05-17 Created: 2016-05-17 Last updated: 2018-01-10Bibliographically approved
Cheddad, A. (2016). Towards Query by Text Example for pattern spotting in historical documents. In: Proceedings - CSIT 2016: 2016 7th International Conference on Computer Science and Information Technology: . Paper presented at 7th International Conference on Computer Science and Information Technology, CSIT 2016; Applied Science University (ASU) Conference PalaceAmman; Jordan. IEEE Computer Society, Article ID 7549479.
Open this publication in new window or tab >>Towards Query by Text Example for pattern spotting in historical documents
2016 (English)In: Proceedings - CSIT 2016: 2016 7th International Conference on Computer Science and Information Technology, IEEE Computer Society, 2016, article id 7549479Conference paper, Published paper (Refereed)
Abstract [en]

Historical documents are essentially formed of handwritten texts that exhibit a variety of perceptual environment complexities. The cursive and connected nature of text lines on one hand and the presence of artefacts and noise on the other hand hinder achieving plausible results using current image processing algorithm. In this paper, we present a new algorithm which we termed QTE (Query by Text Example) that allows for training-free and binarisation-free pattern spotting in scanned handwritten historical documents. Our algorithm gives promising results on a subset of our database revealing ∌83% success rate in locating word patterns supplied by the user.

Place, publisher, year, edition, pages
IEEE Computer Society, 2016
Series
International Conference on Computer Science and Information Technology, ISSN 2381-3458
Keywords
Character recognition; History; Pattern recognition; Query processing, Binarisation; Current image; Environment complexity; handwritten; Handwritten texts; Hessian filter; Historical documents; SURF, Image processing
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-13085 (URN)10.1109/CSIT.2016.7549479 (DOI)000390458000030 ()2-s2.0-84987678228 (Scopus ID)9781467389136 (ISBN)
Conference
7th International Conference on Computer Science and Information Technology, CSIT 2016; Applied Science University (ASU) Conference PalaceAmman; Jordan
Note

Conference of 7th International Conference on Computer Science and Information Technology, CSIT 2016 ; Conference Date: 13 July 2016 Through 14 July 2016; Conference Code:123537

Available from: 2016-10-06 Created: 2016-10-03 Last updated: 2018-01-14Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-4390-411x

Search in DiVA

Show all publications