"This site requires JavaScript to work correctly"
minimize Header

Prof. Dr. Benedikt Elser

Faculty of Computer Science

Professors

Professor

A 011

0991/3615-739

consulting time

drop me a mail

Sortierung:
Lecture
  • Benedikt Elser

Die digitale Wagenreihung bei der Deutschen Bahn.

In: WI-Symposium

Deggendorf

  • 28.10.2018 (2018)
Journal article
  • Marco Kretschmann
  • Andreas Fischer
  • Benedikt Elser

Extracting Keywords from Publication Abstracts for an Automated Researcher Recommendation System.

In: Digitale Welt (Proceedings of the First International Symposium on Applied Artificial Intelligence in Conjunction with DIGICON) vol. 4 pg. 20-25

  • (2020)

DOI: 10.1007/s42354-019-0227-2

show abstract

This paper presents an automated keyword assignment system for scientific abstracts. That system is applied to paper abstracts collected in a local publication database and used to drive a researcher recommendation system. Problems like low data volume and missing keywords are discussed. For remediation, training is performed on an extended data set based on large online publication databases. Additionally a closer look at label imbalance in the dataset is taken. Ten multi-label classification algorithms for assigning keywords from a given catalogue to a scientific abstract are compared. The usage of binary relevance as transformation method with LightGBM as classifier yields the best results. Random oversampling before the training phase additionally increases the F1-Score by around 5-6%.
Contribution
  • Sebastian Wilhelm
  • Dietmar Jakob
  • Jakob Kasbauer
  • Melanie Dietmeier
  • A. Gerl
  • Benedikt Elser
  • Diane Ahrens

Organizational, Technical, Ethical and Legal Requirements of Capturing Household Electricity Data for Use as an AAL System.

In: Proceedings of the Fifth International Congress on Information and Communication Technology (ICPCCI 2019) [20-21 February 2020; London, UK]. (Advances in Intelligent Systems and Computing)

Springer International Publishing Singapore

  • (2020)

DOI: 10.1007/978-981-15-5856-6_38

show abstract

Due to demographic change elderly care is one of the major challenges for society in near future fostering new services to support and enhance the life quality of the elderly generation. A particular aspect is the desire to live in one’s homes instead of hospitals and retirement homes as long as possible. Therefore it is essential to monitor the health status i.e. the activity of the individual. In our data-driven society data is collected at an increasing rate enabling personalized services for our daily life using machine-learning and data mining technologies. However the lack of labeled datasets from a realistic environment hampers research for training and evaluating algorithms. In the project BLADL we use data mining technologies to gauge the health status of elderly people. Within this work we discuss the challenges and caveats both from a technical and ethical perspectives to create such a dataset.
Journal article
  • Florian Wahl
  • Matthias Breslein
  • Benedikt Elser

On-demand forklift hailing system for Intralogistics 4.0.

In: Procedia Computer Science vol. 200 pg. 878-886

  • (2022)

DOI: 10.1016/j.procs.2022.01.285

show abstract

The shift to I4.0 is happening. While large companies have a range of solutions to implement that change, small and medium-sized enterprises (SME) fall short on solutions tailored for their specific needs. To support SMEs in their transformation toward I4.0, we propose a lightweight system to hail forklifts in a production facility of a medium-sized enterprise. Existing shop floor workflows are implemented within the system and allow machine operators to hail forklift drivers using an embedded or a web-based client. Forklift drivers receive driving instructions on their smartphones. Shift managers can monitor intralogistic activities on a dashboard. Management can extract relevant production and forklift KPIs from the system. In a two-week evaluation phase, we installed our system in a production facility for injection moulded plastic parts. We equipped 12 machines and two forklifts and registered a total of 690 jobs. We found half of the jobs were picked up in 4:05 min and 80% of all jobs were completed in less than 40:02 min.
Journal article
  • Michael Fernandes
  • Alexander Pletl
  • N. Thomas
  • A. Rossi
  • Benedikt Elser

Generation and Optimization of Spectral Cluster Maps to Enable Data Fusion of CaSSIS and CRISM Datasets.

In: Remote Sensing vol. 14 pg. 2524

  • (2022)

DOI: 10.3390/rs14112524

show abstract

Four-band color imaging of the Martian surface using the Color and Stereo Surface Imaging System (CaSSIS) onboard the European Space Agency’s ExoMars Trace Gas Orbiter exhibits a high color diversity in specific regions. Not only is the correlation of color diversity maps with local morphological properties desirable, but mineralogical interpretation of the observations is also of great interest. The relatively high spatial resolution of CaSSIS data mitigates its low spectral resolution. In this paper, we combine the broad-band imaging of the surface of Mars, acquired by CaSSIS with hyperspectral data from the Compact Reconnaissance Imaging Spectrometer (CRISM) onboard NASA’s Mars Reconnaissance Orbiter to achieve a fusion of both datasets. We achieve this using dimensionality reduction and data clustering of the high dimensional datasets from CRISM. In the presented research, CRISM data from the Coprates Chasma region of Mars are tested with different machine learning methods and compared for robustness. With the help of a suitable metric, the best method is selected and, in a further step, an optimal cluster number is determined. To validate the methods, the so-called “summary products” derived from the hyperspectral data are used to correlate each cluster with its mineralogical properties. We restrict the analysis to the visible range in order to match the generated clusters to the CaSSIS band information in the range of 436–1100 nm. In the machine learning community, the so-called UMAP method for dimensionality reduction has recently gained attention because of its speed compared to the already established t-SNE. The results of this analysis also show that this method in combination with the simple K-Means outperforms comparable methods in its efficiency and speed. The cluster size obtained is between three and six clusters. Correlating the spectral cluster maps with the given summary products from CRISM shows that four bands, and especially the NIR bands and VIS albedo, are sufficient to discriminate most of these clusters. This demonstrates that features in the four-band CaSSIS images can provide robust mineralogical information, despite the limited spectral information using semi-automatic processing.
Journal article
  • Benedikt Elser
  • Michael Scholz

Price Optimisation of Perishable Goods Using a Genetic Algorithm.

In: International Journal of Revenue Management vol. 1 pg. 1

  • (2022)

DOI: 10.1504/IJRM.2022.10044440

show abstract

Multi-product profit optimisation problems have been studied under nested logit models of consumer behaviour. Although attractive through to the relaxation of strong assumptions of multinomial logit models, nested logit models as well as multinomial logit models require costly discrete choice experiments in order to collect data for estimating model parameters. We propose a novel formulation of multi-product profit optimisation that is especially useful for perishable goods that are of the same type and different only in their quality level. Our model relies on willingness to pay data that can be elicited directly, derived from market data or measured indirectly in auctions or through transactions. We furthermore present a genetic algorithm for solving the formulated multi-product profit optimisation and show that our proposed genetic algorithm finds nearby optimal solutions within a very short time span.
Contribution
  • L. Huneck
  • Roman-David Kulko
  • S. Wittmann
  • Benedikt Elser
  • H. Mempel

Predicting shelf life along horticultural supply chains: Evaluation of applicable quality parameters using near-infrared scanner.

In: Proceedings of the Annual Conference BGG and BHGL 2021. Short Communications of the DGG and BHGL Annual Conference 2021, Stuttgart (online), Germany. pg. 1-8

German Society for Horticultural Science (DGG)

  • (2022)

DOI: 10.5288/dgg-pr-10-05-lh-2021

show abstract

Visible-Near-Infrared Scanners enable a noninvasive prediction of quality properties of fruit and vegetable based on previously created models. A combination of NIR scanners and machine learning methods can lead to economic improvements and reduction of food waste by strategies like "first expired, first out" and dynamic pricing. In order to identify parameters capable of showing dynamic postharvest development, three horticultural products with different postharvest behavior (e. g. strawberry, table grape and mango) were chosen for morphological and statictical analysis. According to the results, a graduation of spectra in correspondence to the day of measurement was noticeable for strawberry regarding the a-value as well as presumingly mass loss for both mango and table grape. Furthermore, a PLS model for the a-values r2cv = 0.80 was developed for strawberries.
Lecture
  • Michael Fernandes
  • N. Thomas
  • Benedikt Elser
  • A. Rossi
  • Alexander Pletl
  • G. Cremonese

Extrapolation of CRISM based spectral feature maps using CaSSIS four-band images with machine learning techniques.

In: EGU General Assembly 2022

Vienna, Austria

  • 23.-27.05.2022 (2022)

DOI: 10.5194/egusphere-egu22-2765

show abstract

Spectroscopy provides important information on the surface composition of Mars. Spectral data can support studies such as the evaluation of potential (manned) landing sites as well as supporting determination of past surface processes. The CRISM instrument on NASA’s Mars Reconnaissance Orbiter is a high spectral resolution visible infrared mapping spectrometer currently in orbit around Mars. It records 2D spatially resolved spectra over a wavelength range of 362 nm to 3920 nm. At present data collected covers less than 2% of the planet. Lifetime issues with the cryo-coolers prevents limits further data acquisition in the infrared band. In order to extend areal coverage for spectroscopic analysis in regions of major importance to the history of liquid water on Mars (e.g. Valles Marineris, Noachis Terra), we investigate whether data from other instruments can be fused to extrapolate spectral features in CRISMto these non-spectral imaged areas. The present work will use data from the CaSSIS instrument which is a high spatial resolution colour and stereo imager onboard the European Space Agency’s ExoMars Trace Gas Orbiter (TGO). CaSSIS returns images at 4.5 m/px from the nominal 400 km altitude orbit in four colours. Its filters were selected to provide mineral diagnostics in the visible wavelength range (400 – 1100 nm). It has so far imaged around 2% of the planet with an estimated overlap of ≲0.01% of CRISM data. This study introduces a two-step pixel based reconstruction approach using CaSSIS four band images. In the first step advanced unsupervised techniques are applied on CRISM hyperspectral datacubes to reduce dimensionality and establish clusters of spectral features. Given that these clusters contain reasonable information about the surface composition, in a second step, it is feasible to map CaSSIS four band images to the spectral clusters by training a machine learning classifier (for the cluster labels) using only CaSSIS datasets. In this way the system can extrapolate spectral features to areas unmapped by CRISM. To assess the performance of this proposed methodology we analyzed actual and artificially generated CaSSIS images and benchmarked results against traditional correlation based methods. Qualitative and quantitative analyses indicate that by this novel procedure spectral features of in non-spectral imaged areas can be predicted to an extent that can be evaluated quantitatively, especially in highly feature-rich landscapes.
Lecture
  • N. Thomas
  • Michael Fernandes
  • Benedikt Elser
  • A. Rossi
  • Alexander Pletl
  • G. Cremonese

Machine learning approaches to matching CaSSIS colour imaging with CRISM imaging spectroscopy (Abstract B4.2-0036-22).

In: 44th COSPAR Scientific Assembly

Committee on Space Research Online

  • 16.-24.07.2022 (2022)

show abstract

The Colour and Stereo Surface Imaging System (CaSSIS) onboard ESA's ExoMars Trace Gas Orbiter (TGO) (Thomas et al., 2017) has been providing 4-band colour observations of the surface of Mars since entering prime mission on 21 April 2018. The filters were selected to provide discrimination between minerals at high signal to noise while retaining the relatively high spatial resolution of a broad-band visible imager. Tornabene et al. (2018) showed that CaSSIS should be effective at this task although the atmospheric contribution to the data had not been modelled at that time. The data set obtained in the prime mission has more than justified the careful selection of the filters and imaging approach. The data quality has prompted us to consider whether CaSSIS data can be used to "extend" the coverage of imaging spectroscopy data provided by the CRISM instrument onboard NASA's Mars Reconnaissance Orbiter. The idea is that by linking CRISM spectra to the CaSSIS colour data one can then use CaSSIS data to identify mineral relationships beyond the coverage of the CRISM data set. The link is provided by mapping the CaSSIS four-band images to spectral clusters using a machining learning classifier. Clearly, it is important to benchmark this approach with respect to traditional correlation based methods. Furthermore, quantitative analyses are needed to provide a statistically justifiable confidence level for the derived results. Currently the work suggests that this can be achieved at least in highly feature-rich landscapes. We also note that Gao et al. (2021) have been applying similar approaches for studies of Jezero Crater. In principle, three different statistical tasks have to be addressed to apply machine learning: Dimensionality reduction, clustering and classification. Tests are being carried out to establish the best algorithm for the classification and the optimum number of classes. We also seek to establish why one algorithm is better than another so that a robust approach can be adopted for many sites. Correlation between CRISM and CaSSIS data shows that the CaSSIS NIR band has a high discrimination power (as we intuitively assumed leading to its inclusion in the design) and certain spectral features in CRISM do correlate strongly. First preliminary results indicate that a Random Forest classifier slightly outperforms other standard machine learning methods. Splitting the spectral data into VIS, NIR- ranges is a relevant preprocessing step to determine suitable clusters. The progress will be described in the presentation with examples from the Vallis Marineris and Noachis Terra regions. Ref. Gao et al., (2021), Generalized Unsupervised Clustering of Hyperspectral Images of Geological Targets in the Near Infrared, arXiv:2106.13315v1 [Titel anhand dieser ArXiv-ID in Citavi-Projekt übernehmen] Thomas, N., and 60 colleagues,(2017),The Colour and Stereo Surface Imaging System (CaSSIS) for the ExoMars Trace Gas Orbiter,Space Science Reviews,212,1897 Tornabene, L.L. et al., (2018),Image Simulation and Assessment of the Colour and Spatial Capabilities of the Colour and Stereo Surface Imaging System (CaSSIS) on the ExoMars Trace Gas Orbiter, Space Science Reviews,214,18
Journal article
  • Alexander Pletl
  • Michael Fernandes
  • N. Thomas
  • A. Rossi
  • Benedikt Elser

Spectral clustering of CRISM datasets in Jezero crater using UMAP and k-Means.

In: Remote Sensing vol. 15

  • (2023)

DOI: 10.3390/rs15040939

show abstract

In this paper, we expand upon our previous research on unsupervised learning algorithms to map the spectral parameters of the Martian surface. Previously, we focused on the VIS-NIR range of hyperspectral data from the CRISM imaging spectrometer instrument onboard NASA’s Mars Reconnaissance Orbiter to relate to other correspondent imager data sources. In this study, we generate spectral cluster maps on a selected CRISM datacube in a NIR range of 1050–2550 nm. This range is suitable for identifying most dominate mineralogy formed in ancient wet environment such as phyllosilicates, pyroxene and smectites. In the machine learning community, the UMAP method for dimensionality reduction has recently gained attention because of its computing efficiency and speed. We apply this algorithm in combination with k-Means to data from Jezero Crater. Such studies of Jezero Crater are of priority to support the planning of the current NASA’s Perseversance rover mission. We compare our results with other methodologies based on a suitable metric and can identify an optimal cluster size of six for the selected datacube. Our proposed approach outperforms comparable methods in efficiency and speed. To show the geological relevance of the different clusters, the so-called “summary products” derived from the hyperspectral data are used to correlate each cluster with its mineralogical properties. We show that clustered regions relate to different mineralogical compositions (e.g., carbonates and pyroxene). Finally the generated spectral cluster map shows a qualitatively strong resemblance with a given manually compositional expert map. As a conclusion, the presented method can be implemented for automated region-based analysis to extend our understanding of Martian geological history.
Journal article
  • Roman-David Kulko
  • Alexander Pletl
  • A. Hanus
  • Benedikt Elser

Detection of Plastic Granules and Their Mixtures.

In: Sensors vol. 23 pg. 3441

  • (2023)

DOI: 10.3390/s23073441

show abstract

Chemically pure PG is used as the starting material in the production of plastic parts. Extrusion machines rely on purity, otherwise resources are lost, and waste is produced. To avoid losses, the machines need to analyze the raw material. Spectroscopy in the VIS-NIR range and machine learning can be used as analyzers. We present an approach using two spectrometers with a spectral range of 400–1700 nm and a fusion model comprising classification, regression, and validation to detect 25 materials and proportions of their binary mixtures. 1D-CNN is used for classification and PLS for the estimation of proportions. The classification is validated by reconstructing the sample spectrum using the component spectra in LSF. To save time and effort, the fusion model is trained on semi-empirical spectral data. The component spectra are acquired empirically and the binary mixture spectra are computed as linear combinations. The fusion model achieves very a high accuracy on VIS-NIR spectral data. Even in a smaller spectral range from 400–1100 nm, the accuracy is high. The VIS-NIR spectroscopy and the presented fusion model can be used as a concept for building an analyzer. Inexpensive silicon sensor-based spectrometers can be used.
Journal article
  • Roman-David Kulko
  • Alexander Pletl
  • H. Mempel
  • Florian Wahl
  • Benedikt Elser

OpenVNT: An Open Platform for VIS-NIR Technology.

In: Sensors vol. 23 pg. 3151

  • (2023)

DOI: 10.3390/s23063151

show abstract

Spectrometers measure diffuse reflectance and create a “molecular fingerprint” of the material under investigation. Ruggedized, small scale devices for “in-field” use cases exist. Such devices might for example be used by companies in the food supply chain for inward inspection of goods. However, their application for the industrial Internet of Things workflows or scientific research is limited due to their proprietary nature. We propose an open platform for visible and near-infrared technology (OpenVNT), an open platform for capturing, transmitting, and analysing spectral measurements. It is built for use in the field, as it is battery-powered and transmits data wireless. To achieve high accuracy, the OpenVNT instrument contains two spectrometers covering a wavelength range of 400–1700 nm. We conducted a study on white grapes to compare the performance of the OpenVNT instrument against the Felix Instruments F750, an established commercial instrument. Using a refractometer as ground truth, we built and validated models to estimate the Brix value. As a quality measure, we used coefficient of determination of the cross-validation (R2CV) between the instrument estimation and ground truth. With 0.94 for the OpenVNT and 0.97 for the F750, a comparable R2CV was achieved for both instruments. OpenVNT matches the performance of commercially available instruments at one tenth of the price. We provide an open bill of materials, building instructions, firmware, and analysis software to enable research and industrial IOT solutions without the limitations of walled garden platforms.
Journal article
  • Sebastian Wilhelm
  • Jakob Kasbauer
  • Dietmar Jakob
  • Benedikt Elser
  • Diane Ahrens

Exploiting Smart Meter Water Consumption Measurements for Human Activity Event Recognition.

In: Journal of Sensor and Actuator Networks (Special Issue Smart Cities and Homes: Current Status and Future Possibilities) vol. 12

  • (2023)

DOI: 10.3390/jsan12030046

show abstract

Human activity event recognition (HAER) within a residence is a topic of significant interest in the field of ambient assisted living (AAL). Commonly, various sensors are installed within a residence to enable the monitoring of people. This work presents a new approach for HAER within a residence by (re-)using measurements from commercial smart water meters. Our approach is based on the assumption that changes in water flow within a residence, specifically the transition from no flow to flow above a certain threshold, indicate human activity. Using a separate, labeled evaluation data set from three households that was collected under controlled/laboratory-like conditions, we assess the performance of our HAER method. Our results showed that the approach has a high precision (0.86) and recall (1.00). Within this work, we further recorded a new open data set of water consumption data in 17 German households with a median sample rate of 0.083̲ Hz to demonstrate that water flow data are sufficient to detect activity events within a regular daily routine. Overall, this article demonstrates that smart water meter data can be effectively used for HAER within a residence.
Broadcast
  • Benedikt Elser

Maschinelles Lernen: Wie Künstliche Intelligenz in der Obst- und Gemüsebranche eingesetzt wird (Beitrag von Marlene Mengue).

In: radioWelt

Bayern 2

  • 10.02.2023 (2023)

Lecture
  • Dominik Hürland
  • Michael Fernandes
  • Benedikt Elser

HRSC colour data for mineral mapping. Science Talk.

In: HRSC Team Meeting

Deutsches Zentrum für Luft- und Raumfahrt Venice, Italy

  • 19.06.2024 (2024)
Lecture
  • N. Thomas
  • Michael Fernandes
  • Benedikt Elser
  • L. Almeida
  • M. Read

Mineralogical Diversity on the Northern Rim of Hellas Basin seen by CaSSIS [#3419].

In: The Tenth International Conference on Mars (Poster Session: Geophysics, Tectonics, and Interior Processes: Surface Remote Sensing)

Pasadena, CA, USA

  • 22.-25.07.2024 (2024)

show abstract

The northern rim of Hellas Basin between Terby and Niesten craters has exposures of diverse mineralogies. Diversity is seen on small scales. Spectral clustering on CaSSIS data in combination with CRISM mineralogical identification is a useful tool.

projects

FreshRegio https://www.regiothek.de/p/freshregio, Zukunftslabor 2030 https://www.zukunftslabor2030.de

Other

Bachelor/Master Thesis

https://ilearn.th-deg.de/user/profile.php?id=36858