Auflistung nach:
Auflistung Künstliche Intelligenz 36(2) - September 2022 nach Titel
1 - 10 von 13
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelAI: Back to the Roots?(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Wrede, Britta
- ZeitschriftenartikelAutomatic Classification of Bloodstains with Deep Learning Methods(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Bergman, Tommy; Klöden, Martin; Dreßler, Jan; Labudde, DirkThe classification of detected bloodstains into predetermined categories is a crucial component of the so-called bloodstain pattern analysis. As in other forensic disciplines, deep learning methods may help to reduce human subjectivity within this process, may increase the classification accuracy, shorten the calculation time and thus, enable high-throughput analysis. In this work, an approach is presented in which a convolutional neural network (Inception v3) was trained from 965 drip stains (passive origin) and 1595 blood spatters (active origin). The trained CNN was evaluated with a test data set consisting of 366 images of drip stains and blood spatters. The success rate was 99.73% which suggests that neural networks could also be used to automatically classify other classes of bloodstain patterns to speed up the investigation process in the future.
- ZeitschriftenartikelAutomatic Generation of Personalised and Context-Dependent Textual Interventions During Neuro-rehabilitation(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Felske, Timon; Bader, Sebastian; Kirste, ThomasIn this paper we present our system that synthesises personalised and context dependent texts during robot guided exercises for neuro-rehabilitation. This system is used to generate texts for the communication between a care robot and patients. We present requirements that a system in such a medical domain has to meet. Afterwards the results of a systematic literature review are presented. We present our solution based on the RosaeNLG system. It supports different language levels and referring expressions in a real-time text generation system, so that generated texts can be adapted to the reader in the best possible way. We evaluate our system with respect to the requirements. The contribution of the paper is twofold: We present a set of requirements for Natural Language Generation (NLG) in medical domains and we show how to extend RosaeNLG with an external dialogue memory to handle complex referring expressions in medical real time settings.
- ZeitschriftenartikelCOMBI: Artificial Intelligence for Computer-Based Forensic Analysis of Persons(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Becker, Sven; Heuschkel, Marie; Richter, Sabine; Labudde, DirkDuring the prosecution process the primary objective is to prove criminal offences to the correct perpetrator to convict them with legal effect. However, in reality this may often be difficult to achieve. Suppose a suspect has been identified and is accused of a bank robbery. Due to the location of the crime, it can be assumed that there is sufficient image and video surveillance footage available, having recorded the perpetrator at the crime scene. Depending on the surveillance system used, there could be even high-resolution material available. In short, optimal conditions seem to be in place for further investigations, especially as far as the identification of the perpetrator and the collection of evidence of their participation in the crime are concerned. However, perpetrators usually act using some kind of concealment to hide their identity. In most cases, they disguise their faces and even their gait. Conventional investigation approaches and methods such as facial recognition and gait analysis then quickly reach their limits. For this reason, an approach based on anthropometric person-specific digital skeletons, so-called rigs, that is being researched by the COMBI research project is presented in this publication. Using these rigs, it should be possible to assign known identities, comparable to suspects, to unknown identities, comparable to perpetrators. The aim of the COMBI research project is to study the anthropometric pattern as a biometric identifier as well as to make it feasible for the standardised application in the taking of evidence by the police and prosecution. The approach is intended to present computer-aided opportunities for the identification of perpetrators that can support already established procedures.
- ZeitschriftenartikelCorrection to: Analyzing Teacher Competency with TPACK for K-12 AI Education(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Kim, Seonghun; Jang, Yeonju; Choi, Seongyune; Kim, Woojin; Jung, Heeseok; Kim, Soohwan; Kim, Hyeoncheol
- ZeitschriftenartikelCorrection to: Computational Thinking as a Social Movement(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Mørch, Anders; Kafai, Yasmin
- ZeitschriftenartikelDigital Forensics AI: Evaluating, Standardizing and Optimizing Digital Evidence Mining Techniques(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Solanke, Abiodun A.; Biasiotti, Maria AngelaThe impact of AI on numerous sectors of our society and its successes over the years indicate that it can assist in resolving a variety of complex digital forensics investigative problems. Forensics analysis can make use of machine learning models’ pattern detection and recognition capabilities to uncover hidden evidence in digital artifacts that would have been missed if conducted manually. Numerous works have proposed ways for applying AI to digital forensics; nevertheless, scepticism regarding the opacity of AI has impeded the domain’s adequate formalization and standardization. We present three critical instruments necessary for the development of sound machine-driven digital forensics methodologies in this paper. We cover various methods for evaluating, standardizing, and optimizing techniques applicable to artificial intelligence models used in digital forensics. Additionally, we describe several applications of these instruments in digital forensics, emphasizing their strengths and weaknesses that may be critical to the methods’ admissibility in a judicial process.
- ZeitschriftenartikelExplaining Artificial Intelligence with Care(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Szepannek, Gero; Lübke, KarstenIn the recent past, several popular failures of black box AI systems and regulatory requirements have increased the research interest in explainable and interpretable machine learning. Among the different available approaches of model explanation, partial dependence plots (PDP) represent one of the most famous methods for model-agnostic assessment of a feature’s effect on the model response. Although PDPs are commonly used and easy to apply they only provide a simplified view on the model and thus risk to be misleading. Relying on a model interpretation given by a PDP can be of dramatic consequences in an application area such as forensics where decisions may directly affect people’s life. For this reason in this paper the degree of model explainability is investigated on a popular real-world data set from the field of forensics: the glass identification database. By means of this example the paper aims to illustrate two important aspects of machine learning model development from the practical point of view in the context of forensics: (1) the importance of a proper process for model selection, hyperparameter tuning and validation as well as (2) the careful used of explainable artificial intelligence. For this purpose, the concept of explainability is extended to multiclass classification problems as e.g. given by the glass data.
- ZeitschriftenartikelInterview: AI Expert Prof. Müller on XAI(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Fähndrich, Johannes; Povalej, Roman; Rittelmeier, Heiko; Berner, Silvio
- ZeitschriftenartikelMoNA: A Forensic Analysis Platform for Mobile Communication(KI - Künstliche Intelligenz: Vol. 36, No. 2, 2022) Spranger, Michael; Xi, Jian; Jaeckel, Lukas; Felser, Jenny; Labudde, DirkMobile communication devices are a popular means of planning, commissioning and carrying out criminal offenses. In particular, data from messengers such as WhatsApp or Telegram often contain conclusive information. Organized crime also usually involves many devices, but not all of them contain the full history of communication. Rather, it is heavily fragmented due to individual deletions of messages or different joining times to groups. A singular evaluation of individual devices is therefore often not expedient, since important relationships cannot be recognized. Furthermore, communication is often distributed across different channels and modalities and can only be fully and correctly understood through a joint semantic analysis. The linking of related communications of different devices enables an almost complete reconstruction of the communication with a simultaneous reduction in reading effort by merging identical messages. Grouping coherent messages into conversations enables efficient comparison with a knowledge model. Building such a model is complex, but can be supported by a term recommender system. In this paper, MoNA is presented as a platform that implements these approaches and enables an assisted analysis of mobile communications.