Soft Computing and Hybrid Intelligence for Decision Support in Forensics Science

Due to increase in complexity and variety of crimes, Forensics Science requires more advanced data analysis techniques to improve understandability, processing speed and efficiency of the crime investigations. The investigation is facing multiple challenges while dealing with data due to its uniqueness and specific conditions of surrounding environment and a crime scene. Soft Computing methods proved their efficiency before and can help to establish a closer collaboration between the Forensics Analyst and Computational Intelligence Scientist by using inexact solutions and human understandable models. The importance of such methods lies in ability to seek for approximate and fast decisions regardless the complexity and volume of the stored data. The purpose of this paper is to provide a solid overview and achieved improvements in the application of Soft Computing for Forensic Science that also complies with Daubert Standards.

[1]  Fakhreddine O. Karray,et al.  Soft Computing and Intelligent Systems Design, Theory, Tools and Applications , 2006, IEEE Transactions on Neural Networks.

[2]  Sargur N. Srihari,et al.  Computational Forensics: An Overview , 2008, IWCF.

[3]  Katrin Franke,et al.  Automated generation of fuzzy rules from large-scale network traffic analysis in digital forensics investigations , 2015, 2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[4]  Sankar K. Pal,et al.  Data mining in soft computing framework: a survey , 2002, IEEE Trans. Neural Networks.

[5]  Kim-Kwang Raymond Choo,et al.  Impacts of increasing volume of digital forensic data: A survey and future research challenges , 2014, Digit. Investig..

[6]  Alessandro Guarino,et al.  Digital Forensics as a Big Data Challenge , 2013, ISSE.

[7]  Katrin Franke,et al.  The influence of physical and biomechanical processes on the ink trace. Methodological foundations for the forensic analysis of signatures , 2005 .

[8]  Katrin Franke,et al.  A New Method for an Optimal SOM Size Determination in Neuro-Fuzzy for the Digital Forensics Applications , 2015, IWANN.

[9]  Katrin Franke,et al.  Multinomial classification of web attacks using improved fuzzy rules learning by Neuro-Fuzzy , 2016, Int. J. Hybrid Intell. Syst..

[10]  Katrin Franke,et al.  Malware Beaconing Detection by Mining Large-scale DNS Logs for Targeted Attack Identification , 2016 .

[11]  Andrew Freeman.  Probabilistic modeling as an exploratory decision-making tool , 2010 .

[12]  Nadia Nedjah,et al.  Special issue on soft computing for information system security , 2011, Appl. Soft Comput..

[13]  Lotfi A. Zadeh,et al.  Fuzzy logic, neural networks, and soft computing , 1993, CACM.

[14]  Katrin Franke,et al.  A new method of fuzzy patches construction in Neuro-Fuzzy for malware detection , 2015, IFSA-EUSFLAT.

[15]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery in Databases , 1996, AI Mag..

[16]  Katrin Franke,et al.  Towards Improvement of Multinomial Classification Accuracy of Neuro-Fuzzy for Digital Forensics Applications , 2016, HIS.