Refine
Departments, institutes and facilities
- Fachbereich Informatik (64)
- Fachbereich Angewandte Naturwissenschaften (49)
- Institut für Technik, Ressourcenschonung und Energieeffizienz (TREE) (42)
- Fachbereich Ingenieurwissenschaften und Kommunikation (33)
- Fachbereich Wirtschaftswissenschaften (22)
- Institut für Cyber Security & Privacy (ICSP) (18)
- Institut für funktionale Gen-Analytik (IFGA) (17)
- Institut für Verbraucherinformatik (IVI) (16)
- Institute of Visual Computing (IVC) (16)
- Institut für Sicherheitsforschung (ISF) (8)
Document Type
- Conference Object (96)
- Article (88)
- Preprint (9)
- Doctoral Thesis (6)
- Part of a Book (5)
- Report (4)
- Book (monograph, edited volume) (3)
- Master's Thesis (3)
- Conference Proceedings (1)
- Research Data (1)
Year of publication
- 2019 (217) (remove)
Language
- English (217) (remove)
Keywords
- lignin (4)
- Navigation (3)
- security (3)
- work engagement (3)
- Aminoacylase (2)
- Design (2)
- Drosophila (2)
- Exergame (2)
- Extrusion blow molding (2)
- FPGA (2)
Traffic sign recognition is an important component of many advanced driving assistance systems, and it is required for full autonomous driving. Computational performance is usually the bottleneck in using large scale neural networks for this purpose. SqueezeNet is a good candidate for efficient image classification of traffic signs, but in our experiments it does not reach high accuracy, and we believe this is due to lack of data, requiring data augmentation. Generative adversarial networks can learn the high dimensional distribution of empirical data, allowing the generation of new data points. In this paper we apply pix2pix GANs architecture to generate new traffic sign images and evaluate the use of these images in data augmentation. We were motivated to use pix2pix to translate symbolic sign images to real ones due to the mode collapse in Conditional GANs. Through our experiments we found that data augmentation using GAN can increase classification accuracy for circular traffic signs from 92.1% to 94.0%, and for triangular traffic signs from 93.8% to 95.3%, producing an overall improvement of 2%. However some traditional augmentation techniques can outperform GAN data augmentation, for example contrast variation in circular traffic signs (95.5%) and displacement on triangular traffic signs (96.7 %). Our negative results shows that while GANs can be naively used for data augmentation, they are not always the best choice, depending on the problem and variability in the data.
This research was conducted to determine the relationship between entrepreneurship educations, venture intention on venture creation among entrepreneurial graduate in Kenya focusing on selected universities in Kenya. The study was grounded on the economic entrepreneurship theory, an attitude-based view on entrepreneurship education and resource-based theory. This research embraced a cross-sectional descriptive survey design. Study population was 2500 student taking entrepreneurship course in various universities of whom a sample of 345 students was chosen using purposive and simple random sampling technique. The study used both primary and secondary data. Statistical Package for Social Sciences (SPSS Version 21) was used to analyse quantitative date. The findings of the study revealed that entrepreneurial education had a noteworthy influence on venture creation (r= 0. 512, p = .001<0.05, t= 10.904) increase in entrepreneurial education would lead to significant increase in venture creation. The study revealed that entrepreneurial training has significance influence in venture creation among graduate as indicated by β1=-0.670, p=0.002<0.05, t= 10.304. Study established that increase in entrepreneurial orientation would lead to increase in venture creation among graduates by a factor of 0.519 with P value of 0.002 (r =0.519, P=0.03< 0.05). The research conclusion was that entrepreneurial knowledge acquisition, entrepreneurial training and entrepreneurial orientation combined have important and positive relationship with venture creation among the graduates.
For years, the common logic that underpinned entrepreneurship was to find a niche within in a market/sector and then solidify business practice to achieve success in the market segment. The dawn of technologically-based disruptive enterprises, such as Uber and Air B&B, coupled with the nearing Fourth Industrial revolution seriously call into question the conventional business logic. In this article, the projected impact of these forces on African entrepreneurs is explored. We look at the role of government, business and education systems to prepare for the impact of the Fourth Industrial revolution. Specific focus is placed on the need for entrepreneurial skills and training to prepare for the impact of the Fourth Industrial revolution. We also explore the importance of innovation, both in terms of products and processes to mitigate against the impact of these forces.