Sürdürülebilir Kalkınma Amaçları

• 1
• 1

• MakaleAçık Erişim2025Scopus SJRQ1/r/munzur/821
  A new lightweight convolutional neural network model for detecting drivable road regions

  Doğan, Gürkan; Uyanık, Hakan; Ergen, Burhan

  Nowadays, due to the rapid increase in the number of autonomous vehicles on the market, the safe navigation of these vehicles in drivable road areas has become extremely important. One of the most crucial factors in ensuring safe navigation is addressing the detection of drivable road areas as a task of semantic segmentation. Considering that autonomous vehicles are modular, the algorithm to perform this task must have the optimum trade-off in terms of lightweight, computational complexity, and segmentation accuracy. In this study, RoNet, a new model based on convolutional neural networks that provides an optimum trade-off for the detection of drivable road regions, was designed and proposed. The standard convolution types for the encoder and decoder bottleneck module of the RoNet model, as well as the spatial edge attention mechanism, have been optimized by developing asymmetric convolution types using asymmetric atrous convolution, asymmetric convolution types using Prewitt and Sobel kernels. Spatial edge attention mechanism is designed to reduce the loss of detailed information in small-resolution feature maps. In experimental tests performed with CamVid and FUVid datasets, RoNet achieved a better trade-off in terms of segmentation accuracy, number of parameters, and computational complexity compared to other state-of-the-art methods.

  • 
  • 
  AtıfScopus3·WoS3·OpenAlex6

  İncele
• MakaleAçık Erişim2021Scopus SJRQ1/r/munzur/2741
  An effective method to improve nonlinearity value of substitution boxes based on random selection

  Artuğer, Fırat; Özkaynak, Fatih

  In today's digital society, new design alternatives are needed for substitution box structures, which has critical importance in developing secure information systems that are resistant to algebraic and application attacks, as new attacks negatively affect designs based on mathematical transformations. Although random selection-based substitution box structures are a good alternative against algebraic and application attacks, the low value of nonlinearity criterion is an important problem. Solution suggestions using optimization algorithms have been proposed to address this problem. “Information Sciences 523 (2020) 152–166” is the study that reached the highest nonlinearity value based on optimization algorithms to date. However, the high computational costs of optimization algorithms are another challenge that must be overcome. In this study, it has been shown that the nonlinearity values ​​of random (chaotic) selection substitution box structures can be improved as much as mathematically based designs by using a method that is too simple to compare with optimization algorithms. It has been shown that the nonlinearity value can be improved up to 110 for random selection-based substitution box designs. Although this nonlinearity value is the highest achievable value in the literature based on the random selection principle, the fact that it requires only 2×255×255 processes in the worst case has been evaluated as an important success of the proposed method compared to other design approaches. Other advantages of the proposed method are that the improved substitution box structures are resistant to side-channel attacks, simple structure, easy hardware implementation, and successful results in practical applications such as image encryption. It is believed that all these results will be a motivation for new post-processing techniques to be designed in the future for random selection-based substitution box designs.

  AtıfScopus42·WoS30·OpenAlex42

  İncele
• MakaleAçık Erişim2020Scopus SJRQ1/r/munzur/3711
  Time-aware link prediction based on strengthened projection in bipartite networks

  Aslan, Serpil; Kaya, B.

  The traditional projection models in the bipartite networks involve many node pairs that consist of weak relationships. These node pairs lead to poor quality predictions as well as high computation time. In this paper, to cope with these problems, we firstly propose a novel projection model, which is called “Strengthened Projection Model”. Then, to predict the potential links in the future, we present a new link prediction approach based on the proposed projection model. Thanks to the proposed model, the computation time is shortened, and the high probability predictions are extracted. The majority of the previous works conducted in this area have used the classical proximity measure algorithms that only take into account the current network structure, regardless of when events occur in the network evolution. To overcome these limited methods, in this paper, we also propose a novel proximity measure algorithm that considers the bipartite network evolution. To the best of our knowledge, this is the first attempt that takes into account the time-awareness in bipartite networks. To evaluate the performance of our proposed approach, we conducted experiments on the academic information network. To construct this bipartite network, we collected data from IEEE Xplore. The experimental results show that the success of the proposed method is promising.

  AtıfScopus11·WoS9·OpenAlex10

  İncele