On the Deficiency of the Ott-Clemmow Modified Saddle-Point Method in the Sommerfeld Half-Space Problem

Preprint of a submitted article.

On the Deficiency of the Ott-Clemmow Modified Saddle-Point Method in the Sommerfeld Half-Space Problem

Preprint of a submitted article.

Autonomous Penetration Testing Based on Improved Deep Q-Network

Penetration testing is an effective way to test and evaluate cybersecurity by simulating a cyberattack. However, the traditional methods deeply rely on domain expert knowledge, which requires prohibitive labor and time costs. Autonomous penetration testing is a more efficient and intelligent way to solve this problem. In this paper, we model penetration testing as a Markov decision process problem and use reinforcement learning technology for autonomous penetration testing in large scale networks. We propose an improved deep Q-network (DQN) named NDSPI-DQN to address the sparse reward problem and large action space problem in large-scale scenarios. First, we reasonably integrate five extensions to DQN, including noisy nets, soft Q-learning, dueling architectures, prioritized experience replay, and intrinsic curiosity model to improve the exploration efficiency. Second, we decouple the action and split the estimators of the neural network to calculate two elements of action separately, so as to decrease the action space. Finally, the performance of algorithms is investigated in a range of scenarios. The experiment results demonstrate that our methods have better convergence and scaling performance.

IoT Botnet Detection Using Salp Swarm and Ant Lion Hybrid Optimization Model

In the last decade, the devices and appliances utilizing the Internet of things (IoT) have expanded tremendously, which has led to revolutionary developments in the network industry. Smart homes and cities, wearable devices, traffic monitoring, health systems, and energy savings are typical IoT applications. The diversity in IoT standards, protocols, and computational resources makes them vulnerable to security attackers. Botnets are challenging security threats in IoT devices that cause severe Distributed Denial of Service (DDoS) attacks. Intrusion detection systems (IDS) are necessary for safeguarding Internet-connected frameworks and enhancing insufficient traditional security countermeasures, including authentication and encryption techniques. This paper proposes a wrapper feature selection model (SSA–ALO) by hybridizing the salp swarm algorithm (SSA) and ant lion optimization (ALO). The new model can be integrated with IDS components to handle the high-dimensional space problem and detect IoT attacks with superior efficiency. The experiments were performed using the N-BaIoT benchmark dataset, which was downloaded from the UCI repository. This dataset consists of nine datasets that represent real IoT traffic. The experimental results reveal the outperformance of SSA–ALO compared to existing related approaches using the following evaluation measures: TPR (true positive rate), FPR (false positive rate), G-mean, processing time, and convergence curves. Therefore, the proposed SSA–ALO model can serve IoT applications by detecting intrusions with high true positive rates that reach 99.9% and with a minimal delay even in imbalanced intrusion families.

A Novel Behavioral Strategy for RoboCode Platform Based on Deep Q-Learning

This paper addresses a new machine learning-based behavioral strategy using the deep Q-learning algorithm for the RoboCode simulation platform. According to this strategy, a new model is proposed for the RoboCode platform, providing an environment for simulated robots that can be programmed to battle against other robots. Compared to Atari Games, RoboCode has a fairly wide set of actions and situations. Due to the challenges of training a CNN model for such a continuous action space problem, the inputs obtained from the simulation environment were generated dynamically, and the proposed model was trained by using these inputs. The trained model battled against the predefined rival robots of the environment (standard robots) by cumulatively benefiting from the experience of these robots. The comparison between the proposed model and standard robots of RoboCode Platform was statistically verified. Finally, the performance of the proposed model was compared with machine learning based-customized robots (community robots). Experimental results reveal that the proposed model is mostly superior to community robots. Therefore, the deep Q-learning-based model has proven to be successful in such a complex simulation environment. It should also be noted that this new model facilitates simulation performance in adaptive and partially cluttered environments.

A Three-Section-Settlement Calculation Method for Composite Foundation Reinforced by Geogrid-Encased Stone Columns

The analysis of the bearing characteristics and deformation mechanism of composite foundation reinforced with geogrid-encased stone columns is presented in order to obtain its settlement calculation method. The settlement of composite foundation is divided into three sections which are the reinforced section, unreinforced section, and underlying stratum. Based on Hooke’s law of space problem and the thoughts of the layer-wise summation method, the relative slip displacement between pile and soil of reinforced section without plastic zone is analyzed. The settlement of reinforced section is calculated by the layered iteration method based on the pile element model. The compatibility of vertical and radial deformations of unreinforced section is analyzed based on the pile-soil element model. The settlement of underlying stratum is still calculated by the layer-wise summation method. Finally, two engineering examples are analyzed and the results show that the settlement calculated by the presented method is close to the measured one. The method overcomes the defect that the calculated results by the other existing methods are more dangerous and it is more feasible and can be applied in engineering practice.

Energy-aware task offloading with deadline constraint in mobile edge computing

With the development of the wireless network, increasing mobile applications are emerging and receiving great popularity. These applications cover a wide area, such as traffic monitoring, smart homes, real-time vision processing, objective tracking, and so on, and typically require computation-intensive resources to achieve a high quality of experience. Although the performance of mobile devices (MDs) has been continuously enhanced, running all the applications on a single MD still causes high energy consumption and latency. Fortunately, mobile edge computing (MEC) allows MDs to offload their computation-intensive tasks to proximal eNodeBs (eNBs) to augment computational capabilities. However, the current task offloading schemes mainly concentrate on average-based performance metrics, failing to meet the deadline constraint of the tasks. Based on the deep reinforcement learning (DRL) approach, this paper proposes an Energy-aware Task Offloading with Deadline constraint (DRL-E2D) algorithm for a multi-eNB MEC environment, which is to maximize the reward under the deadline constraint of the tasks. In terms of the actor-critic framework, we integrate the action representation into DRL-E2D to handle the large discrete action space problem, i.e., using the low-complexity k-nearest neighbor as an approximate approach to extract optimal discrete actions from the continuous action space. The extensive experimental results show that DRL-E2D achieves better performance than the comparison algorithms on all parameter settings, indicating that DRL-E2D is robust to the state changes in the MEC environment.

MICRO-APARTMENT IN PONTIANAK

As the world population, the majority of Indonesian’s town all knows an increase of their population that results in an augmentation of the housing needs. What is called Micro-housing is a new global trend that targets a younger worker part of the population and also a newly married couple that doesn’t have children yet. Indeed, this part of the population is in need to find house or apartment close to their workplace, close to the transportation of the city but also close to all the other town facilities like hospitals, restaurant, stores. This desire of finding a house or apartment in a strategic location known as the center of a town tends to increase but the available spaces to build more houses tend to decrease. That is why one of the solutions to this space problem is micro-housing; this type of new housing will allow responding to this problem of available space. This design project is not only about reducing space, but it is also focus on being able to design and create a layout space that responds to the multiple needs of the tenant by using multiple techniques in the design layout but also using transformable and foldable pieces of furniture.