GOAMLP: Network Intrusion Detection With Multilayer Perceptron and Grasshopper Optimization Algorithm

Moghanian, Shadi; Saravi, Farshid Bagheri; Javidi, Giti; Sheybani, Ehsan

doi:10.1109/access.2020.3040740

Cited by 40 publications

(12 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike IoT devices with micro intelligence, learning systems and forecasting can be implemented in upper layers. A more robust mechanism using combinations of neural networks and metaheuristic grasshopper algorithm GOAMLP [53] can learn to predict errors in different stages and different network elements, including machinery. The machinery operators may have no access to the status.…”

Section: Management Model Requirementsmentioning

confidence: 99%

An IIoT-Based Approach to the Integrated Management of Machinery in the Construction Industry

et al. 2023

View full text Add to dashboard Cite

In recent years, considerable advances in connecting industrial equipment to the Internet allowed a higher level of operational efficiency, productivity, and automation. Nevertheless, the construction industry still presents challenging requirements, like long-distance wireless communication, interconnection of out-ofcoverage areas, constant mobility of machinery, and support for legacy and proprietary systems. All these requirements pose different challenges when compared with traditional smart factory Industry 4.0 solutions. This paper discusses some of the current key questions regarding fleet management in the construction industry, identifies requirements for heavy-duty machinery, and proposes an Industrial Internet of Things (IIoT)-based solution for the integrated monitoring of such machinery. Also, it proposes and presents an open, innovative solution for the integrated management of non-standardized civil construction vehicle technologies. The developed prototype uses the J1939 protocol to collect machinery status and Long-Range Wide Area Network (LoRaWAN) to communicate the monitored data. The solution was assessed at the construction site of the new port of Sines in Portugal. A detailed description of the proposed system is provided, along with information on trials and evaluation results regarding its performance. Additionally, the paper provides insights into open issues and challenges in this field and how our solution can contribute to overcoming them.

show abstract

Section: Management Model Requirementsmentioning

confidence: 99%

An IIoT-Based Approach to the Integrated Management of Machinery in the Construction Industry

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In [15], an IDS can be presented that uses ML and data mining ideas for detecting network intrusion paradigms. In the presented technique, an ANN was utilized as a learning technique.…”

Section: Related Workmentioning

confidence: 99%

Intelligent Intrusion Detection System using Enhanced Arithmetic Optimization Algorithm with Deep Learning Model

2023

Teh. vjesn.

View full text Add to dashboard Cite

The widespread use of interoperability and interconnectivity of computing systems is becoming indispensable for enhancing our day-to-day actions. The susceptibilities deem cyber-security systems necessary for assuming communication interchanges. Secure transmission needs security measures for combating the threats and required developments to security measures that counter evolving security risks. Though firewalls were devised to secure networks, in real-time they cannot detect intrusions. Hence, destructive cyber-attacks put forward severe security complexities, requiring reliable and adaptable intrusion detection systems (IDS) that could monitor unauthorized access, policy violations, and malicious activity practically. Conventional machine learning (ML) techniques were revealed for identifying data patterns and detecting cyber-attacks IDSs successfully. Currently, deep learning (DL) methods are useful for designing accurate and effective IDS methods. In this aspect, this study develops an intelligent IDS using enhanced arithmetic optimization algorithm with deep learning (IIDS-EAOADL) method. The presented IIDS-EAOADL model performs data standardization process to normalize the input data. Besides, equilibrium optimizer based feature selection (EOFS) approach is developed to elect an optimal subset of features. For intrusion detection, deep wavelet autoencoder (DWAE) classifier is applied. Since the proper tuning of parameters of the DWNN is highly important, EAOA algorithm is used to tune them. For assuring the simulation results of the IIDS-EAOADL technique, a widespread simulation analysis takes place using a benchmark dataset. The experimentation outcomes demonstrate the improvements of the IIDS-EAOADL model over other existing techniques

show abstract

“…Through multiple RL trials, the authors demonstrated that PB2 can achieve remarkable performance levels while adhering to a moderate computational budget. In another study by Moghanian et al [38], a swarm-based metaheuristic algorithm is employed to minimize errors in intrusion detection. In the novel approach, the Grasshopper Optimization Algorithm (GOA) is harnessed to enhance the precision of artificial neural networks (ANNs) in order to decrease the rate of intrusion detection errors.…”

Section: Related Workmentioning

confidence: 99%

Enhanced Deep Deterministic Policy Gradient Algorithm Using Grey Wolf Optimizer for Continuous Control Tasks

Sumiea,

Abdulkadir,

Ragab

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Deep Reinforcement Learning (DRL) allows agents to make decisions in a specific environment based on a reward function, without prior knowledge. Adapting hyperparameters significantly impacts the learning process and time. Precise estimation of hyperparameters during DRL training poses a major challenge. To tackle this problem, this study utilizes Grey Wolf Optimization (GWO), a metaheuristic algorithm, to optimize the hyperparameters of the Deep Deterministic Policy Gradient (DDPG) algorithm for achieving optimal control strategy in two simulated Gymnasium environments provided by OpenAI. The ability to adapt hyperparameters accurately contributes to faster convergence and enhanced learning, ultimately leading to more efficient control strategies. The proposed DDPG-GWO algorithm is evaluated in the 2DRobot and MountainCarContinuous simulation environments, chosen for their ease of implementation. Our experimental results reveal that optimizing the hyperparameters of the DDPG using the GWO algorithm in the Gymnasium environments maximizes the total rewards during testing episodes while ensuring the stability of the learning policy. This is evident in comparing our proposed DDPG-GWO agent with optimized hyperparameters and the original DDPG. In the 2DRobot environment, the original DDPG had rewards ranging from -150 to -50, whereas, in the proposed DDPG-GWO, they ranged from -100 to 100 with a running average between 1 and 800 across 892 episodes. In the MountainCarContinuous environment, the original DDPG struggled with negative rewards, while the proposed DDPG-GWO achieved rewards between 20 and 80 over 218 episodes with a total of 490 timesteps.

show abstract

GOAMLP: Network Intrusion Detection With Multilayer Perceptron and Grasshopper Optimization Algorithm

Cited by 40 publications

References 52 publications

An IIoT-Based Approach to the Integrated Management of Machinery in the Construction Industry

An IIoT-Based Approach to the Integrated Management of Machinery in the Construction Industry

Intelligent Intrusion Detection System using Enhanced Arithmetic Optimization Algorithm with Deep Learning Model

Enhanced Deep Deterministic Policy Gradient Algorithm Using Grey Wolf Optimizer for Continuous Control Tasks

Contact Info

Product

Resources

About