Search results

In this research, the authors demonstrate the advantage of reinforcement learning (RL) based intrusion detection systems (IDS) to solve very complex problems (e.g. selecting input features, considering scarce resources and constrains) that cannot be solved by classical machine learning. The authors include a comparative study to build intrusion detection based on statistical machine learning and representational learning, using knowledge discovery in databases (KDD) Cup99 and Installation Support Center of Expertise (ISCX) 2012.

The methodology applies a data analytics approach, consisting of data exploration and machine learning model training and evaluation. To build a network-based intrusion detection system, the authors apply dueling double deep Q-networks architecture enabled with costly features, k-nearest neighbors (K-NN), support-vector machines (SVM) and convolution neural networks (CNN).

Machine learning-based intrusion detection are trained on historical datasets which lead to model drift and lack of generalization whereas RL is trained with data collected through interactions. RL is bound to learn from its interactions with a stochastic environment in the absence of a training dataset whereas supervised learning simply learns from collected data and require less computational resources.

All machine learning models have achieved high accuracy values and performance. One potential reason is that both datasets are simulated, and not realistic. It was not clear whether a validation was ever performed to show that data were collected from real network traffics.

The study provides guidelines to implement IDS with classical supervised learning, deep learning and RL.

The research applied the dueling double deep Q-networks architecture enabled with costly features to build network-based intrusion detection from network traffics. This research presents a comparative study of reinforcement-based instruction detection with counterparts built with statistical and representational machine learning.

Just-in-Time (JIT) arrival in the context of port calls can be used to reduce fuel and emissions to achieve environmental targets. The purpose of this paper is to study the implementation process of the Pre-booking Berth Allocation Policy (PBP) and analyze the effectiveness of this policy for the implementation of JIT in port calls.

The study deploys a single case study approach to empirically analyze port authority’s transition from a first-come-first-served (FCFS) arrival policy to the PBP. Observations, interviews and documents were used to collect data during 2020–2022. The analysis deployed the capability, opportunity, motivation and behavior model.

The transition from FCFS to PBP requires an inter-organizational approach, engaging external actors to manage diverse needs and preferences. This fosters effective transition and addresses conflicting interests. The PBP enables JIT arrival, enhancing operational and environmental performance, but faces barriers such as resource dependency and lack of trust. Information sharing capability among the actors, supported by Port Community Systems and adjusted operating rules, is crucial. Moreover, the PBP facilitates integration between sea and hinterland transportation, improving planning and efficiency across maritime transportation chains.

The single case study limits the generalizability of the findings.

Implementing the PBP is complex and demands careful planning from managers. Involving port call actors in the transition is helpful for port managers because they provide valuable feedback and highlight overlooked issues.

Five propositions are suggested to highlight the role of inter-organizational collaboration, information sharing and overcoming barriers such as resource dependency to successfully realize the benefits of JIT in maritime transportation chains.