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.

This paper aims to highlight the factors affecting health and safety (H&S) and the SMART Technologies (ST) used to mitigate them in the construction industry through a range of selected papers to encourage readers and potential audiences to consider the need for intelligent technologies to minimize the risks of injuries, illnesses and severe harm in the construction industry.

This paper adopts a double systematic literature review (SLR) to analyse studies investigating the factors affecting H&S and the ST in the construction industry using databases such as Google Scholar, Scopus, Science Direct and Emerald Insight publication.

The SLR identified “fatal or focus five factors” that include objects Fall from heights (FFH) and trapped between objects; Falls, Trips and slips (FTS); Machinery/Equipment Malfunction and Moving Equipment; Pollutants: Chemicals, Airborne Dust, Asbestos; and Electrocution. The ST includes Safety Boots/SMART Glasses/SMART Helmet/SMART Vests/SMART PPE/SMART Watch, Mobile Apps, Building Information Modelling (BIM), Virtual Reality/Augmented Reality (VR/AR), Drones/Unmanned Aerial Vehicles and Wearable Technology/Mobile Sensors help mitigate the risk posed by “Fatal five”. However, other factors within the scope of ST, such as Weather Conditions, Vibrations, Violence, Disease and illness, Fire and Explosion and Over Exertion, are yet to be adopted in the field.

SLR methodology limitations of not obtaining the most updated field knowledge are critical and are offset by choosing 72% of H&S and 92% of SM review literature post-2017. Limitations to capturing articles because of the restriction of database access: only English language search and journals that are not a part of the databases selected are acknowledged. However, key database search that recognizes rigorous peer-reviewed articles offset these limitations. The researcher’s Bias is acknowledged.

This paper unravels the construction H&S factors and their interlinks with ST, which would aid industry understanding and focus on mitigating associated risks. The paper highlights the Fatal five and trivial 15, which would help better understand the causes of the H&S risks. Further, the paper discusses ST’s connectivity, which would aid the organization’s overall H&S management. The practical and theoretical implications include a better understanding of all factors that affect H&S and ST available to help mitigate concerns. The operating managers could use the ST to reduce H&S risks at every construction process stage. This paper on H&S and ST and relationships can theorize that the construction industry is more likely to identify clear root causes of H&S and ST usage than previously. The theoretical implications include enhanced understanding for academics on H&S factors, ST and gaps in ST concerning H&S, which can be expanded to provide new insights into existing knowledge.

This paper highlights all factors affecting H&S and ST that help mitigate associated risks and identifies the “Fatal five” factors. The paper is the first to highlight the factors affecting H&S combined with ST in use and their interactions. The paper also identified factors within the ST scope that are yet to be explored.

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.