You are here

Home

News

  • Surveillance in Logistics Facilities and Ports via UAVs Using YOLOv3 Algorithm

    Tepteris, G., Mamasis, K., Minis, I.

    Surveillance in Logistics Facilities and Ports via UAVs Using YOLOv3 Algorithm, accepted for the 9th International Symposium and 31st National Conference on Operational Research (HELORS 2023), taking place in Aigaleo, Athens, on June 29-30 and July, 1, 2023.

    Abstract
    We investigate advanced methods for improving security and preventing intrusions in logistics hubs and ports. For this purpose, we employ unmanned aerial vehicles (UAVs) and object detection artificial intelligence (AI) methods. In recent years, UAVs have become an increasingly popular tool for surveillance due to their ability to provide real time video feed from difficult or inaccessible areas. Leveraging these UAV strengths, we use the YOLOv3 algorithm for real time object detection in surveillance images captured by UAVs. We train the YOLOv3 algorithm using various combinations of three UAV-generated datasets; VisDrone, DAC-SDC and the Stanford Drone Dataset. We then test the model versions obtained from each training dataset on independent images created under practical conditions. The results demonstrate the importance of robust training by using a dataset that has similar characteristics with the environment in which the system will operate.
     
    Keywords
    UAVs, image detection, logistics 4.0, automated surveillance
    Post date: Thursday, May 30, 2024 - 10:53
  • Smart Ports in Industry 4.0: A systematic literature review

    Paraskevas, A., Madas, M., Zeimpekis, V., Fouskas, K. 

    Smart Ports in Industry 4.0: A systematic literature review, Logistics 8(1), 28,2024

    https://doi.org/10.3390/logistics8010028 

    Abstract
    Background: Information and communication technologies (ICT) have introduced “smart” concepts across industries, including ports. Smart ports, leveraging IoT, cybersecurity, and cloud computing, are trending in maritime operations. They optimize data for informed decision-making, cutting costs, enhancing efficiency, mitigating risks, and fostering growth. Methods: To consolidate knowledge in this area, we are conducting a systematic literature review and meta-analysis using the PRISMA framework. Our goal is to synthesize existing insights, minimize biases, increase reliability, and effectively communicate our findings. To address the research needs mentioned, the current study focuses on implementing a systematic literature review (SLR). Results: The goals of this review are: (i) to present and describe the main categories and themes within the research topic, and (ii) to identify research gaps that will aid future research. Key findings include the identification and classification of current literature trends in the smart port performance evaluation framework and the examination of fundamental themes discussed within this area of research. Conclusions: In our review, we emphasize the smart port concept, clarifying its common interpretations amid the industry 4.0 revolution. We discuss recent advancements in emerging technologies and identify key challenges driving researchers’ exploration of the evolving smart port landscape.
     
    Keywords: smart ports; port performance; industry 4.0; information and communication technologies; PRISMA framework; systematic literature review
    Post date: Wednesday, March 13, 2024 - 08:55
  • Investigating the impact of operational efficiency and perceived workload in pickers-to-parts order-picking technologies: Evidence from laboratory experiments
     
    Chondromatidis, N., Gialos, A., Zeimpekis, V. 
     
    Investigating the impact of operational efficiency and perceived workload in pickers-to-parts order-picking technologies: Evidence from laboratory experiments, Logistics, 8(1) 13, 2024
     
    Abstract
    Purpose: Recently, the complexity of managing warehouses has been amplified significantly due to factors that include increased requests for more frequent and smaller order fulfilment, reduction of operational cost, and improvement of customer experience. Product stock count is a critical process in order to address the aforementioned challenges. This article presents experimental results from the adoption of drones coupled with RFID tags used for real time goods’ stock count. Design/methodology/approach: The research methodology adopted combines three different methods, namely Systematic Literature Review (SLR) for identifying parameters that affect the performance of drones in stock count process, survey via questionnaire and interviews to logistics managers to map needs and requirements in warehouse operations, as well as laboratory testing via Design of Experiment (24 full factorial design & ANOVA) methodology to investigate how certain parameters corelate and affect the reading accuracy of RFID tags as well as the time needed by a drone for stock count completion. Findings: The results of the experiments are encouraging, showing that the use of drones coupled with RFID tags may support faster, cost-effective, and safer stock count in warehouses. In both ambient and chilled storage environment a 100% RFID tag reading accuracy was achieved. Less stock-count completion time when compared to manual stock-count was achieved in both cases. Research implications: Understanding the effect of technical and operational parameters of RFID technology in conjunction with unmanned aerial vehicles (UAVs)-drones may have the potential to radically transform the stock count process by considerably increase the efficiency and accuracy of the process. Practical implications: Real-time stock count via drones has significant cost-saving implications for organizations. The elimination of manual stock counting saves operational expenses and increases staff safety. Furthermore, real-time data collection of existing product stock allows managers to efficiently allocate resources, enhancing overall efficiency and performance. Originality/value: This research is among the first studies that aim to present evidence from experimental results that assess the use of drones coupled with RFID technology for real-time stock count. The results from laboratory experiments demonstrate the effect of certain operational parameters,
    such as drone speed, number of rack levels, and RFID tag location on products, during the execution of the stock count process in terms of RFID reading accuracy and stock-count completion time. 
     
    Keywords: drones, logistics, industry 4.0, stock count, warehouse, RFID technology
    Post date: Wednesday, March 13, 2024 - 08:51
  • A state-of-the-art classification and review of parameters that affect the design, control, and operating strategies of order picking systems, Operational Research-An International Journal, 24(6) , 2024

    Gialos, A., Zeimpekis, V.

    Abstract

    The order-picking process has a signifcant impact on both the overall logistics costs as well as the customer service level, and as a result, is characterized as one of the highest priority warehouse activities for productivity and performance  improvements. Although various existing studies focus on the design of order-picking systems as well as on a series of decision-making problems, there is still a need for a holistic framework that will map and categorize the parameters (e.g. total/forward area design, order-picking equipment, storage assignment policies, level of picking locations, order picking technologies, resource planning characteristics, order picking operational policies, routing strategies, product characteristics, order profle, etc.) that should be considered by researchers and practitioners for the design, control, and evaluation of order picking systems. To this end, the aim of this paper is to provide a state-of-the-art classifcation and review of parameters by adopting the Systematic Literature Review (SLR) approach. Overall, 389 articles were reviewed, and the identifed parameters are classifed into three categories: order-picking system design, order-picking system control, and order-picking system evaluation. Furthermore, this literature review aims to present managerial implications that directly afect the successful design of order-picking systems and identify a future research agenda.
     
    Keywords Logistics · Order picking · Warehousing · Systematic literature review · Framework · Picking parameters
    Post date: Friday, February 2, 2024 - 08:17
  • Investigating the impact of operational efficiency and perceived workload in pickers-to-parts order-picking technologies: Evidence from laboratory experiments, Logistics, 8(13), 2024

    Chondromatidis, N., Gialos, A., Zeimpekis, V. 

    Abstract: 

    Despite the general impression that digital order-picking supportive technologies can manage a series of emerging challenges, there is still a very limited amount of research concerning the implementation and evaluation of such technologies in manual picker-to-goods order-picking systems. Therefore, this paper aims to evaluate the performance of three alternative picker-to-goods technologies (i.e., Pick-by-Radio Frequency (RF) Scanner, Pick-to-light, and Pick-byvision) in terms of completion time and perceived workload. Methods: The Design of Experiments (DoE) methodology is adopted to investigate order-picking technologies in terms of completion time. More specifically, a full factorial design has been used (23 × 3 full factorial design) for the assessment of the aforementioned order-picking technologies via laboratory testing. Furthermore, for the comparative assessment of the reviewed order-picking technologies in terms of workload, the NASA Task Load Index (NASA-TLX) is embraced by system users. Results: The results reveal that the best picker-to-goods technology in terms of order-picking completion time and perceived workload under certain laboratory setup is light picking when combined with few items per order line and many order lines per order. Conclusion: The paper successfully identified the best picker-to-goods technology, however it is important to mention that the adoption of such order-picking technology implies certain managerial implications that include training programs for employees to ensure they are proficient in using such technologies, upfront costs for purchasing and implementing the order picking system, and adjustments to existing workflows.
     
    Keywords: order-picking; pick-by-RF scanning; pick-to-light; Pick-by-vision; design of experiments;laboratory testing
     
    Post date: Friday, February 2, 2024 - 08:13


Τhe Design, Operations, and Production Systems Lab is “knowledge Partner” of the Green Freight Europe Initiative.

User login

Lab Reports

© DeOPSys Lab 2007-2008 | Created by Vanessa Pappa | Powered by Drupal | Theme Busy

Built by undpaul Drupal development