Currently, road transport constitutes a considerable proportion of global fossil fuel consumption, as well as CO₂ and pollutant emissions. To mitigate transportation energy consumption, two primary approaches have emerged: the large-scale adoption of Hybrid Electric Vehicles (HEVs) and Plug-In Electric Vehicles (PHEVs), as well as the implementation of eco-driving strategies, which present an immediate and low-cost solution. In this context, this paper provides a comprehensive review of these two technologies and their integration for connected HEV/PHEVs. We summarize the framework of recent approaches to incorporate fusion road information in single-vehicle and multi-vehicle scenarios, respectively, wherein we compare their advantages, their disadvantages, and their effectiveness in reducing energy consumption. Additionally, we reflect on the future development directions of cooperative optimization in EMS and eco-driving strategies from various perspectives. This comprehensive review underscores the importance and potential impact of these approaches in addressing environmental challenges in transportation systems, thereby offering useful insights for new researchers and practitioners in this area. Full article

Despite rapid advances in vehicle intelligence and connectivity, there is still a significant period in mixed traffic where connected, automated vehicles and human-driven vehicles coexist. The behavioral uncertainty of human-driven vehicles makes decision-making a challenging task in an unsignalized intersection scenario. In this paper, a decentralized multi-agent proximal policy optimization (MAPPO) based on an attention representations algorithm (Attn-MAPPO) was developed to make joint decisions at an intersection to avoid collisions and cross the intersection effectively. To implement this framework, by exploiting the shared information, the system was modeled as a model-free, fully cooperative, multi-agent system. The vehicle employed an attention module to extract the most valuable information from its neighbors. Based on the observation and traffic rules, a joint policy was identified to work more cooperatively based on the trajectory prediction of all the vehicles. To facilitate the collaboration between the vehicles, a weighted reward assignment scheme was proposed to focus more on the vehicles approaching intersections. The results presented the advantages of the Attn-MAPPO framework and validated the effectiveness of the designed reward function. Ultimately, the comparative experiments were conducted to demonstrate that the proposed approach was more adaptive and generalized than the heuristic rule-based model, which revealed its great potential for reinforcement learning in the decision-making of autonomous driving. Full article

The development of computer hardware and communications has brought with it many exciting applications in the Internet of Things. More and more Single Board Computers (SBC) with high performance and low power consumption are used to infer deep learning models at the edge of the network. In this article, we investigate a cooperative task execution system in an edge computing architecture. In our topology, the edge server offloads different workloads to end devices, which collaboratively execute object detection on the transmitted sets of images. Our proposed system attempts to provide optimization in terms of execution accuracy and execution time for inferencing deep learning models. Furthermore, we focus on implementing new policies to optimize the E2E execution time and the execution accuracy of the system by highlighting the key role of effective image compression and the batch sizes (splitting decisions) received by the end devices from a server at the network edge. In our testbed, we used the You Only Look Once (YOLO) version 5, which is one of the most popular object detectors. In our heterogeneous testbed, an edge server and three different end devices were used with different characteristics like CPU/TPU, different sizes of RAM, and different neural network input sizes to identify sharp trade-offs. Firstly, we implemented the YOLOv5 on our end devices to evaluate the performance of the model using metrics like Precision, Recall, and mAP on the COCO dataset. Finally, we explore optimal trade-offs for different task-splitting strategies and compression decisions to optimize total performance. We demonstrate that offloading workloads on multiple end devices based on different splitting decisions and compression values improves the system’s performance to respond in real-time conditions without needing a server or cloud resources. Full article

The Athenet network is the network of the Seismological Laboratory of the National and Kapodistrian University of Athens. We present the geophysical investigation that has been carried out at six seismological stations of the Athenet network for their site characterization. More specifically, at the location of each seismological station, four geophysical methods have been carried out: Seismic Refraction Tomography (SRT), Multichannel Analysis of Surface Waves (MASW), the Horizontal to Vertical Spectral Ratio (HVSR) technique, and Electrical Resistivity Tomography (ERT). The applied geophysical survey provided important information regarding the site characterization at the selected seismological stations, including key parameters such as the fundamental frequency f_o, the shear-wave velocity V_S, the average shear-wave velocity for the upper 30 m depth (V_S30), the seismic bedrock depth, the soil type, and the subsurface geology. Moreover, selected elastic moduli (Poisson’s ratio, shear, bulk, and Young moduli) have been calculated. The site characterization information contributes to the determination of the amplification factors for each site that can lead to more accurate calculation of Peak Ground Acceleration (PGA) or Peak Ground Velocity (PGV) and, therefore, trustworthy Probabilistic and Stochastic Seismic Hazard Assessments. The derived fundamental frequency for the seismological stations of VILL, LOUT, THAL, and EPID have been determined to be equal to 10.4, 2.7, 1.4, and 7.1 Hz and their amplification factors to be 1.9, 3.1, 1.7, and 2.6, respectively. For stations MDRA and ATAL, these parameters could not be determined. Full article

This research examines the opportunities provided by advances in digital manufacturing technologies for the provision of products designed to meet the needs of an individual consumer. The ability to co-create products with customers could enable mass personalisation to become a popular and fast-growing mode of production. Additive manufacturing, in both 3D and 4D printing forms, opens up new opportunities for circular economy-compliant production of such highly personalised products. Industry 4.0 has been seen by many as an agenda for the utilisation of interconnected digital technologies in industry, with a particular focus on manufacturing. Industry 5.0 seeks to address challenges that have grown in importance since the inception of Industry 4.0, such as the efficient inclusion of human worker skills in tandem with automation solutions, to address highly complex manufacturing scenarios while mitigating many of the environmental issues inherent with current manufacturing practices, while using circular economy principles. In examining the production of smart fabrics, this paper puts forward a framework for circular production of additively manufactured personalised products, co-designed with inputs from consumers. Full article

Due to the simplified assumptions or unascertained equipment parameters, traditional mechanism models of boiler system in coal-fired power plant usually have predictive errors that cannot be ignored. In order to further improve the predictive accuracy of the model, this paper proposes a novel recurrent neural network-based hybrid modeling method for digital twin of boiler system. First, the mechanism model of boiler system is described through recurrent neural network (RNN) to facilitate training and updating parameters, while the interpretability of the model does not degenerate. Second, for the time-varying parameters in the mechanism model, the functional relationship between them and the state variables is constructed by neurons to improve the predictive accuracy. Third, the long short-term memory (LSTM) neural network model is established to describe the unascertained dynamic characteristics to compensate the predictive residual of the mechanism model. Fourth, the update architecture and training algorithm applicable to the hybrid model are established to realize the iterative optimization of model parameters. Finally, experimental results show that the hybrid modeling method proposed in this paper can improve the predictive performance of traditional models effectively. Full article

License plate identification remains a crucial problem in computer vision, particularly in complex environments where license plates may be confused with road signs, billboards, and other objects. This paper proposes a solution by modifying the standard car–license plate–letter detection approach into a preliminary license plate detection–precise license plate detection of the four corners where the numbers are located–license plate correction–letter identification. This way, the first algorithm identifies all potential license plates and passes them as input parameters to the next algorithm for more precise detection. The main difference between this approach and other algorithms is that it uses a relatively small image compared to the whole vehicle. Thus, a small but robust network is used to find the four corners and perform a perspective transformation. This simplifies the letter recognition task for the next algorithm, as no additional transformations are required. This solution could be useful for research focusing on this specific task. It allows to apply another compact but robust neural network, increasing the overall speed of the system. Publicly available datasets were used for training and validation. The CenterNet object detection algorithm was used as a basis with a modified Hourglass-type network. The size of the network was decreased by 40% and the average accuracy was 96.19%. Speed significantly increased, reaching 2.71 ms and 405 FPS on average. Full article

Hemp inflorescences from byproducts have been proposed as an addition to gluten-free rice bread. The scope of the research was to bake a control loaf of bread as well as bread loaves containing 1%, 2%, 3%, 4%, and 5% dried and crushed hemp inflorescence (HI). The loaves of bread were evaluated in terms of their physical and sensory properties, polyphenol and flavonoid contents, and DPPH and FRAP antioxidant activities. The study’s findings revealed that the addition of HI influenced changes in the physical properties of the bread loaves, such as increased specific volume, decreased bread hardness, increased elasticity, and chewiness of the breadcrumb, especially when the additive concentrations were greater than 3%. The addition of HI significantly increased the total amount of polyphenols, flavonoids, and antioxidant activity in the bread. The sensory evaluation revealed that gluten-free bread can be produced with a maximum of 2% HI without affecting its taste and aroma. Full article

The effect of the extraction conditions on the DPPH radical scavenging activity and isolation of bioactive compounds from the maca (Lepidium meyenii) root was investigated. Different extraction techniques (maceration, maceration with shaking, ultrasound-assisted extraction, and reflux extraction) were compared. Moreover, the effect of the extraction time and two various solvents (water and ethanol) was studied. The antioxidant activity of extracts was determined by the spectrophotometric method with the DPPH radical, while total phenolic content (TPC) was analyzed by the Folin–Ciocalteu method. Using gas chromatography with a mass selective detector (GC-MS), some characteristics of maca bioactive compounds were identified in the extracts: benzylalkamides (macamides), sterols, nitriles, fatty acids, and their derivatives. The influence of various factors on the extraction process of health-promoting antioxidant compounds from maca root was discussed. It was found that water was a more effective solvent than ethanol for obtaining extracts characterized by high radical scavenging activity and phenolics content. Nevertheless, some ethanol-extractable valuable compounds specific for maca, e.g., macamides or fatty acids derivatives, were not present in water extracts. In developing nutritional and therapeutic formulations based on maca extracts, it is important to take into account that the bioactivity of maca extracts varies depending on the solvent used. Full article

Radiochromic films have widely been used for quality assurance (QA) in radiation therapy and have many advantageous features such as self-developing visible coloration, wide dose range and easiness to handle. These features have a good potential for application to other fields associated with high-dose radiation exposure, e.g., verification of various radiation sources used in industry and research, occupational radiation monitoring as a preparedness for radiological emergencies. One of the issues in such applications is the elaborate process of acquisition and analyses of the color image using a flatbed scanner and image processing software, which is desirably to be improved for achieving a practical on-site dosimetry. In the present study, a simple method for reading a radiochromic film by using a portable colorimeter (nix pro 2; abbreviated here “Nix”) was proposed and its feasibility for diagnostic X-rays was tested with a commercial radiochromic film (Gafchromic EBT-XD). It was found that the color intensities of red and green components of EBT-XD were successfully measured by Nix over a wide dose range up to 40 Gy. Though some angle dependence was observed, this error could be well averted by careful attention to the film direction in a reading process. According to these findings, it is expected that the proposed on-site dosimetry method of combining a radiochromic film and a portable colorimeter will be practically utilized in various occasions. Full article

Both constructivist learning and situation-cognitive learning believe that learning outcomes are significantly affected by the context or learning environments. However, since 2019, the world has been ravaged by COVID-19. Under the threat of the virus, many offline activities, such as some practical or engineering courses, have been subjected to certain restrictions. Virtual Reality (VR) is an emerging, promising, and rapidly developing technology that enables users to obtain a near-real immersion experience by combining technologies such as computer science, communication, vision, etc. In the context of COVID-19, the advantages of VR immersive experiences are highlighted. By constructing a virtual learning environment, VR technology can greatly compensate for the shortage of traditional teaching conditions and help learners to carry out cognitive learning better. However, currently, VR-enhanced cognitive learning is still in its infancy, along with numerous problems and limitations. Therefore, this paper first conducted an in-depth study of some related concepts, such as constructivist learning and situated cognition learning. Then it proposes a general VR-enhanced cognitive learning framework and designs the general steps for constructing learning situations with VR technology. Based on the proposed model and framework, it developed a campus knowledge-learning APP using VR tools. Through a case study, it verified the validity and performance of the model and strategies. Questionnaire survey and experimental results show that the new model achieves a good learning effect and improves the efficiency of learning by at least 20% compared to the traditional learning methods. Full article

Control mechanisms for biological treatment of wastewater treatment plants are mostly based on PIDS. However, their performance is far from optimal due to the high non-linearity of the biological and changing processes involved. Therefore, more advanced control techniques are proposed in the literature (e.g., using artificial intelligence techniques). However, these new control techniques have not been compared to the traditional approaches that are actually being used in real plants. To this end, in this paper, we present a comparison of the PID control configurations currently applied to control the dissolved oxygen concentration (in the active sludge process) against a reinforcement learning agent. Our results show that it is possible to have a very competitive operating cost budget when these innovative techniques are applied. Full article

The detection of leakages in Water Distribution Networks (WDNs) is usually challenging and identifying their locations may take a long time. Current water leak detection methods such as model-based and measurement-based approaches face significant limitations that impact response times, resource requirements, accuracy, and location identification. This paper presents a method for determining locations in the WDNs that are vulnerable to leakage by combining six leakage-conditioning factors using logistic regression and vulnerability analysis. The proposed model considered three fixed physical factors (pipe length per junction, number of fittings per length, and pipe friction factor) and three varying operational aspects (drop in pressure, decrease in flow, and variations in chlorine levels). The model performance was validated using 13 district metered areas (DMAs) of the Sharjah Electricity and Water Authority (SEWA) WDN using ArcGIS. Each of the six conditioning factors was assigned a weight that reflects its contribution to leakage in the WDNs based on the Analytic Hierarchy Process (AHP) method. The highest weight was set to 0.25 for both pressure and flow, while 0.2 and 0.14 were set for the chlorine and number of fittings per length, respectively. The minimum weight was set to 0.08 for both length per junction and friction factor. When the model runs, it produces vulnerability to leakage maps, which indicate the DMAs’ vulnerability classes ranging from very high to very low. Real-world data and different scenarios were used to validate the method, and the areas vulnerable to leakage were successfully identified based on fixed physical and varying operational factors. This vulnerability map will provide a comprehensive understanding of the risks facing a system and help stakeholders develop and implement strategies to mitigate the leakage. Therefore, water utility companies can employ this method for corrective maintenance activities and daily operations. The proposed approach can offer a valuable tool for reducing water production costs and increasing the efficiency of WDN. Full article

Iodine deficiency impacts on the development of thyroid disease. Vegetables and fruits usually have a low iodine content; hence, it makes sense to increase their iodine content. Potato is consumed daily by millions of consumers and would, therefore, be a good target for biofortification with iodine programs. The aim of this study was to determine the effects of biofortification via the application of soil solutions of two iodoquinolines [8-hydroxy-7-iodo-5-quinolinic acid (8-OH-7-I-5QSA) and 5-chloro-7-iodo-8-quinoline (5-Cl-7-I-8-Q)] and KIO₃ (as an iodine positive control) on the iodine content and basic chemical composition, macro and micronutrient content, nitrogen compounds, vitamin C, and antioxidant potential of potato tubers Solanum tuberosum L. The biofortification process had no significant effect on the tuber weight in yield. The application of I in forms of KIO₃, 8-OH-7-I-5QSA, 5-Cl-7-I-8-Q resulted in an increase in the I content of tubers (1400.15; 693.65; 502.79, respectively, compared with control, 24.96 µg·kg⁻¹ d.w.). This also resulted in a decrease in elements that are harmful to consumers, such as: Al, Ni, Cr, Ag, Pb and Tl. The enrichment of tubers with 8-OH-7-I-5QSA and 5-Cl-7-I-8-Q resulted in a significant reduction in the content of ammonium ions (from 19.16 to 14.96; 13.52 mg∙kg⁻¹ f.w.) and chlorides (from 423.59 to 264.92; 265.31 mg∙kg⁻¹ f.w.). Biofortification with 8-OH-7-I-5QSA improved the polyphenolic profile of the potato tuber from 197.31 to 233.33 mg GAE·100 g⁻¹ f.w. A significant reduction in the carotenoid content of tubers after the enrichment of the plant with iodine in KIO₃, 8-OH-7-I-5QSA and 5-Cl-7-I-8-Q (from 3.46 to 2.96, 2.45, and 1.47 mg∙100 g⁻¹ d.w., respectively) was observed. It can be postulated that the production of potatoes enriched with iodoquinolines and/or KIO₃ is worthwhile, as it can provide a good source of I in the diet and simultaneously reduce the risk of developing deficiencies. Full article

Through the construction of parametric simulation models in which possible storage space distributions and positioning logics are also considered as variables, it is possible to build scenarios that allow analyzing the changing reality of storage needs in order to minimize material movements in each case, optimize internal transportation, and increase the efficiency of production processes. This article shows a particular analysis of a restricted storage space in height, typical to when it comes to logistics associated with raw material in a “big bag” format made of recycled and easily deteriorated material. In conjunction, a location management solution based on passive RFID (radio-frequency identification) tags has been chosen. The process is carried out through simulations with object-oriented discrete event software, where the optimization of the internal transport associated with the layout is carried out considering network theory to define the shortest path between warehouse nodes. The combination of both approaches allows, on the one hand, the evaluation of alternatives in terms of distribution and positioning logics, while the implemented system enables the possibility of making agile changes in the physical configuration of this type of storage space. Full article