The widespread adoption of technology-enhanced learning in various knowledge disciplines has pushed forward the development of information technology-assisted media for language learning and teaching. However, most of the existing electronic-learning (e-learning) solutions have underexplored and under-addressed given specific characteristics of grammar learning, which is one of the most demanding areas of language education. The lack of pedagogically-informed instructional design to enhance learning performance on the current system can result in low motivation and engagement due to imbalance and excessive increase of the cognitive load. This paper attempts to address these deficiencies posed by the existing systems by proposing smart communication networks that are driven by the student learning experience to manage cognitive load in the context of grammar learning. The e-grammar learning networks serve as a collaborative learning platform that combines a pedagogically-informed instructional model named Attention, Relevance, Confidence and Satisfaction (ARCS) and cyber interaction among teaching/learning agents. From the technological perspective, our numerical simulations demonstrate the desirable performance indicators of the proposed networks to facilitate information exchange and learning. From the education perspective, our empirical studies shows that the overall smart network-enabled egrammar learning system has desirable characteristics to motivate learners (m = 3.78) and manage their overall cognitive load (m=1.73), which suggest promising capability of the proposed system.

Motivated by enormous highway-lighting energy consumption, smart lighting development is crucial to better manage available resources. While existing literature focused on ensuring cost-effective lighting, an equally important requirement, namely the visual comfort of motorists, is almost disregarded. This article proposes a novel Internet of Things-enabled system that can be intelligently controlled according to the traffic demand. Cooperative relay-network architecture is the central element that leverages upon placement of cyber-enabled lampposts to allow for sensing-exchanging highway traffic information. Data accumulation is exploited to automate adaptive switching on/off the lighting and provide backtracking detection of faulty lampposts. From the service provider’s perspective, we envision to deploy low-cost highly durable sensing and network components to significantly cut down the operating cost. From the road user’s perspective, the relay-network is envisaged to provide seamless driving experience where sufficient lighting is always perceived along the road. A critical analysis quantitatively evaluates the seamless driving experience considering car arrival rate, outage probability, and device malfunction probability. A road occupancy-based cost estimation analysis demonstrates the effective cost reduction of the proposal compared to existing systems. Furthermore, the performance of chosen communication modules under different setups is assessed through simulation, suggesting appropriate protocol for different highway traffic conditions.

Waste management has been identified as a critical problem underpinning the vision of sustainable cities. Despite existing efforts to tackle this challenge, traditional approaches still undermine resource allocation and utilization for the task. Most methods have overlooked the fairness problem found in the garbage-collection transportation units, producing noticeable varying active time differences among the participating units. The integration of Internet of Things (IoT) to waste management has recently been an emerging trend, which offers coordinated garbage collection benefiting from IoT networks. This work investigates utilization of LoRa technology for such a purpose and argues the importance of fairness perspective in actuating the truck agents for collecting the wastes in a given region. Through enabling reliable waste data exchange by a proper design and specification of the LoRa network, we can then cast the collection issue as a capacitated vehicle routing problem with a well-formulated objective function. To improve the fairness in the waste management, we propose an objective function that incorporates both the total distance covered by all the trucks and overall distance dispersion from individual trucks. Numerical simulation demonstrates the superiority and consistency of the fairness-based optimum solution in both minimizing the total distance and achieving the fairness.

Wall crack detection is one of the primary tasks in determining the structural integrity of a building for both restorative and preventive attempts. Machine learning techniques, such as deep learning (DL) with computer vision capabilities, have gradually become more prevalent as they can provide expert assessments with an acceptable performance when the crack detection involves a considerable number of structures. Despite such a prospective application, classification on different types of wall cracks is relatively less common, possibly due to the absence of the professional-standard-to-dataset translation. In this work, we utilised a complete pipeline, starting from novel dataset construction, ground truth formulation based on civil engineering standards, and training and testing steps. Our work focused on multi-class classification with regard to the binary classification (i.e., determining only two categories) used in previous studies. We implemented transfer learning based on VGG16 and RestNET50 for feature extraction, combined them with an ANN and kNN for the classifier, and compared their prediction performances. Our results indicate that the developed models can distinguish images that contain wall cracks into three categories of features based on the degree of damage: light, medium, and severe. Furthermore, since greyscale images offer more precise readings and predictions, the use of augmentation in dataset generation is critical. Although ResNet50 is the most stable network in terms of accuracy, it performs better when paired with kNN.

A figure of 33,000 search and rescue (SAR) incidents were responded to by the UK’s HM Coastguard in 2020, and over 1322 rescue missions were conducted by SAR helicopters during that year. Combined with Unmanned Aerial Vehicles (UAVs), artificial intelligence, and computer vision, SAR operations can be revolutionized through enabling rescuers to expand ground coverage with improved detection accuracy whilst reducing costs and personal injury risks. However, detecting small objects is one of the significant challenges associated with using computer vision on UAVs. Several approaches have been proposed for improving small object detection, including data augmentation techniques like replication and variation of image sizes, but their suitability for SAR application characteristics remains questionable. To address these issues, this paper evaluates four float detection algorithms against the baseline and augmented datasets to improve float detection for maritime SAR. Results demonstrated that YOLOv8 and YOLOv5 outperformed the others in which F1 scores ranged from 82.9 to 95.3%, with an enhancement range of 0.1–29.2%. These models were both of low complexity and capable of real-time response.

This paper discusses an optimized method of terminal nodes integration that belongs to two merged and reorganized companies. The optimization process, prioritized under the process of merging and reorganization, is designed in accordance with the rules of economics and charasteristics of express delivery networks. Subsequently, a mathematical model of optimization of terminal networks integration is formulated and tested. According to our experiment results, the resulting cost can be efficiently obtained by choosing the smallest cost from the process outcome.