Search

In the dynamic landscape of contemporary education, the evolution of teaching strategies such as blended learning and flipped classrooms has highlighted the need for efficient and effective generation of multiple-choice questions (MCQs). To address this, we introduce MCQGen, a novel generative artificial intelligence framework designed for the automated creation of MCQs. MCQGen uniquely integrates a large language model (LLM) with retrieval-augmented generation and advanced prompt engineering techniques, drawing from an extensive external knowledge base. This integration significantly enhances the ability of the LLM to produce educationally relevant questions that align with both the goals of educators and the diverse learning needs of students. The framework employs innovative prompt engineering, combining chain-of-thought and self-refine prompting techniques, to enhance the performance of the LLM. This process leads to the generation of questions that are not only contextually relevant and challenging but also reflective of common student misconceptions, contributing effectively to personalized learning experiences and enhancing student engagement and understanding. Our extensive evaluations showcase the effectiveness of MCQGen in producing high-quality MCQs for various educational needs and learning styles. The framework demonstrates its potential to significantly reduce the time and expertise required for MCQ creation, marking its practical utility in modern education. In essence, MCQGen offers an innovative and robust solution for the automated generation of MCQs, enhancing personalized learning in the digital era.

In the era of artificial intelligence and big data, the demand for data processing has surged, leading to larger datasets and computation capability. Distributed machine learning (DML) has been introduced to address this challenge by distributing tasks among multiple workers, reducing the resources required for each worker. However, in distributed systems, the presence of slow machines, commonly known as stragglers, or failed links can lead to prolonged runtimes and diminished performance. This survey explores the application of coding techniques in DML and coded edge computing in the distributed system to enhance system speed, robustness, privacy, and more. Notably, the study delves into coding in Federated Learning (FL), a specialized distributed learning system. Coding involves introducing redundancy into the system and identifying multicast opportunities. There exists a tradeoff between computation and communication costs. The survey establishes that coding is a promising approach for building robust and secure distributed systems with low latency.

Federated learning allows multiple parties to train models while jointly protecting user privacy. However, traditional federated learning requires each client to have the same model structure to fuse the global model. In real-world scenarios, each client may need to develop personalized models based on its environment, making it difficult to perform federated learning in a heterogeneous model environment. Some knowledge distillation methods address the problem of heterogeneous model fusion to some extent. However, these methods assume that each client is trustworthy. Some clients may produce malicious or low-quality knowledge, making it difficult to aggregate trustworthy knowledge in a heterogeneous environment. To address these challenges, we propose a trustworthy heterogeneous federated learning framework (FedTKD) to achieve client identification and trustworthy knowledge fusion. Firstly, we propose a malicious client identification method based on client logit features, which can exclude malicious information in fusing global logit. Then, we propose a selectivity knowledge fusion method to achieve high-quality global logit computation. Additionally, we propose an adaptive knowledge distillation method to improve the accuracy of knowledge transfer from the server side to the client side. Finally, we design different attack and data distribution scenarios to validate our method. The experiment shows that our method outperforms the baseline methods, showing stable performance in all attack scenarios and achieving an accuracy improvement of 2% to 3% in different data distributions.

Abstract Background Intussusception is the telescoping of a proximal segment of the bowel into a distal segment. It can be idiopathic or pathological. Children commonly present with colicky abdominal pain, vomiting, a palpable abdominal mass, and bloody stools. Our case describes the unusual presentation of bowel sphacelation with auto-anastomosis in a child with intussusception and its clinical progression. Case presentation A 3-year-old boy with underlying stage IV rhabdomyosarcoma of the left orbit presented with high-grade fever and diarrhea for 1 day. He was treated for neutropenic sepsis in view of low absolute neutrophil count and recent history of chemotherapy. During his admission, he developed abdominal distension, high bilious aspirates, and diarrhea with bloody stools. Abdominal X-ray showed dilated bowel loops. Impression was septic ileus with coagulopathy. He was treated with blood transfusion and bowel rest. On the 6th day of illness, he passed out a tubular structure per rectum which was confirmed to be a segment of gangrenous bowel by histopathological examination. A diagnosis of intussusception with bowel sphacelation was made. He was treated conservatively, and his obstruction was resolved. He was discharged well with no abdominal symptoms during follow-up. Conclusion Intussusception is a common cause of small bowel obstruction in children. A high index of suspicion of intussusception should be maintained in children presenting with vomiting and bloody stools complemented by ultrasound to avoid missing this diagnosis. Sphacelation of the intussuscepted bowel with auto-anastomosis is a rare presentation of intussusception with a favorable outcome.

In recent years, AI technologies have been developed to promote students' self-regulated learning (SRL) and proactive learning in digital learning environments. This paper discusses a comparative study between generative AI-based (SRLbot) and rule-based AI chatbots (Nemobot) in a 3-week science learning experience with 74 Secondary 4 students in Hong Kong. The experimental group used SRLbot to maintain a regular study habit and facilitate their SRL, while the control group utilized rule-based AI chatbots. Results showed that SRLbot effectively enhanced students' science knowledge, behavioural engagement and motivation. Quantile regression analysis indicated that the number of interactions significantly predicted variations in SRL. Students appreciated the personalized recommendations and flexibility of SRLbot, which adjusted responses based on their specific learning and SRL scenarios. The ChatGPT-enhanced instructional design reduced learning anxiety and promoted learning performance, motivation and sustained learning habits. Students' feedback on learning challenges, psychological support and self-regulation behaviours provided insights into their progress and experience with this technology. SRLbot's adaptability and personalized approach distinguished it from rule-based chatbots. The findings offer valuable evidence for AI developers and educators to consider generative AI settings and chatbot design, facilitating greater success in online science learning.

The area of a Microgrid (μG) is a very fast-growing and promising system for overcoming power barriers. This paper examines the impacts of a microgrid system considering Electric Vehicle Grid Integration (EVGI) based on stochastic metaheuristic methods. One of the biggest challenges to slowing down global climate change is the transition to sustainable mobility. Renewable Energy Sources (RESs) integrated with Evs are considered a solution for the power and environmental issues needed to achieve Sustainable Development Goal Seven (SDG7) and Climate Action Goal 13 (CAG13). The aforementioned goals can be achieved by coupling Evs with the utility grid and other RESs using Vehicle-to-Grid (V2G) technology to form a hybrid system. Overloading is a challenge due to the unknown number of loads (unknown number of Evs). Thus, this study helps to establish the system impact of the uncertainties (arrival and departure Evs) by proposing Stochastic Monte Carlo Method (SMCM) to be addressed. The main objective of this research is to size the system configurations using a metaheuristic algorithm and analyze the impact of an uncertain number of Evs on the distribution of residential power in Tripoli-Libya to gain a cost-effective, reliable, and renewable system. The Improved Antlion Optimization (IALO) algorithm is an optimization technique used for determining the optimal number of configurations of the hybrid system considering multiple sources, while the Rule-Based Energy Management Strategy (RB-EMS) controlling algorithm is used to control the flow of power in the electric power system. The sensitivity analysis of the effect parameters has been taken into account to assess the expected impact in the future. The results obtained from the sizing, controlling, and sensitivity analyses are discussed.

Nanodielectrics have been regarded as a class of material system that can provide significantly improved chemical, mechanical and dielectric properties over conventional microcomposites. This is due to the presence of a high volume fraction of the interphase between nanoparticles and polymers. However, precise effects of nanodielectrics are not well understood, leading to difficulties in interpreting the dielectric behaviours of nanodielectrics. In the current work, effects of nanoparticle distributions, interparticle distances, nanoparticle sizes, interphase permittivities and interphase thicknesses on the possible electric field variations within a nanodielectric model have been simulated using Finite Element Method Magnetics (FEMM) 4.2. The results demonstrate that different nanoparticle and interphase configurations lead to different effects on the electric field intensity within the nanodielectric model. Mechanisms leading to changes in dielectric properties based on the observed electric field variations are discussed.

This paper proposes an improved one-power-point (OPP) maximum power point tracking (MPPT) algorithm for wind energy conversion system (WECS) to overcome the problems of the conventional OPP MPPT algorithm, namely, the difficulty in getting a precise value of the optimum coefficient, requiring pre-knowledge of system parameters, and non-uniqueness of the optimum curve. The solution is based on combining the particle swarm optimization (PSO) and optimum-relation-based (ORB) MPPT algorithms. The PSO MPPT algorithm is used to search for the optimum coefficient. Once the optimum coefficient is obtained, the proposed algorithm switches to the ORB MPPT mode of operation. The proposed algorithm neither requires knowledge of system parameters nor mechanical sensors. In addition, it improves the efficiency of the WECS. The proposed algorithm is studied for two different wind speed profiles, and its tracking performance is compared with conventional optimum torque control (OTC) and conventional ORB MPPT algorithms under identical conditions. The improved performance of the algorithm in terms of tracking efficiency is validated through simulation using MATLAB/Simulink. The simulation results confirm that the proposed algorithm has a better performance in terms of tracking efficiency and energy extracted. The tracking efficiency of the PSO-ORB MPPT algorithm could reach up to 99.4% with 1.9% more harvested electrical energy than the conventional OTC and ORB MPPT algorithms. Experiments have been carried out to demonstrate the validity of the proposed MPPT algorithm. The experimental results compare well with system simulation results, and the proposed algorithm performs well, as expected.