Recent advancements in Natural Language Processing (NLP) technologies have been driven at an unprecedented pace by the development of Large Language Models (LLMs). However, challenges remain, such as generating responses that are misaligned with the intent of the question or producing incorrect answers. This paper analyzes various Prompt Engineering techniques for large-scale language models and identifies methods that can optimize response performance across different datasets without the need for extensive retraining or fine-tuning. In particular, we examine prominent Prompt Engineering techniques including In-Context Learning (ICL), Chain of Thought (CoT), Retrieval-Augmented Generation (RAG), Step-by-Step Reasoning (SSR), and Tree of Thought (ToT), and we apply these techniques to leading LLMs such as Gemma2, LlaMA3, and Mistral. The performance of these models was evaluated using the AI2 Reasoning Challenge (ARC), HellaSwag, Massive Multitask Language Understanding (MMLU), TruthfulQA, Winogrande, and Grade School Math (GSM8k) datasets across metrics such as BLEU, ROUGE, METEOR, BLEURT, and BERTScore. The experimental results indicate that the most suitable Prompt Engineering technique can vary depending on the characteristics of each dataset. Specifically, for datasets emphasizing mathematical and logical reasoning, Prompt Engineering strategies centered around CoT, SSR, and ToT were found to be advantageous. For datasets focusing on natural language understanding, ICL-centric strategies were more effective, while RAG-based strategies were beneficial for datasets where factual accuracy is crucial. However, it was also observed that the optimal combination of Prompt Engineering techniques could differ depending on the specific LLM, indicating that fine-tuning the Prompt Engineering approach to the model and dataset is essential for achieving the best performance. The findings indicate that as LLMs become more advanced, their reliance on Prompt Engineering (PE) techniques diminishes, yet the magnitude of their performance improvement when PE strategies are applied increases. Furthermore, these advanced models tend to depend less on ICL techniques while exhibiting a greater reliance on RAG strategies. It is also evident that implementing RAG with PE-based preprocessing yields superior performance enhancements compared to the mere application of RAG on raw data.

Due to the recent increasing utilization of deep learning models on edge devices, the industry demand for Deep Learning Model Optimization (DLMO) is also increasing. This paper derives a usage strategy of DLMO based on the performance evaluation through light convolution, quantization, pruning techniques and knowledge distillation, known to be excellent in reducing memory size and operation delay with a minimal accuracy drop. Through experiments regarding image classification, we derive possible and optimal strategies to apply deep learning into Internet of Things (IoT) or tiny embedded devices. In particular, strategies for DLMO technology most suitable for each on-device Artificial Intelligence (AI) service are proposed in terms of performance factors. In this paper, we suggest a possible solution of the most rational algorithm under very limited resource environments by utilizing mature deep learning methodologies.

This paper explored techniques for diagnosing breast cancer using deep learning based medical image recognition. X-ray (Mammography) images, ultrasound images, and histopathology images are used to improve the accuracy of the process by diagnosing breast cancer classification and by inferring their affected location. For this goal, the image recognition application strategies for the maximal diagnosis accuracy in each medical image data are investigated in terms of various image classification (VGGNet19, ResNet50, DenseNet121, EfficietNet v2), image segmentation (UNet, ResUNet++, DeepLab v3), and related loss functions (binary cross entropy, dice Loss, Tversky loss), and data augmentation. As a result of evaluations through the presented methods, when using filter-based data augmentation, ResNet50 showed the best performance in image classification, and UNet showed the best performance in both X-ray image and ultrasound image as image segmentation. When applying the proposed image recognition strategies for the maximal diagnosis accuracy in each medical image data, the accuracy can be improved by 33.3% in image segmentation in X-ray images, 29.9% in image segmentation in ultrasound images, and 22.8% in image classification in histopathology images.

This study investigates prompt engineering (PE) strategies to mitigate hallucination, a key limitation of multimodal large language models (MLLMs). To address this issue, we explore five prominent multimodal PE techniques: in-context learning (ICL), chain of thought (CoT), step-by-step reasoning (SSR), tree of thought (ToT), and retrieval-augmented generation (RAG). These techniques are systematically applied across multiple datasets with distinct domains and characteristics. Based on the empirical findings, we propose the greedy prompt engineering strategy (Greedy PES), a methodology for optimizing PE application across different datasets and MLLM models. To evaluate user satisfaction with MLLM-generated responses, we adopt a comprehensive set of evaluation metrics, including BLEU, ROUGE, METEOR, S-BERT, MoverScore, and CIDEr. A weighted aggregate evaluation score is introduced to provide a holistic assessment of model performance under varying conditions. Experimental results demonstrate that the optimal prompt engineering strategy varies significantly depending on both dataset properties and the MLLM model used. Specifically, datasets categorized as general benefit the most from ICL, ToT, and RAG, whereas mathematical datasets perform optimally with ICL, SSR, and ToT. In scientific reasoning tasks, RAG and SSR emerge as the most effective strategies. Applying Greedy PES leads to a substantial improvement in performance across different multimodal tasks, achieving an average evaluation score enhancement of 184.3% for general image captioning, 90.3% for mathematical visual question answering (VQA), and 49.1% for science visual question answering (VQA) compared to conventional approaches. These findings highlight the effectiveness of structured PE strategies in optimizing MLLM performance and provide a robust framework for PE-driven model enhancement across diverse multimodal applications.

To enable autonomous driving in real-world environments that involve a diverse range of geographic variations and complex traffic regulations, it is essential to investigate Deep Reinforcement Learning (DRL) algorithms capable of policy learning in high-dimensional environments characterized by intricate state–action interactions. In particular, closed-loop experiments, which involve continuous interaction between an agent and their driving environment, serve as a critical framework for improving the practical applicability of DRL algorithms in autonomous driving systems. This study empirically analyzes the capabilities of several representative DRL algorithms—namely DDPG, SAC, TD3, PPO, TQC, and CrossQ—in handling various urban driving scenarios using the CARLA simulator within a closed-loop framework. To evaluate the adaptability of each algorithm to geographical variability and complex traffic laws, scenario-specific reward and penalty functions were carefully designed and incorporated. For a comprehensive performance assessment of the DRL algorithms, we defined several driving performance metrics, including Route Completion, Centerline Deviation Mean, Episode Reward Mean, and Success Rate, which collectively reflect the quality of the driving in terms of its completeness, stability, efficiency, and comfort. Experimental results demonstrate that TQC and SAC, both of which adopt off-policy learning and stochastic policies, achieve superior sample efficiency and learning performances. Notably, the presence of geographically variant features—such as traffic lights, intersections, and roundabouts—and their associated traffic rules within a given town pose significant challenges to driving performance, particularly in terms of Route Completion, Success Rate, and lane-keeping stability. In these challenging scenarios, the TQC algorithm achieved a Route Completion rate of 0.91, substantially outperforming the 0.23 rate observed with DDPG. This performance gap highlights the advantage of approaches like TQC and SAC, which address Q-value overestimation through statistical methods, in improving the robustness and effectiveness of autonomous driving in diverse urban environments.

This paper proposes a novel algorithm, Terrain Analysis–Rapidly exploring Random Tree* (TA-RRT*), which improves the performance of path planning using adaptive sampling and step size based on terrain analysis. While existing RRT*-based algorithms perform node sampling and tree expansion in various ways to optimize path planning, they may still generate inefficient paths in complex terrain environments. In this paper, TA-RRT* analyzes the complexity of the terrain to generate a probability density function, which is then used to guide adaptive sampling and tree expansion during the path planning process. In addition, we reduce the length of generated paths using an adaptive step size based on terrain complexity. To verify the performance of the proposed algorithm, we conduct experiments with various path planning algorithms in three different environments: simple, intermediate, and complex. The experimental results demonstrate that TA-RRT* outperforms other algorithms in terms of path length, computational time, and memory usage. Furthermore, its robustness was validated in dynamic environments, where it effectively performed real-time path replanning to adapt to environmental changes, such as the appearance of new obstacles.