Heat Pump Systems with energy efficiency greater than 1 are mainly used in electric vehicles to increase vehicle mileage. However, the lower the ambient air temperature, the lower the saturation pressure of the low-pressure side refrigerant, making it impossible to use the Heat Pump System. This paper suggests a method of increasing the flow rate by recirculating the high-pressure side refrigerant to the low-pressure side using the Hot Gas Recycle System. Experiments are conducted to investigate the hot gas recycle mode in a EV6 car at various EXV steps, ambient air temperatures, and waste heats. The heating performance is increased by 63.2% when the refrigerant is recycled at 0C ambient air temperature. Because the saturation pressure of low-pressure side refrigerant increased, resulting in the higher mass flowrate

The next-generation electric vehicle will be applied with a next generation battery and autonomous driving system that generates high heat. However, since the proper operating temperature is low, it is essential to combine it with a refrigeration cycle for vehicle air conditioning. However, the existing cooling system is difficult to satisfy air conditioning and battery load at the same time, so to solve this problem, we developed a cascade cooling system using two vapor compression refrigeration systems connected by PIHX for the first time in the world. In this paper, the existing system and the cascade system were compared. Compared to the existing system, it was found that the cooling performance of the battery was improved while the cooling performance of the air conditioning was at the same level.

Vocal health plays a crucial role in peoples' lives, significantly impacting their communicative abilities and interactions. However, despite the global prevalence of voice disorders, many lack access to convenient diagnosis and treatment. This paper introduces VocalAgent, an audio large language model (LLM) to address these challenges through vocal health diagnosis. We leverage Qwen-Audio-Chat fine-tuned on three datasets collected in-situ from hospital patients, and present a multifaceted evaluation framework encompassing a safety assessment to mitigate diagnostic biases, cross-lingual performance analysis, and modality ablation studies. VocalAgent demonstrates superior accuracy on voice disorder classification compared to state-of-the-art baselines. Its LLM-based method offers a scalable solution for broader adoption of health diagnostics, while underscoring the importance of ethical and technical validation.

Diffusion generative modeling has become a promising approach for learning robotic manipulation tasks from stochastic human demonstrations. In this paper, we present Diffusion-EDFs, a novel SE(3)-equivariant diffusion-based approach for visual robotic manipulation tasks. We show that our proposed method achieves remarkable data efficiency, requiring only 5 to 10 human demonstrations for effective end-to-end training in less than an hour. Furthermore, our benchmark experiments demonstrate that our approach has superior generalizability and robustness compared to state-of-the-art methods. Lastly, we validate our methods with real hardware experiments. Project Website: https://sites.google.com/view/diffusion-edfs

In speech separation, time-domain approaches have successfully replaced the time-frequency domain with latent sequence feature from a learnable encoder. Conventionally, the feature is separated into speaker-specific ones at the final stage of the network. Instead, we propose a more intuitive strategy that separates features earlier by expanding the feature sequence to the number of speakers as an extra dimension. To achieve this, an asymmetric strategy is presented in which the encoder and decoder are partitioned to perform distinct processing in separation tasks. The encoder analyzes features, and the output of the encoder is split into the number of speakers to be separated. The separated sequences are then reconstructed by the weight-shared decoder, which also performs cross-speaker processing. Without relying on speaker information, the weight-shared network in the decoder directly learns to discriminate features using a separation objective. In addition, to improve performance, traditional methods have extended the sequence length, leading to the adoption of dual-path models, which handle the much longer sequence effectively by segmenting it into chunks. To address this, we introduce global and local Transformer blocks that can directly handle long sequences more efficiently without chunking and dual-path processing. The experimental results demonstrated that this asymmetric structure is effective and that the combination of proposed global and local Transformer can sufficiently replace the role of inter- and intra-chunk processing in dual-path structure. Finally, the presented model combining both of these achieved state-of-the-art performance with much less computation in various benchmark datasets.

In this study, a novel top-K ranking recommendation method called collaborative social metric learning (CSML) is proposed, which implements a trust network that provides both user-item and user-user interactions in simple structure. Most existing recommender systems adopting trust networks focus on item ratings, but this does not always guarantee optimal top-K ranking prediction. Conventional direct ranking systems in trust networks are based on sub-optimal correlation approaches that do not consider item-item relations. The proposed CSML algorithm utilizes the metric learning method to directly predict the top-K items in a trust network. A new triplet loss is further proposed, called socio-centric loss, which represents user-user interactions to fully exploit the information contained in a trust network, as an addition to the two commonly used triplet losses in metric learning for recommender systems, which consider user-item and item-item relations. Experimental results demonstrate that the proposed CSML outperformed existing recommender systems for real-world trust network data.