Search

High-speed metropolitan railway services have been introduced in several mega cities to solve traffic problems stemming from urban sprawl. The success of such huge public transportation projects depends on how to design them more attractively based on profound insight into people’s preferences in the context of travel mode choice. Although many previous studies have investigated factors affecting the preferences for high-speed metropolitan railway services in general, possible heterogeneity in the preferences by different travel contexts tends to be largely ignored. In addition, the effects of personal latent attitudes toward travel mode choice have not been investigated thoroughly in the context of using high-speed metropolitan railway services. Incorporating such latent attitudes in mode choice analysis is helpful for better understanding the motivation of choosing a travel mode. The present study investigates people’s preferences for high-speed metropolitan railway service and their heterogeneity by different travel contexts using stated choice data. In addition, the hybrid choice modeling approach is employed to identify simultaneously the relevant latent attitudes and their effects on the preference for high-speed metropolitan railway service. The data collection was conducted in 2021, with respect to the great train express (GTX) project of the Seoul metropolitan area. The estimation results suggest that the latent attitudes about risk-minimizing and comfort-seeking have different effects on people’s intention to use GTX according to travel contexts. Moreover, the difference in sensitivity to the attributes of GTX exists depending on the travel contexts.

Contextualized word embeddings can lead to state-of-the-art performances in natural language understanding. Recently, a pre-trained deep contextualized text encoder such as BERT has shown its potential in improving natural language tasks including abstractive summarization. Existing approaches in dialogue summarization focus on incorporating a large language model into summarization task trained on large-scale corpora consisting of news articles rather than dialogues of multiple speakers. In this paper, we introduce self-supervised methods to compensate shortcomings to train a dialogue summarization model. Our principle is to detect incoherent information flows using pretext dialogue text to enhance BERT's ability to contextualize the dialogue text representations. We build and fine-tune an abstractive dialogue summarization model on a shared encoder-decoder architecture using the enhanced BERT. We empirically evaluate our abstractive dialogue summarizer with the SAMSum corpus, a recently introduced dataset with abstractive dialogue summaries. All of our methods have contributed improvements to abstractive summary measured in ROUGE scores. Through an extensive ablation study, we also present a sensitivity analysis to critical model hyperparameters, probabilities of switching utterances and masking interlocutors., 5 pages, 3 figures, INTERSPEECH 2021

As individuals have different thoughts about automated driving (AD) vehicles, the gap between their manual driving (MD) styles and their expected AD styles would affect their willingness to ride AD vehicles. The objective of this study is to investigate the effects of personal driving styles on AD preference and the variations of these effects by travel distance. To identify latent driving styles and their effects simultaneously, we developed a hybrid choice model using sequential stated-choice data from an online survey administered to 511 respondents in South Korea in 2019. The latent driving styles were classified as impatient, over-nervous, and cautious driving styles. The results significantly show that individuals of each style prefer AD vehicles in different situations. Impatient drivers, who are concerned about travel delays, rarely worry about the driving mode if it drives them faster. Over-nervous drivers, who lack confidence in their driving skills, tend to trust AD technology, regardless of the travel distance. Cautious drivers, who are mindful of their surroundings, prefer AD when traveling relatively short distances. The elasticities of the travel time and cost show that the driving styles have impacts on the AD preference. Moreover, the results of value of time (VoT) for AD have been estimated to differ by travel distance. The results of this study have identified the effects of personal driving styles on AD preference, providing valuable insights that can be used to improve AD vehicle related policies and marketing strategies (such as implementing price discrimination by travel distance and lowering the overall price of AD vehicles), which may increase the market share of AD vehicles.

Background Recognition is an essential function of human beings. Humans easily recognize a person using various inputs such as voice, face, or gesture. In this study, we mainly focus on DL model with multi-modality which has many benefits including noise reduction. We used ResNet-50 for extracting features from dataset with 2D data. Results This study proposes a novel multimodal and multitask model, which can both identify human ID and classify the gender in single step. At the feature level, the extracted features are concatenated as the input for the identification module. Additionally, in our model design, we can change the number of modalities used in a single model. To demonstrate our model, we generate 58 virtual subjects with public ECG, face and fingerprint dataset. Through the test with noisy input, using multimodal is more robust and better than using single modality. Conclusions This paper presents an end-to-end approach for multimodal and multitask learning. The proposed model shows robustness on the spoof attack, which can be significant for bio-authentication device. Through results in this study, we suggest a new perspective for human identification task, which performs better than in previous approaches.

Autonomous driving technologies (ADTs) are transformative because they are expected to assume the task of driving. Since travel distance is closely related to the burden of driving, it is expected to affect the ADT preference; however, this effect has not been investigated in the transportation literature. Therefore, this study is designed to investigate the ADT preference and heterogeneity with respect to different travel distances. Hypothetical choice situations were designed to investigate people's ADT preferences over human driving for varying travel distances. Using the stated preference data collected via the experiments, four latent class models were estimated for heterogeneity across classes and travel distances. The estimation results show that three classes, we labeled as competitive, autonomous vehicle oriented, human-driven vehicle oriented, are revealed by the ADT preference, regardless of the travel distance. In addition, in-vehicle activities in hypothetical autonomous driving situations were observed across all the classes and travel distances.

An amendment to this paper has been published and can be accessed via the original article.

The demands on higher bandwidth with reduced power consumption in mobile market are driving mobile DRAM with advanced design techniques. Proposed LPDDR4 in this paper achieves over 39% improvement in power efficiency and over 4.3 Gbps data rate with 1.1 V supply voltage. These are challenging targets compared with those of LPDDR3. This work describes design schemes employed in LPDDR4 to satisfy these requirements, such as multi-channel-per-die architecture, multiple training modes, low-swing interface, DQS and clock frequency dividing, and internal reference for data and command-address signals. This chip was fabricated in a 3-metal 2y-nm DRAM CMOS process.