Due to the limited internal space and economic costs, virtual keyboards(VKs) of mobile devices commonly use monotonous global sound and vibration feedback, resulting in unsatisfactory realism and negative experience. To mitigate the monotonous feedback of high-frequency keystrokes on VKs, we propose an interactive sound-vibrotactile feedback design. This system dynamically adjusts sound and vibrotactile re-sponses based on the user's typing speed. We conducted a user study (N=30) and found that the collaborative varied auditory-vibrotactile feedback provided a better experience, created a local feedback illusion, and improved global feedback. Additionally, users preferred subtle variations over distinct variations. Our method can improve global VK feedback and provide a better experience without increasing additional costs and burdens. This study contributes to improving the VK experience on low-cost mobile devices and provides design suggestions for VKs.

Selecting appropriate fonts for sentence-level text, such as slide titles and poster headings, requires pleasing glyphs and semantic congruence with the text. This task is especially challenging for users without design backgrounds. Previous studies established associations between tags and fonts but overlooked the different design intents between sentence-level text and word-level text influencing font selections. Recently, large language models (LLMs) like ChatGPT with extensive knowledge bases have emerged as promising solutions for various tasks. This study evaluated the capabilities of GPT-3.5 in recommending fonts compared to professional designers to explore the application of LLMs in the design field. We conducted comprehensive evaluations, including both quantitative metrics to assess font diversity, accuracy, and consistency, and a user study involving designers and non-designers. The results indicate that while GPT-3.5 performs well in selecting common serif and sans-serif fonts suitable for general use that align with the preferences of users without design backgrounds, it falls short in stylized font selection. Our findings highlight the potential and limitations of using GPT-3.5 for font selection in collaborative design environments and provide insights into integrating such models into design tools to support multidisciplinary teams.

In the digital era, the significance of design education is on the rise due to its ability to cultivate creativity. However, the disconnect between design practice and theory, coupled with the abundance of design knowledge, poses challenges to learning in this field. Despite the potential of large language models (LLMs) to integrate various data sources for facilitating design knowledge dissemination, they face obstacles such as the scarcity of design-related datasets and limited natural language representations. To overcome these challenges, we introduce DRELM, a design-centric language model that serves as an assistant providing UI design recommendations. We also offer corresponding resources to advance language modeling research in the design domain. Importantly, DesignInstruct stands out as a premier dataset for guiding user interface tasks, while DesignEvaluation significantly contributes to autonomous design evaluation and decision support. In our research, we utilize supervised data from DesignInstruct and DesignEvaluation to fine-tune pre-trained Qwen-7B models for design tasks. Experiments conducted on test data affirm the effectiveness of our dataset in enhancing knowledge comprehension, design execution, and evaluation. We commit to making all training data and DRELM models at https://github.com/sssala/DRELM-A-Language-Model-for-Design-Recommendation-and-Evaluation.

This study addresses the challenge of font retrieval in design by proposing a novel approach utilizing contrastive learning to establish a shared embedding space for texts and fonts. In contrast to previous methods limited to word-level queries, our method enables text-font retrieval at the sentence level. We collected text-font pair data from web pages and design templates on the Internet, finetuned the CLIP model on these pairs, and obtained text and font encoders for our application. The top-k fonts were then retrieved using the cosine distance between input text and font embeddings. Our approach offers three key advantages: (1) retrieving fonts with sentence-level text as input, which is intuitively consistent with design behaviors; (2) leveraging text-font pair data available on the Internet without manual annotation; and (3) scalability, the trained font encoder can encode new font candidates without retraining the model. We introduced an evaluation metric for font retrieval results. The results indicate that the retrieved fonts in the top 3 score better than those from baseline methods, and the top 1 retrieved font is competitive with the fonts selected by experienced graphic designers.

BACKGROUND: Osteoporosis is a common metabolic skeletal disease and usually lacks obvious symptoms. Many individuals are not diagnosed until osteoporotic fractures occur. Bone mineral density (BMD) measured by dual-energy X-ray absorptiometry (DXA) is the gold standard for osteoporosis detection. However, only a limited percentage of people with osteoporosis risks undergo the DXA test. As a result, it is vital to develop methods to identify individuals at-risk based on methods other than DXA. RESULTS: We proposed a hierarchical model with three layers to detect osteoporosis using clinical data (including demographic characteristics and routine laboratory tests data) and CT images covering lumbar vertebral bodies rather than DXA data via machine learning. 2210 individuals over age 40 were collected retrospectively, among which 246 individuals' clinical data and CT images are both available. Irrelevant and redundant features were removed via statistical analysis. Consequently, 28 features, including 16 clinical data and 12 texture features demonstrated statistically significant differences (p < 0.05) between osteoporosis and normal groups. Six machine learning algorithms including logistic regression (LR), support vector machine with radial-basis function kernel, artificial neural network, random forests, eXtreme Gradient Boosting and Stacking that combined the above five classifiers were employed as classifiers to assess the performances of the model. Furthermore, to diminish the influence of data partitioning, the dataset was randomly split into training and test set with stratified sampling repeated five times. The results demonstrated that the hierarchical model based on LR showed better performances with an area under the receiver operating characteristic curve of 0.818, 0.838, and 0.962 for three layers, respectively in distinguishing individuals with osteoporosis and normal BMD. CONCLUSIONS: The proposed model showed great potential in opportunistic screening for osteoporosis without additional expense. It is hoped that this model could serve to detect osteoporosis as early as possible and thereby prevent serious complications of osteoporosis, such as osteoporosis fractures.

Mandarin speech synthesis was conducted by generating prosodic features by the proposed method and segmental features by HMM-based method. The proposed method generates sentence fundamental frequency (F0) contours by representing them as a superposition of tone components on phrase components. The tone components are realized by concatenating their fragments at tone nuclei predicted by a corpus-based method, while the phrase components are generated by rules under the generation process model (F0model) framework. The method includes prediction of phoneme/pause durations in a statistical method as the first step. Through a listening test on the quality of synthetic speech, it was shown that a better quality was obtainable by the method as compared to that by the full HMM-based method. It was also shown that a better quality is obtainable as compared to the case of generating F0contours without super-positional scheme.

A new method for generating sentence F 0 contours of Mandarin speech is proposed.The method assumes the F 0 contour generation process model, but generates the tone and phrase components in different ways and sums them to produce a sentence F 0 contour.The tone component is generated concatenating F 0 patterns of tone nuclei, which are predicted by a corpus-based scheme (binary decision trees).Experiments of F 0 contour generation were conducted by using 100 news utterances by a female speaker.The results showed that the method could generate F0 contours close to those of target speech.A perceptual evaluation was also conducted on the synthetic speech using the F0 contours generated by the method.An average score of 4.5 in a 5-point scale indicates the high naturalness, verifying the validity of the method.