Graphical User Interfaces (GUIs) are central to app development projects. App developers may use the GUIs of other apps as a means of requirements refinement and rapid prototyping or as a source of inspiration for designing and improving their own apps. Recent research has thus suggested retrieving relevant GUI designs that match a certain text query from screenshot datasets acquired through crowdsourced or automated exploration of GUIs. However, such text-to-GUI retrieval approaches only leverage the textual information of the GUI elements, neglecting visual information such as icons or background images. In addition, retrieved screenshots are not steered by app developers and lack app features that require particular input data. To overcome these limitations, this article proposes GUing, a GUI search engine based on a vision-language model called GUIClip, which we trained specifically for the problem of designing app GUIs. For this, we first collected from Google Play app introduction images which display the most representative screenshots and are often captioned (i.e., labeled) by app vendors. Then, we developed an automated pipeline to classify, crop, and extract the captions from these images. This resulted in a large dataset which we share with this article: including 303k app screenshots, out of which 135k have captions. We used this dataset to train a novel vision-language model, which is, to the best of our knowledge, the first of its kind for GUI retrieval. We evaluated our approach on various datasets from related work and in a manual experiment. The results demonstrate that our model outperforms previous approaches in text-to-GUI retrieval achieving a Recall@10 of up to 0.69 and a HIT@10 of 0.91. We also explored the performance of GUIClip for other GUI tasks, including GUI classification and sketch-to-GUI retrieval with encouraging results.

Over recent decades, neuroimaging tools, partic-ularly electroencephalography (EEG), have revolutionized our understanding of the brain and its functions. EEG is extensively used in traditional brain-computer interface (BCI) systems due to its low cost, non-invasiveness, and high temporal resolution. This makes it invaluable for identifying different brain states relevant to both medical and non-medical applications. Although this practice is widely recognized, current methods are mainly confined to lab or clinical environments because they rely on data from multiple EEG electrodes covering the entire head. Nonethe-less, a significant advancement for these applications would be their adaptation for “real-world” use, using portable devices with a single-channel. In this study, we tackle this challenge through two distinct strategies: the first approach involves training models with data from multiple channels and then testing new trials on data from a single channel individually. The second method focuses on training with data from a single channel and then testing the performances of the models on data from all the other channels individually. To efficiently classify cognitive tasks from EEG data, we propose Convolutional Neural Networks (CNNs) with only a few parameters and fast learnable spectral-temporal features. We demonstrated the feasibility of these approaches on EEG data recorded during mental arithmetic and motor imagery tasks from three datasets. We achieved the highest accuracies of 100%, 91.55% and 73.45% in binary and 3-class classification on specific channels across three datasets. This study can contribute to the development of single-channel BCI and provides a robust EEG biomarker for brain states classification.

Monitoring fatigue in sport is critical to achieve elite performance and may benefit from machine learning techniques that are liable to predict changes in fatigue state. In this paper we present and compare different machine learning models to predict the Rate of Perceived Exertion (RPE) of training or game sessions for professional football (soccer) players. We compare different approaches to train predictive models in a supervised setting (regression) with a focus on individualized and group-based approaches, i.e. training a specific model for each player or predefined groups of players (full team or clusters defined using unsupervised learning). Both player-informed and player-agnostic models are compared in the group-based approach, i.e. providing or not player id as feature during training and inference. Compared models have been trained on real data collected during a full season of professional football players, and using among others, anthropometric, running activity, heart rate and weather data. The best results are obtained using a player-informed team-based approach with a Random Forest regressor (0.793 MAE, 1.033 RMSE). Results obtained are competitive with the best reported in the literature for this predictive task in elite Football players.

Over the past decade, app store (AppStore)-inspired requirements elicitation has proven to be highly beneficial. Developers often explore competitors' apps to gather inspiration for new features. With the advance of Generative AI, recent studies have demonstrated the potential of large language model (LLM)-inspired requirements elicitation. LLMs can assist in this process by providing inspiration for new feature ideas. While both approaches are gaining popularity in practice, there is a lack of insight into their differences. We report on a comparative study between AppStore- and LLM-based approaches for refining features into sub-features. By manually analyzing 1,200 sub-features recommended from both approaches, we identified their benefits, challenges, and key differences. While both approaches recommend highly relevant sub-features with clear descriptions, LLMs seem more powerful particularly concerning novel unseen app scopes. Moreover, some recommended features are imaginary with unclear feasibility, which suggests the importance of a human-analyst in the elicitation loop.

App reviews from app stores are crucial for improving software requirements. A large number of valuable reviews are continually being posted, describing software problems and expected features. Effectively utilizing user reviews necessitates the extraction of relevant information, as well as their subsequent summarization. Due to the substantial volume of user reviews, manual analysis is arduous. Various approaches based on natural language processing (NLP) have been proposed for automatic user review mining. However, the majority of them requires a manually crafted dataset to train their models, which limits their usage in real-world scenarios. In this work, we propose Mini-BAR, a tool that integrates large language models (LLMs) to perform zero-shot mining of user reviews in both English and French. Specifically, Mini-BAR is designed to (i) classify the user reviews, (ii) cluster similar reviews together, (iii) generate an abstractive summary for each cluster and (iv) rank the user review clusters. To evaluate the performance of Mini-BAR, we created a dataset containing 6,000 English and 6,000 French annotated user reviews and conducted extensive experiments. Preliminary results demonstrate the effectiveness and efficiency of Mini-BAR in requirement engineering by analyzing bilingual app reviews.

GUI (graphical user interface) prototyping is a widely-used technique in requirements engineering for gathering and refining requirements, reducing development risks and increasing stakeholder engagement. However, GUI prototyping can be a time-consuming and costly process. In recent years, deep learning models such as Stable Diffusion have emerged as a powerful text-to-image tool capable of generating detailed images based on text prompts. In this paper, we propose UI-Diffuser, an approach that leverages Stable Diffusion to generate mobile UIs through simple textual descriptions and UI components. Preliminary results show that UI-Diffuser provides an efficient and cost-effective way to generate mobile GUI designs while reducing the need for extensive prototyping efforts. This approach has the potential to significantly improve the speed and efficiency of GUI prototyping in requirements engineering.

Reducing calibration time while maintaining good classification accuracy has been one of the most challenging problems in electroencephalography (EEG) -based brain-computer interfaces (BCIs) research during the last years. Most of machine learning approaches that have been attempted to address this issue are based on knowledge transfer between different BCIs users. Assuming that there is a common underlying data generating process, they try to learn a subject-independent classification model from multiple users in order to classify data of future users. In this paper, we propose a novel approach that allows inter-subjects classification of EEG signals without relying on the strong assumptions considered in previous work. It consists of learning a prediction model of a new BCI user through an ensemble of classifiers where base classifiers are trained on data from other users separately and weighted according to the performance of the ensemble on few labeled data of the new user. Evaluation on real EEG data showed that our approach allows achieving good classification accuracy when the size of calibration set is small.

Security of web servers has become a sensitive subject today. Prediction of normal and abnormal request is problematic due to large number of false alarms in many anomaly based Intrusion Detection Systems (IDS). SS-IDS derives automatically the parameter profiles from the analyzed data thereby generating the Statistical Signatures. Statistical Signatures are based on modeling of normal requests and their distribution value without explicit intervention. Several attributes are used to calculate the behavior of the legitimate request on the web server. SS-IDS is best suited for the newly installed web servers which doesn’t have large number of requests in the data set to train the IDS and can be used on top of currently used signature based IDS like SNORT. Experiments conducted on real data sets have shown high accuracy up to 99.98% for predicting valid request as valid and false positive rate ranges from 3.82-7.84%.