User interactions with mobile applications (apps) are accompanied by continuous visual changes in the Graphical UI (GUI), guiding task completion and feedback. These changes help users complete intended tasks or assess the appropriateness of their actions, typically conveyed through visual cues such as appearance and color. While such visual changes are effective for sighted users, they are inaccessible to blind users, creating substantial barriers to GUI interaction. To address these challenges, we propose VisualDroid , a method based on a multi-modal large language model (LLM) for testing and classifying GUI visual changes using a tailored three-hop reasoning prompting framework. VisualDroid achieved an F1 score of 94.7% in 34 apps from 17 domains, surpassing all baseline methods. When evaluated on five open source apps from F-Droid, our method enabled developers to resolve three identified issues, with two still under review. In terms of efficiency and cost, our method indicates minimal resource consumption.

Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by smoothing outliers. However, end-to-end fine-tuning of rotational optimization algorithms incurs high computational costs and is prone to overfitting. To address this challenge, we propose an efficient distribution-aware rotational calibration method, DartQuant, which reduces the complexity of rotational optimization by constraining the distribution of the activations after rotation. This approach also effectively reduces reliance on task-specific losses, thereby mitigating the risk of overfitting. Additionally, we introduce the QR-Orth optimization scheme, which replaces expensive alternating optimization with a more efficient solution. In a variety of model quantization experiments, DartQuant demonstrates superior performance. Compared to existing methods, it achieves 47$\times$ acceleration and 10$\times$ memory savings for rotational optimization on a 70B model. Furthermore, it is the first to successfully complete rotational calibration for a 70B model on a single 3090 GPU, making quantization of large language models feasible in resource-constrained environments.

In manufacturing environment, hundreds of input parameters are related to product quality. To build an accurate machine learning model for quality prediction, it is necessary to find major input parameters which have a big influence in quality prediction. The procedure of identifying major factors out of original high-dimensional input parameters is called to be feature selection. This paper proposes a hybrid method for feature selection, which effectively reduces the searching space by leveraging feature subset chosen by Fast Correlation Based Filter (FCBF) and Relief-based feature selection. The computational complexity is proved to be quadratic in feature number, while most of the existing methods suffer from exponential computation complexity. This improvement is crucial especially when we deal with high-dimensional input parameters because it dramatically reduces the computational time. Further, the proposed method outperforms in prediction accuracy as well when it compares with the benchmarking method. It has been demonstrated by the implementation of our method into real-world manufacturing data sets and open source benchmarking data set.

On September 6, 2008, a Micro-satellite Constellation for Monitoring and Forecasting Environment and Disaster was successfully launched in China. This Micro-satellite Constellation includes two small satellites, Satellite-A (abbreviated as HJ-1A) and Satellite-B (abbreviated as HJ-1B). HJ-1A is installed with a Hyperspectral Imager (abbreviated as HSI), which is China's first satellite-based hyperspectral remote sensor. The advantages of HJ-1A HSI is that is has high spectral resolution and wide swath, and therefore it has much potential in monitoring water quality of large-scale inland waters. To validate the application of HJ-1A HSI in monitoring water quality of large-scale inland waters, we used two scenes of HJ-1A HSI images to retrieve total suspended matter of Lake Taihu. Then we used the insitu measured data at a station in Lake Taihu to calculate the retrieved absolute error and relative error, which showed that the retrieved total suspended matter results were reasonable.

A new architecture for REMS (Remote-sensing Environmental Monitoring System V1.0) is introduced in this paper. REMS is the first integrated system in China developed to meet the multi-resource, multi-temporal and multi-thematic data processing, analyzing and products distributing, especially to process and monitor inland water resource pollution. The most important components of REMS are presented in this paper including tools for multi-resource data input/output, preprocessing, data visualization and mapping, environment information extraction, conventional image analysis, advanced tools for eco-environment modeling, and integrated interface to connect with general spatial and spectral database and water quality monitoring database. REMS provide professional ability to extract the major characters of water resource such as Chlorophyll content, Total Suspended Matter (TSM), Yellow Substance or CDOM etc. In order to retrieve and predict the blue algae distribution and water quality evolvement, a group of statistical algorithms are also realized to analyses the result and at the same time data assurance measures are also given respectively. Finally, we select the Taihu Lake, JiangShu Province, South China, as the representative research area and some field applications constructed based on REMS are discussed

This paper describes how an inductive fault analysis (IFA) method was used in determining the expected yield and test algorithm effectiveness in SRAMs. One portion of the paper describes the process of gathering and correlating defect data from different sources to get a meaningful and accurate defect distribution. This data is used in the IFA software to weight the probability of faults occurring. With the fault data from two SRAM cells the yield of those devices is estimated and compared with actual yield. The effectiveness of certain test patterns is also evaluated based on the probable faults for those circuits.