Homework tutoring work is a demanding and often conflict-prone practice in family life, and parents often lack targeted support for managing its cognitive and emotional burdens. Through interviews with 18 parents of children in grades 1–3, we examine how homework-related labor is divided and coordinated between parents, and where AI might meaningfully intervene. We found three key insights: (1) Homework labor encompasses distinct dimensions: physical, cognitive, and emotional, with the latter two often remaining invisible. (2) We identified father-mother-child triadic dynamics in labor division, with children’s feedback as the primary factor shaping parental labor adjustments. (3) Building on prior HCI research, we propose an AI design that prioritizes relationship maintenance over task automation or broad labor mitigation. By employing labor as a lens that integrates care work, we explore the complexities of labor within family contexts, contributing to feminist and care-oriented HCI and to the development of context-sensitive coparenting practices.

Image cropping is a crucial means of enhancing the aesthetic quality of images. However, it relies on photographic knowledge and experience. For novice users, it is challenging to obtain satisfactory results through cropping. To meet the image cropping needs of novice users and improve efficiency, this article designs and develops an intelligent image cropping application, AesthetiCropper, and proposes two cropping methods. One is based on visual balance. The other is based on deep learning. This system features an intuitive user interface and automatically crops images to high aesthetic standards. It also offers customizable parameters and an editing module to meet users’ personalized requirements. User studies show that participants are more satisfied with the system’s cropping results compared to manual ones. The System Usability Scale (SUS) score indicates that its usability reaches a good level, making it worthy of promotion.

Tactile information plays a vital role in human perception, robotics, and human-computer interaction, encapsulating the richness of physical sensations. Storing tactile information enables the preservation and precise reproduction of these sensory experiences, which can be used to enhance robotic manipulation with realistic feedback and preserve cultural artifacts for future study and interaction. With unparalleled density, stability, and longevity, DNA emerges as an ideal solution for the long-term preservation of such valuable data. However, the high cost of DNA synthesis and sequencing poses significant challenges for scalable storage. To address this, we propose an end-to-end neural network compression framework based on RVQGAN, MP-SENet, and robust DNA encoding strategies, enabling efficient compression of complex tactile data. Experimental results demonstrate that our method achieves high compression rates, maintains data integrity, and exhibits exceptional robustness against DNA-specific noise. This work also lays the foundation for the future development of multimodal perception AI by enabling the long-term storage of tactile information, ensuring its availability for future applications and advancements.

Filter bank multicarrier with offset quadrature amplitude modulation (FBMC-OQAM) is considered as a promising waveform for Internet of Things (IoT) due to its capability to mitigate interference among asynchronous users. However, as a multicarrier technique, the FBMC-OQAM signal also has a high peak-to-average power ratio (PAPR), which is detrimental to low-power transmission. To address this issue, this article proposes a novel discrete Fourier transform (DFT)-spread scheme to exhaustively reduce the PAPR of the FBMC-OQAM signal. In this scheme, the transmitting data symbols are first mapped with a conjugate symmetry rule and then coded by the DFT. Using this method, the preprocessing step in FBMC-OQAM that involves separating the real and imaginary parts of the quadrature amplitude modulation (QAM) symbols can be avoided. Compared with existing DFT-spread FBMC-OQAM schemes, the proposed scheme demonstrates better PAPR performance while maintaining equivalent spectral efficiency. Additionally, the computational complexity of the proposed scheme experiences only a slight increase, thereby preserving a relatively low computational burden. Numerical simulation results validate the effectiveness of the proposed scheme. Furthermore, the effect of the prototype filter on the PAPR is investigated, and a tradeoff exists between the PAPR and out-of-band performance.

Traditional logging methods often encounter complications like collapses of wellbores and instrument malfunctions, leading to the loss or misalignment of logging data. Re-logging is expensive, particularly for oil and gas wells that have already been cemented; therefore, reconstructing logging curves is a more economical option. Although traditional methods like empirical modeling and multiple fitting are effective in some cases, they are limited by geographic location and rock type, making it difficult to meet the demands for precise interpretation of logging data and detailed description of reservoirs. In this study, a CNN-BiLSTM-Attention model is proposed that combines a bidirectional long and short-term memory network (BiLSTM), a convolutional neural network (CNN), and an integrated attention mechanism. The model optimizes the ability of traditional deep learning methods to process time-series data and effectively establishes complex nonlinear mapping relationships between inputs and outputs. In this paper, root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R-squared) are used to evaluate the performance of the CNN-BiLSTM-Attention model. The results demonstrate that the divergence between the reconstructed value and the actual value is negligible in the log reconstruction experiment of CNN-BiLSTM-Attention, particularly under difficult geological settings. This study not only provides an innovative solution for the accurate prediction and effective reconstruction of logging curves but also provides valuable practical experience and a foundation for the implementation of deep learning in geophysics.

We propose a novel dynamic software watermarking design based on Return-Oriented Programming (ROP). Our design formats watermarking code into well-crafted data arrangements that look like normal data but could be triggered to execute. Once triggered, the pre-constructed ROP execution will recover the hidden watermark message. The proposed ROP-based watermarking technique is more stealthy and resilient over existing techniques since the watermarking code is allocated dynamically into data region and therefore out of reach of attacks based on code analysis. Evaluations show that our design not only achieves satisfying stealth and resilience, but also causes significantly lower overhead to the watermarked program.