Search

Autonomous vehicle (AV) algorithms tend to be designed with a techno-solutionism mindset, causing algorithms to fail in real-world applications. This can be attributed to algorithm developers’ lack of routines and knowledge to consider the environments and circumstances AVs are intended to partake in. This paper argues for shifting towards a more responsible human-centred algorithm design (HCAD). It addresses this by demonstrating the different reflective practice qualities obtained by engaging algorithm designers from four companies with ethnographic materials. The study shows that Design Ethnographic (DE) approach allowed developers to consider the value of AVs from sociotechnical perspectives and facilitated collaborative learning and debating about what problems truly need solving to bring societal value. This demonstrates how ethnographically infused HCAD helps expand algorithm developers’ opportunities to participate responsibly in value co-creation for society.

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental learning, focusing on introducing FSCIL from two perspectives, while reviewing over 30 theoretical research studies and more than 20 applied research studies. From the theoretical perspective, we provide a novel categorization approach that divides the field into five subcategories, including traditional machine learning methods, meta learning-based methods, feature and feature space-based methods, replay-based methods, and dynamic network structure-based methods. We also evaluate the performance of recent theoretical research on benchmark datasets of FSCIL. From the application perspective, FSCIL has achieved impressive achievements in various fields of computer vision such as image classification, object detection, and image segmentation, as well as in natural language processing and graph. We summarize the important applications. Finally, we point out potential future research directions, including applications, problem setups, and theory development. Overall, this paper offers a comprehensive analysis of the latest advances in FSCIL from a methodological, performance, and application perspective. © 2023 The Author(s), Funding: This work is supported by the National Natural Science Foundation of China (Grant No. 62373343) and the Beijing Natural Science Foundation, China (No. L233036).

Document-level relation extraction faces two often overlooked challenges: long-tail problem and multi-label problem. Previous work focuses mainly on obtaining better contextual representations for entity pairs, hardly address the above challenges. In this paper, we analyze the co-occurrence correlation of relations, and introduce it into the document-level relation extraction task for the first time. We argue that the correlations can not only transfer knowledge between data-rich relations and data-scarce ones to assist in the training of long-tailed relations, but also reflect semantic distance guiding the classifier to identify semantically close relations for multi-label entity pairs. Specifically, we use relation embedding as a medium, and propose two co-occurrence prediction sub-tasks from both coarse- and fine-grained perspectives to capture relation correlations. Finally, the learned correlation-aware embeddings are used to guide the extraction of relational facts. Substantial experiments on two popular datasets (i.e., DocRED and DWIE) are conducted, and our method achieves superior results compared to baselines. Insightful analysis also demonstrates the potential of relation correlations to address the above challenges. The data and code are released at https://github.com/RidongHan/DocRE-Co-Occur. © 2023 Elsevier Ltd, Funding: This work is supported by the National Natural Science Foundation of China under grant No. 61872163 and 61806084, Jilin Province Key Scientific and Technological Research and Development Project under grant No. 20210201131GX, and Jilin Provincial Education Department Project under grant No. JJKH20190160KJ.

This paper proposes a compact and frequency-adjustable/reconfigurable dielectric (DR)-loaded eighth-mode substrate integrated waveguide (EMSIW) antenna for duplex wireless communications. The miniaturization of the resonators is realized using a rectangular slot and high isolation is achieved by keeping a reasonable space between them. The proposed design is simulated using a three-dimensional (3D) full-wave simulator, then analysed with a circuit model and finally validated experimentally. Frequency-reconfigurability in the suggested antenna is achieved by placing DRs with different permittivities in the designated holes that are realized in the open-ended portion of each resonator. Consequently, the lower- and high-resonant bands can be reconfigured from 4.70 to 5.23 GHz and from 5.55 to 6.34 GHz, respectively. It is worth mentioning that both resonant band can be independently reconfigured. Moreover, the inter-resonator coupling is always lower than −23.5 dB in the bands of interest. Furthermore, the peak realized gains are always greater than 4.7 dBi in the lower frequency band and 5.5 dBi in the higher one. The suggested antenna has stable radiation properties in both bands in all frequency ranges. Hence, this design is suitable for compact reconfigurable devices due to its compactness, large frequency ranges, stable radiation patterns, and high isolation. © 2023 Elsevier GmbH, Funding: The Deanship of Scientific Research at Majmaah University for supporting this work under Project number R-2023-791.

An orthogonal representation of features can offer valuable insights into feature selection as it aims to find a representative subset of features in which all features can be accurately reconstructed by a set of features that are linearly independent, uncorrelated, and perpendicular to each other. In this paper, a novel feature selection method, called Low-Redundant Unsupervised Feature Selection based on Data Structure Learning and Feature Orthogonalization (LRDOR), is presented. In the first stage, the suggested LRDOR method makes use of the QR factorization over the whole set of features to find the orthogonal representation of the feature space. Then, LRDOR utilizes the directional distance based on the matrix factorization in order to determine the distance among the set of considered features and the orthogonal set obtained from the original features. Moreover, LRDOR simultaneously takes into account the local correlation of features and the data manifold as dual information into the feature selection process, which can lead to a low level of redundancy and maintain the geometric data structure when reducing the data dimension. In addition to providing a proficient iterative algorithm, the convergence analysis is also included to solve the objective function of LRDOR. The results of the experiments demonstrate that for clustering purposes, LRDOR works better than other related state-of-the-art unsupervised feature selection methods on ten real-world datasets. © 2023 Elsevier Ltd

Sentiment and sarcasm detection in social media contribute to assessing social opinion trends. Over the years, most artificial intelligence (AI) methods have relied on real values to characterize the sentimental and sarcastic features in language. These methods often overlook the complexity and uncertainty of sentimental and sarcastic elements in human language. Therefore, this paper proposes the Quantum Fuzzy Neural Network (QFNN), a multimodal fusion and multitask learning algorithm with a Seq2Seq structure that combines Classical and Quantum Neural Networks (QNN), and fuzzy logic. Complex numbers are used in the Fuzzifier to capture sentiment and sarcasm features, and QNN are used in the Defuzzifier to obtain the prediction. The experiments are conducted on classical computers by constructing quantum circuits in a simulated noisy environment. The results show that QFNN can outperform several recent methods in sarcasm and sentiment detection task on two datasets (Mustard and Memotion). Moreover, by assessing the fidelity of quantum circuits in a noisy environment, QFNN was found to have excellent robustness. The QFNN circuit also possesses expressible and entanglement capabilities, proving effective in various settings. Our code is available at https://github.com/prayagtiwari/QFNN. © 2023 Elsevier B.V.

As an epigenetic modification that plays an important role in modifying gene function and controlling gene expression during cell development, DNA N4-methylcytosine (4mC) is still lack of researching. It is therefore necessary to accurately predict the 4mC sites to make fully aware of its mechanism and function. In this paper, we propose a novel model which is called Structural Sparse Regularized Random Vector Functional Link Network (SSR-RVFL) for predicting 4mC sites. Compared with other state-of-the-art methods, SSR-RVFL performs better and achieves higher prediction accuracy. There are total six benchmark datasets used in the experiments, namely C.elegans, D.elanogaster, E.coli, A.thaliana G.subterraneus and G.pickeringii. Our model improves the accuracy by 0.42%, 0.45%, 0.48%, 0.91%, 0.66% and 0.7% on these six benchmark datasets respectively, so it can be regarded as a more effective prediction tool. © 2023 The Author(s)