Question answering (QA) systems are designed to answer questions based on given information or with the help of external information. Recent advances in QA systems are overwhelmingly contributed by deep learning techniques, which have been employed in a wide range of fields such as finance, sports and biomedicine. For generative QA in open-domain QA, although deep learning can leverage massive data to learn meaningful feature representations and generate free text as answers, there are still problems to limit the length and content of answers. To alleviate this problem, we focus on the variant YNQA of generative QA and propose a model CasATT (cascade prompt learning framework with the sentence-level attention mechanism). In the CasATT, we excavate text semantic information from document level to sentence level and mine evidence accurately from large-scale documents by retrieval and ranking, and answer questions with ranked candidates by discriminative question answering. Our experiments on several datasets demonstrate the superior performance of the CasATT over state-of-the-art baselines, whose accuracy score can achieve 93.1% on IR&QA Competition dataset and 90.5% on BoolQ dataset.

This paper addresses the novel task of detecting chorus sections in English and Japanese lyrics text. Although chorus-section detection using audio signals has been studied, whether chorus sections can be detected from text-only lyrics is an open issue. Another open issue is whether patterns of repeating lyric lines such as those appearing in chorus sections depend on language. To investigate these issues, we propose a neural-network-based model for sequence labeling. It can learn phrase repetition and linguistic features to detect chorus sections in lyrics text. It is, however, difficult to train this model since there was no dataset of lyrics with chorus-section annotations as there was no prior work on this task. We therefore generate a large amount of training data with such annotations by leveraging pairs of musical audio signals and their corresponding manually time-aligned lyrics; we first automatically detect chorus sections from the audio signals and then use their temporal positions to transfer them to the line-level chorus-section annotations for the lyrics. Experimental results show that the proposed model with the generated data contributes to detecting the chorus sections, that the model trained on Japanese lyrics can detect chorus sections surprisingly well in English lyrics, and that patterns of repeating lyric lines are language-independent.

Conventional Nyquist folding receiver (NYFR) uses zero crossing rising (ZCR) voltage times to control the RF sample clock, which is easily affected by noise. Moreover, the analog and digital parts are not synchronized so that the initial phase of the input signal is lost. Furthermore, it is assumed in most literature that the input signal is in a single Nyquist zone (NZ), which is inconsistent with the actual situation. In this paper, we propose an improved architecture denominated as a dual-channel NYFR with adjustable local oscillator (LOS) and an information recovery algorithm. The simulation results demonstrate the validity and viability of the proposed architecture and the corresponding algorithm.

Let f be a Boolean function in n variables. The Möbius transform and its converse of f can describe the transformation behaviors between the truth table of f and the coefficients of the monomials in the algebraic normal form representation of f. In this letter, we develop the Möbius transform and its converse into a more generalized form, which also includes the known result given by Reed in 1954. We hope that our new result can be used in the design of decoding schemes for linear codes and the cryptanalysis for symmetric cryptography. We also apply our new result to verify the basic idea of the cube attack in a very simple way, in which the cube attack is a powerful technique on the cryptanalysis for symmetric cryptography.

Single image deraining is an ill-posed problem which also has been a long-standing issue. In past few years, convolutional neural network (CNN) methods almost dominated the computer vision and achieved considerable success in image deraining. Recently the Swin Transformer-based model also showed impressive performance, even surpassed the CNN-based methods and became the state-of-the-art on high-level vision tasks. Therefore, we attempt to introduce Swin Transformer to deraining tasks. In this paper, we propose a deraining model with two sub-networks. The first sub-network includes two branches. Rain Recognition Network is a Unet with the Swin Transformer layer, which works as preliminarily restoring the background especially for the location where rain streaks appear. Detail Complement Network can extract the background detail beneath the rain streak. The second sub-network which called Refine-Unet utilizes the output of the previous one to further restore the image. Through experiments, our network achieves improvements on single image deraining compared with the previous Transformer research.

The application of time-series prediction is very extensive, and it is an important problem across many fields, such as stock prediction, sales prediction, and loan prediction and so on, which play a great value in production and life. It requires that the model can effectively capture the long-term feature dependence between the output and input. Recent studies show that Transformer can improve the prediction ability of time-series. However, Transformer has some problems that make it unable to be directly applied to time-series prediction, such as: (1) Local agnosticism: Self-attention in Transformer is not sensitive to short-term feature dependence, which leads to model anomalies in time-series; (2) Memory bottleneck: The spatial complexity of regular transformation increases twice with the sequence length, making direct modeling of long time-series infeasible. In order to solve these problems, this paper designs an efficient model for long time-series prediction. It is a double pyramid bidirectional feature fusion mechanism network with parallel Temporal Convolution Network (TCN) and FastFormer. This network structure can combine the time series fine-grained information captured by the Temporal Convolution Network with the global interactive information captured by FastFormer, it can well handle the time series prediction problem.

A formal graph system (FGS for short) is a logic program consisting of definite clauses whose arguments are graph patterns instead of first-order terms. The definite clauses are referred to as graph rewriting rules. An FGS is shown to be a useful unifying framework for learning graph languages. In this paper, we show the polynomial-time PAC learnability of a subclass of FGS languages defined by parameterized hereditary FGSs with bounded degree, from the viewpoint of computational learning theory. That is, we consider VH-FGSLk,Δ(m, s, t, r, w, d) as the class of FGS languages consisting of graphs of treewidth at most k and of maximum degree at most Δ which is defined by variable-hereditary FGSs consisting of m graph rewriting rules having TGP patterns as arguments. The parameters s, t, and r denote the maximum numbers of variables, atoms in the body, and arguments of each predicate symbol of each graph rewriting rule in an FGS, respectively. The parameters w and d denote the maximum number of vertices of each hyperedge and the maximum degree of each vertex of TGP patterns in each graph rewriting rule in an FGS, respectively. VH-FGSLk,Δ(m, s, t, r, w, d) has infinitely many languages even if all the parameters are bounded by constants. Then we prove that the class VH-FGSLk,Δ(m, s, t, r, w, d) is polynomial-time PAC learnable if all m, s, t, r, w, d, Δ are constants except for k.

Gaze following is the task of estimating where an observer is looking inside a scene. Both the observer and scene information must be learned to determine the gaze directions and gaze points. Recently, many existing works have only focused on scenes or observers. In contrast, revealed frameworks for gaze following are limited. In this paper, a gaze following method using a hybrid transformer is proposed. Based on the conventional method (GazeFollow), we conduct three developments. First, a hybrid transformer is applied for learning head images and gaze positions. Second, the pinball loss function is utilized to control the gaze point error. Finally, a novel ReLU layer with the reborn mechanism (reborn ReLU) is conducted to replace traditional ReLU layers in different network stages. To test the performance of our developments, we train our developed framework with the DL Gaze dataset and evaluate the model on our collected set. Through our experimental results, it can be proven that our framework can achieve outperformance over our referred methods.

This paper proposes a method in calculating the field distribution of the cross section in a transverse electromagnetic (TEM) cell based on the method of finite difference. Besides, E-field uniformity of the cross section is analyzed with the calculation results and the measured field strength. Analysis indicates that theoretical calculation via method proposed in this paper can guide the setup of E-field probes to some extent when it comes to the E-field uniformity analysis in a TEM cell.

To achieve the extreme high data rate and extreme coverage extension requirements of 6G wireless communication, new spectrum in sub-THz (100-300GHz) and non-terrestrial network (NTN) are two of the macro trends of 6G candidate technologies, respectively. However, non-linearity of power amplifiers (PA) is a critical challenge for both sub-THz and NTN. Therefore, high power efficiency (PE) or low peak to average power ratio (PAPR) waveform design becomes one of the most significant 6G research topics. Meanwhile, high spectral efficiency (SE) and low out-of-band emission (OOBE) are still important key performance indicators (KPIs) for 6G waveform design. Single-carrier waveform discrete Fourier transform spreading orthogonal frequency division multiplexing (DFT-s-OFDM) has achieved many research interests due to its high PE, and it has been supported in 5G New Radio (NR) when uplink coverage is limited. So DFT-s-OFDM can be regarded as a candidate waveform for 6G. Many enhancement schemes based on DFT-s-OFDM have been proposed, including null cyclic prefix (NCP)/unique word (UW), frequency-domain spectral shaping (FDSS), and time-domain compression and expansion (TD-CE), etc. However, there is no unified framework to be compatible with all the enhancement schemes. This paper firstly provides a general description of the 6G candidate waveforms based on DFT-s-OFDM enhancement. Secondly, the more flexible TD-CE supporting methods for unified non-orthogonal waveform (uNOW) are proposed and discussed. Thirdly, a unified waveform framework based on DFT-s-OFDM structure is proposed. By designing the pre-processing and post-processing modules before and after DFT in the unified waveform framework, the three technical methods (NCP/UW, FDSS, and TD-CE) can be integrated to improve three KPIs of DFT-s-OFDM simultaneously with high flexibility. Then the implementation complexity of the 6G candidate waveforms are analyzed and compared. Performance of different DFT-s-OFDM enhancement schemes is investigated by link level simulation, which reveals that uNOW can achieve the best PAPR performance among all the 6G candidate waveforms. When considering PA back-off, uNOW can achieve 124% throughput gain compared to traditional DFT-s-OFDM.

This paper proposes an algorithm for estimating the location of wireless access points (APs) in indoor environments to realize smartphone positioning based on Wi-Fi without pre-constructing a database. The proposed method is designed to overcome the main problem of existing positioning methods requiring the advance construction of a database with coordinates or precise AP location measurements. The proposed algorithm constructs a local coordinate system with the first four APs that are activated in turn, and estimates the AP installation location using Wi-Fi round-trip time (RTT) lateration and the ranging results between the APs. The effectiveness of the proposed algorithm is confirmed by conducting experiments in a real indoor environment consisting of two rooms of different sizes to evaluate the positioning performance of the algorithm. The experimental results showed the proposed algorithm using Wi-Fi RTT lateration delivers high smartphone positioning performance without a pre-constructed database or precise AP location measurements.

In this study, a blind carrier frequency offset (CFO) estimation method is proposed using the time-frequency symmetry of the transmitted signals of a weighted Fourier transform (WFrFT) communication system. Blind CFO estimation is achieved by focusing on the property that results in matching the signal waveforms before and after the Fourier transform when the WFrFT parameter is set to a certain value. Numerical simulations confirm that the proposed method is more resistant to Rayleigh fading than the conventional estimation methods.

In this paper, some properties of Boolean functions via the unitary transform and c-correlation functions are presented. Based on the unitary transform, we present two classes of secondary constructions for c-bent4 functions. Also, by using the c-correlation functions, a direct link between c-autocorrelation function and the unitary transform of Boolean functions is provided, and the relationship among c-crosscorrelation functions of arbitrary four Boolean functions can be obtained.

Recent studies in protein structure prediction such as AlphaFold have enabled deep learning to achieve great attention on the Drug-Target Affinity (DTA) task. Most works are dedicated to embed single molecular property and homogeneous information, ignoring the diverse heterogeneous information gains that are contained in the molecules and interactions. Motivated by this, we propose an end-to-end deep learning framework to perform Molecular Heterogeneous features Fusion (MolHF) for DTA prediction on heterogeneity. To address the challenges that biochemical attributes locates in different heterogeneous spaces, we design a Molecular Heterogeneous Information Learning module with multi-strategy learning. Especially, Molecular Heterogeneous Attention Fusion module is present to obtain the gains of molecular heterogeneous features. With these, the diversity of molecular structure information for drugs can be extracted. Extensive experiments on two benchmark datasets show that our method outperforms the baselines in all four metrics. Ablation studies validate the effect of attentive fusion and multi-group of drug heterogeneous features. Visual presentations demonstrate the impact of protein embedding level and the model ability of fitting data. In summary, the diverse gains brought by heterogeneous information contribute to drug-target affinity prediction.

Online social networks have increased their impact on the real world, which motivates information senders to control the propagation process of information to promote particular actions of online users. However, the existing works on information provisioning seem to oversimplify the users' decision-making process that involves information reception, internal actions of social networks, and external actions of social networks. In particular, characterizing the best practices of information provisioning that promotes the users' external actions is a complex task due to the complexity of the propagation process in OSNs, even when the variation of information is limited. Therefore, we propose a new information diffusion model that distinguishes user behaviors inside and outside of OSNs, and formulate an optimization problem to maximize the number of users who take the external actions by providing information over multiple rounds. Also, we define a robust provisioning policy for the problem, which selects a message sequence to maximize the expected number of desired users under the probabilistic uncertainty of OSN settings. Our experiment results infer that there could exist an information provisioning policy that achieves nearly-optimal solutions in different types of OSNs. Furthermore, we empirically demonstrate that the proposed robust policy can be such a universally optimal solution.

To protect user privacy and establish self-information control rights, service providers must notify users of their privacy policies and obtain their consent in advance. The frameworks that impose these requirements are mandatory. Although originally designed to protect user privacy, obtaining user consent in advance has become a mere formality. These problems are induced by the gap between service providers' privacy policies, which prioritize the observance of laws and guidelines, and user expectations which are to easily understand how their data will be handled. To reduce this gap, we construct a tool supporting users in reading privacy policies in Japanese. We designed the tool to present users with separate unique expressions containing relevant information to improve the display format of the privacy policy and render it more comprehensive for Japanese users. To accurately extract the unique expressions from privacy policies, we created training data for machine learning for the constructed tool. The constructed tool provides a summary of privacy policies for users to help them understand the policies of interest. Subsequently, we assess the effectiveness of the constructed tool in experiments and follow-up questionnaires. Our findings reveal that the constructed tool enhances the users' subjective understanding of the services they read about and their awareness of the related risks. We expect that the developed tool will help users better understand the privacy policy content and and make educated decisions based on their understanding of how service providers intend to use their personal data.

For many fields in real life, time series forecasting is essential. Recent studies have shown that Transformer has certain advantages when dealing with such problems, especially when dealing with long sequence time input and long sequence time forecasting problems. In order to improve the efficiency and local stability of Transformer, these studies combine Transformer and CNN with different structures. However, previous time series forecasting network models based on Transformer cannot make full use of CNN, and they have not been used in a better combination of both. In response to this problem in time series forecasting, we propose the time series forecasting algorithm based on convolution Transformer. (1) ES attention mechanism: Combine external attention with traditional self-attention mechanism through the two-branch network, the computational cost of self-attention mechanism is reduced, and the higher forecasting accuracy is obtained. (2) Frequency enhanced block: A Frequency Enhanced Block is added in front of the ESAttention module, which can capture important structures in time series through frequency domain mapping. (3) Causal dilated convolution: The self-attention mechanism module is connected by replacing the traditional standard convolution layer with a causal dilated convolution layer, so that it obtains the receptive field of exponentially growth without increasing the calculation consumption. (4) Multi-layer feature fusion: The outputs of different self-attention mechanism modules are extracted, and the convolutional layers are used to adjust the size of the feature map for the fusion. The more fine-grained feature information is obtained at negligible computational cost. Experiments on real world datasets show that the time series network forecasting model structure proposed in this paper can greatly improve the real-time forecasting performance of the current state-of-the-art Transformer model, and the calculation and memory costs are significantly lower. Compared with previous algorithms, the proposed algorithm has achieved a greater performance improvement in both effectiveness and forecasting accuracy.

The purpose of this study was to develop a practical functional electrical stimulation (FES) controller for joint movements restoration based on an optimal control technique by cascading a linear model predictive control (MPC) and a nonlinear transformation. The cascading configuration was aimed to obtain an FES controller that is able to deal with a nonlinear system. The nonlinear transformation was utilized to transform the linear solution of linear MPC to become a nonlinear solution in form of optimized electrical stimulation intensity. Four different types of nonlinear functions were used to realize the nonlinear transformation. A simple parameter estimation to determine the value of the nonlinear transformation parameter was also developed. The tracking control capability of the proposed controller along with the parameter estimation was examined in controlling the 1-DOF wrist joint movement through computer simulation. The proposed controller was also compared with a fuzzy FES controller. The proposed MPC-FES controller with estimated parameter value worked properly and had a better control accuracy than the fuzzy controller. The parameter estimation was suggested to be useful and effective in practical FES control applications to reduce the time-consuming of determining the parameter value of the proposed controller.

In this paper, we propose an interpretation method on amplitude intensities for response waveforms of backward transient scattered field components for both E- and H-polarizations by a 2-D coated metal cylinder. A time-domain (TD) asymptotic solution, which is referred to as a TD Fourier transform method (TD-FTM), is derived by applying the FTM to a backward transient scattered field expressed by an integral form. The TD-FTM is represented by a combination of a direct geometric optical ray (DGO) and a reflected GO (RGO) series. We use the TD-FTM to derive amplitude intensity ratios (AIRs) between adjacent backward transient scattered field components. By comparing the numerical values of the AIRs with those of the influence factors that compose the AIRs, major factor(s) can be identified, thereby allowing detailed interpretation method on the amplitude intensities for the response waveforms of backward transient scattered field components. The accuracy and practicality of the TD-FTM are evaluated by comparing it with three reference solutions. The effectiveness of an interpretation method on the amplitude intensities for response waveforms of backward transient scattered field components is revealed by identifying major factor(s) affecting the amplitude intensities.

The hardness of the syndrome decoding problem (SDP) is the primary evidence for the security of code-based cryptosystems, which are one of the finalists in a project to standardize post-quantum cryptography conducted by the U.S. National Institute of Standards and Technology (NIST-PQC). Information set decoding (ISD) is a general term for algorithms that solve SDP efficiently. In this paper, we conducted a concrete analysis of the time complexity of the latest ISD algorithms under the limitation of memory using the syndrome decoding estimator proposed by Esser et al. As a result, we present that theoretically nonoptimal ISDs, such as May-Meurer-Thomae (MMT) and May-Ozerov, have lower time complexity than other ISDs in some actual SDP instances. Based on these facts, we further studied the possibility of multiple parallelization for these ISDs and proposed the first GPU algorithm for MMT, the multiparallel MMT algorithm. In the experiments, we show that the multiparallel MMT algorithm is faster than existing ISD algorithms. In addition, we report the first successful attempts to solve the 510-, 530-, 540- and 550-dimensional SDP instances in the Decoding Challenge contest using the multiparallel MMT.