Integrated sensing and communication (ISAC) with orthogonal frequency division multiplexing (OFDM) waveform has been expected to be a key technique in the future 6th generation ( 6 G ) communication networks. In OFDM ISAC systems, joint range-angle estimation (JRAE) of targets is a essential requirement. Current works focus on far-field target sensing, while this paper studies JRAE for both near-field and far-field targets. First, the signal model is established and the Cramér-Rao bounds on JRAE and localization are derived. Then, an auto-paired high-accuracy JRAE method that applies to both near-field and far-field targets is proposed. Specifically, the proposed method consists of two stages. First, it performs frequency smoothing on the observation matrix to obtain multiple observation submatrices. Then, range estimation is performed by using the translational invariance of the submatrices, while angle estimation is achieved by utilizing the orthogonality between the noise subspace and the steering vectors. Under the 5G New Radio standard parameter setup, simulation results demonstrate that the proposed method achieves superior estimation performance, with its root mean square error approaching the root of CRB compared to the conventional methods. Specifically, at a signal-to-noise ratio (SNR) of 0 dB, the proposed method reduces the root mean square error in terms of range, angle and location estimation by 65.8%, 62.8% and 65.9%, respectively, compared to the benchmark schemes.

Orthogonal frequency division multiplexing (OFDM)-based integrated sensing and communication (ISAC) is promising for the future sixth-generation mobile communication systems. The joint sensing of target range and velocity is crucial in OFDM-based ISAC systems. When the targets are highly correlated with similar range and velocity, it is challenging for the conventional two-dimensional subspace-based sensing methods to achieve accurate joint range-velocity estimation (JRVE), particularly in the low signal-to-noise ratio (SNR) region. As such, this paper proposes a high-resolution JRVE method. Specifically, the proposed method first applies equal interval sampling smoothing to the observation signal, introducing ambiguity in range-velocity-induced phase pairs. It then utilizes the translation invariance of the signal subspace to extract these ambiguous phase pairs. Finally, it leverages the orthogonality between the constructed steering vector pair and the noise subspace to resolve the ambiguity and achieve accurate estimation. Under a 5G New Radio parameter setup, simulation results demonstrate that the proposed method significantly outperforms conventional methods in terms of both resolution and accuracy. At an SNR of -10 dB, the proposed method reduces the root mean square error of range and velocity estimation by 83.7 % and 87.3 %, respectively, compared to the benchmark scheme, while its computational cost is less than 50 % of that of the benchmark.

Integrated sensing and communication (ISAC) utilizing orthogonal frequency division multiplexing (OFDM) wave-forms is emerging as a critical technology for forthcoming sixth-generation mobile communication networks. The joint sensing of target range, velocity and azimuth is essential for OFDM-based ISAC systems. When the targets are highly correlated with similar range, velocity and azimuth, it is challenging for the conventional three dimensional subspace-based sensing methods to achieve accurate joint range-velocity-azimuth estimation (JRVAE), particularly in the low signal-to-noise ratio (SNR) region. Thus, this paper focuses on high-resolution JRVAE for highly correlated targets. First, a signal model is established, and the Cramér–Rao bounds for JRVAE are derived, considering communication symbols belonging to an arbitrary-order quadrature amplitude modulation constellation. Then, a high-resolution JRVAE method is proposed. Specifically, it first performs equal interval sampling smoothing on the observation signal, resulting in ambiguity in range-velocity-azimuth-induced phases, then uses the translation invariance of the signal subspace to extract the ambiguous phases, finally utilizes the orthogonality between the constructed steering vector pair and the corresponding noise subspaces to resolve ambiguity and obtaining accurate estimation. With 5G New Radio parameters setup, simulation results shows that the proposed method achieves higher resolution and accuracy compared to the conventional methods. At an SNR of -10 dB, the proposed method reduces the root mean square error in range, velocity, and azimuth by 76.0%, 82.7%, and 73.2%, respectively, compared to the benchmark scheme, while its computation cost is less than 1/3 of that of the benchmark.

Intelligent control has become an important research direction of a combine harvester. However, the impact of cleaning control parameters in rice–wheat combine harvesters on cleaning loss rate and impurity rate often tends to be contradictory. In this paper, an intelligent controlling model based on multi-objective optimization particle swarm (MOPSO) was constructed to solve this problem. The control model can real-time monitor the cleaning performance such as the cleaning loss rate and impurity rate and regulate the cleaning operation conditions such as the angle of the air distributor plate, the opening of the upper sieve and the fan speed. The field operation experiment of 10[Formula: see text]kg feeding rice–wheat combine harvester proves that the control model based on MOPSO is more effective than the model based on fuzzy control.

Orthogonal frequency division multiplexing (OFDM)-based integrated sensing and communication (ISAC) is promising for future sixth-generation mobile communication systems. For OFDM-based ISAC systems, it is important to accurately sense the target’s parameters. This paper studies the three-dimensional joint estimation (3DJE) of range, velocity, and azimuth for OFDM-based ISAC systems with multiple receive antennas. First, we establish the signal model and derive the Cramér–Rao bounds (CRBs) on the 3DJE. CRBs are widely used benchmarks that provide the theoretical lower bounds of the variances for unbiased estimation. Furthermore, an auto-paired super-resolution 3DJE algorithm is proposed by exploiting the reconstructed observation sub-signal’s translational invariance property in the delay, Doppler, and angle domains. Finally, with the 5G New Radio parameter setup, simulation results show that the proposed algorithm achieves better estimation performance and its root mean square error is closer to the square root of CRBs than existing methods.

In Taobao, the largest e-commerce platform in China, billions of items are provided and typically displayed with their images.For better user experience and business effectiveness, Click Through Rate (CTR) prediction in online advertising system exploits abundant user historical behaviors to identify whether a user is interested in a candidate ad. Enhancing behavior representations with user behavior images will help understand user's visual preference and improve the accuracy of CTR prediction greatly. So we propose to model user preference jointly with user behavior ID features and behavior images. However, training with user behavior images brings tens to hundreds of images in one sample, giving rise to a great challenge in both communication and computation. To handle these challenges, we propose a novel and efficient distributed machine learning paradigm called Advanced Model Server (AMS). With the well-known Parameter Server (PS) framework, each server node handles a separate part of parameters and updates them independently. AMS goes beyond this and is designed to be capable of learning a unified image descriptor model shared by all server nodes which embeds large images into low dimensional high level features before transmitting images to worker nodes. AMS thus dramatically reduces the communication load and enables the arduous joint training process. Based on AMS, the methods of effectively combining the images and ID features are carefully studied, and then we propose a Deep Image CTR Model. Our approach is shown to achieve significant improvements in both online and offline evaluations, and has been deployed in Taobao display advertising system serving the main traffic.

Estimating post-click conversion rate (CVR) accurately is crucial for ranking systems in industrial applications such as recommendation and advertising. Conventional CVR modeling applies popular deep learning methods and achieves state-of-the-art performance. However it encounters several task-specific problems in practice, making CVR modeling challenging. For example, conventional CVR models are trained with samples of clicked impressions while utilized to make inference on the entire space with samples of all impressions. This causes a sample selection bias problem. Besides, there exists an extreme data sparsity problem, making the model fitting rather difficult. In this paper, we model CVR in a brand-new perspective by making good use of sequential pattern of user actions, i.e., impression -> click -> conversion. The proposed Entire Space Multi-task Model (ESMM) can eliminate the two problems simultaneously by i) modeling CVR directly over the entire space, ii) employing a feature representation transfer learning strategy. Experiments on dataset gathered from Taobao's recommender system demonstrate that ESMM significantly outperforms competitive methods. We also release a sampling version of this dataset to enable future research. To the best of our knowledge, this is the first public dataset which contains samples with sequential dependence of click and conversion labels for CVR modeling.

Nowadays proteomics becomes more and more popular in life science. Protein quantification, especially based on mass spectrometry (short for MS) method, is perceived as an essential part of research on proteomics. There have been some algorithms and software for protein quantification based on MS. But they have difficulties on portability, applicability and longtime running. To solve these problems, we developed a new domestic parallel software package called QuantWiz for high performance liquid chromatography (short for LC)-MS-based label-free protein quantification. In this paper, we described the framework design and prototype development of this high performance software package firstly. Also, user interface developed for the visualization of QuantWiz is introduced. Finally, we showed implementation of the parallelization version and performance of some experiments on this software package.