Spiking Neural Networks(SNNs) are a promising paradigm designed to emulate the brain's energy efficient by incorporating the timing of spikes. Conversion is an efficient way to obtain high-performance SNNs from Artificial Neural Networks(ANNs). Existing conversion methods often face a trade-off between accuracy and time steps, which is largely caused by the incomplete release of residual membrane potentials. To minimize the conversion error, this paper proposed a harmonious mathematical property-based neuron, called Harmony Multi-Threshold Neurons (H-MT Neuron), which utilizes multiple spikes to minimize residual membrane potentials. The proposed neuron is further enhanced with an optional effective communication mechanism to achieve more accurate conversion. In addition, we propose a threshold optimization method applicable to a broader range cases of spiking neurons to to find the optimal neuron thresholds. Experiment results demonstrate that our method achieve superior accuracy on ImageNet benchmark datasets while significantly reducing the required time steps and energy consumption.

Mobile app usage behavior reveals human patterns and is crucial for stakeholders, but data collection is costly and raises privacy issues. Data synthesis can address this by generating artificial datasets that mirror real-world data. In this paper, we propose AppGen, an autoregressive generative model designed to generate app usage behavior based on users' mobility trajectories, improving dataset accessibility and quality. Specifically, AppGen employs a probabilistic diffusion model to simulate the stochastic nature of app usage behavior. By utilizing an autoregressive structure, AppGen effectively captures the intricate sequential relationships between different app usage events. Additionally, AppGen leverages latent encoding to extract semantic features from spatio-temporal points, guiding behavior generation. These key designs ensure the generated behaviors are contextually relevant and faithfully represent users' environments and past interactions. Experiments with two real-world datasets show that AppGen outperforms state-of-the-art baselines by over 12% in critical metrics and accurately reflects real-world spatio-temporal patterns. We also test the generated datasets in applications, demonstrating their suitability for downstream tasks by maintaining algorithm accuracy and order.

Simulation-based optimization has emerged as a crucial methodology in the field of mobile network optimization, addressing the need for dynamic and predictive network management. To address the scarcity of open-source mobile network simulators for advanced research, we developed GenNet—a generative AI-driven mobile network simulator. GenNet can create virtual replicas of mobile users, base stations, and wireless environments, utilizing generative AI methods to simulate the behaviors of these entities under various network settings with high accuracy. GenNet features a tailor-made API explicitly designed for reinforcement learning environments, enabling researchers to finely adjust network parameters such as tilts, azimuth, and transmitting power. Extensive experiments have utilized GenNet to benchmark multi-objective optimization algorithms, with a focus on enhancing network coverage, throughput, and energy efficiency, thereby validating its effectiveness as a robust platform for advancing network optimization techniques. Through this innovative tool, we aim to empower researchers and practitioners to identify and implement the most effective approaches for network optimization, paving the way for future advancements in mobile network management.

Mobile app usage data reveal user behavioral characteristics and is crucial for mobile operators for network service optimization, but its data collection is pricey and presents privacy concerns. Data synthesis, fortunately, can tackle this barrier by generating diverse and representative artificial datasets that resemble real-world data. In this paper, we propose SMAUG, a diffusion model-based generative model with large language models (LLMs) designed to generate personalized app usage data based on mobile users' mobility trajectories. To address the data inaccuracy issue brought by the sparsity nature of mobile app usage behavior, SMAUG decomposes the generation process and adopts a hierarchical structure framework to gradually refine the generation from the session level to the specific app level. By encoding spatio-temporal context and applying an attention mechanism, SMAUG effectively represents personalized user representations. Moreover, aiming to extensively explore the semantic information in app usage sessions, SMAUG incorporates LLMs to gain deeper insight into user behavior characteristics revealed in sessions, and also exploits a curriculum representation learning approach based on contrastive learning, exploring session characteristics from elementary to profound. Experiments on two real-world datasets show that SMAUG outperforms existing generative baseline approaches by over 25% under the metrics of RMSE, MAE, CRPS, JSD, M-TV, and Spearmanr. The model has also been successfully deployed to assist network service simulation, demonstrating their suitability for downstream tasks in real-world systems.

Image Difference Captioning (IDC) aims to generate natural language descriptions that highlight subtle differences between two visually similar images.While recent advances leverage pre-trained vision-language models to align fine-grained visual differences with textual semantics, existing supervised approaches often overly focus on dataset-specific language patterns and fail to capture fine-grained and context-aware preferences on IDC, due to limited annotation diversity and a lack of semantically informative negative examples during training, To address these limitations, we propose an adversarial direct preference optimization (ADPO) framework for IDC, which formulates IDC as a preference optimization problem under the Bradley-Terry-Luce model, directly aligning the captioning policy with pairwise difference preferences via Direct Preference Optimization (DPO).To model more accurate and diverse IDC preferences, we introduce an adversarially trained hard negative retriever that selects counterfactual captions, This results in a minimax optimization problem, which we solve via policy-gradient reinforcement learning, enabling the policy and retriever to improve jointly.By dynamically generating semantically challenging negatives, our method reduces reliance on dataset-specific patterns.Experiments on benchmark IDC datasets show that our approach outperforms existing baselines, especially in generating fine-grained and accurate difference descriptions.

With the increasing applications of ultra-high frequency (UHF) radio-frequency identification (RFID) in various fields that require rapid identification of a large number of tags, improving the throughput of RFID systems has become the research focus currently. By modulating tag signals to different Miller-subcarrier frequencies, the frequency division multiple access (FDMA) RFID system with$M$-values of 2 and 6 has been proposed. Furthermore, after analyzing the spectrum of the Miller-coded signal, the tag harmonic signal suppression algorithm, based on the Costas loop, has been proposed, which reconstructs the harmonic interference signal of the first channel and subtracts the interference in the second channel. The suppression performance of the algorithm can reach 14 dB and 11 dB through simulation and experiment. The reader that supports simultaneous query for tags has been designed and developed utilizing the Xilinx XC7Z020 chip and can successfully receive the tag signals in two channels.

Spiking Neural Networks (SNNs) exhibit significant potential due to their low energy consumption. Converting Artificial Neural Networks (ANNs) to SNNs is an efficient way to achieve high-performance SNNs. However, many conversion methods are based on rate coding, which requires numerous spikes and longer time-steps compared to directly trained SNNs, leading to increased energy consumption and latency. This article introduces differential coding for ANN-to-SNN conversion, a novel coding scheme that reduces spike counts and energy consumption by transmitting changes in rate information rather than rates directly, and explores its application across various layers. Additionally, the threshold iteration method is proposed to optimize thresholds based on activation distribution when converting Rectified Linear Units (ReLUs) to spiking neurons. Experimental results on various Convolutional Neural Networks (CNNs) and Transformers demonstrate that the proposed differential coding significantly improves accuracy while reducing energy consumption, particularly when combined with the threshold iteration method, achieving state-of-the-art performance. The source codes of the proposed method are available at https://github.com/h-z-h-cell/ANN-to-SNN-DCGS.

ANN-to-SNN conversion has emerged as a key approach to train Spiking Neural Networks (SNNs), particularly for Transformer architectures, as it maps pre-trained ANN parameters to SNN equivalents without requiring retraining, thereby preserving ANN accuracy while eliminating training costs. Among various coding methods used in ANN-to-SNN conversion, time-to-first-spike (TTFS) coding, which allows each neuron to at most one spike, offers significantly lower energy consumption. However, while previous TTFS-based SNNs have achieved comparable performance with convolutional ANNs, the attention mechanism and nonlinear layers in Transformer architectures remains a challenge by existing SNNs with TTFS coding. This paper proposes a new neuron structure for TTFS coding that expands its representational range and enhances the capability to process nonlinear functions, along with detailed designs of nonlinear neurons for different layers in Transformer. Experimental results on different models demonstrate that our proposed method can achieve high accuracy with significantly lower energy consumption. To the best of our knowledge, this is the first work to focus on converting Transformer to SNN with TTFS coding.

Spiking Neural Networks (SNNs) are distinguished from Artificial Neural Networks (ANNs) for their complex neuronal dynamics and sparse binary activations (spikes) inspired by the biological neural system. Traditional neuron models use iterative step-by-step dynamics, resulting in serial computation and slow training speed of SNNs. Recently, parallelizable spiking neuron models have been proposed to fully utilize the massive parallel computing ability of graphics processing units to accelerate the training of SNNs. However, existing parallelizable spiking neuron models involve dense floating operations and can only achieve high long-term dependencies learning ability with a large order at the cost of huge computational and memory costs. To solve the dilemma of performance and costs, we propose the mul-free channel-wise Parallel Spiking Neuron, which is hardware-friendly and suitable for SNNs’ resource-restricted application scenarios. The proposed neuron imports the channel-wise convolution to enhance the learning ability, induces the sawtooth dilations to reduce the neuron order, and employs the bit-shift operation to avoid multiplications. The algorithm for the design and implementation of acceleration methods is discussed extensively. Our methods are validated in neuromorphic Spiking Heidelberg Digits voices, sequential CIFAR images, and neuromorphic DVS-Lip vision datasets, achieving superior performance over SOTA spiking neurons. Training speed results demonstrate the effectiveness of our acceleration methods, providing a practical reference for future research. Our code is available at Github.

As the use of ultrahigh frequency (UHF) radio-frequency identification (RFID) increases in various fields requiring the rapid identification of a large number of tags, research has shifted toward improving the access capacity of RFID systems. This article proposes a frequency division multiple access (FDMA) extension of conventional time division multiple access (TDMA) RFID systems by modulating tag signals to different Miller-subcarrier frequencies, achieving a theoretical throughput limit value of 0.9135 average successfully read tags per slot, which is 2.48 times that of the usually referred dynamic frame-slotted Aloha algorithm. The power spectral density (PSD) of Miller-modulated subcarrier (MMS) sequences is derived to uncover the tag interference caused by the modulation signal sidelobe power within each subchannel. After that, a successive interference cancellation (SIC) scheme is employed in a four-tag signal reception situation, enhancing the simultaneous tag replies interference suppression and achieving a small performance deterioration if compared with a conventional TDMA system. An experimental analysis is also described to show the feasibility of the proposed FDMA extension of TDMA-based UHF RFID systems.

App usage prediction aims to predict the next app most likely to be used based on historical behaviors, which is beneficial for smartphone system optimization, such as system resource management, battery energy optimization, and user experience enhancement. Existing studies have treated it as a simple time series prediction problem and overlooked the sessionization characteristic of mobile app usage, i.e., neglecting the intent context in which the user interacts with apps. In this paper, we explore the context of user intents and incorporate app sessionization features into prediction models to improve prediction accuracy. Specifically, we first extract the semantic meaning of spatio-temporal contextual information of app usage by constructing an urban knowledge graph. Second, we devise a hypergraph-based embedding model to extract the hyper-relations of intra-session apps. Third, we utilize a self-attention mechanism to fuse intra-session apps’ representations and combine spatio-temporal contextual embedding to form the session representation. We further leverage a transformer for inter-session intent transition modeling to extract users’ dynamic intent (i.e., the semantic meaning of sessions) for app usage. Finally, we jointly fuse dynamic intent and recently used app features using the MLP model for the prediction. The novelty of our method is that we are the first to leverage dynamic hypergraphs for modeling sessionization features, and we model both inter-session and intra-session relations. We evaluate our model based on two real-world datasets collected in Shanghai and Nanchang. In terms of prediction accuracy, mean reciprocal rank, and normalized discounted cumulative gain, our proposed framework outperforms state-of-the-art baselines by more than 30% in the Shanghai dataset and 20% in the Nanchang dataset, respectively.

With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning. However, existing research has primarily focused on text-based algebra problems, neglecting the study of geometry due to the lack of high-quality geometric datasets. To address this gap, this paper introducesAutoGeo, a novel approach for automatically generating mathematical geometric images to fulfill the demand for large-scale and diverse geometric datasets. AutoGeo facilitates the creation ofAutoGeo-100k, an extensive repository comprising 100k high-quality geometry image-text pairs. By leveraging precisely defined geometric clauses, AutoGeo-100k contains a wide variety of geometric shapes, including lines, polygons, circles, and complex spatial relationships, etc. Furthermore, this paper demonstrates the efficacy of AutoGeo-100k in enhancing the performance of multimodal large language models through fine-tuning. Experimental results indicate significant improvements in the model's ability in handling geometric images, as evidenced by enhanced accuracy in tasks such as geometric captioning and mathematical reasoning. This research not only fills a critical gap in the availability of geometric datasets but also paves the way for the advancement of sophisticated AI-driven tools in education and research. Project page:https://autogeo-official.github.io/.

Spiking Neural Networks (SNNs) have received widespread attention in academic communities due to their superior spatio-temporal processing capabilities and energy-efficient characteristics. With further in-depth application in various fields, the vulnerability of SNNs under adversarial attack has become a focus of concern. In this paper, we draw inspiration from two mainstream learning algorithms of SNNs and observe that SNN models reserve both rate and temporal information. To better understand the capabilities of these two types of information, we conduct a quantitative analysis separately for each. In addition, we note that the retention degree of temporal information is related to the parameters and input settings of spiking neurons. Building on these insights, we propose a hybrid adversarial attack based on rate and temporal information (HART), which allows for dynamic adjustment of the rate and temporal attributes. Experimental results demonstrate that compared to previous works, HART attack can achieve significant superiority under different attack scenarios, data types, network architecture, time-steps, and model hyper-parameters. These findings call for further exploration into how both types of information can be effectively utilized to enhance the reliability of SNNs. Code is available at [https://github.com/hzc1208/HART_Attack](https://github.com/hzc1208/HART_Attack).

Spiking Neural Networks (SNNs) have garnered considerable attention due to their energy efficiency and unique biological characteristics. However, the widely adopted Leaky Integrate-and-Fire (LIF) model, as the mainstream neuron model in current SNN research, has been revealed to exhibit significant deficiencies in deep-layer gradient calculation and capturing global information on the time dimension. In this paper, we propose the Learnable Multi-hierarchical (LM-H) model to address these issues by dynamically regulating its membrane-related factors. We point out that the LM-H model fully encompasses the information representation range of the LIF model while offering the flexibility to adjust the extraction ratio between historical and current information. Additionally, we theoretically demonstrate the effectiveness of the LM-H model and the functionality of its internal parameters, and propose a progressive training algorithm tailored specifically for the LM-H model. Furthermore, we devise an efficient training framework for our novel advanced model, encompassing hybrid training and time-slicing online training. Through extensive experiments on various datasets, we validate the remarkable superiority of our model and training algorithm compared to previous state-of-the-art approaches. Code is available at [https://github.com/hzc1208/STBP_LMH](https://github.com/hzc1208/STBP_LMH).

At the age of big data, recommender systems have shown remarkable success as a key means of information filtering in our daily life. Recent years have witnessed the technical development of recommender systems, from perception learning to cognition reasoning which intuitively build the task of recommendation as the procedure of logical reasoning. However, the logical statement in reasoning implicitly admits irrelevance of ordering, even does not consider time information which plays an important role in recommendation. Furthermore, recommendation model incorporated with temporal context would tend to be self-attentive, i.e., automatically focus more (less) on the relevance (irrelevance), respectively.In this paper, we propose a Time-aware Self-Attention with Neural Collaborative Reasoning (TiSANCR) based recommendation model, which integrates temporal patterns and self-attention mechanism into reasoning-based recommendation. Specially, temporal patterns represented by relative time provide context and auxiliary information to characterize the user’s preference in recommendation, while self-attention is leveraged to distill informative patterns and suppress irrelevances. Extensive experiments on benchmark datasets demonstrate that the proposed TiSANCR achieves significant improvement and consistently outperforms the state-of-the-art recommendation methods.

Powered upper limb prostheses offer a particularly interesting case of human-machine interaction, where the user and the robot are physically coupled as an open chain manipulator. The biological and mechanical degrees of freedom (DOF) must collaborate for the user to manipulate objects in the environment. Current state-of-the-art systems use machine learning models to classify electromyogram (EMG) signals into motion intent primitives, allowing users to move the prosthetic joints sequentially at a fixed velocity. This interface is intended to work for simple systems but does not extend well into higher DOF. Consequently, current commercially available systems are limited to 1 or 2 powered DOF. In this paper, we present a semi-autonomous (SA) hybrid gaze-EMG interface that allows users to command the device in task-space instead of joint-space. Target end-effector poses are selected by tracking the user’s gaze vector, and then EMG signals guide the prosthetic along a calculated trajectory towards that pose. To examine how prosthesis interface performance scales with available mechanical DOF, we had 4 subjects complete virtual pick and place tasks with SA and traditional controller interfaces, varying the available DOF in the prosthetic wrist. Our results show that with the SA interface, increased DOF leads to a significant (p≤0.05) reduction in compensatory motion of the upper arm, more effective (p≤0.01) utilization of the increased configuration space, and overall more efficient motion (p≤0.01) than traditional classification based interfaces. These findings indicate that when given SA interfaces, subjects can benefit from fully articulated prosthetic devices, which motivates more clinical research into SA systems and commercial development of higher-DOF devices.

Spiking neural networks (SNNs) show great potential due to their energy efficiency, fast processing capabilities, and robustness. There are two main approaches to constructing SNNs. Direct training methods require much memory, while conversion methods offer a simpler and more efficient option. However, current conversion methods mainly focus on converting convolutional neural networks (CNNs) to SNNs. Converting Transformers to SNN is challenging because of the presence of non-linear modules. In this paper, we propose an Expectation Compensation Module to preserve the accuracy of the conversion. The core idea is to use information from the previous T time-steps to calculate the expected output at time-step T. We also propose a Multi-Threshold Neuron and the corresponding Parallel Parameter normalization to address the challenge of large time steps needed for high accuracy, aiming to reduce network latency and power consumption. Our experimental results demonstrate that our approach achieves state-of-the-art performance. For example, we achieve a top-1 accuracy of 88.60% with only a 1% loss in accuracy using 4 time steps while consuming only 35% of the original power of the Transformer. To our knowledge, this is the first successful Artificial Neural Network (ANN) to SNN conversion for Spiking Transformers that achieves high accuracy, low latency, and low power consumption on complex datasets. The source codes of the proposed method are available at https://github.com/h-z-h-cell/Transformer-to-SNN-ECMT.

Image captured under low-light conditions presents unpleasant artifacts, which debilitate feature extraction performance in upstream visual tasks. Low-light image enhancement (LLIE) aims to improve brightness and contrast, further reducing noise that corrupts the visual quality. Recently, many image restoration methods based on Swin Transformer have been proposed, and impressive performance has been achieved. However, on one hand, trivially employing Swin Transformer for LLIE would expose several artifacts, including over-exposure, brightness imbalance, noise corruption, etc. On the other hand, it is impractical to capture image pairs of low-light images and corresponding ground truth, i.e., well-exposed images in the same visual scene, for model training. In this paper, we propose a dual-branch network based on Swin Transformer, guided by a signal-to-noise ratio prior map which provides the spatial-varying information for LLIE. Moreover, we leverage unsupervised learning to construct the optimization objective based on the Retinex model, to guide the training of the proposed network. Experimental results demonstrate that the proposed model is competitive with the baseline models.

Unraveling the intricate network of associations among microRNAs (miRNAs), genes, and diseases is pivotal for deciphering molecular mechanisms, refining disease diagnosis, and crafting targeted therapies. Computational strategies, leveraging link prediction within biological graphs, present a cost-efficient alternative to high-cost empirical assays. However, while plenty of methods excel at predicting specific associations, such as miRNA-disease associations (MDAs), miRNA-target interactions (MTIs), and disease-gene associations (DGAs), a holistic approach harnessing diverse data sources for multifaceted association prediction remains largely unexplored. The limited availability of high-quality data, as vitro experiments to comprehensively confirm associations are often expensive and time-consuming, results in a sparse and noisy heterogeneous graph, hindering an accurate prediction of these complex associations. To address this challenge, we propose a novel framework called Global-local aware Heterogeneous Graph Contrastive Learning (GlaHGCL). GlaHGCL combines global and local contrastive learning to improve node embeddings in the heterogeneous graph. In particular, global contrastive learning enhances the robustness of node embeddings against noise by aligning global representations of the original graph and its augmented counterpart. Local contrastive learning enforces representation consistency between functionally similar or connected nodes across diverse data sources, effectively leveraging data heterogeneity and mitigating the issue of data scarcity. The refined node representations are applied to downstream tasks, such as MDA, MTI, and DGA prediction. Experiments show GlaHGCL outperforming state-of-the-art methods, and case studies further demonstrate its ability to accurately uncover new associations among miRNAs, genes, and diseases. We have made the datasets and source code publicly available at https://github.com/Sue-syx/GlaHGCL.

Temperature sensing based on emerging techniques, such as the novel electromagnetic resonant unit, has been the vital research direction. However, current works only focused on the initial and principal verifications, and it is far away to the real application. In this article, a temperature sensor based on mercury-inspired electromagnetic resonant unit holding high-$Q$-factor and with complete circuit system is proposed. The excellent properties of mercury, including the liquid-shape, highly conductivity, and high-temperature sensitivity, are utilized to achieve the effective fusion of such liquid material and high-$Q$-factor electromagnetic resonant unit, so as to realize the integrated design of high-precision temperature sensing. Furthermore, four functional circuits, including signal generation, temperature sensing, signal reception, and signal processing, are designed and constructed, and finally an integrated mercury-inspired electromagnetic resonant-unit temperature sensor system with good temperature sensing performances is realized. Experimental results show that the temperature measured by the proposed sensor is highly consistent with the actual temperature values, with sensing sensitivity up to 1459 mV/ °C. Such achieved high-precision temperature sensor system can be further integrated and can open a new way for the high-precision environment temperature monitoring in the Internet of Thing (IoT) area.

Lawyers and judges spend a large amount of time researching the proper legal authority to cite while drafting decisions. In this paper, we develop a citation recommendation tool that can help improve efficiency in the process of opinion drafting. We train four types of machine learning models, including a citation-list based method (collaborative filtering) and three context-based methods (text similarity, BiLSTM and RoBERTa classifiers). Our experiments show that leveraging local textual context improves recommendation, and that deep neural models achieve decent performance. We show that non-deep text-based methods benefit from access to structured case metadata, but deep models only benefit from such access when predicting from context of insufficient length. We also find that, even after extensive training, RoBERTa does not outperform a recurrent neural model, despite its benefits of pretraining. Our behavior analysis of the RoBERTa model further shows that predictive performance is stable across time and citation classes.

Recently how to select seeding users with large impacts in social networks has gained more and more attention in many studies. It has been demonstrated in a number of researches that the seeding users, playing vital roles in social groups, could be exploited to promote the dissemination of popular contents. Nevertheless, the existed algorithms, which are performed on small-scale data sets with limited feature dimensions, mostly base on unconsolidated hypotheses and measurements of data sets. Consequently, their performance and precision cannot be well evaluated and improved. In this paper, we firstly make comprehensive and large-scale measurements on 3.56 TBytes of real data sets related to Device-to-Device (D2D) content sharing activity traces from a popular D2D sharing application (APP). The mobile social networks generated by the offline content deliveries between users are presented and analyzed. Focusing on the seeding users' selection problem in social networks, we propose algorithms of weighted SeedRanks (SRs) to select the seeding users with accuracy. The algorithms are adapted to the parallel computing platform of Apache Spark with high performance. The results of the recurrent experiment on the large-scale D2D data sets prove the efficiency of our algorithms. Finally, we make conclusions and discuss future work.