Search

Complex tasks in the real world involve different modal models, such as visual question answering (VQA). However, traditional multimodal learning requires a large amount of aligned data, such as image text pairs, and constructing a large amount of training data is a challenge for multimodal learning. Therefore, we propose VL-Few, which is a simple and effective method to solve the multimodal few-shot problem. VL-Few (1) proposes the modal alignment, which aligns visual features into language space through a lightweight model network and improves the multimodal understanding ability of the model; (2) adopts few-shot meta learning in the multimodal problem, which constructs a few-shot meta task pool to improve the generalization ability of the model; (3) proposes semantic alignment to enhance the semantic understanding ability of the model for the task, context, and demonstration; (4) proposes task alignment that constructs training data into the target task form and improves the task understanding ability of the model; (5) proposes generation alignment, which adopts the token-level training and multitask fusion loss to improve the generation ability of the model. Our experimental results show the effectiveness of VL-Few for multimodal few-shot problems. [ABSTRACT FROM AUTHOR]

Training large-scale models needs big data. However, the few-shot problem is difficult to resolve due to inadequate training data. It is valuable to use only a few training samples to perform the task, such as using big data for application scenarios due to cost and resource problems. So, to tackle this problem, we present a simple and efficient method, contrastive label generation with knowledge for few-shot learning (CLG). Specifically, we: (1) Propose contrastive label generation to align the label with data input and enhance feature representations; (2) Propose a label knowledge filter to avoid noise during injection of the explicit knowledge into the data and label; (3) Employ label logits mask to simplify the task; (4) Employ multi-task fusion loss to learn different perspectives from the training set. The experiments demonstrate that CLG achieves an accuracy of 59.237%, which is more than about 3% in comparison with the best baseline. It shows that CLG obtains better features and gives the model more information about the input sentences to improve the classification ability. [ABSTRACT FROM AUTHOR]

Multimodal learning is a promising area in artificial intelligence (AI) that can make the model understand different kinds of data. Existing works are trying to re-train a new model based on pre-trained models that requires much data, computation power, and time. However, it is difficult to achieve in low-resource or small-sample situations. Therefore, we propose VL-Meta, Vision Language Models for Multimodal Meta Learning. It (1) presents the vision-language mapper and multimodal fusion mapper, which are light model structures, to use the existing pre-trained models to make models understand images to language feature space and save training data, computation power, and time; (2) constructs the meta-task pool that can only use a small amount of data to construct enough training data and improve the generalization of the model to learn the data knowledge and task knowledge; (3) proposes the token-level training that can align inputs with the outputs during training to improve the model performance; and (4) adopts the multi-task fusion loss to learn the different abilities for the models. It achieves a good performance on the Visual Question Answering (VQA) task, which shows the feasibility and effectiveness of the model. This solution can help blind or visually impaired individuals obtain visual information. [ABSTRACT FROM AUTHOR]

With the application of graph neural network (GNN) in the communication physical layer, GNN-based channel decoding algorithms have become a research hotspot. Compared with traditional decoding algorithms, GNN-based channel decoding algorithms have a better performance. GNN has good stability and can handle large-scale problems; GNN has good inheritance and can generalize to different network settings. Compared with deep learning-based channel decoding algorithms, GNN-based channel decoding algorithms avoid a large number of multiplications between learning weights and messages. However, the aggregation edges and nodes for GNN require many parameters, which requires a large amount of memory storage resources. In this work, we propose GNN-based channel decoding algorithms with shared parameters, called shared graph neural network (SGNN). For BCH codes and LDPC codes, the SGNN decoding algorithm only needs a quarter or half of the parameters, while achieving a slightly degraded bit error ratio (BER) performance. [ABSTRACT FROM AUTHOR]

Channel neural decoding is very promising as it outperforms the traditional channel decoding algorithms. Unfortunately, it still faces the disadvantage of high computational complexity and storage complexity compared with the traditional decoding algorithms. In this paper, we propose that low rank decomposition techniques based on tensor train decomposition and tensor ring decomposition can be utilized in neural offset min-sum (NOMS) and neural scale min-sim (NSMS) decoding algorithms. The experiment results show that the proposed two algorithms achieve near state-of-the-art performance with low complexity. [ABSTRACT FROM AUTHOR]

In this letter, reconfigurable intelligent surface (RIS) is studied from an electronic device reliability perspective. Runtimes and lifetimes of the RIS are introduced for the first time as impairment factors that degrade the system performance. In particular, Weibull distributions are used to model the runtime‐related hardware aging (HA) effect on the RIS at first. Then, a practical RIS‐assisted system model with phase‐dependent amplitude variations, residual hardware impairments, and HA effects, is obtained. Besides, closed‐form expressions of the received signal power and spectral efficiency for the proposed system are also derived. Analytical and numerical evaluations reveal that the HA effect on the RIS is the major impairment factor when the runtime is beyond the lifetime of the RIS. [ABSTRACT FROM AUTHOR]

A novel single-carrier-based space-time code construction scheme to exploit the advantages of a frequency-selective fading channel is investigated in this paper. The proposed construction scheme is based on multiplexing independent streams of phase-rotated space-time codes in a time-interleaved fashion. The advantage of such design is that it guarantees full space-time-multipath diversity by using traditional space-time codes or MIMO signaling schemes originally designed for flat fading channels as the constituent codes. Another advantage is that this approach incurs no loss in bandwidth efficiency and it alleviates the problem of high PAPR in OFDM-based space-time codes. By employing random or algebraic rotations, the design is potentially suitable for any number of transmit antennas or multipaths. The simulation results indicate that full space-time-multipath diversity is attained using this new approach, and comparisons with some existing space-time codes designed for frequency-selective channels are made to show its performance advantage. [ABSTRACT FROM AUTHOR]

Reconfigurable intelligent surface (RIS) has been envisioned as one of the promising solutions for enhancing signal transmissions in high-speed communications (HSC). In this paper, we present a time-varying channel model with distance-dependent Rician factors for the RIS-assisted HSC. Our model not only contains Rayleigh components and Doppler shift (DS) terms but also distance-dependent Rician factors, for characterizing time-varying features. In particular, we show that when the vehicle is far from the base station and the RIS, the channel contains only Rayleigh fading. However, when they are close enough, the channel can be considered as a light-of-sight channel. Based on the proposed model, it is proven that using RIS phase shift optimization, the DS of the cascaded links can be aligned with the DS of the direct link; and if the direct link is blocked, the DS can be removed entirely. Furthermore, we derive the closed-form expressions for the ergodic spectral efficiency and the outage probability of the proposed system. Besides, it is observed that the deployment strategy also affects the system performance. Simulation results validate all analyses. [ABSTRACT FROM AUTHOR]

Cognitive Radio (CR) is a practical technique for overcoming spectrum inefficiencies by sensing and utilizing spectrum holes over a wide spectrum. In particular, cooperative spectrum sensing (CSS) determines the state of primary users (PUs) by cooperating with multiple secondary users (SUs) distributed around a Cognitive Radio Network (CRN), further overcoming various noise and fading issues in the radio environment. But it's still challenging to balance energy efficiency and good sensing performances in the existing CSS system, especially when the CRN consists of battery-limited sensors. This article investigates the application of machine learning technologies for cooperative spectrum sensing, especially through solving a multi-dimensional optimization that cannot be readily addressed by traditional approaches. Specifically, we develop a neural network, which involves parameters that are integral to the CSS performance, including a device sleeping rate for each sensor and thresholds used in the energy detection method, and a customized loss function based on the energy consumption of the CSS system and multiple penalty terms reflecting the system requirements. Using this formulation, energy consumption is to be minimized with the guarantee of reaching a certain probability of false alarm and detection in the CSS system. With the proposed method, comparison studies under different hard fusion rules ('OR' and 'AND') demonstrate its effectiveness in improving the CSS system performances, as well as its robustness in the face of changing global requirements. This paper also suggests the combination of the traditional and the proposed scheme to circumvent the respective inherent pitfalls of neural networks and the traditional semi-analytic methods. [ABSTRACT FROM AUTHOR]

In this paper, we consider a multiple reconfigurable intelligent surface (RIS)-assisted system using positioning information (PI) to explore the potential of Doppler effect mitigation and spectral efficiency (SE) enhancement in high-speed communications (HSC) in the presence of hardware impairments (HWI). In particular, we first present a general multi-RIS-assisted system model for HSC with HWI. Then, based on PI, different phase shift optimization strategies are designed and compared for maximizing SE, eliminating Doppler spread, and maintaining a very low delay spread. Moreover, we compare the performance of different numbers of RISs with HWI in terms of SE and delay spread. Finally, we extend our channel model from line-of-sight to the Rician channel to demonstrate the effectiveness and robustness of our proposed scheme. Numerical results reveal that the HWI of RISs increases the delay spread, but has no impact on Doppler shift and spread. Additionally, the multiple RIS system not only suffers a more severe delay spread, but is limited in SE due to the HWI. When the number of RISs increases from 2 to 16, the range of average spectral efficiency and delay spread are from 4 to 4.6 Bit/s/Hz and from 0.7 μs to 2.5 μs, respectively. In contrast to conventional RIS-assisted systems that require channel estimation, the proposed PI-based RIS system offers simplicity without compromising effectiveness and robustness in both SE enhancement and Doppler mitigation. [ABSTRACT FROM AUTHOR]

A novel spectrum sensing (SS) technique based on the higher order statistics (HOS) of spatial samples, obtained through a large receive antenna array, is proposed. Unlike conventional SS schemes, our approach, relying mainly on large number of spatial samples, exploits the spatial properties of the primary user’s signals and differentiates them from the Gaussian noises, white or colored, across different antennas. The novelty of our approach lies in treating the spatial samples as though they are the time-domain samples of a non-stationary random process (NSRP). This, in turn, enables the application of HOS-based detection of NSRP while taking advantage of its asymptotic properties as the number of antennas grows large. Simulation results show that, over one time instant, the proposed method is able to detect primary signals under correlated Gaussian noise and is superior to existing approaches in terms of its robustness against any variation of the correlation coefficient of the noise. [ABSTRACT FROM AUTHOR]

In this paper, we consider the joint power and modulation optimization in two-user non-orthogonal multiple access (NOMA) channels based on error-rate performance criterion and finite-alphabet inputs. Specifically, with joint maximum-likelihood detection being employed at each user's receiver, the users’ transmission power levels are jointly determined with the 4-QAM constellation of one of the users being rotated such that the probability of dominant pairwise error event in the NOMA channel is minimized. Toward solving the joint power and modulation problem, our results are twofold. First, with $M$ antennas at the receiver, closed-form expressions for the optimal angles as a function of $M$ , the channel coefficients, and the users’ power levels are derived. Second, closed-form expressions are derived for the joint power allocation with optimal rotation by casting the joint optimization as a piecewise convex optimization problem over its sub-domains. Using the proposed joint optimization, the error-rate performance of NOMA improves significantly and it outperforms traditional NOMA power allocation methods for the selected transmission rates. The proposed approach thus represents a rather distinct approach in NOMA optimization, and it is applicable in the uplink NOMA where users share the same time/frequency channel or in the downlink NOMA where users are multiplexed in the power domain. [ABSTRACT FROM AUTHOR]

Myelination is dependent on complex reciprocal interactions between the Schwann cell (SC) and axon. Recent evidence suggests that the SC-axon interface represents a membrane specialization essential for myelination; however, the manner in which this polarized-apical domain is generated remains a mystery. The cell adhesion molecule N-cadherin is enriched at the SC-axon interface and colocalizes with the polarity protein Par-3. The asymmetric localization is induced on SC-SC and SC-axon contact. Knockdown of N-cadherin in SCs cocultured with DRG neurons disrupts Par-3 localization and delays the initiation of myelination. However, knockdown or overexpression of neuronal N-cadherin does not influence the distribution of Par-3 or myelination, suggesting that homotypic interactions between SC and axonal N-cadherin are not essential for the events surrounding myelination. To further investigate the role of N-cadherin, mice displaying SC-specific gene ablation of N-cadherin were generated and characterized. Surprisingly, myelination is only slightly delayed, and mice are viable without any detectable myelination defects. β-Catenin, a downstream effector of N-cadherin, colocalizes and coimmuno precipitates with N-cadherin on the initiation of myelination. To determine whether β-catenin mediates compensation on N-cadherin deletion, SC-specific gene ablation of β-catenin was generated and characterized. Consistent with our hypothesis, myelination is more severely delayed than when manipulating N-cadherin alone, but without any defect to the myelin sheath. Together, our results suggest that N-cadherin interacts with β-catenin in establishing SC polarity and the timely initiation of myelination, but they are nonessential components for the formation and maturation of the myelin sheath. [ABSTRACT FROM AUTHOR]

The neurotrophin brain-derived neurotrophic factor (BDNF) inhibits Schwann cell (SC) migration and promotes myelination via the p75 neurotrophin receptor (NTR). Despite these recent findings, the expression, localization, and mechanism of BDNF action has yet to be determined. Here we demonstrate that the sensory neurons of the dorsal root ganglion (DRG) are a major source of BDNF during postnatal development. The expression of BDNF is initially elevated before myelination and decreases dramatically after the onset of myelination. BDNF expression is controlled in part by transcriptional regulation and the increased expression of the truncated TrkB receptor on SCs. To investigate the possible mechanism of BDNF transport and release, multicompartment Campenot chambers were used. DRG neurons transported and secreted endogenous BDNF along the surface of axons in anterograde fashion. In an attempt to enhance myelination by SCs, DRG neurons were transduced with an adenovirus to overexpress BDNF. BDNF was transported and secreted along the axons and enhanced myelination when compared with control cocultures. Together, the events surrounding the expression, localization, and mechanism of BDNF action in DRG neurons may hint at potential therapeutic implications to efficiently promote remyelination. [ABSTRACT FROM AUTHOR]

The formation of myelin is dependent on a reciprocal and intimate relationship between neurons and the myelin-forming glia. Recently, the neurotrophin family of growth factors has been shown to regulate the complex cell–cell interactions that control myelination. Neurotrophins and their receptors influence myelin formation via two distinct mechanisms, either by acting on the neurons, changing the axonal signals that control myelination, or by acting directly on the myelin-forming glia. In this review, we will discuss research highlighting the ability of neurotrophins to both promote and inhibit the myelination process. As reflected in the work presented here, these effects are dependent on a delicate balance of which neurotrophins are expressed, and what receptors are activated. Additionally, we examine an emerging model in which the growth factors that promote the early survival and differentiation of particular sets of neurons later play important roles as key regulators in glial development. Characterizing the temporal expression and the cellular targets of neurotrophins, both during development and after injury, represents a pivotal step in developing a greater understanding of the myelination process, contributing to the development of effective treatments for demyelinating conditions. We conclude this review by discussing the potential for neurotrophins as therapeutics in the quest for remyelination. [ABSTRACT FROM AUTHOR]

Fluorescence digital imaging microscopy was used to develop a method that allows the continuous monitoring and quantitative measurement of a single myelin internode throughout its development. Using this technique, steroid hormones such as progesterone and dexamethasone were shown to reduce the time required for the initiation and to regulate the rate of myelin synthesis. Progesterone was capable of increasing the rate of myelin synthesis in Schwann cell/neuronal co-cultures in a dose-dependent manner. RT-PCR and in situ hydridization studies revealed that the mRNAs for P450scc and 3&#03B2;-hydroxysteroid dehydrogenase, the enzymes involved in progesterone biosynthesis, were induced at the onset of myelin synthesis. The progesterone receptor protein translocated into the nucleus of the neurons during myelin synthesis, suggesting that progesterone could also be affecting neuronal gene expression. Changes in gene expression caused by progesterone are being examined to identify additional factors that may control myelin formation. [ABSTRACT FROM AUTHOR]

Proposes an interference-resistant modulation (IRM) to improve performance without coding nor bandwidth expansion. Discussion on the system model; Design criteria of IRM; Construction of rotated constellations.