Auto-encoding GPS data to reveal individual and collective behaviour

We propose an innovative and generic methodology to analyse individual and collective behaviour through individual trajectory data. The work is motivated by the analysis of GPS trajectories of fishing vessels collected from regulatory tracking data in the context of marine biodiversity conservation and ecosystem-based fisheries management. We build a low-dimensional latent representation of trajectories using convolutional neural networks as non-linear mapping. This is done by training a conditional variational auto-encoder taking into account covariates. The posterior distributions of the latent representations can be linked to the characteristics of the actual trajectories. The latent distributions of the trajectories are compared with the Bhattacharyya coefficient, which is well-suited for comparing distributions. Using this coefficient, we analyse the variation of the individual behaviour of each vessel during time. For collective behaviour analysis, we build proximity graphs and use an extension of the stochastic block model for multiple networks. This model results in a clustering of the individuals based on their set of trajectories. The application to French fishing vessels enables us to obtain groups of vessels whose individual and collective behaviours exhibit spatio-temporal patterns over the period 2014-2018.

Towards Redundancy-Free Sub-networks in Continual Learning

Catastrophic Forgetting (CF) is a prominent issue in continual learning. Parameter isolation addresses this challenge by masking a sub-network for each task to mitigate interference with old tasks. However, these sub-networks are constructed relying on weight magnitude, which does not necessarily correspond to the importance of weights, resulting in maintaining unimportant weights and constructing redundant sub-networks. To overcome this limitation, inspired by information bottleneck, which removes redundancy between adjacent network layers, we propose \textbf{\underline{I}nformation \underline{B}ottleneck \underline{M}asked sub-network (IBM)} to eliminate redundancy within sub-networks. Specifically, IBM accumulates valuable information into essential weights to construct redundancy-free sub-networks, not only effectively mitigating CF by freezing the sub-networks but also facilitating new tasks training through the transfer of valuable knowledge. Additionally, IBM decomposes hidden representations to automate the construction process and make it flexible. Extensive experiments demonstrate that IBM consistently outperforms state-of-the-art methods. Notably, IBM surpasses the state-of-the-art parameter isolation method with a 70\% reduction in the number of parameters within sub-networks and an 80\% decrease in training time.

Beamforming Design for the Distributed RISs-aided THz Communications with Double-Layer True Time Delays

In this paper, we investigate the reconfigurable intelligent surface (RIS)-aided terahertz (THz) communication system with the sparse radio frequency chains antenna structure at the base station (BS). To overcome the beam split of the BS, different from the conventional single-layer true-time-delay (TTD) scheme, we propose a double-layer TTD scheme that can effectively reduce the number of large-range delay devices, which involve additional insertion loss and amplification circuitry. Next, we analyze the system performance under the proposed double-layer TTD scheme. To relieve the beam split of the RIS, we consider multiple distributed RISs to replace an ultra-large size RIS. Based on this, we formulate an achievable rate maximization problem for the distributed RISs-aided THz communications via jointly optimizing the hybrid analog/digital beamforming, time delays of the double-layer TTD network and reflection coefficients of RISs. Considering the practical hardware limitation, the finite-resolution phase shift, time delay and reflection phase are constrained. To solve the formulated problem, we first design an analog beamforming scheme including optimizing phase shift and time delay based on the RISs' locations. Then, an alternatively optimization algorithm is proposed to obtain the digital beamforming and reflection coefficients based on the minimum mean square error and coordinate update techniques. Finally, simulation results show the effectiveness of the proposed scheme.

Individualized Dynamic Model for Multi-resolutional Data

Mobile health has emerged as a major success in tracking individual health status, due to the popularity and power of smartphones and wearable devices. This has also brought great challenges in handling heterogeneous, multi-resolution data which arise ubiquitously in mobile health due to irregular multivariate measurements collected from individuals. In this paper, we propose an individualized dynamic latent factor model for irregular multi-resolution time series data to interpolate unsampled measurements of time series with low resolution. One major advantage of the proposed method is the capability to integrate multiple irregular time series and multiple subjects by mapping the multi-resolution data to the latent space. In addition, the proposed individualized dynamic latent factor model is applicable to capturing heterogeneous longitudinal information through individualized dynamic latent factors. In theory, we provide the integrated interpolation error bound of the proposed estimator and derive the convergence rate with B-spline approximation methods. Both the simulation studies and the application to smartwatch data demonstrate the superior performance of the proposed method compared to existing methods.

Words, Subwords, and Morphemes: What Really Matters in the Surprisal-Reading Time Relationship?

An important assumption that comes with using LLMs on psycholinguistic data has gone unverified. LLM-based predictions are based on subword tokenization, not decomposition of words into morphemes. Does that matter? We carefully test this by comparing surprisal estimates using orthographic, morphological, and BPE tokenization against reading time data. Our results replicate previous findings and provide evidence that in the aggregate, predictions using BPE tokenization do not suffer relative to morphological and orthographic segmentation. However, a finer-grained analysis points to potential issues with relying on BPE-based tokenization, as well as providing promising results involving morphologically-aware surprisal estimates and suggesting a new method for evaluating morphological prediction.

Enhanced MIMO-DCT-OFDM System Using Cosine Domain Equalizer

Discrete Cosine Transform (DCT) can be used instead of conventional Discrete Fourier Transform (DFT) for the Orthogonal Frequency Division Multiplexing (OFDM) construction, which offers many advantages. In this paper, the Multiple-Input-Multiple-Output (MIMO) DCT-OFDM is enhanced using a proposed Cosine Domain Equalizer (CDE) instead of a Frequency Domain Equalizer (FDE). The results are evaluated through the Rayleigh fading channel with Co-Carrier Frequency Offset (Co-CFO) of different MIMO configurations. The average bit error probability and the simulated time of the proposed scheme and the conventional one is compared, which indicates the importance of the proposed scheme. Also, a closed formula for the number of arithmetic operations of the proposed equalizer is developed. The proposed equalizer gives a simulation time reduction of about 81.21%, 83.74% compared to that of the conventional LZF-FDE, and LMMSE-FDE, respectively for the case of 4x4 configuration.

Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies

Forecasting models for systematic trading strategies do not adapt quickly when financial market conditions change, as was seen in the advent of the COVID-19 pandemic in 2020, when market conditions changed dramatically causing many forecasting models to take loss-making positions. To deal with such situations, we propose a novel time-series trend-following forecaster that is able to quickly adapt to new market conditions, referred to as regimes. We leverage recent developments from the deep learning community and use few-shot learning. We propose the Cross Attentive Time-Series Trend Network - X-Trend - which takes positions attending over a context set of financial time-series regimes. X-Trend transfers trends from similar patterns in the context set to make predictions and take positions for a new distinct target regime. X-Trend is able to quickly adapt to new financial regimes with a Sharpe ratio increase of 18.9% over a neural forecaster and 10-fold over a conventional Time-series Momentum strategy during the turbulent market period from 2018 to 2023. Our strategy recovers twice as quickly from the COVID-19 drawdown compared to the neural-forecaster. X-Trend can also take zero-shot positions on novel unseen financial assets obtaining a 5-fold Sharpe ratio increase versus a neural time-series trend forecaster over the same period. X-Trend both forecasts next-day prices and outputs a trading signal. Furthermore, the cross-attention mechanism allows us to interpret the relationship between forecasts and patterns in the context set.

Dynamic interactive group decision making method on two-dimensional language

The language evaluation information of the interactive group decision method at present is based on the one-dimension language variable. At the same time, multi-attribute group decision making method based on two-dimension linguistic information only use single-stage and static evaluation method. In this paper, we propose a dynamic group decision making method based on two-dimension linguistic information, combining dynamic interactive group decision making methods with two-dimensional language evaluation information The method first use Two-Dimensional Uncertain Linguistic Generalized Weighted Aggregation (DULGWA) Operators to aggregate the preference information of each decision maker, then adopting dynamic information entropy method to obtain weights of attributes at each stage. Finally we propose the group consistency index to quantify the termination conditions of group interaction. One example is given to verify the developed approach and to demonstrate its effectiveness

A transductive few-shot learning approach for classification of digital histopathological slides from liver cancer

This paper presents a new approach for classifying 2D histopathology patches using few-shot learning. The method is designed to tackle a significant challenge in histopathology, which is the limited availability of labeled data. By applying a sliding window technique to histopathology slides, we illustrate the practical benefits of transductive learning (i.e., making joint predictions on patches) to achieve consistent and accurate classification. Our approach involves an optimization-based strategy that actively penalizes the prediction of a large number of distinct classes within each window. We conducted experiments on histopathological data to classify tissue classes in digital slides of liver cancer, specifically hepatocellular carcinoma. The initial results show the effectiveness of our method and its potential to enhance the process of automated cancer diagnosis and treatment, all while reducing the time and effort required for expert annotation.

Threat-Based Resource Allocation Strategy for Target Tracking in a Cognitive Radar Network

Cognitive radar is developed to utilize the feedback of its operating environment obtained from a beam to make resource allocation decisions by solving optimization problems. Previous works focused on target tracking accuracy by designing an evaluation metric for an optimization problem. However, in a real combat situation, not only the tracking performance of the target but also its operational perspective should be considered. In this study, the usage of threats in the allocation of radar resource is proposed for a cognitive radar framework. Resource allocation regarding radar dwell time is considered to reflect the operational importance of target effects. The dwell time allocation problem is solved using a Second-Order Cone Program (SOCP). Numerical simulations are performed to verify the effectiveness of the proposed framework.