Multi-Source and Multi-Representation Adaptation for Cross-Domain Electroencephalography Emotion Recognition

Due to the non-invasiveness and high precision of electroencephalography (EEG), the combination of EEG and artificial intelligence (AI) is often used for emotion recognition. However, the internal differences in EEG data have become an obstacle to classification accuracy. To solve this problem, considering labeled data from similar nature but different domains, domain adaptation usually provides an attractive option. Most of the existing researches aggregate the EEG data from different subjects and sessions as a source domain, which ignores the assumption that the source has a certain marginal distribution. Moreover, existing methods often only align the representation distributions extracted from a single structure, and may only contain partial information. Therefore, we propose the multi-source and multi-representation adaptation (MSMRA) for cross-domain EEG emotion recognition, which divides the EEG data from different subjects and sessions into multiple domains and aligns the distribution of multiple representations extracted from a hybrid structure. Two datasets, i.e., SEED and SEED IV, are used to validate the proposed method in cross-session and cross-subject transfer scenarios, experimental results demonstrate the superior performance of our model to state-of-the-art models in most settings.

Unlocking digital archives: cross-disciplinary perspectives on AI and born-digital data

Co-authored by a Computer Scientist and a Digital Humanist, this article examines the challenges faced by cultural heritage institutions in the digital age, which have led to the closure of the vast majority of born-digital archival collections. It focuses particularly on cultural organizations such as libraries, museums and archives, used by historians, literary scholars and other Humanities scholars. Most born-digital records held by cultural organizations are inaccessible due to privacy, copyright, commercial and technical issues. Even when born-digital data are publicly available (as in the case of web archives), users often need to physically travel to repositories such as the British Library or the Bibliothèque Nationale de France to consult web pages. Provided with enough sample data from which to learn and train their models, AI, and more specifically machine learning algorithms, offer the opportunity to improve and ease the access to digital archives by learning to perform complex human tasks. These vary from providing intelligent support for searching the archives to automate tedious and time-consuming tasks. In this article, we focus on sensitivity review as a practical solution to unlock digital archives that would allow archival institutions to make non-sensitive information available. This promise to make archives more accessible does not come free of warnings for potential pitfalls and risks: inherent errors, "black box" approaches that make the algorithm inscrutable, and risks related to bias, fake, or partial information. Our central argument is that AI can deliver its promise to make digital archival collections more accessible, but it also creates new challenges - particularly in terms of ethics. In the conclusion, we insist on the importance of fairness, accountability and transparency in the process of making digital archives more accessible.

Humans depart from optimal computational models of interactive decision-making during competition under partial information

Decision making under uncertainty in multiagent settings is of increasing interest in decision science. The degree to which human agents depart from computationally optimal solutions in socially interactive settings is generally unknown. Such understanding provides insight into how social contexts affect human interaction and the underlying contributions of Theory of Mind. In this paper, we adapt the well-known ‘Tiger Problem’ from artificial-agent research to human participants in solo and interactive settings. Compared to computationally optimal solutions, participants gathered less information before outcome-related decisions when competing than cooperating with others. These departures from optimality were not haphazard but showed evidence of improved performance through learning. Costly errors emerged under conditions of competition, yielding both lower rates of rewarding actions and accuracy in predicting others. Taken together, this work provides a novel approach and insights into studying human social interaction when shared information is partial.

Shortfall Risk Models When Information on Loss Function Is Incomplete

Utility-based shortfall risk measures effectively captures a decision maker's risk attitude on tail losses. In this paper, we consider a situation where the decision maker's risk attitude toward tail losses is ambiguous and introduce a robust version of shortfall risk, which mitigates the risk arising from such ambiguity. Specifically, we use some available partial information or subjective judgement to construct a set of plausible utility-based shortfall risk measures and define a so-called preference robust shortfall risk as through the worst risk that can be measured in this (ambiguity) set. We then apply the robust shortfall risk paradigm to optimal decision-making problems and demonstrate how the latter can be reformulated as tractable convex programs when the underlying exogenous uncertainty is discretely distributed.

Closing a Bitcoin Trade Optimally under Partial Information: Performance Assessment of a Stochastic Disorder Model

The Bitcoin market exhibits characteristics of a market with pricing bubbles. The price is very volatile, and it inherits the risk of quickly increasing to a peak and decreasing from the peak even faster. In this context, it is vital for investors to close their long positions optimally. In this study, we investigate the performance of the partially observable digital-drift model of Ekström and Lindberg and the corresponding optimal exit strategy on a Bitcoin trade. In order to estimate the unknown intensity of the random drift change time, we refer to Bitcoin halving events, which are considered as pivotal events that push the price up. The out-of-sample performance analysis of the model yields returns values ranging between 9% and 1153%. We conclude that the return of the initiated Bitcoin momentum trades heavily depends on the entry date: the earlier we entered, the higher the expected return at the optimal exit time suggested by the model. Overall, to the extent of our analysis, the model provides a supporting framework for exit decisions, but is by far not the ultimate tool to succeed in every trade.

Ciphertext-Policy Attribute-Based Encryption for Cloud Storage: Toward Data Privacy and Authentication in AI-Enabled IoT System

People can store their data on servers in cloud computing and allow public users to access data via data centers. One of the most difficult tasks is to provide security for the access policy of data, which is also needed to be stored at cloud servers. The access structure (policy) itself may reveal partial information about what the ciphertext contains. To provide security for the access policy of data, a number of encryption schemes are available. Among these, CP-ABE (Ciphertext-Policy Attribute-Based Encryption) scheme is very significant because it helps to protect, broadcast, and control the access of information. The access policy that is sent as plaintext in the existing CP-ABE scheme along with a ciphertext may leak user privacy and data privacy. To resolve this problem, we hereby introduce a new technique, which hides the access policy using a hashing algorithm and provides security against insider attack using a signature verification scheme. The proposed system is compared with existing CP-ABE schemes in terms of computation and expressive policies. In addition, we can test the functioning of any access control that could be implemented in the Internet of Things (IoT). Additionally, security against indistinguishable adaptive chosen ciphertext attacks is also analyzed for the proposed work.

Informeasure: an R/Bioconductor package to quantify nonlinear dependence between variables in biological networks from an information theory perspective

Using information measures to infer biological regulatory networks can observe nonlinear relationship between variables, but it is computationally challenging and there is currently no convenient tool available. We here describe an information theory R package named Informeasure that devotes to quantifying nonlinear dependence between variables in biological regulatory networks from an information theory perspective. This package compiles most of the information measures currently available: mutual information, conditional mutual information, interaction information, partial information decomposition and part mutual information. The first estimator is used to infer bivariate networks while the last four estimators are dedicated to analysis of trivariate networks. The base installation of this turn-key package allows users to approach these information measures out of the box. Informeasure is implemented in R program and is available as an R/Bioconductor package at https://bioconductor.org/packages/Informeasure.

Towards Data-Driven Vehicle Estimation for Signalised Intersections in a Partially Connected Environment

Connected vehicles (CVs) have the potential to collect and share information that, if appropriately processed, can be employed for advanced traffic control strategies, rendering infrastructure-based sensing obsolete. However, before we reach a fully connected environment, where all vehicles are CVs, we have to deal with the challenge of incomplete data. In this paper, we develop data-driven methods for the estimation of vehicles approaching a signalised intersection, based on the availability of partial information stemming from an unknown penetration rate of CVs. In particular, we build machine learning models with the aim of capturing the nonlinear relations between the inputs (CV data) and the output (number of non-connected vehicles), which are characterised by highly complex interactions and may be affected by a large number of factors. We show that, in order to train these models, we may use data that can be easily collected with modern technologies. Moreover, we demonstrate that, if the available real data is not deemed sufficient, training can be performed using synthetic data, produced via microscopic simulations calibrated with real data, without a significant loss of performance. Numerical experiments, where the estimation methods are tested using real vehicle data simulating the presence of various penetration rates of CVs, show very good performance of the estimators, making them promising candidates for applications in the near future.

How the value of the environment controls persistence in visual search

Classic foraging theory predicts that humans and animals aim to gain maximum reward per unit time. However, in standard instrumental conditioning tasks individuals adopt an apparently suboptimal strategy: they respond slowly when the expected value is low. This reward-related bias is often explained as reduced motivation in response to low rewards. Here we present evidence this behavior is associated with a complementary increased motivation to search the environment for alternatives. We trained monkeys to search for reward-related visual targets in environments with different values. We found that the reward-related bias scaled with environment value, was consistent with persistent searching after the target was already found, and was associated with increased exploratory gaze to objects in the environment. A novel computational model of foraging suggests that this search strategy could be adaptive in naturalistic settings where both environments and the objects within them provide partial information about hidden, uncertain rewards.