Article presents research that creates an automatic repetition counting system that is flexible enough to measure multiple distinct and repeating movements during physical therapy without being trained on the specific motion.

Article presents a new benchmark for natural language inference in which negation plays a critical role and shows that state-of-the-art transformers struggle making inference judgments with the new pairs.

Article proposes a novel Bayesian method, named BAM, for simultaneously partitioning Single Nucleotide Polymorphisms (SNPs) into Linkage Disequilibrium(LD)-blocks and detecting genome-wide multi-locus epistatic interactions that are associated with multiple diseases. Experimental results on the simulated datasets demonstrate that BAM is powerful and efficient.

This article aims to generate all theorems of a given size in the implicational fragment of propositional intuitionistic linear logic. It was presented at the 36th International Conference on Logic Programming (ICLP).

Article addresses the processing of negation in Spanish by presenting a machine learning system that processes negation in Spanish and providing a qualitative error analysis aimed at understanding the limitations of the system and showing which negation cues and scopes are straightforward to predict automatically, and which ones are challenging.

Article presents research determining event outcomes in social media.

Article reviews the current techniques of low-light image enhancement.

Article and accompanying poster presenting a prototype for the use of Edge with MR devices to provide cooperative perception capability to the MR device.

Article studies the communication styles present in chat interactions of thousands of aspiring entrepreneurs who discuss and develop business models. The authors find that these styles can be reliably predicted, and that the communication styles can be used to predict a number of indices of business success.

Article describes study which sought to evaluate methods for activity recognition for toddlers.

Article investigates whether translating negation is an issue for modern MT systems using 17 translation directions as test bed and provides a linguistically motivated analysis that explains the majority of the findings. The authors release their annotations and code to replicate analysis here: https://github.com/mosharafhossain/negation-mt.

Article develops a a simple, fast, and powerful method, named JS-MA, based on Jensen-Shannon divergence and agglomerative hierarchical clustering, to detect the genome-wide multi-locus interactions associated with multiple diseases.

This article presents a comprehensive overview of the key enabling technologies required for 5G and 6G networks, highlighting the massive MIMO systems. The authors discuss the fundamental challenges related to pilot contamination, channel estimation, precoding, user scheduling, energy efficiency, and signal detection in massive MIMO systems and discuss state-of-the-art mitigation techniques. Recent trends such as terahertz communication, ultra massive MIMO (UM-MIMO), visible light communication (VLC), machine learning, and deep learning for massive MIMO systems are outlined. Finally, future research for massive MIMO systems for 5G and beyond is discussed.

Article investigating HUMIRA effects mentioned in Twitter posts using a relational similarity-based method. The authors were able to identify effects previously known as well as potentially unreported, which demonstrates the power of this method and its potential for studying effects of other medications shared by Twitter users.

Article implements and tests the performances of several approximation algorithms for computing the minimum dominating set of a graph. This article belongs to the Special Issue: Algorithms for Hard Graph Problems.

Article proposes a Social- and Content-aware Video content delivery Prediction method (SCVP) to address the problem of predicting whether a video will be watched by a user for efficient video content delivery in mobile social networks.

This article proposes a new truncated statistic method (TS) by utilizing a truncated method to find the genes that have a true contribution to the genetic association. The proposed truncated statistic outperforms existing methods. It can be employed to detect novel traits associated genes using GWAS summary data.

Article presents WikiPossessions, a new benchmark corpus for the task of temporally-oriented possession (TOP), or tracking objects as they change hands over time. In addition to the corpus, the authors release evaluation scripts and a baseline model for the task.