Machine Learning
This benchmark dataset accompanies an article paper titled ``Learning to Reuse Distractors to support Multiple Choice Question Generation in Education''. It contains a test of 298 educational questions covering multiple subjects & languages and a 77K multilingual pool of distractor vocabulary. The goal is for a given question to propose a list of relevant candidate distractors from the pool of distractors.
- Categories:
358 Views
The dataset contains physiological data collected using a wearable device from 5 children with autism (all males) during interaction sessions with different stimuli. The dataset (QU_Autism_dataset.csv) is related to our investigations of using wearable devices to detect the occurrence of challenging behaviors among children with autism. The study used a wearable device that acquired the acceleration (ACC) (i.e., in X, Y, Z), electrodermal activity (EDA), temperature (TEMP), heart rate (HR), and blood volume pulse (BVP).
- Categories:
152 Views
In this paper, we develop a hierarchical aerial computing framework composed of high altitude platform (HAP) and unmanned aerial vehicles (UAVs) to compute the fully offloaded tasks of terrestrial mobile users which are connected through an uplink non-orthogonal multiple access (UL-NOMA).
- Categories:
447 Views
This dataset contains pathloss and ToA radio maps generated by the ray-tracing software WinProp from Altair. The dataset allows to develop and test the accuracies of pathloss radio map estimation methods and localization algorithms based on RSS or ToA in realistic urban scenarios. More details on the datasets can be found in the dataset paper: https://arxiv.org/abs/2212.11777.
- Categories:
4087 Views
More than 85% of traffic utilization via mobile phones are consumed in the urban area, and most of the traffic is used for downloading. Improving the throughput in LTE for 1 user equipment (UE) in cities is an urgent problem. The collected data is intended to study a dependence of the KPI mobile base station and neighboring from installation extra technology. This study will support the development of methods for comparing traffic utilization of urban area and carry out recommendations for the Channel Quality Indicator (CQI) increases.
- Categories:
498 Views
Deep video representation learning has recently attained state-of-the-art performance in video action recognition. However, when used with video clips from varied perspectives, the performance of these models degrades significantly. Existing VAR models frequently simultaneously contain both view information and action attributes, making it difficult to learn a view-invariant representation.
- Categories:
224 Views
Devanagari is a phonetic script that originated from Ancient Brahmi. It is the foundation of various Indian languages. According to data from the year 2022, the Devanagari Hindi script is spoken by over 342 million people worldwide and ranks third among the top 45 languages. There are approximately 11 vowels and 33 consonants and 10 numerals in the Devanagari script. The Devanagari script has no upper-or lower-case letters and is written from left to right.
- Categories:
118 Views
The provided dataset is created is created by using European Commission Rapid Alert System's data for Salmonella cases. The dataset composed by 5 variables and all data is providet in categorical format. it is possible to use the dataset predict the salmonella cases based on type of food, month, country and warmth.
- Categories:
156 Views
In recent years, it has become more difficult to identify road traffic signage and panel guide material. Few studies have been made to solve these two issues at the same time, especially in the Arabic language. Additionally, the limited number of datasets for traffic signs and panel guide content makes the investigation more interesting. the Tunisian research groups in intelligent machines of the University of Sfax (REGIM laboratory of Sfax) will provide the NaSTSArLaT dataset free to researchers in traffic detection signs and traffic road scene text detection.
- Categories:
688 Views
This is the dataset we collected for the article "Scalable Undersized Dataset RF Classification: Using Convolutional Multistage Training". 17 objects were collected in the laboratory and scanned using a 'cw radar' setup featuring 2x UWB antennas (1 transmit antenna, 1 receive antenna), inside anechoic chamber. There was no clutter added in the experiment.
- Categories:
1360 Views