Distribution of training data with 90 percent hybrid images.

Performance of model trained on 90 percent hybrid data generated offline.

About This Dataset

The Roboflow Packages dataset is a collection of packages located at the doors of various apartments and homes. Packages are flat envelopes, small boxes, and large boxes. Some images contain multiple annotated packages.

Usage

This dataset may be used as a good starter dataset to track and identify when a package has been delivered to a home. Perhaps you want to know when a package arrives to claim it quickly or prevent package theft.

If you plan to use this dataset and adapt it to your own front door, it is recommended that you capture and add images from the context of your specific camera position. You can easily add images to this dataset via the web UI or via the Roboflow Upload API.

About Roboflow

Roboflow enables teams to build better computer vision models faster. We provide tools for image collection, organization, labeling, preprocessing, augmentation, training and deployment. :fa-spacer: Developers reduce boilerplate code when using Roboflow's workflow, save training time, and increase model reproducibility. :fa-spacer:

BIRD is an open dataset that consists of 100,000 multichannel room impulse responses generated using the image method. This makes it the largest multichannel open dataset currently available. We provide some Python code that shows how to download and use this dataset to perform online data augmentation. The code is compatible with the PyTorch dataset class, which eases integration in existing deep learning projects based on this framework.

Data associated with research towards a surrogate machine learning model for the Advanced Gas-cooled Reactor (AGR). This data was generated using the Parmec software package [1] and can be used to train machine learning models using the Surrogate Machine Optimisation and Learning (SMOL) framework [2]. Visit the aforementioned repository, clone the code, then download the files into repository folder.

If you are not planning on working with data augmentation, exclude the files with flip and rotate in the title, e.g. dataset_flip_13_rotate_123_cases.pkl.

1. Koziara, T., 2019. Parmec documentation. URL: https://parmes.org/parmec/index.html [Online; accessed 05-August-2022].

2. Github Repository. URL: https://gitlab.cs.man.ac.uk/q59494hj/parmec_agr_ml_surrogate [Online; accessed 05-August-2022].

Number and class distribution of cut-paste eligible images.

BIRD (Big Impulse Response Dataset) is an open dataset that consists of 100,000 multichannel room impulse responses (RIRs) generated from simulations using the Image Method, making it the largest multichannel open dataset currently available. These RIRs can be used to perform efficient online data augmentation for scenarios that involve two microphones and multiple sound sources.

This COVID-19 dataset consists of Non-COVID and COVID cases of both X-ray and CT images. The associated dataset is augmented with different augmentation techniques to generate about 17099 X-ray and CT images. The dataset contains two main folders, one for the X-ray images, which includes two separate sub-folders of 5500 Non-COVID images and 4044 COVID images. The other folder contains the CT images. It includes two separate sub-folders of 2628 Non-COVID images and 5427 COVID images.

This repository includes datasets on experimental cases of study and analysis regarding the research called "Programmable content and a pattern-matching algorithm for automatic adaptive authoring in Augmented Reality for maintenance".DOI:Abstract: "Augmented Reality (AR) can increase efficiency and safety of maintenance operations, but costs of augmented content creation (authoring) are hindering its industrial deployment. A relevant research gap involves the ability of authoring solutions to automatically generate content for multiple operations. Hence, this paper offers programmable content formats and a pattern-matching algorithm for automatic adaptive authoring of ontology -based maintenance data. The proposed solution is validated against common authoring tools for repair and remote diagnosis AR applications in terms of operational efficiency gains achieved with the content they produce. Experimental results show that content from all authoring solutions attain same time reductions (42%) in comparison with non-AR information delivery tools. Surveys results suggest alike perceived usability of all authoring solutions and better content adaptiveness and user’s performance tracking of this authoring proposal."

Augmented custom dataset with images sourced from online sources and camera captures. The dataset was used to train YOLO models for road obstacle detection on African roads specificallly.

The United States Sentencing Commission, established by the 98th Congress, is an independent agency in the judicial branch of government. The Commission recommends guidelines prescribing the appropriate form and severity of punishment for offenders convicted of federal crimes. These data were collected to determine whether sentencing disparities existed and whether the guidelines were adequate. Basic information in the collection includes a description of the offense, characterization of the defendant's background and criminal record, method of disposition of the case, and sentence imposed. Felony and misdemeanor cases are included while petty offense cases are excluded. Three types of additional information were used to augment the existing data: (1) more detailed offense and offender characteristics identified by the United States Sentencing Commission but coded by federal probation officers, (2) actual time served in prison from the SENTRY data file of the United States Bureau of Prisons, and (3) information necessary to estimate prospective release dates from the hearing files of the United States Parole Commission. The unit of analysis is the defendant.

For semiparametric survival models with interval-censored data and a cure fraction, it is often difficult to derive nonparametric maximum likelihood estimation due to the challenge in maximizing the complex likelihood function. In this article, we propose a computationally efficient EM algorithm, facilitated by a gamma-Poisson data augmentation, for maximum likelihood estimation in a class of generalized odds rate mixture cure (GORMC) models with interval-censored data. The gamma-Poisson data augmentation greatly simplifies the EM estimation and enhances the convergence speed of the EM algorithm. The empirical properties of the proposed method are examined through extensive simulation studies and compared with numerical maximum likelihood estimates. An R package “GORCure” is developed to implement the proposed method and its use is illustrated by an application to the Aerobic Center Longitudinal Study dataset. Supplementary material for this article is available online.

The measurement and diagnosis of the severity of failures in rotating machines allow the execution of predictive maintenance actions on equipment. These actions make it possible to monitor the operating parameters of the machine and to perform the prediction of failures, thus avoiding production losses, severe damage to the equipment, and safeguarding the integrity of the equipment operators. This paper describes the construction of a dataset composed of vibration signals of a rotating machine. The acquisition has taken into consideration seven distinct operating scenarios, with different speed values. Unlike the few datasets that currently exist, the resulting dataset contains simple and combined faults with several severity levels. The considered operating setups are normal condition, unbalance, horizontal misalignment, vertical misalignment, unbalance combined with horizontal misalignment, unbalance combined with vertical misalignment, and vertical misalignment combined with horizontal misalignment. The dataset described in this paper can be utilized by machine learning researchers that intend to detect faults in rotating machines in an automatic manner. In this context, several related topics might be investigated, such as feature extraction and/or selection, reduction of feature space, data augmentation methods, and prognosis of rotating machines through the analysis of failure severity parameters.

According to Cognitive Market Research, the global Augmented Intelligence market size is USD 54.7 Billion in 2024 and will expand at a compound annual growth rate (CAGR) of 25.1% from 2024 to 2031. Market Dynamics of Augmented Intelligence Market

Key Drivers for Augmented Intelligence Market

Increase in Use of Advance Technologies to Increase the Demand Globally. Several businesses across the globe have been using advanced technologies, such as big data, blockchain artificial intelligence, and the Internet of Things, to solve complex business problems and improve their revenue. In addition, artificial intelligence technology provides numerous applications to businesses, which include transferring and cross-referencing data, predicting consumer behaviors, and personalized advertising and marketing products. In addition, it provides support in various applications ranging from appointment decisions to employee training and development. Increase the Volume of Complex Business Data

Key Restraints for Augmented Intelligence Market

Data Privacy and Security Concerns Lack of Skilled Professionals Introduction of the Augmented Intelligence Market

Augmented intelligence is an alternative form of artificial intelligence that focuses on AI's assistive role. In addition, augmented intelligence is developed to help organizations make more accurate data-driven decisions in business and everyday life. In addition, it elevates the employees' performance in the organization and helps the organization understand the areas that could be improved in employees. The increase in the use of advanced technologies such as big data, blockchain, artificial intelligence, and the internet of things among businesses and the rise in the use of digital technology to fulfill the customer's expectations boost the growth of the global augmented intelligence market. In addition, the surge in demand for business intelligence tools positively impacts the growth of the market.

This is a dataset obtained from an online survey conducted in August 2020.

In the survey, participants were introduced to the concept of a smartphone-based shopping assistant application with the help of pictures and videos when shopping with and without the application. Participants were presented with three different shopping scenarios. In each scenario, we showed products on a shelf (groceries, luxury chocolate, shoes, books). The first shopping scenario was a regular shopping scenario (RSS), the second was an augmented reality shopping scenario (ARSS), and the third was an augmented reality shopping scenario with explainable AI features (XARSS). For each scenario participants had to answer questions about how they perceived the scenario and how it influenced their overall purchase intention.

The present work was conducted within the Innovative Training Network project PERFORM funded by the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No. 765395. The EU Research Executive Agency is not responsible for any use that may be made of the information it contains.

Touch interactions are central to many human activities, but there are few technologies for computationally augmenting free-hand interactions with real environments. Here, we describe Tactile Echoes, a finger-wearable system for augmenting touch interactions with physical objects. This system captures and processes touch-elicited vibrations in real-time in order to enliven tactile experiences. We process these signals via a parametric signal processing network in order to generate responsive tactile and auditory feedback. Just as acoustic echoes are produced through the delayed replication and modification of sounds, so are Tactile Echoes produced through transformations of vibrotactile inputs in the skin. The echoes also reflect the contact interactions and touched objects involved. A transient tap produces discrete echoes, while a continuous slide yields sustained feedback. We also demonstrate computational methods that allow these effects to be selectively assigned to different objects or actions by optically tracking the motion of the finger. A large variety of distinct multisensory effects can be designed via ten processing parameters. We investigated how Tactile Echoes are perceived in several perceptual experiments using multidimensional scaling methods. This allowed us to deduce low-dimensional, semantically grounded perceptual descriptions. We describe several virtual and augmented reality applications of Tactile Echoes. In a user study, we found that these effects made interactions more responsive and engaging. Our findings show how to endow a large variety of touch interactions with expressive multisensory effects.

Methods Movie file: Tactile Echoes.mp4

The movie shows the demonstration of Tactile Echoes device which is augmenting tactile sensation in free-hand interactions with real environments. This movie also presents the application of Tactile Echoes. For example, 2D touch display application with Tactile Echoes and using Tactile Echoes feedback in the Virtual Reality. The concept of Tactile Echoes, system, and hardware configuration are also included. With the Tactile Echoes device, we measured output and conducted perceptual study and user study. How to do the user study of Tactile Echoes is also described in the video.

Web page (Appendix of “Tactile Echoes: Multisensory Augmented Reality for the Hand”): Appendix_of_Tactile_Echoes.webloc

In the corresponding paper, we conducted 3 perceptual experiments to investigate how touch interaction augmented by the Tactile Echoes were perceived and to identify a perceptual space that adequately described the perceptual similarity of different output from Tactile Echoes. On the web page, additional three results from these experiments and a data set of parameters used in these three perceptual experiments are described. First, the result from the first perceptual experiment of descriptive word harvesting is described. Second, the result from word voting is showed. The selected rate and words are presented. Third, from the third perceptual study, the all R-Square value of regression MDS perceptual study is showed. It contains the statistical result of MDS analysis. Finally, the engineering parameters of Tactile Echoes to create each output stimuli used in these experiments are described.

Comparison of the effect of the three data augmentation methods on the algorithms with selected features (no. classes = 2).

Data Analytics Market Valuation – 2024-2031

Data Analytics Market was valued at USD 68.83 Billion in 2024 and is projected to reach USD 482.73 Billion by 2031, growing at a CAGR of 30.41% from 2024 to 2031.

Data Analytics Market Drivers

Data Explosion: The proliferation of digital devices and the internet has led to an exponential increase in data generation. Businesses are increasingly recognizing the value of harnessing this data to gain competitive insights.

Advancements in Technology: Advancements in data storage, processing power, and analytics tools have made it easier and more cost-effective for organizations to analyze large datasets.

Increased Business Demand: Businesses across various industries are seeking data-driven insights to improve decision-making, optimize operations, and enhance customer experiences.

Data Analytics Market Restraints

Data Quality and Integrity: Ensuring the accuracy, completeness, and consistency of data is crucial for effective analytics. Poor data quality can hinder insights and lead to erroneous conclusions.

Data Privacy and Security Concerns: As organizations collect and analyze sensitive data, concerns about data privacy and security are becoming increasingly important. Breaches can have significant financial and reputational consequences.

Natal dispersal is a successful tactic under a range of conditions in spite of significant costs. Habitat quality is a frequent proximate cause of dispersal, and studies have shown that dispersal increases both when natal habitat quality is good or poor. In social species kin competition, favoring dispersal, may be balanced by the benefits of group living, favoring philopatry. We investigated the effect of changes in the local environment on natal dispersal of adult females in a social spider species, Stegodyphus dumicola (Araneae, Eresidae), with a flexible breeding system, where females can breed either within the colony or individually following dispersal. We manipulated foraging opportunities in colonies by either removing the capture webs or by adding prey and recorded the number of dispersing females around each focal colony, and their survival and reproductive success. We predicted that increasing kin competition should increase dispersal of less-competitive individuals, while reducing competition could cause either less dispersal (less competition) or more dispersal (a cue indicating better chances to establish a new colony). Dispersal occurred earlier and at a higher rate in both food-augmented and web-removal colonies than in control colonies. Fewer dispersing females survived and reproduced in the web-removal group than in the control or food augmented groups. The results support our prediction that worsening conditions in web-removal colonies favor dispersal, whereby increased kin competition and increased energy expenditure on web renewal cause females to leave the natal colony. By contrast, prey augmentation may serve as a habitat-quality cue; when the surrounding habitat is expected to be of high quality, females assess the potential benefit of establishing a new colony to be greater than the costs of dispersal.

We propose a generative model and an inference scheme for epidemic processes on dynamic, adaptive contact networks. Network evolution is formulated as a link-Markovian process, which is then coupled to an individual-level stochastic susceptible-infectious-recovered model, to describe the interplay between the dynamics of the disease spread and the contact network underlying the epidemic. A Markov chain Monte Carlo framework is developed for likelihood-based inference from partial epidemic observations, with a novel data augmentation algorithm specifically designed to deal with missing individual recovery times under the dynamic network setting. Through a series of simulation experiments, we demonstrate the validity and flexibility of the model as well as the efficacy and efficiency of the data augmentation inference scheme. The model is also applied to a recent real-world dataset on influenza-like-illness transmission with high-resolution social contact tracking records. Supplementary materials for this article are available online.