Artificial Intelligence
This dataset extends the standard Myers-Briggs Type Indicator (MBTI) dataset, widely available on Kaggle, by incorporating advanced data augmentation techniques leveraging GPT-based Transformers. The augmentation addresses inherent class imbalance and data sparsity issues in the original dataset, significantly enriching the volume and diversity of textual samples while maintaining linguistic and contextual fidelity to the MBTI personality types.
- Categories:
75 Views
This data examines the evolution of telehealth technologies across three distinct phases: Pre-2010, 2010–2019, and 2020–Present. The timeline highlights the progression from basic video consultations and electronic health records (EHR) to more advanced remote patient monitoring, mobile health applications, and cloud-based platforms. Recent advancements in AI-powered diagnostics, natural language processing (NLP) for clinical documentation, predictive analytics, and virtual health assistants represent a transformative shift in healthcare delivery.
- Categories:
53 Views
With the continuous advancement of technology, small and portable physiological sensors that can be worn on the body are quietly integrating into our daily lives, and are expected to greatly enhance our quality of life. In order to further enrich and expand the emotional physiological signals captured by portable wearable devices, we utilized the 14-channel portable EEG acquisition device Emotiv EPOC X, and with emotional video clips as the stimulus source, we collected two sets of emotional EEG signals from two groups of 10 participants each, named EmoX1 and EmoX2.
- Categories:
211 Views
This dataset was developed using the MOBATSim simulator in MATLAB 2020b, designed to mimic real-world autonomous vehicle (AV) environments. It focuses on providing high-quality data for research in anomaly detection and cybersecurity, particularly addressing False Data Injection Attacks (FDIA). The dataset includes comprehensive sensor information, such as speed, rotational movements, positional coordinates, and labelled attack data, enabling supervised learning.
- Categories:
426 Views
The existing public datasets often suffer from small data volumes, leading to insufficient training processes that result in severe overfitting and poor generalization performance. To address this issue, a radar dataset named RadSet is constructed. During the data acquisition phase, frequency modulated continuous wave (FMCW) radar system IWR1843 Boost manufactured by Texas Instruments (TI) was used.
- Categories:
155 Views
MaskTIF is collected from different scenarios from ETIF and contains 3,000 thermal infrared face images. The collection time was during the severe COVID-19 epidemic period, and contains a large number of mask-wearing samples.
- Categories:
27 Views
Artificial Intelligence (AI) is revolutionizing telehealth by addressing persistent challenges in diagnosis, patient monitoring, and healthcare accessibility. This data evaluates AI's integration into telehealth systems, emphasizing its transformative role in enhancing diagnostic precision, personalizing treatments, and bridging gaps in healthcare equity. The study explores methodologies such as machine learning, natural language processing, and predictive analytics, presenting their impact on optimizing care delivery.
- Categories:
48 Views
This Dataset is a self-harm dataset developed by ZIOVISION Co. Ltd. It consists of 1,120 videos. Actors were hired to simulate self-harm behaviors, and the scenes were recorded using four cameras to ensure full coverage without blind spots. Self-harm behaviors in the dataset are limited to "cutting" actions targeting specific body parts. The designated self-harm areas include the wrists, forearms, and thighs.
The full dataset can be accesssed through https://github.com/zv-ai/ZV_Self-harm-Dataset.git
- Categories:
46 Views
- The dataset consists of feature vectors belonging to 12,330 sessions. The dataset was formed so that each session would belong to a different user in a 1-year period to avoid any tendency to a specific campaign, special day, user profile, or period.
- Of the 12,330 sessions in the dataset, 84.5% (10,422) were negative class samples that did not end with shopping, and the rest (1908) were positive class samples ending with shopping.
- The dataset consists of 10 numerical and 8 categorical attributes. The 'Revenue' attribute can be used as the class label.
- Categories:
141 Views
The dataset was specifically created to address the need for violence detection in surveillance systems. It consists of self-recorded videos simulating different types of violent activities relevant to college environments. The dataset is organized into four distinct classes:
Slap
Punch
Kick
Group Violence
Others - Over Crowding, Loitering, Assault, Abuse
Each video is labeled according to its corresponding class to facilitate supervised learning for violence detection models.
- Categories:
463 Views