What are the current advancements in mobile applications for pill detection and identification?
Best insight from top research papers
Current advancements in mobile applications for pill detection and identification include various innovative approaches. ClinicYA utilizes the Mask-RCNN algorithm for pill shape extraction and achieves over 99.27% accuracy in localization and recognition of pill shapes . Another development involves a gesture identification algorithm running on a smart wearable device, using supervised machine learning techniques to detect pill ingestion gestures with high accuracy . Additionally, a tool employing digital image processing and the circular Hough transform has been proposed for pill intake monitoring in mHealth apps, showing promising results in detecting round pills and determining the number of untaken pills in blisters . Furthermore, object detection models like RetinaNet, SSD, and YOLO v3 have been compared for pill identification, with YOLO v3 standing out for its detection speed and suitability for hospital equipment deployment .
Answers from top 5 papers
More filters
| Papers (5) | Insight |
|---|---|
| Not addressed in the paper. | |
17 Feb 2022 1 Citations | Development of a digital image processing-based pill detection tool for mHealth apps allows pill intake monitoring without extra devices, showing promise for round pill detection but needing improvement for non-round shapes. |
21 Nov 2022 | Not addressed in the paper. |
21 Dec 2022 | The paper introduces ClinicYA, a mobile app utilizing Mask-RCNN for pill shape recognition and HSV color clustering for identification, achieving high accuracy rates in pill detection and color matching. |
21 Dec 2022 | The paper introduces ClinicYA, a mobile app utilizing deep learning and K-means clustering for pill identification, achieving over 99.27% accuracy in shape recognition and up to 93.85% in color detection. |
Related Questions
What are the current advancements in technology for the detection of epileptic seizures in children during sleep?5 answersRecent advancements in technology for detecting epileptic seizures in children during sleep include wearable devices like the NightWatch system, which has shown high sensitivity in detecting major motor seizures. Additionally, research has focused on utilizing EEG signals for seizure detection, with advancements in computerized intelligent spike and seizure detection techniques, such as tensor factorization and deep learning. Furthermore, innovative approaches like hybrid models combining EEG signals with other biomedical signals like blood pressure and nasal signals have demonstrated improved performance in detecting seizures and differentiating between sleep states. These technological developments aim to provide accurate and timely detection of seizures in children during sleep, ultimately enhancing epilepsy management and improving the quality of life for both patients and caregivers.
What are the current advancements in technology being used for pothole detection and identification?5 answersAdvancements in technology for pothole detection and identification include the use of machine learning algorithms, deep learning models, and sensor methods. Machine learning algorithms and deep learning models, such as convolutional neural networks (CNNs), have been successfully applied to detect potholes in road photos. These algorithms and models extract patterns and characteristics from large amounts of data, enabling accurate pothole detection. Additionally, the fusion of accelerometer data and in-vehicle video data has been proposed as a method to improve pothole detection accuracy. Furthermore, YOLO models, such as YOLOv4 and YOLOv5, have been customized and used for pothole detection, offering high accuracy and reduced inference time. These advancements in technology provide efficient and reliable solutions for detecting and identifying potholes on roads.
What are the current advancements in fruit detection systems using deep neural networks?5 answersCurrent advancements in fruit detection systems using deep neural networks include the use of convolutional neural networks (CNN) for accurate and fast fruit detection and recognition. These systems have shown comparable accuracy and speed levels to humans in some fruit detection and automatic harvesting fields. Different deep learning models such as Single-Shot Multibox Detection (SSD) Mobilenet, Faster Region-CNN (Faster R-CNN), DenseNet-201, Xception, MobileNetV3-Small, and ResNet-50 have been employed for fruit detection and classification. These models have achieved high accuracy rates, ranging from 93% to almost 99%, in detecting and classifying fruits. The use of pre-trained deep learning models has also been effective in fruit classification, with models like DenseNet-201 and Xception achieving accuracies of around 98% to 99%. Additionally, the YOLO-based method has been proposed for fruit classification and detection, providing accuracy, real-time performance, and compatibility required by the industry. These advancements in deep neural networks have revolutionized fruit detection systems, enabling automated and precise fruit detection and classification for various applications.
What are the latest advances in the electrochemical detection of food additives?4 answersRecent advances in the electrochemical detection of food additives have been focused on the development of biosensors and nanomaterial-based sensors. Biosensors, such as electrochemical biosensors, have been designed to offer rapid, sensitive, and user-friendly detection of food contaminants, including allergens, pesticides, antibiotic traces, toxins, and bacteria. On the other hand, nanomaterial-based sensors, particularly those using carbon-based nanomaterials (CNMs), have shown promise in detecting pharmaceutical and food pollutants, such as pesticides, heavy metals, antibiotics, and other medical drugs. These sensors utilize techniques like voltammetry and electrochemical impedance spectroscopy to detect and quantify the presence of additives and contaminants in food samples. Additionally, the use of modified electrodes, such as La2NiO4 functionalized carbon nanofiber (f-CNF) electrodes, has been explored for the effective detection of specific additives like vanillin in food samples, offering high sensitivity and low limits of detection. These advancements in electrochemical detection techniques provide valuable tools for ensuring food safety and quality control.
How do mobile applications facilitate crime reporting?5 answersMobile applications facilitate crime reporting by providing a convenient and efficient platform for the public to report crimes in real-time. These applications, integrated with map features, allow users to track and report the location of the crime. The mobile applications also enable the police department and intelligence agencies to receive and access these reports instantly, improving their ability to respond quickly and effectively to crimes. Additionally, these applications provide a means for the public to stay informed about the crime situation in their area, as they can view crime locations on a map. The use of mobile technology in crime reporting enhances the accuracy and speed of reporting, making it easier for law enforcement agencies to gather information and take appropriate actions. Overall, mobile applications play a crucial role in facilitating crime reporting by enabling real-time reporting, location tracking, and improved communication between the public and law enforcement agencies.
What are some of the most common object detection applications?5 answersObject detection has a wide range of applications in various industries. It is used in autonomous driving to identify vehicles, pedestrians, and traffic signs from road videos. In robotics, object detection is used to recognize specific machine elements. In the security field, it is used for accurate face recognition. Object detection is also used in areas such as unmanned vehicles, public safety, and intelligent robotics. It is being used in home automation, agriculture, surveillance, traffic tracking systems, activity recognition, defense systems, sports, industrial work, automobile industries, robotics, aviation industry, and many other fields. Overall, object detection is a crucial technology that is widely applied in various industries for improving efficiency and performance in tasks such as recognition, localization, and tracking of objects.