22 skills found
dolongbien / HumanBehaviorBKUAbnormal Human Behaviors Detection/ Road Accident Detection From Surveillance Videos/ Real-World Anomaly Detection in Surveillance Videos/ C3D Feature Extraction
ShoupingShan / Abnormal Behavior DetectionAbnormal behavior detection in the video surveillance based on yolo darknet
YuriSizuku / Research AbnormalBehaviorDetectionabnormal behavior detection using CNN and RNN
Baavanadhaz / AI Anomaly Detection SystemThis project is an AI-powered anomaly detection system that monitors social media trends, physical environmental conditions, and stock market behavior in real time. It correlates signals across multiple domains using machine learning and LLMs to detect abnormal patterns and explain why anomalies occur and what they may indicate.
dipankarsk / Feature Selection HybridIntrusion Detection is a technique to identify the abnormal behavior of system due to attack. The unusual behavior of the environment is then identified and steps are taken and methods are formed to classify and recognize attacks. Data set containing a number of records sometimes may decrease the classifiers performance due to redundancy of data. The other problems may include memory requirements and processing power so we need to either reduce the number of data or the number of records. Feature Selection techniques are used to reduce the vertical largeness of data set. This project makes a comparative study of Particle Swarm Optimization, Genetic Algorithm and a hybrid of the two where we see that PSO being simpler swarm algorithm works for feature selection problems but since it is problem dependent and more over its stochastic approach makes it less efficient in terms of error reduction compared to GA. In standard PSO, the non-oscillatory route can quickly cause a particle to stagnate and also it may prematurely converge on sub optimal solutions that are not even guaranteed to be local optimum. A further drawback is that stochastic approaches have problem-dependent performance. This dependency usually results from the parameter settings in each algorithm. The different parameter settings for a stochastic search algorithm result in high performance variances. In this project the modification strategies are proposed in PSO using GA. Experimental results show that GA performs better than PSO for the feature selection in terms of error reduction problems whereas hybrid outperforms both the model in terms of error reduction.
Smart-Safety-Ocean / HAAR DeepModelDetects the abnormal behaviors of passengers on a ship so we can prevent accidents from occurring
ArielNing / Passenger Abnormal Behavior Detection In Elevator电梯轿厢内乘客异常行为检测
vidhiJain / Deep Learning For Sentiment AnalysisAbnormality detection in human emotional behavior through sentiment analysis
ShixianGuo / Abnormal Behavior Detection异常行为检测
Lynda-Starkus / DeepvisionAI BackendDeepvisionAI-backend is the code core of a desktop software providing detection/tracking of pedestrians and abnormal crowd activity using convolutional auto-encoders.
js-lee-AI / Abnormal DetectionAbnormal behavior detection for corporate internal security using customized YOLO-v3.
lacie-life / AbnormalBehaviorRecognitionAbnormal Behavior Recognition
superYong2020 / Hajj Abnormal Behavior DetectionThis the code of paper "Generative Adversarial Network Based Abnormal Behavior Detection in Massive Crowd Videos: A Hajj Case Study"
SIDD2310 / Abnormal Activity Detection Deep LearningAbnormal Activity Detection using Deep Learning LRCN is a model that combines CNN and RNN to identify abnormal behavior in videos. With reduced layers, resized frames, and augmented datasets, it achieves an 82% accuracy, making it suitable for real-time applications like surveillance and anomaly detection.
aradhya29 / ABNORMAL HUMAN ACTIVITY DETECTION SYSTEM# Abnormal-Human-Activity-Detection With the increase in the amount of anti-social activities taking place in the environment, security has been given the utmost importance lately. Therefore, organizations require a constant monitoring of people and their interactions. Since this constant monitoring of data by humans to judge if the events are abnormal is a near impossible task as it requires a lot of workforce and constant attention. Therefore, the challenge that comes up is the demand for an automatic and intelligent analysis for such video sequences. Our project comes forward as an attempt to provide solution to such a problem as the model developed is a smart surveillance system which can detect unusual or abnormal activity automatically. A method for representing the motion characteristics is described for detection and localization of unusual activities in the crowd scenes on a generalized framework which includes both a local and global range for detection of such activities.
guanliu321 / Anomaly Detection Model Deployment Using AWSUtilized a sample solution deployed by using the AWS CloudFormation template provided by the AWS,We have developed an end-to-end workflow in a dataset with more than 280,000 records for detecting abnormal behaviors of customers' credit cards.Here is the detail of the workflow: Using Amazon Sagemaker's algorithm, we built a Logistic model, then used incremental learning to refine and expand the model, and deploy the model to AWS endpoints. When the streaming data comes in,SNS client will be invoted and a notification of whether exist abnormal behaviors or not will be sent to the designed endpoint. At the end of each day, a summary dashboard which record the pattern of daily abnormal activities will be automatically generated and sent to key stakeholders. Utilized:Python,AWS,Pandas,Numpy,Json,Boto3,Base64,Amazon Sagemaker,ETL,Anomaly Detection,Logistic Model,SQL.
Srivardhan04 / IoT Based Cyclist Safety System.This project focuses on enhancing cyclist safety using an ESP32-based IoT system that detects falls and abnormal cycling behavior in real time. By integrating ML/DL algorithms and anomaly detection on an ESP32 microcontroller, the system provides real-time alerts to emergency contacts and logs incident data on a cloud-based web platform.
PoojaPatel35 / Human Activity Recognition Mobily Path PredictionIndividual Mobility is the study that depicts how individuals move inside a region or system. As of late a few researches have been accomplished for this reason and there has been a flood in enormous informational accessible in individual developments. Most of these information’s are gathered from cellphone or potentially GPS with variable accuracy relying upon the distance from the tower. Enormous scope information, for example, cell phone follows are significant hotspot for urban modeling. The individual travel designs breakdown into a solitary likelihood distribution however despite the assorted variety of their travel history people follow basic reproducible examples. This similitude in movement example can help us in an extremely different zones of utilizations, for example, city arranging, traffic building, spread of disease and versatile infections. The motive of this project is to show that by utilizing a measure of direct estimation that human directions do follow a few high reproducible scaling designs. Activity recognition expects to perceive the activities and objectives of at least one operator from a progression of perceptions on the specialists' activities and the natural conditions. Human movement acknowledgment, which is one of the developing fields of research, plans to figure out which action is finished by people. Some true applications, for example, health monitoring, abnormal behavior detection, and sport. In this way, it is a troublesome issue given the enormous number of perceptions delivered each second, the fleeting idea of the perceptions, and the absence of an unmistakable method to relate accelerometer information to known developments. Keen PDAs presently fuse numerous different and ground-breaking sensors, for example, GPS sensors, vision sensors, sound sensors, light sensors, temperature sensors, course sensors and speeding up sensors. This project is about utilizations telephone-based accelerometers to perform activity recognition, which includes identifying the physical movement a user is performing
beomwon / CCTV Abnormal Behavior Detection Serviceuse yolo v7, flask, telegram
KAU-Smart-Crowd / Hajj Abnormal Behavior DetectionNo description available
