Fruits are a rich source of vitamins and minerals and also have fiber content. Fruit ripeness detection has been playing an important role in the production industry as it plays a prominent role during harvesting. It has to be performed in a non-destructive manner. Due to the considerable amount of water and vitamins, fruits are agricultural products most vulnerable to decay and spoilage. In this work, a portable setup using a color sensor integrated with an optical method has been developed to detect the quality of apples. The difference in the amount of light reflected by ripe and unripe apples is taken into account to determine the ripeness. The portable instrument developed calculates the amount of light reflected from the apple samples using optical fiber and color sensor reliably which is then used to differentiate between ripe and unripe fruits using a decision tree classifier as the amount of light absorbed by ripe and unripe fruits are proved to vary always.
28 March 2025 in Multimedia Tools and Applications
Sensor networks play a critical role in applications such as smart cities, industrial automation, and environmental monitoring. However, their reliability can be compromised by sensor faults, measurement inaccuracies, or environmental disruptions that lead to anomalous data. This study proposes a hybrid anomaly detection framework that integrates machine learning and spatial analysis techniques to improve the detection of such anomalies. Specifically, the approach leverages Isolation Forest and DBSCAN for anomaly detection, complemented by Moran's I index to capture spatial dependencies often overlooked by traditional methods. This combination enables the identification of both local and spatially clustered anomalies, addressing the challenge of geospatial irregularities in sensor measurements. Experimental validation across real-world datasets including environmental, seismic, and meteorological sensor data demonstrates that the proposed model outperforms conventional statistical methods in accuracy, recall, and robustness. Overall, this hybrid model offers a promising solution for enhancing the precision, reliability, and situational awareness of sensor-based monitoring systems.