An Improved Method to Obtain Fish Weight Using Machine Learning and NIR Camera with Haar Cascade Classifier

López-Tejeida, Samuel; Soto-Zarazúa, Genaro M.; Toledano‐Ayala, Manuel; Contreras-Medina, Luis Miguel; Rivas-Araiza, Edgar A.; Flores-Aguilar, Priscila Sarai

doi:10.3390/app13010069

Cited by 8 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performance Indicators [36] In this study, a system composed of several hardware and software components is implemented. The detection of fish images is performed with videos captured with a NIR camera.…”

Section: Reference Methods Data Characteristics Fish Speciesmentioning

confidence: 99%

Optimizing XGBoost Performance for Fish Weight Prediction through Parameter Pre-Selection

Hamzaoui,

Aoueileyine,

Romdhani

et al. 2023

Fishes

View full text Add to dashboard Cite

Fish play a major role in the human nutritional system, and farmers need to know the accurate prediction of fish weight in order to optimize the production process and reduce costs. However, existing prediction methods are not efficient. The formulas for calculating fish weight are generally designed for a single species of fish or for species of a similar shape. In this paper, a new hybrid method called SFI-XGBoost is proposed. It combines the VIF (variance inflation factor), PCC (Pearson’s correlation coefficient), and XGBoost methods, and it covers different fish species. By applying GridSearchCV validation, normalization, augmentation, and encoding techniques, the obtained results show that SFI-XGBoost is more efficient than simple XGBoost. The model generated by our approach is more generalized, achieving accurate results with a wide variety of species. Using the r2_score evaluation metric, SFI-XGBoost achieves an accuracy rate of 99.94%.

show abstract

Section: Reference Methods Data Characteristics Fish Speciesmentioning

confidence: 99%

Optimizing XGBoost Performance for Fish Weight Prediction through Parameter Pre-Selection

Hamzaoui,

Aoueileyine,

Romdhani

et al. 2023

Fishes

View full text Add to dashboard Cite

show abstract

“…A face can be found in an image using the Haar cascade algorithm. For the Haar cascade algorithm to be trained, positive images with faces and images without faces are required [4]. The advantage of this method is that it produces a distinctive impact by identifying the edge line features displayed in Fig.…”

Section: Haar Cascade Classifiermentioning

confidence: 99%

Visual object detection using audio data

Chaturvedi,

Sahu,

Tyagi

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Nowadays Internet of Things (IoT) and Machine Learning (ML) are growing fields. One application of these two fields is object detection, which detects semantic objects using digital images and videos of classes like humans, vehicles, buildings, etc. Visual object detection systems are very effective and accurate due to the appearance information obtained from the cameras. But they face the problem of a limited Field of View. This paper aims to tackle this issue by using audio data to localize the object. A microphone is used to estimate the angular position of the object emitting the sound. Objects currently in the Field of View of a camera are detected and tracked using optical flow, but when they go out of the Field of View, the sound emitted by the object is used by the microphone to calculate the object‘s angular position. Once the angle is calculated, the camera is rotated in that direction. This thus ensures that the object can be located even if it goes out of frame. Once the object is located through IoT devices, we use ML to identify the person‘s face.

show abstract

“…In this paper, we train our model using a transfer‐learning algorithm ResNet152V2 and the haar cascade classifier (Javed Mehedi Shamrat et al, 2022; Lopez‐Tejeida et al, 2022; Martínez‐Zarzuela et al, 2011) for detecting the face. In the proposed system, we explain how this system will collectively work and suggest how to translate it for GPU execution.…”

Section: Proposed Model Implementationmentioning

confidence: 99%

An automated face mask detection system using transfer learning based neural network to preventing viral infection

Verma,

Rani,

Gupta

et al. 2023

Expert Systems

View full text Add to dashboard Cite

As the “Internet of Medical Things (IoMT)” grows, healthcare systems can collect and process data. It is also challenging to study public health prevention requirements. Virus transmission can be prevented by wearing a mask. The World Health Organization (WHO) recommends wearing a facemask to protect against the COVID‐19 pandemic—the levels of a pandemic rise across almost all regions of the world. By following the WHO rules, we support the development of face mask‐detecting technologies and determine whether or not people are using masks in public locations. The proposed paradigm in this paper will work in three stages. Firstly, we use an Image data generator to import the images. In addition to using a Haar cascade (HC) classifier for detecting faces, residual learning (ResNet152V2) trains a model that detects whether someone is wearing a face mask. Detection and classification are carried out in real‐time with high precision. Compared with other recently proposed methods, the model achieved 99.65% accuracy during training and 99.63% during validation.

show abstract

An Improved Method to Obtain Fish Weight Using Machine Learning and NIR Camera with Haar Cascade Classifier

Cited by 8 publications

References 31 publications

Optimizing XGBoost Performance for Fish Weight Prediction through Parameter Pre-Selection

Optimizing XGBoost Performance for Fish Weight Prediction through Parameter Pre-Selection

Visual object detection using audio data

An automated face mask detection system using transfer learning based neural network to preventing viral infection

Contact Info

Product

Resources

About