Dealing With Highly Unbalanced Sidescan Sonar Image Datasets for Deep Learning Classification Tasks

Steiniger, Yannik; Stoppe, Jannis; Meisen, Tobias; Kraus, Dieter

doi:10.1109/ieeeconf38699.2020.9389373

Cited by 10 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The F1 score was selected due to the context of the problem (multi-class classification) and the nature of the data; which had imbalanced classes. It is noted that accuracy tends to underestimate classes with a smaller number of samples in relation to those with a larger number (Steiniger et al, 2020 ). Therefore, the accuracy score was chosen to compare its performance against the F1-score as it was the most used evaluation metric across many insects' song classification problems (Silva et al, 2013 ; Noda et al, 2016 , 2019 ; Amlathe, 2018 ; Kim et al, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

A convolutional neural network with image and numerical data to improve farming of edible crickets as a source of food—A decision support system

Kyalo,

Tonnang,

Egonyu

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Crickets (Gryllus bimaculatus) produce sounds as a natural means to communicate and convey various behaviors and activities, including mating, feeding, aggression, distress, and more. These vocalizations are intricately linked to prevailing environmental conditions such as temperature and humidity. By accurately monitoring, identifying, and appropriately addressing these behaviors and activities, the farming and production of crickets can be enhanced. This research implemented a decision support system that leverages machine learning (ML) algorithms to decode and classify cricket songs, along with their associated key weather variables (temperature and humidity). Videos capturing cricket behavior and weather variables were recorded. From these videos, sound signals were extracted and classified such as calling, aggression, and courtship. Numerical and image features were extracted from the sound signals and combined with the weather variables. The extracted numerical features, i.e., Mel-Frequency Cepstral Coefficients (MFCC), Linear Frequency Cepstral Coefficients, and chroma, were used to train shallow (support vector machine, k-nearest neighbors, and random forest (RF)) ML algorithms. While image features, i.e., spectrograms, were used to train different state-of-the-art deep ML models, i,e., convolutional neural network architectures (ResNet152V2, VGG16, and EfficientNetB4). In the deep ML category, ResNet152V2 had the best accuracy of 99.42%. The RF algorithm had the best accuracy of 95.63% in the shallow ML category when trained with a combination of MFCC+chroma and after feature selection. In descending order of importance, the top 6 ranked features in the RF algorithm were, namely humidity, temperature, C#, mfcc11, mfcc10, and D. From the selected features, it is notable that temperature and humidity are necessary for growth and metabolic activities in insects. Moreover, the songs produced by certain cricket species naturally align to musical tones such as C# and D as ranked by the algorithm. Using this knowledge, a decision support system was built to guide farmers about the optimal temperature and humidity ranges and interpret the songs (calling, aggression, and courtship) in relation to weather variables. With this information, farmers can put in place suitable measures such as temperature regulation, humidity control, addressing aggressors, and other relevant interventions to minimize or eliminate losses and enhance cricket production.

show abstract

Section: Methodsmentioning

confidence: 99%

A convolutional neural network with image and numerical data to improve farming of edible crickets as a source of food—A decision support system

Kyalo,

Tonnang,

Egonyu

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…We based performance mostly on the F1-score since classes were unbalanced and Accuracy tends to underestimate classes with a smaller number of samples in relation to those with a larger number (Steiniger et al, 2020). The F 1 measure is a combination of the precision and recall measures and is defined by Eq.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…We employed macro-F1 since Accuracy underestimates classes with a smaller number of samples in relation to the larger ones. Macro-F1 score is considered a suited metric for an unbalanced test set because it better describes performance by class and not by sample number (Steiniger et al, 2020).…”

Section: Imbalanced Data Bias and Noise Corruptionmentioning

confidence: 99%

Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation

et al. 2023

View full text Add to dashboard Cite

IntroductionBees capable of performing floral sonication (or buzz-pollination) are among the most effective pollinators of blueberries. However, the quality of pollination provided varies greatly among species visiting the flowers. Consequently, the correct identification of flower visitors becomes indispensable to distinguishing the most efficient pollinators of blueberry. However, taxonomic identification normally depends on microscopic characteristics and the active participation of experts in the decision-making process. Moreover, the many species of bees (20,507 worldwide) and other insects are a challenge for a decreasing number of insect taxonomists. To overcome the limitations of traditional taxonomy, automatic classification systems of insects based on Machine-Learning (ML) have been raised for detecting and distinguishing a wide variety of bioacoustic signals, including bee buzzing sounds. Despite that, classical ML algorithms fed by spectrogram-type data only reached marginal performance for bee ID recognition. On the other hand, emerging systems from Deep Learning (DL), especially Convolutional Neural Networks (CNNs), have provided a substantial boost to classification performance in other audio domains, but have yet to be tested for acoustic bee species recognition tasks. Therefore, we aimed to automatically identify blueberry pollinating bee species based on characteristics of their buzzing sounds using DL algorithms.MethodsWe designed CNN models combined with Log Mel-Spectrogram representations and strong data augmentation and compared their performance at recognizing blueberry pollinating bee species with the current state-of-the-art models for automatic recognition of bee species.Results and DiscussionWe found that CNN models performed better at assigning bee buzzing sounds to their respective taxa than expected by chance. However, CNN models were highly dependent on acoustic data pre-training and data augmentation to outperform classical ML classifiers in recognizing bee buzzing sounds. Under these conditions, the CNN models could lead to automating the taxonomic recognition of flower-visiting bees of blueberry crops. However, there is still room to improve the performance of CNN models by focusing on recording samples for poorly represented bee species. Automatic acoustic recognition associated with the degree of efficiency of a bee species to pollinate a particular crop would result in a comprehensive and powerful tool for recognizing those that best pollinate and increase fruit yields.

show abstract

“…Sedangkan Steiniger et.al. melakukan penelitian terkait dengan permasalahan dataset dari sonar yang tidak seimbang (balance) untuk tugas klasifikasi dengan menggunakan deep learning [7]. Penelitian yang terkait SONAR juga dilakukan oleh Ghosh, dengan membandingkan 29 macam algoritme pembelajaran mesin antara lain: Logistic Regression, Decision Tree, K-Nearest Neighbor (KNN), Nave Bayes, Support Vector Machines, Random Forest, Ada Boost, dan lain sebagainya [8].…”

Section: Pendahuluanunclassified

Peningkatan Kinerja Pengklasifikasi Objek Bawah Laut dengan Deep Learning

Tjahyanto

Atletiko

2022

matrik

View full text Add to dashboard Cite

Pengenalan objek bawah laut dapat dilakukan berdasarkan pola hamburan SONAR, seperti untuk deteksi ranjau dan deteksi batu yang terletak di dasar laut. Kesulitan yang dihadapi pada pengenalan objek bawah laut antara lain adalah pemilihan metode ekstraksi fitur, adanya rotasi objek yang menghasilkan pola hamburan yang berbeda, lingkungan atau latar belakang bervariasi, dan kemampuan pengklasifikasi yang berbeda untuk lingkungan yang lebih kompleks. Pada penelitian ini, kami menggunakan deep learning neural network untuk meningkatkan kinerja klasifikasi dua buah objek bawah laut. Secara khusus, dibandingkan jumlah neuron pada lapisan tersembunyi dan fungsi aktivasi yang dapat menghasilkan kinerja yang lebih tinggi dari penelitian sebelumnya. Pada penelitian sebelumnya, proses klasifikasi dilakukan dengan menggunakan neural network dengan 12 buah lapisan tersembunyi, dan menghasilkan akurasi maksimal sebesar 90.4%. Dilakukan percobaan pada struktur jaringan syaraf tiruan berupa multilayer perceptron dengan 2 buah lapisan tersembunyi dan 7 macam fungsi aktivasi. Dari percobaan yang dilakukan diperolehbahwa deep learning neural network memberikan rata-rata akurasi terbaik sebesar 85,9% dengan akurasi maksimal sebesar 96,15% lebih baik dibandingkan hasil penelitian sebelumnya. Akurasi terbaik tersebut diperoleh dengan memanfaatkan jumlah neuron pada lapisan tersembunyi sebanyak 140 buah, dan fungsi aktivasi reLU untuk lapisan tersembunyi fungsi aktivasi Linear untuk lapisan output.

show abstract

Dealing With Highly Unbalanced Sidescan Sonar Image Datasets for Deep Learning Classification Tasks

Cited by 10 publications

References 5 publications

A convolutional neural network with image and numerical data to improve farming of edible crickets as a source of food—A decision support system

A convolutional neural network with image and numerical data to improve farming of edible crickets as a source of food—A decision support system

Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation

Peningkatan Kinerja Pengklasifikasi Objek Bawah Laut dengan Deep Learning

Contact Info

Product

Resources

About