Multiple classifier system for automated quality assessment of marine sensor data

Abstract

Numerous sources of uncertainty are associated with the data acquisition process in marine sensor networks. It is thus required to assure that the data quality of sensors is fit for the intended purpose. We propose a supervised learning framework to infer the quality of sensor observations online. A problem with using supervised classification in quality assessment is that sensor observations from the class of uncertain data will be far outweighed by class instances of good data quality. This leads to an imbalanced data set, which can potentially reduce the classification accuracy of uncertain data. A multiple classifier (or ensemble classifier) system is proposed to deal with this problem. Training sets are randomly under-sampled to develop training subsets with balanced class membership. The process is repeated to produce multiple balanced training subsets. Individual classifiers are then trained upon each of these balanced data sets. The quality classifications from the individual classifiers are then combined using majority voting. We evaluated the ensemble classifier system using conductivity and temperature sensors from the Tasmanian Marine Analysis Network (TasMAN). Experiments demonstrate that the ensemble classifier balances the classification accuracy of the majority and minority classes, achieving a higher overall classification accuracy than its constituent classifiers.

Komparasi Algoritma Klasifikasi dengan Pendekatan Level Data untuk Menangani Data Kelas Tidak Seimbang

“…Masalah data kelas tidak seimbang sering disebabkan oleh satu kelas kalah banyak dengan kelas lain didalam dataset [1] [2]. Masalah ini banyak dijumpai diberbagai data pada domain aplikasi seperti deteksi tumpahan minyak [4], pengindraan jarak jauh [5] klasifikasi teks [6], pemodelan respon [7], penilaian kualitas data sensor [8], deteksi kartu kredit palsu [9] dan extraksi pengetahuan dari database [10] sehingga hal ini menjadi penting bagi para peneliti di bidang data mining [11]. Namun dalam maslah ini cukupa sulit karena algoritma klasifikasi tradisional bias terhadap kelas minoritas [12], artinya apabila dipaksakan hasil prediksi dapat mendekati keliru bahkan salah [13].…”

Ensemble Classifiers and Their Applications: A Review

“…The authorities monitor a number of environmental and water quality variables through a set of sensors to check the health of shellfish farms and to decide on the closure of the farms. The research presented in [39] [40] develops an ensemble of class-balancing classifiers (similar to [37] [38]) to identify the cause of closure.…”

Application of Machine Learning Techniques in Aquaculture

“…The decisions based on faulty sensor reading will result in wrong conclusion. In [19] [20] the authors have presented a novel ensemble classifier approach for assessing the quality of sensor data. The base classifiers are constructed by random under-sampling of the training data where the sampling process is guided by clustering.…”