scholarly journals Improving Convolutional Neural Networks’ Accuracy in Noisy Environments Using k-Nearest Neighbors

2018 ◽  
Vol 8 (11) ◽  
pp. 2086 ◽  
Author(s):  
Antonio-Javier Gallego ◽  
Antonio Pertusa ◽  
Jorge Calvo-Zaragoza
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Nearest Neighbor ◽  
Hybrid Approach ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Neural Codes ◽  
K Nearest Neighbors ◽  
Network Topologies ◽  
Common Technique

We present a hybrid approach to improve the accuracy of Convolutional Neural Networks (CNN) without retraining the model. The proposed architecture replaces the softmax layer by a k-Nearest Neighbor (kNN) algorithm for inference. Although this is a common technique in transfer learning, we apply it to the same domain for which the network was trained. Previous works show that neural codes (neuron activations of the last hidden layers) can benefit from the inclusion of classifiers such as support vector machines or random forests. In this work, our proposed hybrid CNN + kNN architecture is evaluated using several image datasets, network topologies and label noise levels. The results show significant accuracy improvements in the inference stage with respect to the standard CNN with noisy labels, especially with relatively large datasets such as CIFAR100. We also verify that applying the ℓ 2 norm on neural codes is statistically beneficial for this approach.

scholarly journals SMS Spam Detection Framework Using Machine Learning Algorithms and Neural Networks

2021 ◽  
Vol 10 (6) ◽  
pp. 10-19
Author(s):  
T. Jhansi Rani ◽  
T. Jaya Vumesh ◽  
P. Saiteja ◽  
V. Ajay Kumar Reddy ◽  
M. Meghana
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Nearest Neighbor ◽  
Personal Information ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Short Message ◽  
K Nearest Neighbor ◽  
Communication Services ◽  
Visualization Techniques

In our current generation we are very much habituated to many mobile services like communication, ecommerce etc. In mobile communication services SMS’s (Short Message Service’s) are very common and important services which we are using in personal purposes and profession. In these services some messages may cause spam attacks which is trap to users to access their personal information or attracting them to purchase a product from unauthorized websites. It is very easy for companies send any information or service or alert to their customers/users with these SMS API’s. Based on these services it is also possible for sending spam messages. So in this system we are using advance Machine Learning concepts for detection of the spam filtering in the SMS’s. In this system we are importing the dataset from UCI repository and for spam SMS detection we implementing machine learning classifiers like Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Neural Networks (NN) algorithms and with their metrics like accuracy, precision, recall and f-score. We calculate performances between there algorithms as well as we show the experiment results with visualization techniques and analyses which algorithm is best for spam SMS detection.

scholarly journals IDENTIFIKASI JENIS IKAN MENGGUNAKAN MODEL HYBRID DEEP LEARNING DAN ALGORITMA KLASIFIKASI

Sebatik ◽  
2020 ◽  
Vol 24 (2) ◽  
Author(s):  
Anifuddin Azis
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Logistic Regression ◽  
Deep Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Nearest Neighbor ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Data Output

Indonesia merupakan negara dengan keanekaragaman hayati terbesar kedua di dunia setelah Brazil. Indonesia memiliki sekitar 25.000 spesies tumbuhan dan 400.000 jenis hewan dan ikan. Diperkirakan 8.500 spesies ikan hidup di perairan Indonesia atau merupakan 45% dari jumlah spesies yang ada di dunia, dengan sekitar 7.000an adalah spesies ikan laut. Untuk menentukan berapa jumlah spesies tersebut dibutuhkan suatu keahlian di bidang taksonomi. Dalam pelaksanaannya mengidentifikasi suatu jenis ikan bukanlah hal yang mudah karena memerlukan suatu metode dan peralatan tertentu, juga pustaka mengenai taksonomi. Pemrosesan video atau citra pada data ekosistem perairan yang dilakukan secara otomatis mulai dikembangkan. Dalam pengembangannya, proses deteksi dan identifikasi spesies ikan menjadi suatu tantangan dibandingkan dengan deteksi dan identifikasi pada objek yang lain. Metode deep learning yang berhasil dalam melakukan klasifikasi objek pada citra mampu untuk menganalisa data secara langsung tanpa adanya ekstraksi fitur pada data secara khusus. Sistem tersebut memiliki parameter atau bobot yang berfungsi sebagai ektraksi fitur maupun sebagai pengklasifikasi. Data yang diproses menghasilkan output yang diharapkan semirip mungkin dengan data output yang sesungguhnya.  CNN merupakan arsitektur deep learning yang mampu mereduksi dimensi pada data tanpa menghilangkan ciri atau fitur pada data tersebut. Pada penelitian ini akan dikembangkan model hybrid CNN (Convolutional Neural Networks) untuk mengekstraksi fitur dan beberapa algoritma klasifikasi untuk mengidentifikasi spesies ikan. Algoritma klasifikasi yang digunakan pada penelitian ini adalah : Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbor (KNN),  Random Forest, Backpropagation.

scholarly journals Analisis Perbandingan Algoritma Klasifikasi Citra Chest X-ray Untuk Deteksi Covid-19

Teknika ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 96-103
Author(s):  
Mohammad Farid Naufal ◽  
Selvia Ferdiana Kusuma ◽  
Kevin Christian Tanus ◽  
Raynaldy Valentino Sukiwun ◽  
Joseph Kristiano ◽  
...  
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Cross Validation ◽  
Nearest Neighbor ◽  
Nearest Neighbors ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
K Nearest Neighbors ◽  
X Ray ◽  
Chest X Ray

Kondisi pandemi global Covid-19 yang muncul diakhir tahun 2019 telah menjadi permasalahan utama seluruh negara di dunia. Covid-19 merupakan virus yang menyerang organ paru-paru dan dapat mengakibatkan kematian. Pasien Covid-19 banyak yang telah dirawat di rumah sakit sehingga terdapat data citra chest X-ray paru-paru pasien yang terjangkit Covid-19. Saat ini sudah banyak peneltian yang melakukan klasifikasi citra chest X-ray menggunakan Convolutional Neural Network (CNN) untuk membedakan paru-paru sehat, terinfeksi covid-19, dan penyakit paru-paru lainnya, namun belum ada penelitian yang mencoba membandingkan performa algoritma CNN dan machine learning klasik seperti Support Vector Machine (SVM), dan K-Nearest Neighbor (KNN) untuk mengetahui gap performa dan waktu eksekusi yang dibutuhkan. Penelitian ini bertujuan untuk membandingkan performa dan waktu eksekusi algoritma klasifikasi K-Nearest Neighbors (KNN), Support Vector Machine (SVM), dan CNN  untuk mendeteksi Covid-19 berdasarkan citra chest X-Ray. Berdasarkan hasil pengujian menggunakan 5 Cross Validation, CNN merupakan algoritma yang memiliki rata-rata performa terbaik yaitu akurasi 0,9591, precision 0,9592, recall 0,9591, dan F1 Score 0,959 dengan waktu eksekusi rata-rata sebesar 3102,562 detik.

scholarly journals Product Review Based Customer Sentiment Analysis using an Ensemble of mRMR and Forest Optimization Algorithm (FOA)

2022 ◽  
Vol 13 (1) ◽  
pp. 0-0
Keyword(s):  
Feature Selection ◽  
Sentiment Analysis ◽  
Optimization Algorithm ◽  
Nearest Neighbor ◽  
Hybrid Approach ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Feature Selection Technique ◽  
Feature Selection Problem

This research presents a way of feature selection problem for classification of sentiments that use ensemble-based classifier. This includes a hybrid approach of minimum redundancy and maximum relevance (mRMR) technique and Forest Optimization Algorithm (FOA) (i.e. mRMR-FOA) based feature selection. Before applying the FOA on sentiment analysis, it has been used as feature selection technique applied on 10 different classification datasets publically available on UCI machine learning repository. The classifiers for example k-Nearest Neighbor (k-NN), Support Vector Machine (SVM) and Naïve Bayes used the ensemble based algorithm for available datasets. The mRMR-FOA uses the Blitzer’s dataset (customer reviews on electronic products survey) to select the significant features. The classification of sentiments has noticed to improve by 12 to 18%. The evaluated results are further enhanced by the ensemble of k-NN, NB and SVM with an accuracy of 88.47% for the classification of sentiment analysis task.

scholarly journals A Hybrid EEG-Based Emotion Recognition Approach Using Wavelet Convolutional Neural Networks (WCNN) and Support Vector Machine

2021 ◽  
pp. 1-29
Author(s):  
Sara Bagherzadeh ◽  
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Convolutional Neural Networks ◽  
Hybrid Approach ◽  
Support Vector ◽  
Emotional States ◽  
Eeg Signals ◽  
Color Representation ◽  
Time Frequency ◽  
Average Accuracy

Nowadays, deep learning and convolutional neural networks (CNNs) have become widespread tools in many biomedical engineering studies. CNN is an end-to-end tool which makes processing procedure integrated, but in some situations, this processing tool requires to be fused with machine learning methods to be more accurate. In this paper, a hybrid approach based on deep features extracted from Wavelet CNNs (WCNNs) weighted layers and multiclass support vector machine (MSVM) is proposed to improve recognition of emotional states from electroencephalogram (EEG) signals. First, EEG signals were preprocessed and converted to time-frequency (T-F) color representation or scalogram using the continuous wavelet transform (CWT) method. Then, scalograms were fed into four popular pre-trained CNNs, AlexNet, ResNet-18, VGG-19 and Inception-v3 to fine-tune them. Then, the best feature layer from each one was used as input to the MSVM method to classify four quarters of the valence-arousal model. Finally, subject-independent Leave-One-Subject-Out criterion was used to evaluate the proposed method on DEAP and MAHNOB-HCI databases. Results show that extracting deep features from the earlier convolutional layer of ResNet-18 (Res2a) and classifying using the MSVM increases the average accuracy, precision and recall about 20% and 12% for MAHNOB-HCI and DEAP databases, respectively. Also, combining scalograms from four regions of pre-frontal, frontal, parietal and parietal-occipital and two regions of frontal and parietal achieved the higher average accuracy of 77.47% and 87.45% for MAHNOB-HCI and DEAP databases, respectively. Combining CNN and MSVM increased recognition of emotion from EEG signal and results were comparable to state-of-the-art studies.

scholarly journals Implementasi K-Nearest Neighbor untuk Klasifikasi Bunga Dengan Ekstraksi Fitur Warna RGB

2020 ◽  
Vol 7 (6) ◽  
pp. 1129
Author(s):  
Lia Farokhah
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Convolutional Neural Networks ◽  
Nearest Neighbor ◽  
Nearest Neighbour ◽  
K Nearest Neighbor ◽  
Color Features ◽  
Knn Classification ◽  
Total Data ◽  
Shape Characteristics

<p class="Abstrak">Era computer vision merupakan era dimana komputer dilatih untuk bisa melihat, mengidentifikasi dan mengklasifikasi seperti kecerdasan manusia. Algoritma klasifikasi berkembang dari yang paling sederhana seperti K-Nearest Neighbor (KNN) sampai Convolutional Neural Networks. KNN merupakan algoritma klasifikasi yang paling sederhana dalam mengklasifikasikan sebuah gambar kedalam sebuah label. Metode ini mudah dipahami dibandingkan metode lain karena mengklasifikasikan berdasarkan jarak terdekat dengan objek lain (tetangga). Tujuan penelitian ini untuk membuktikan kelemahan metode KNN dan ekstraksi fitur warna RGB dengan karakteristik tertentu. Percobaan pertama dilakukan terhadap dua objek dengan kemiripan bentuk tetapi dengan  warna yang  mencolok di salah satu sisi objek. Percobaan kedua terhadap dua objek yang memiliki perbedaan karakteristik bentuk meskipun memiliki kemiripan warna. Empat objek tersebut adalah bunga coltsfoot, daisy, dandelion dan matahari. Total data dalam dataset adalah 360 data. Dataset memiliki tantangan variasi sudut pandang, penerangan, dan  gangguan dalam latar. Hasil menunjukkan bahwa kolaborasi metode klasifikasi KNN dengan ekstraksi fitur warna RGB memiliki kelemahan terhadap percobaan pertama dengan akurasi 50-60% pada K=5. Percobaan kedua memiliki akurasi sekitar 90-100% pada K=5. Peningkatan akurasi, precision dan recall terjadi ketika menaikkan jumlah K yaitu dari K=1menjadi K=3 dan K=5.</p><p><strong>Kata kunci</strong>: k-nearest neighbour, RGB, kelemahan, kemiripan, bunga</p><p class="Judul2" align="left"> </p><p class="Judul2"> </p><p class="Judul"><em>IMPLEMENTATION OF K-NEAREST NEIGHBOR FOR FLOWER CLASSIFICATION WITH EXTRACTION OF RGB COLOR FEATURES</em></p><p class="Judul"><em>The era of computer vision is an era where computers are trained to be able to see, identify and classify as human intelligence. Classification algorithms develop from the simplest such as K-Nearest Neighbor (KNN) to Convolutional Neural Networks. KNN is the simplest classification algorithm in classifying an image into a label. This method is easier to understand than other methods because it classifies based on the closest distance to other objects (neighbors). The purpose of this research is to prove the weakness of the KNN method and the extraction of RGB color features for specific characteristics. The first  experiment on two objects with similar shape but with sharp color on one side of the object. The second experiment is done on two objects that have different shape characteristics even having a similar colors. The four objects are coltsfoot, daisy, dandelion and sunflower. Total data in the dataset is 360 data. The dataset has the challenge of varying viewpoints, lighting and background noise. The results show that the collaboration of the KNN classification method with RGB color feature extraction has weakness in the first experiment with the level of accuracy about 50-60% at K = 5. The second experiment has an accuracy of around 90-100% at K = 5. Increased accuracy, precision and recall occur when increasing the amount of K, from K = 1 to K = 3 and K = 5.</em></p><p class="Judul2"> </p><p class="Judul2" align="left"> </p><strong>Keywords</strong>: <em>k-nearest neighbour</em>, RGB, <em>weakness, similar, flower</em>

Sign in / Sign up

Export Citation Format

Share Document