scholarly journals MACHINE LEARNING PREDIKSI KEBANGKRUTAN MENGGUNAKAN ALTMAN Z-SCORE

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Bambang Siswoyo ◽  
Encep Sse ◽  
Encep Sse ◽  
Firman Jurnal ◽  
Firman Jurnal
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Anomaly Detection ◽  
Bankruptcy Prediction ◽  
Financial Statement ◽  
Perceptron Algorithm ◽  
Healthy State ◽  
Past Data ◽  
Auc Value ◽  
Main Components

AbstrakIndustri manufaktur adalah salah satu industry yang sangat memperhatikan secara khusus analisis laporan keungan, oleh karena, manajemen harus mempunyai model prediksi kebangkrutan sebagai peringatan dini sehingga bisa mengantisipasi kondisi perusahaan agar dalam keadaan sehat. Machine learning yang mempunyai kemampuan belajar dari data masa lalu sert menghasilkan solusi yang optimal� dengan pendekatan pengenalan pola, akan digunakan dalam kajian ini. Algoritma Principle component analysi-based anomaly detection (PCA-BAD), Multiclass neural network dan Algoritma Perceptron akan digunakan untuk memecahkan masalah. Model yang dihasilkan diuji untuk memperoleh akurasi dan nilai-nilai AUC dari masing-masing algoritma. Nilai� akurasi PCA-BAD nilai accuracy 53% dan nilai AUC adalah 92%. Sementara Multiclass Neural Network� dengan threshold 1% nilai� Acuracy 100 % dan AUC 100%, sedangkan algoritma Perceptron Acuracy 100% dan AUC 100% Dengan demikian dapat disimpulkan bahwa model yang diusulkan adalah algoritma multiclass neural network.Kata Kunci : Kebangkrutan, Machine learning, PrediksiAbstractManufacturing Industry is one industry that is very concerned about financial statement analysis, therefore, management must have a bankruptcy prediction model as an initial publication that can promote the condition of the company to suit a healthy state. Machine learning that has the ability to learn from past data and produces optimal solutions by obtaining pattern recognition, will be used in this study. The main components of the analysis-based anomaly detection (PCA-BAD) algorithm, the Multiclass neural network and the Perceptron Algorithm will be used to solve the problem. The resulting model appreciates the accuracy and AUC values of each algorithm. The value of PCA-BAD accuracy is 53% and the AUC value is 92%. While the Multiclass Neural Network with a threshold of 1% Acuracy value 100% and AUC 100%, while the Perceptron Acuracy algorithm 100% and AUC 100% Thus it can be denied that the model used is a multiclass neural networkKeywords: Bankruptcy, machine learning, predictionManufaktur��

scholarly journals Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case Study

2018 ◽  
Vol 8 (12) ◽  
pp. 2663 ◽  
Author(s):  
Davy Preuveneers ◽  
Vera Rimmer ◽  
Ilias Tsingenopoulos ◽  
Jan Spooren ◽  
Wouter Joosen ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Intrusion Detection ◽  
Anomaly Detection ◽  
Training Data ◽  
Learning Models ◽  
Traditional System ◽  
Blockchain Technology ◽  
Malicious Behavior ◽  
Machine Learning Models

The adoption of machine learning and deep learning is on the rise in the cybersecurity domain where these AI methods help strengthen traditional system monitoring and threat detection solutions. However, adversaries too are becoming more effective in concealing malicious behavior amongst large amounts of benign behavior data. To address the increasing time-to-detection of these stealthy attacks, interconnected and federated learning systems can improve the detection of malicious behavior by joining forces and pooling together monitoring data. The major challenge that we address in this work is that in a federated learning setup, an adversary has many more opportunities to poison one of the local machine learning models with malicious training samples, thereby influencing the outcome of the federated learning and evading detection. We present a solution where contributing parties in federated learning can be held accountable and have their model updates audited. We describe a permissioned blockchain-based federated learning method where incremental updates to an anomaly detection machine learning model are chained together on the distributed ledger. By integrating federated learning with blockchain technology, our solution supports the auditing of machine learning models without the necessity to centralize the training data. Experiments with a realistic intrusion detection use case and an autoencoder for anomaly detection illustrate that the increased complexity caused by blockchain technology has a limited performance impact on the federated learning, varying between 5 and 15%, while providing full transparency over the distributed training process of the neural network. Furthermore, our blockchain-based federated learning solution can be generalized and applied to more sophisticated neural network architectures and other use cases.

scholarly journals Improving Water Quality Assessment through Anomaly Detection Using Hybrid Convolutional Neural Network Approach

2021 ◽  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Water Quality ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Convolutional Neural Network ◽  
Quality Assessment ◽  
Water Quality Assessment ◽  
Machine Learning Algorithms ◽  
Quality Analysis

<p>Water being a precious commodity for every person around the world needs to be quality monitored continuously for ensuring safety whilst usage. The water data collected from sensors in water plants are used for water quality assessment. The anomaly present in the water data seriously affects the performance of water quality assessment. Hence it needs to be addressed. In this regard, water data collected from sensors have been subjected to various anomaly detection approaches guided by Machine Learning (ML) and Deep Learning framework. Standard machine learning algorithms have been used extensively in water quality analysis and these algorithms in general converge quickly. Considering the fact that manual feature selection has to be done for ML algorithms, Deep Learning (DL) algorithm is proposed which involve implicit feature learning. A hybrid model is formulated that takes advantage of both and presented it is data invariant too. This novel Hybrid Convolutional Neural Network (CNN) and Extreme Learning Machine (ELM) approach is used to detect presence of anomalies in sensor collected water data. The experiment of the proposed CNN-ELM model is carried out using the publicly available dataset GECCO 2019. The findings proved that the model has improved the water quality assessment of the sensor water data collected by detecting the anomalies efficiently and achieves F1 score of 0.92. This model can be implemented in water quality assessment.</p>

scholarly journals Analysis of deep learning models for network anomaly detection in Internet of Things

2021 ◽  
pp. 28-37
Author(s):  
Diana Gaifilina ◽  
Igor Kotenko
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Internet Of Things ◽  
Anomaly Detection ◽  
Recurrent Neural Network ◽  
Network Traffic ◽  
Learning Models ◽  
Network Anomaly Detection ◽  
Machine Learning Models

Introduction: The article discusses the problem of choosing deep learning models for detecting anomalies in Internet of Things (IoT) network traffic. This problem is associated with the necessity to analyze a large number of security events in order to identify the abnormal behavior of smart devices. A powerful technology for analyzing such data is machine learning and, in particular, deep learning. Purpose: Development of recommendations for the selection of deep learning models for anomaly detection in IoT network traffic. Results: The main results of the research are comparative analysis of deep learning models, and recommendations on the use of deep learning models for anomaly detection in IoT network traffic. Multilayer perceptron, convolutional neural network, recurrent neural network, long short-term memory, gated recurrent units, and combined convolutional-recurrent neural network were considered the basic deep learning models. Additionally, the authors analyzed the following traditional machine learning models: naive Bayesian classifier, support vector machines, logistic regression, k-nearest neighbors, boosting, and random forest. The following metrics were used as indicators of anomaly detection efficiency: accuracy, precision, recall, and F-measure, as well as the time spent on training the model. The constructed models demonstrated a higher accuracy rate for anomaly detection in large heterogeneous traffic typical for IoT, as compared to conventional machine learning methods. The authors found that with an increase in the number of neural network layers, the completeness of detecting anomalous connections rises. This has a positive effect on the recognition of unknown anomalies, but increases the number of false positives. In some cases, preparing traditional machine learning models takes less time. This is due to the fact that the application of deep learning methods requires more resources and computing power. Practical relevance: The results obtained can be used to build systems for network anomaly detection in Internet of Things traffic.

scholarly journals ANALISIS TINGKAT KEBERHASILAN CRYOTERAPY MENGGUNAKAN NEURAL NETWORK

2019 ◽  
Vol 15 (2) ◽  
pp. 141-148
Author(s):  
Sri Rahayu ◽  
Fitra Septia Nugraha ◽  
Muhammad Ja’far Shidiq
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Side Effects ◽  
20Th Century ◽  
High Accuracy ◽  
Machine Learning Method ◽  
Learning Method ◽  
Good Classification ◽  
Auc Value

Human health is very important to always pay attention especially after someone has been declared suffering from an illness that can inhibit positive activities. One of the most feared diseases of the 20th century is cancer. This disease requires treatment that is quite expensive. Alternative treatments are cryotherapy or ice therapy. But cryotherapy also has side effects, it is necessary to do research on its success by taking into account certain conditions of the parameters. So the purpose of this study is to analyze the success of cryotherapy so that the dataset can be used as one of the benchmarks for the success of the cryotherapy tratment method. The method used in this study is the machine learning method of Neural Network with 500 training cycles, learning rate of 0,003 and momentum 0,9 which results in a good classification of obtaining quite high accuracy of 87,78% and AUC value of 0,955.

scholarly journals Medical Fraud and Abuse Detection System Based on Machine Learning

2020 ◽  
Vol 17 (19) ◽  
pp. 7265 ◽  
Author(s):  
Conghai Zhang ◽  
Xinyao Xiao ◽  
Chao Wu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Health Care ◽  
Anomaly Detection ◽  
Healthcare System ◽  
Loss Function ◽  
Detection System ◽  
Relative Probability ◽  
Fully Connected ◽  
Better Than

It is estimated that approximately 10% of healthcare system expenditures are wasted due to medical fraud and abuse. In the medical area, the combination of thousands of drugs and diseases make the supervision of health care more difficult. To quantify the disease–drug relationship into relationship score and do anomaly detection based on this relationship score and other features, we proposed a neural network with fully connected layers and sparse convolution. We introduced a focal-loss function to adapt to the data imbalance and a relative probability score to measure the model’s performance. As our model performs much better than previous ones, it can well alleviate analysts’ work.

3D-Convolutional Neural Network with Generative Adversarial Network and Autoencoder for Robust Anomaly Detection in Video Surveillance

2020 ◽  
Vol 30 (06) ◽  
pp. 2050034
Author(s):  
Wonsup Shin ◽  
Seok-Jun Bu ◽  
Sung-Bae Cho
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Anomaly Detection ◽  
Learning Approaches ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Video Feature ◽  
Feature Extractor ◽  
Anomaly Detector ◽  
Deep Learning Model

As the surveillance devices proliferate, various machine learning approaches for video anomaly detection have been attempted. We propose a hybrid deep learning model composed of a video feature extractor trained by generative adversarial network with deficient anomaly data and an anomaly detector boosted by transferring the extractor. Experiments with UCSD pedestrian dataset show that it achieves 94.4% recall and 86.4% precision, which is the competitive performance in video anomaly detection.

scholarly journals Transaction Fraud Detection (Anomaly detection) using Machine Learning

2021 ◽  
pp. 361-363
Author(s):  
Prof. Viresh Vanarote ◽  
Omkar Gaykar ◽  
Sarfaraz Saudagar ◽  
Naresh Bulbule ◽  
Tushar Funde
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Anomaly Detection ◽  
Online Shopping ◽  
Learning Algorithm ◽  
Fraud Detection ◽  
Machine Learning Algorithm ◽  
Behavior Profiles

Now a day’s online shopping crazy thing for peoples. As well as many people uses Online transaction for many purposes. Transaction fraud is growing seriously. Therefore, the study on fraud detection is interesting and significant and we can say necessary. An important way of detecting fraud is to extract the behavior profiles (BPs) of users based on their historical transaction records, and then to verify if an incoming transaction is a fraud or not in view of Their BPs. Also we apply SVM, Adaboost, and Neural Network machine learning algorithm to see which one is giving the best result.

scholarly journals Forecasting number of vulnerabilities using long short-term neural memory network

2021 ◽  
Vol 11 (5) ◽  
pp. 4381
Author(s):  
Mohammad Shamsul Hoque ◽  
Norziana Jamil ◽  
Nowshad Amin ◽  
Azril Azam Abdul Rahim ◽  
Razali B. Jidin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Time Series ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Data Points ◽  
Memory Network ◽  
Past Data ◽  
Long Short Term Memory

Cyber-attacks are launched through the exploitation of some existing vulnerabilities in the software, hardware, system and/or network. Machine learning algorithms can be used to forecast the number of post release vulnerabilities. Traditional neural networks work like a black box approach; hence it is unclear how reasoning is used in utilizing past data points in inferring the subsequent data points. However, the long short-term memory network (LSTM), a variant of the recurrent neural network, is able to address this limitation by introducing a lot of loops in its network to retain and utilize past data points for future calculations. Moving on from the previous finding, we further enhance the results to predict the number of vulnerabilities by developing a time series-based sequential model using a long short-term memory neural network. Specifically, this study developed a supervised machine learning based on the non-linear sequential time series forecasting model with a long short-term memory neural network to predict the number of vulnerabilities for three vendors having the highest number of vulnerabilities published in the national vulnerability database (NVD), namely microsoft, IBM and oracle. Our proposed model outperforms the existing models with a prediction result root mean squared error (RMSE) of as low as 0.072.

scholarly journals Anomaly detection and missing data imputation in building energy data for automated data pre-processing

2021 ◽  
Vol 2069 (1) ◽  
pp. 012144
Author(s):  
K Takahashi ◽  
R Ooka ◽  
S Ikeda
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Missing Data ◽  
Anomaly Detection ◽  
Prediction Accuracy ◽  
Energy Savings ◽  
Predictive Accuracy ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Detection Accuracy

Abstract A new trend in building automation is the implementation of smart energy management systems to measure and control building systems without a need for decision-making by human operators. Artificial intelligence can optimize these systems by predicting future demand to make informed decisions about how to efficiently operate individual equipment. These machine learning algorithms use historical data to learn demand trends and require high quality datasets in order to make accurate predictions. But because of issues with data transmission or sensor errors, real world datasets often contain outliers or have data missing. In most research settings, these values can be simply omitted, but in practice, anomalies compromise the automation system’s prediction accuracy, rendering it unable to maximize energy savings. This study explores different machine learning algorithms for anomaly detection for automatically pre-processing incoming data using a case study on an actual electrical demand in a hospital building in Japan, namely cluster-based techniques such as k-means clustering and neural network-based approaches such as the autoencoder. Once anomalies were identified, the missing data was filled with prediction values from a deep neural network model. The newly composed data was then evaluated based on detection accuracy, prediction accuracy and training time. The proposed method of processing anomaly values allows the prediction model to process collected data without interruption, and shows similar predictive accuracy as manually processing the data. These predictions allow energy systems to optimize HVAC equipment control, increasing energy savings and reducing peak building loads.

Sign in / Sign up

Export Citation Format

Share Document