Use of Optical Emission Spectroscopy Data for Fault Detection of Mass Flow Controller in Plasma Etch Equipment

To minimize wafer yield losses by misprocessing during semiconductor manufacturing, faster and more accurate fault detection during the plasma process are desired to increase production yields. Process faults can be caused by abnormal equipment conditions, and the performance drifts of the parts or components of complicated semiconductor fabrication equipment are some of the most unnoticed factors that eventually change the plasma conditions. In this work, we propose improved stability and accuracy of process fault detection using optical emission spectroscopy (OES) data. Under a controlled experimental setup of arbitrarily induced fault scenarios, the extended isolation forest (EIF) approach was used to detect anomalies in OES data compared with the conventional isolation forest method in terms of accuracy and speed. We also used the OES data to generate features related to electron temperature and found that using the electron temperature features together with equipment status variable identification data (SVID) and OES data improved the prediction accuracy of process/equipment fault detection by a maximum of 0.84%.

Hybrid approach with Deep Auto-Encoder and optimized LSTM based Deep Learning approach to detect anomaly in cloud logs

Anomaly-based detection is coupled with recognizing the uncommon, to catch the unusual activity, and to find the strange action behind that activity. Anomaly-based detection has a wide scope of critical applications, from bank application security to regular sciences to medical systems to marketing apps. Anomaly-based detection adopted by various Machine Learning techniques is really a type of system that consists of artificial intelligence. With the ever-expanding volume and new sorts of information, for example, sensor information from an incontestably enormous amount of IoT devices and from network flow data from cloud computing, it is implicitly understood without surprise that there is a developing enthusiasm for having the option to deal with more conclusions automatically by means of AI and ML applications. But with respect to anomaly detection, many applications of the scheme are simply the passion for detection. In this paper, Machine Learning (ML) techniques, namely the SVM, Isolation forest classifiers experimented and with reference to Deep Learning (DL) techniques, the proposed DA-LSTM (Deep Auto-Encoder LSTM) model are adopted for preprocessing of log data and anomaly-based detection to get better performance measures of detection. An enhanced LSTM (long-short-term memory) model, optimizing for the suitable parameter using a genetic algorithm (GA), is utilized to recognize better the anomaly from the log data that is filtered, adopting a Deep Auto-Encoder (DA). The Deep Neural network models are utilized to change over unstructured log information to training ready features, which are reasonable for log classification in detecting anomalies. These models are assessed, utilizing two benchmark datasets, the Openstack logs, and CIDDS-001 intrusion detection OpenStack server dataset. The outcomes acquired show that the DA-LSTM model performs better than other notable ML techniques. We further investigated the performance metrics of the ML and DL models through the well-known indicator measurements, specifically, the F-measure, Accuracy, Recall, and Precision. The exploratory conclusion shows that the Isolation Forest, and Support vector machine classifiers perform roughly 81%and 79%accuracy with respect to the performance metrics measurement on the CIDDS-001 OpenStack server dataset while the proposed DA-LSTM classifier performs around 99.1%of improved accuracy than the familiar ML algorithms. Further, the DA-LSTM outcomes on the OpenStack log data-sets show better anomaly detection compared with other notable machine learning models.

Application of the Isolation Forest Algorithm to Substantiate the Uniqueness of Water Bodies in the Group of Karst Lakes

Improving the scientific foundations for the development and expansion of the network of specially protected natural areas requires the search for algorithms that could be used to identify unique ecosystems. Algorithmization of the anomaly identification process provides an opportunity not only to process large amounts of data but also leads to obtaining objective and comparable estimates. The purpose of this research is to identify the most optimal mechanisms for identifying anomalous values for the morphometric characteristics of karst lakes, which may indicate the uniqueness of the entire lake ecosystem. Within the framework of this article, the study was carried out based on a mathematical analysis of samples built for various characteristics based on the WORLDLAKE database. Statistical methods and the Isolation Forest (iForest) machine learning algorithm were used as methods of analysis. As a result of applying the iForest algorithm to a sample of morphometric parameters of karst lakes, consisting of 738 objects, 43 anomalous water bodies were identified. An expert assessment of the final set of lakes for the uniqueness of their ecosystems showed that the chosen method for identifying anomalous values is well suited for the task at hand. Many lakes with an anomaly index above 60% can be recognized as unique due to the unusualness of their abiotic characteristics; a number of them also have a peculiar biota. The anomalous objects included such well-known lakes as Tserik-Kol’, Crveno, Salda Lake, Trihonida, Vegoritida, Petron, etc. Moreover, for most of them, anomalies were detected for several parameters at once. Thus, the applied algorithm for identifying anomalous morphometric characteristics of lakes made it possible to obtain interesting samples for further expert analysis of the entire lake ecosystem for its uniqueness.

BCEAD: A Blockchain-Empowered Ensemble Anomaly Detection for Wireless Sensor Network via Isolation Forest

The distributed deployment of wireless sensor networks (WSNs) makes the network more convenient, but it also causes more hidden security hazards that are difficult to be solved. For example, the unprotected deployment of sensors makes distributed anomaly detection systems for WSNs more vulnerable to internal attacks, and the limited computing resources of WSNs hinder the construction of a trusted environment. In recent years, the widely observed blockchain technology has shown the potential to strengthen the security of the Internet of Things. Therefore, we propose a blockchain-based ensemble anomaly detection (BCEAD), which stores the model of a typical anomaly detection algorithm (isolated forest) in the blockchain for distributed anomaly detection in WSNs. By constructing a suitable block structure and consensus mechanism, the global model for detection can iteratively update to enhance detection performance. Moreover, the blockchain guarantees the trust environment of the network, making the detection algorithm resistant to internal attacks. Finally, compared with similar schemes, in terms of performance, cost, etc., the results prove that BCEAD performs better.