Failure management and cost-aware traffic engineering are two important tasks done in Network Operation Centers (NOC). These are performed by expert technicians who must carefully analyze the network state and the flow of incoming alarms to decide how, where and when to take actions on the network. While based on implicit guiding principles, these network actions are very hard to automate with explicit rules due to the high complexity of the system; hence NOC action is essentially a manual process today. To automate part of that process, in this paper we introduce an Action Recommendation Engine (ARE) that can learn implicit NOC action rules with supervised machine learning from historical data. As a result, ARE can recommend suitable action(s) to remedy network faults and engineer the traffic to minimize costs, all while maximizing the users' Quality of Experience. To quantify the effectiveness of different NOC action scenarios, we introduce the QoE-OPEX metric which balances between users' quality of Experience and ISP's operational costs. After proper model training on 56,000 data points with 66 features, we demonstrate that ARE can effectively reproduce implicit action-taking logic of NOC technicians, thus moving us one step closer to reliable autonomous networks and fully-automated NOCs.

Although the autonomous detection of network status and localization of network faults can be a valuable tool for network and service operators, very few works have investigated this subject. As a result in today's networks, fault detection and localization remains a mostly-manual process. In this paper, we propose a Machine Learning (ML) method that can automatically detect the status of a network and localize faults. Our method uses Decision Tree, Gradient Boosting (GB), and XGBoost (XGB) ML algorithms to detect the network status as Normal, Congestion, and Network Fault. In comparison, existing related work can at best classify the network status as faulty or non-faulty. Experimental results show that our method yields accuracies of up to 99% on a dataset collected through an emulated network.

This study aims to analyze the effectiveness of the internet-based, free Teachable Machine (TM) platform, which does not entail code knowledge, in detecting the presence and types of strabismus in the optimum hyperparameters. Material and Methods:The images obtained from the patients who presented to our clinic with the complaint of ocular deviation were analyzed, and 523 [176 esotropia (ET), 195 exotropia (XT), and 152 orthophoria (ORTHO)] images were included in this study. After the images were uploaded to the TM platform, 6 different batch sizes and 9 different learning rates were tested using the grid search method, with the number of epochs fixed at 4,000 to determine the optimum hyperparameter. Results: The highest overall test accuracy was 0.887, and the hyperparameters from which this accuracy was obtained were 200 for the number of epochs, 256 for the batch size, and 0.0005 for the learning rate. In the TM model trained with these parameters, accuracy values of ET: 0.96, ORTHO: 0.78 and XT: 0.9 were obtained in the subgroups, respectively. Conclusion: To achieve optimal accuracy at the stage of development of the artificial intelligence model, users should determine the appropriate hyperparameter values depending on the size of the available dataset and the complexity of the data. The results we obtained by determining the optimum hyperparameters have revealed that the presence of strabismus can be detected with high accuracy using TM, an internet-based, free deep learning platform that does not entail having code knowledge.

No abstract

No abstract