ALBERT

Description: The rapid development of Internet technology and the spread of various smart devices have enabled the creation of a convenient environment used by people all around the world. It has become increasingly popular, with the technology known as the Internet of Things (IoT). However, both the development and proliferation of IoT technology have caused various problems such as personal information leakage and privacy violations due to attacks by hackers. Furthermore, countless devices are connected to the network in the sense that all things are connected to the Internet, and network attacks that have thus far been exploited in the existing PC environment are now also occurring frequently in the IoT environment. In fact, there have been many security incidents such as DDoS attacks involving the hacking of IP cameras, which are typical IoT devices, leakages of personal information and the monitoring of numerous persons without their consent. While attacks in the existing Internet environment were PC-based, we have confirmed that various smart devices used in the IoT environment—such as IP cameras and tablets—can be utilized and exploited for attacks on the network. Even though it is necessary to apply security solutions to IoT devices in order to prevent potential problems in the IoT environment, it is difficult to install and execute security solutions due to the inherent features of small devices with limited memory space and computational power in this aforementioned IoT environment, and it is also difficult to protect certificates and encryption keys due to easy physical access. Accordingly, this paper examines potential security threats in the IoT environment and proposes a security design and the development of an intelligent security framework designed to prevent them. The results of the performance evaluation of this study confirm that the proposed protocol is able to cope with various security threats in the network. Furthermore, from the perspective of energy efficiency, it was also possible to confirm that the proposed protocol is superior to other cryptographic protocols. Thus, it is expected to be effective if applied to the IoT environment.

Description: ACS Sustainable Chemistry & Engineering DOI: 10.1021/acssuschemeng.5b01381

Description: This paper proposes a complete framework of a machine learning-based model that detects convective initiation (CI) from geostationary meteorological satellite data. The suggested framework consists of three main processes: (1) An automated sampling tool; (2) machine learning-based CI detection modelling; (3) repeated model tuning through validation. In this study, the automated sampling tool was able to track the CI objects iteratively, even without ancillary data such as an atmospheric motion vector (AMV). The collected samples were used to train the machine learning model for CI detection. Random forest (RF) was used to classify the CI and non-CI. To enhance the advantages of the machine learning approach, we adopted model tuning to iteratively update the training dataset from each validation result by adding hits and misses to the CI samples, and false alarms and correct negatives to the non-CI samples. Using 12 interest fields from the Himawari-8 Advanced Himawari Imager (AHI) over the Korean Peninsula, this simple and intuitive tuning process increased the overall probability of detection (POD) from 0.79 to 0.82 and decreased the overall false alarm rate (FAR) from 0.46 to 0.37 with around 40 min of the lead-time. Amongst the 12 interest fields, T b (11.2) µm was identified as the most significant predictor in the RF model, followed by T b (8.6—11.2) µm, and T b (6.2–7.3) µm. The effect of model tuning on the CI detection performance was also analyzed using spatiotemporal validation maps. By automatically collecting and updating the machine learning training dataset, the suggested framework is expected to help the maintenance of the CI detection model from an operational perspective.

Description: Environmental Science & Technology DOI: 10.1021/es500001q