The electromechanical design of the HDD (Hard Disk Drive) renders it more susceptible to failures than other components of the computer system. The failure of HDD leads to permanent data loss, which is typically more expensive than HDD itself. The SMART (Self-Monitoring, Analysis and Reporting Technology) system warns the user if any HDD parameter has exceeded the predefined threshold value needed for safe HDD operation. Machine learning methods take advantage of dependence between multiple SMART parameters in order to make failure prediction more precise. In this paper, we present a failure prediction model based on the anomaly detection method involving an adjustable decision boundary. SMART parameters are ranked by the importance and the 13 most significant ones are used as the initial feature set in our model. In the following stage, we optimized the feature set by removing those that have no major contribution to the anomaly detection model, forming the final feature set comprising seven features only. The proposed anomaly detection model achieved 96.11% failure detection rate on average, with 0% false detection rate in ten random tests. The proposed model predicted more than 80% of failures 24 hours before their actual occurrence, which enables timely data backup.
European honeybee colonies are the most important pollinator insects and source of honey and other useful products. Honeybee colonies today face new diseases and pests as well as pollution which threaten their survival and endanger whole food production which relies on honey bee pollination. Internet of Things (IoT) technology enables integration of wireless sensors inside beehives to enable remote monitoring of various beehive parameters from remote location using Internet. Detection of certain critical events in beehive is hard to be explicitly program due to complex dependence between multiple input parameters. Machine learning algorithms give computers the ability to learn to detect these events without being explicitly programmed. Detection of these event from streams of data collected from IoT sensors is possible using Complex Event Processing (CEP) which applies machine induced knowledge do detect and warn beekeepers about certain events in beehive.
Colonies of the European honeybee, the most important pollinator insects, are subjected to many negative impacts of modern society, in form of pollution, pests, invading species and colony collapse disorder (CCD). The newly emerging technology of the Internet of Things (IoT), enables remote monitoring using wireless sensors inside beehives. In this paper, we present the model of the system for remote temperature monitoring on a various points inside the beehive colony using IoT devices. Measured data is transmitted to a remote server where received data streams are processed in real-time using Complex Event Processing (CEP) which enables detection of critical events and report it to the beekeeper. These data streams are compared with reference temperature patterns using machine learning algorithms, which give computers the ability to learn to detect events without being explicitly programmed. This system can significantly reduce the beekeeper reaction time and increase chances for a beehive colony overcoming certain types of anomalies with human intervention.
Solid-State Drives (SSDs) enabled the implementation of real-time cloud services, with a primary focus on high performance and high availability. SSD failure prediction can improve overall system availability by preventing data loss and service interruption. SSDs employ a built-in SMART (Self-Monitoring, Analysis, and Reporting Technology) system to predict failures when certain operating parameters exceed predefined thresholds. Such univariate SMART-based models can predict a limited set of drive failures. Research in SSD failure prediction is focused on multivariate models, which can exploit the complex interactions between SMART attributes that lead to drive failure in order to detect a much larger set of failures. This paper presents an anomaly detection model, based on the Mahalanobis distance measure, which is used for the failure prediction of SSD drives. The model is able to rank the features according to their influence on failure prediction by using a forward feature selection algorithm. The proposed model is tested on a publicly available Alibaba SSD dataset, where the six highest-ranked SMART features were identified. Using this subset of SMART features, our model was able to detect 64% of failures with 81% accuracy while keeping a high precision of 96%.
Wireless sensor networks most commonly operate in 2.4 GHz band using the IEEE 802.15.4 standard for wireless transmission between sensor nodes. This frequency band is also used by IEEE 802.11 and IEEE 802.15.1 networks which operate with higher transmitting powers and could cause significant inter-protocol interference, especially in highly urbanized areas. To improve coexistence in 2.4 GHz band, IEEE 802.15.4 networks must to be able to identify and evade these interferences. In this paper, we present practical implementation of interference classification algorithm based on the k-means clustering which could be used by low-cost commercially available IEEE 802.15.4 transceivers.
Broadcast storms represent events in the local area network (LAN) which is the result of excessive amounts of packet retransmissions by network switches which drastically reduce network performance and even overload network infrastructure which can result in that network becoming inoperational. Broadcast storms originate from broadcast and multicast packets which are targeted for all or groups of stations in LAN. Since these packets are addressed to multiple destinations, they are usually forwarded by network switches on multiple ports to reach all targeted destinations. This can become a serious problem in institutional LANs in which broadcast storms can create a temporary or permanent overload of the entire network infrastructure. This is most notably observed during the videoconferencing calls which could cause packet loss or connection interruptions. In this paper, we analyzed the influence of broadcast storms on network performance in institutional LAN and proposed a machine learning algorithm for the detection of broadcast storms based on the network traffic data collected by the Packet Capture (PCAP) Wireshark software.