A potent technique for drawing conclusions from data and advancing corporate analytics is machinelearning (ML). Although successful ML project implementation calls for more than simply academic know-how;it also calls...
详细信息
Water is essential for nurturing plants and ensuring high yields. With optimal plant growth being fundamental, managing irrigation challenges due to lifestyle changes is crucial. Crops have varying water needs, some c...
详细信息
Aquaculture plays a pivotal role in meeting the growing global demand for seafood. However, ensuring optimal water quality within aquaculture ponds is a pressing challenge. This project proposes a paradigm shift by in...
详细信息
Globally, heart disease poses a significant challenge to public health. Early identification is crucial for effectively managing and treating heart conditions. machinelearning has shown promising results in predictin...
详细信息
Nowadays, in a dynamic data center landscape, effective distribution of computational resources is crucial to achieving peak performance and cost-efficiency. This study addresses the challenge of distinguishing artifi...
详细信息
IoT has changed our lives through the increased convenience of automating mundane tasks, enhancing home security systems, wearable devices to improve health and wellness, and improved connectivity. Vast volumes of dat...
详细信息
This work investigates machinelearning and deep learning methods for drug categorization in order to address the urgent problem of opioid abuse. Because of the intricacy of the issue, many approaches to anticipate op...
详细信息
One of the most groundbreaking approaches to the processing and analysis of large datasets has been created as a result of the combination of MapReduce techniques and machinelearning algorithms within the framework o...
详细信息
Anomaly-based attack detection methods that rely on learning the benign profile of operation are commonly used for identifying data falsification attacks and faults in cyber-physical systems. However, most works do no...
详细信息
ISBN:
(纸本)9798350349955;9798350349948
Anomaly-based attack detection methods that rely on learning the benign profile of operation are commonly used for identifying data falsification attacks and faults in cyber-physical systems. However, most works do not assume the presence of attacks while training the anomaly detectors- and their impact on eventual anomaly detection performance during the test set. Some robust learning methods overcompensate mitigation which leads to increased false positives in the absence of attacks/threats during training. To achieve this balance, this paper proposes a framework to enhance the robustness of previous anomaly detection frameworks in smart living applications, by introducing three profound design changes for threshold learning of time series anomaly detectors:(l) Tukey biweight loss function instead of square loss function (2) adding quantile weights to regression errors of Tukey (3) modifying the definition of empirical cost function from MSE to the harmonic mean of quantile weighted Tukey losses. We show that these changes mitigate performance degradation in anomaly detectors caused by untargeted poisoning attacks during training-while is simultaneously able to prevent false alarms in the absence of such training set attacks. We evaluate our work using a proof of concept that uses state-of-the-art anomaly detection in smart living CPS that detects false data injection in smart metering.
In this paper, we characterize symmetric locality. In designing algorithms, compilers, and systems, data movement is a common bottleneck in high-performance computation, in which we improve cache and memory performanc...
详细信息
暂无评论