In general, we wish to interpret the most broadband data possible. However, broadband data do not always provide the best insight for seismic attribute analysis. Obviously, spectral bands contaminated by noise should be eliminated. However, tuning gives rise to spectral bands with higher signal-to-noise ratios. To quantify geologic discontinuities in different scales, we combined spectral decomposition and coherence. Using spectral decomposition, the spectral amplitudes corresponding to a given scale geologic discontinuity, as well as some subtle features, which would otherwise be buried within the broadband seismic response, can be extracted. We applied this workflow to a 3D land data volume acquired over the Tarim Basin, Northwest China, where karst forms the principle reservoirs. We found that channels are better illuminated around 18 Hz, while subtle discontinuities were better delineated around 25 Hz.

Photovoltaic (PV) systems are becoming more vulnerable to cyber threats. In response to this emerging concern, developing cyber-secure power electronics converters has received increased attention from the IEEE Power Electronics Society that recently launched a cyber-physical-security initiative. This letter proposes a deep sequence learning based diagnosis solution for data integrity attacks on PV systems in smart grids, including dc-dc and dc-ac converters. The multilayer long short-term memory networks are used to leverage time-series electric waveform data from current and voltage sensors in PV systems. The proposed method has been evaluated in a PV smart grid benchmark model with extensive quantitative analysis. For comparison, we have evaluated classic data-driven methods, including K-nearest neighbor, decision tree, support vector machine, artificial neural network, and convolutional neural network. Comparison results verify performances of the proposed method for detection and diagnosis of various data integrity attacks on PV systems.

With the dramatic growth and complexity of seismic data, manual seismic facies analysis has become a significant challenge. Machine learning and deep learning (DL) models have been widely adopted to assist geophysical interpretations in recent years. Although acceptable results can be obtained, the uninterpretable nature of DL (which also has a nickname ``alchemy'') does not improve the geological or geophysical understandings on the relationships between the observations and background sciences. This article proposes a noble interpretable DL model based on 3-D (spatial-spectral) attention maps of seismic facies features. Besides regular data-augmentation techniques, the high-resolution spectral analysis technique is employed to generate multispectral seismic inputs. We propose a trainable soft attention mechanism-based deep dilated convolutional neural network (ADDCNN) to improve the automatic seismic facies analysis. Furthermore, the dilated convolution operation in the ADDCNN generates accurate and high-resolution results in an efficient way. With the attention mechanism, not only the facies-segmentation accuracy is improved but also the subtle relations between the geological depositions and the seismic spectral responses are revealed by the spatial-spectral attention maps. Experiments are conducted, where all major metrics, such as classification accuracy, computational efficiency, and optimization performance, are improved while the model complexity is reduced.

Internet of Things (IoT) are vulnerable to both cyber and physical attacks. Therefore, a cyber-physical security system against different kinds of attacks is in high demand. Traditionally, attacks are detected via monitoring system logs. However, the system logs, such as network statistics, file access records, can be forged. Furthermore, existing solutions mainly target cyber attacks. This paper proposes the first energy auditing and analytics based IoT monitoring mechanism. To our best knowledge, this is the first attempt to detect and identify IoT cyber and physical attacks based on energy auditing. Using the energy meter readings, we develop a dual deep learning model system, which adaptively learns the system behaviors in a normal condition. Unlike the previous single deep learning models for energy disaggregation, we propose a disaggregation-aggregation architecture. The innovative design makes it possible to detect both cyber and physical attacks. The disaggregation model analyzes the energy consumptions of system subcomponents, e.g. CPU, network, disk, etc. to identify cyber attacks, while the aggregation model detects the physical attacks by characterizing the difference between the measured power consumption and prediction results. Using energy consumption data only, the proposed system identifies both cyber and physical attacks. The system and algorithm designs are described in detail. In the hardware simulation experiments, the proposed system exhibits promising performances.

This paper presents a novel real-time smart system performing fall detection, location, and notification based on floor vibration data produced by fall downs. Only using floor vibration as the recognition source, the system incorporates a person identification through vibration produced by footsteps to inform who is the fallen person. Our approach operates in a real-time style, which means the system recognizes a fall immediately and can identify a person with only one or two footsteps. A collaborative in-network location method is used in which sensors collaborate with each other to recognize the person walking, and more importantly, detect if the person falls down at any moment. We also introduce a voting system among sensor nodes to improve person identification accuracy. Our system is robust to identify fall downs from other possible similar events, like jumps, door close, objects fall down, etc. Such a smart system can also be connected to smart commercial devices (Google Home or Amazon Alexa) for emergency notifications. Our approach represents an advance in smart technology for elder people who live alone. Evaluation of the system shows it is able to detect fall downs with an acceptance rate of 95.14% (distinguishing from other possible events), and it identifies people with one or two steps in a 97.22% (higher accuracy than other methods that use more footsteps). The fall down location error is smaller than 0.27 meters, which it is acceptable compared to the height of a person.