Search

Machine learning related research in transient control has drawn considerable attention with the rapid increase in data measurement from power grids. Two key components, the control algorithm and system structure, work together to determine the control performance. The design of control laws, the selection of phase measurement units, the allocation of power resources, and the scheduling of communication topology in limited cyber-physical resources need to be considered. Many existing scheduling or planning schemes specialized for control structure are designed based on various linearized analytical models or the optimization of steady states. However, the transient dynamics of power grids are nonlinear and parts of these dynamics are usually unknown. Linearized analytical models cannot represent the transient dynamics of power grids with large disturbances. This article proposes a sparse neural network based reinforcement learning scheme to optimize the control system structure for the transient stability enhancement of power grids with energy storage systems. One adjustable group sparse weight matrix is introduced to formulate both control structure and actor–critic networks. This strategy enables the proposed scheme to simultaneously schedule the control system structure and design the control laws by online learning without solving any combinational optimization problems or requiring any linearized analytical models. The sufficient conditions of learning stability, control stability, and group sparsity are thoroughly studied by mathematical analysis. The proposed scheme is simulated on an IEEE 118-bus test system for verification. The simulation results confirm the feasibility, advantages, and adaptability of the proposed method.

As one chemical composition, nicotine content has an important influence on the quality of tobacco leaves. Rapid and non-destructive quantitative analysis of nicotine is an important task in the tobacco industry. Near-infrared (NIR) spectroscopy as an effective chemical-composition analysis technique has been widely used. In this paper, we propose a one-dimensional Fully Convolutional Network (1D-FCN) model to quantitatively analyze the nicotine composition of tobacco leaves using NIRspectroscopy data in a cloud environment. This 1D-FCN model uses one-dimension convolution layers to directly extract the complex features from sequential spectroscopy data. It consists of five convolutional layers and two full connection layers with the max-pooling layer replaced by a convolutional layer to avoid information loss.Cloud computing techniques are used to solve the increasing requests of large-size data analysis and implement data sharing and accessing.Experimental results show that the proposed 1D-FCN model can effectively extract the complex characteristics inside the spectrum and more accurately predict the nicotine volumes in tobacco leaves than other approaches. This research provides a deep learning foundation for quantitative analysis of NIR spectra data in the tobacco industry.

Poor weather conditions, such as fog, haze, and mist, cause visibility degradation in captured images. Existing imaging devices lack the ability to effectively and efficiently mitigate the visibility degradation caused by poor weather conditions in real time. Image depth information is used to eliminate hazy effects by using existing physical model-based approaches. However, the imprecise depth information always affects dehazing performance. This article proposes an image fusion-based algorithm to enhance the performance and robustness of image dehazing. Based on a set of gamma-corrected underexposed images, pixelwise weight maps are constructed by analyzing both global and local exposedness to guide the fusion process. The spatial-dependence of luminance of the fused image is reduced, and its color saturation is balanced in the dehazing process. The performance of the proposed solution is confirmed in both theoretical analysis and comparative experiments.

Remote sensing images have been widely used in military, national defense, disaster emergency response, ecological environment monitoring, among other applications. However, fog always causes definition of remote sensing images to decrease. The performance of traditional image defogging methods relies on the fog-related prior knowledge, but they cannot always accurately obtain the scene depth information used in the defogging process. Existing deep learning-based image defogging methods often perform well, but they mainly focus on defogging ordinary outdoor foggy images rather than remote sensing images. Due to the different imaging mechanisms used in ordinary outdoor images and remote sensing images, fog residue may exist in the defogged remote sensing images obtained by existing deep learning-based image defogging methods. Therefore, this paper proposes remote sensing image defogging networks based on dual self-attention boost residual octave convolution (DOC). Residual octave convolution (residual OctConv) is used to decompose a source image into high- and low-frequency components. During the extraction of feature maps, high- and low-frequency components are processed by convolution operations, respectively. The entire network structure is mainly composed of encoding and decoding stages. The feature maps of each network layer in the encoding stage are passed to the corresponding network layer in the decoding stage. The dual self-attention module is applied to the feature enhancement of the output feature maps of the encoding stage, thereby obtaining the refined feature maps. The strengthen-operate-subtract (SOS) boosted module is used to fuse the refined feature maps of each network layer with the upsampling feature maps from the corresponding decoding stage. Compared with existing image defogging methods, comparative experimental results confirm the proposed method improves both visual effects and objective indicators to varying degrees and effectively enhances the definition of foggy remote sensing images.

Remote sensing images are widely used in object detection and tracking, military security, and other computer vision tasks. However, remote sensing images are often degraded by suspended aerosol in the air, especially under poor weather conditions, such as fog, haze, and mist. The quality of remote sensing images directly affect the normal operations of computer vision systems. As such, haze removal is a crucial and indispensable pre-processing step in remote sensing image processing. Additionally, most of the existing image dehazing methods are not applicable to all scenes, so the corresponding dehazed images may have varying degrees of color distortion. This paper proposes a novel atmospheric light estimation based dehazing algorithm to obtain high visual-quality remote sensing images. First, a differentiable function is used to train the parameters of a linear scene depth model for the scene depth map generation of remote sensing images. Second, the atmospheric light of each hazy remote sensing image is estimated by the corresponding scene depth map. Then, the corresponding transmission map is estimated on the basis of the estimated atmospheric light by a haze-lines model. Finally, according to the estimated atmospheric light and transmission map, an atmospheric scattering model is applied to remove haze from remote sensing images. The colors of the images dehazed by the proposed method are in line with the perception of human eyes in different scenes. A dataset with 100 remote sensing images from hazy scenes was built for testing. The performance of the proposed image dehazing method is confirmed by theoretical analysis and comparative experiments.

People with complex communication needs can use a high-technology augmentative and alternative communication device to communicate with others. Currently, researchers and clinicians often use data logging from high-tech augmentative and alternative communication devices to analyze augmentative and alternative communication user performance. However, existing automated data logging systems cannot differentiate the authorship of the data log when more than one user accesses the device. This issue reduces the validity of the data logs and increases the difficulties of performance analysis. Therefore, this paper presents a solution using a deep neural network-based visual analysis approach to process videos to detect different augmentative and alternative communication users in practice sessions. This approach has significant potential to improve the validity of data logs and ultimately to enhance augmentative and alternative communication outcome measures.

Person re-identification (Re-ID) is challenging due to host of factors: the variety of human positions, difficulties in aligning bounding boxes, and complex backgrounds, among other factors. This paper proposes a new framework called EXAM (EXtreme And Moderate feature embeddings) for Re-ID tasks. This is done using discriminative feature learning, requiring attention-based guidance during training. Here &ldquo, Extreme&rdquo, refers to salient human features and &ldquo, Moderate&rdquo, refers to common human features. In this framework, these types of embeddings are calculated by global max-pooling and average-pooling operations respectively, and then, jointly supervised by multiple triplet and cross-entropy loss functions. The processes of deducing attention from learned embeddings and discriminative feature learning are incorporated, and benefit from each other in this end-to-end framework. From the comparative experiments and ablation studies, it is shown that the proposed EXAM is effective, and its learned feature representation reaches state-of-the-art performance.

The inconsistency caused by different factors, such as different camera imaging methods, complex imaging environments, and changes in light, present a huge challenge to person re-identification (re-ID). Unsupervised domain adaptation (UDA) can solve the inconsistency issue to a certain extent, but different datasets may not have any overlapping of people’s identities. Therefore, it is necessary to pay attention to people’s identities in solving domain-dissimilarity. A camera imaging style transformation with preserved self-similarity and domain-dissimilarity (CSPSD) is proposed to solve the cross-domain issue in person re-ID. First, CycleGAN is applied to determine the style conversion between source and target domains. Intra-domain identity constraints are used to maintain identity consistency between source and target domains during the image style transformation process. Maximum mean difference (MMD) is used to reduce the difference in feature distribution between source and target domains. Then, a one-to-n mapping method is proposed to achieve the mapping between positive pairs and distinguish negative pairs. Any sample image from the source domain and its transformed image or a transformed image with the same identity information compose a positive pair. The transformed image and any image from the target domain compose a negative pair. Next, a circle loss function is used to improve the learning speed of positive and negative pairs. Finally, the proposed CSPSD that can effectively reduce the difference between domains and an existing feature learning network work together to learn a person re-ID model. The proposed method is applied to three public datasets, Market-1501, DukeMTMC-reID, and MSMT17. The comparative experimental results confirm the proposed method can achieve highly competitive recognition accuracy in person re-ID.

Due to the complex structure of a distributed energy resources system (DES) and a large amount of sensor data, local computers cannot provide enough computing resources to process the related data in a short time. Moreover, network integration causes a power system vulnerable to denial of service (DoS) attacks. DoS attacks result in the loss of partial sensor data, which affects the control performance of local computers on a power system. Therefore, this paper proposes a power system structure optimization strategy based on both sparse constraint optimization and cloud computing to solve the lack of computing power from local computers and prevent DoS attacks. Cloud computing is introduced to provide powerful computing resources for processing the related data in the proposed solution. The blocking probability of sensor data caused by DoS attacks is reduced by optimizing the sensor layout of a power system and reducing the transmission of sensor data. This paper also proposes a control strategy based on actor–critic reinforcement learning (RL) to maintain the stability of a power system during the structure optimization process. Three IEEE bus test systems are used to verify the effectiveness of the proposed structure optimization method and control strategy. The experimental results confirm that the proposed structure optimization method and control strategy can maintain the stability of a power system under DoS attacks.

Buffalo State College has hosted a number of summer institutes and conferences over the years to increase the availability of computer science (CS) courses taught in western and central New York high schools. These institutes and conferences have contributed to strong CS programs in suburban and private schools, but not in urban and rural/small town schools. In the summer of 2018, Buffalo State invited high school principals from across the area to a summit to discuss the future of CS. Forty-six principals participated in the summit and of those school leaders, 30% of them were from rural/small towns. In this poster, the research team will present the results of a mixed-methods school leadership study based on the value rural/small town principals place on CS. Results from a survey, conducted at the summit, and semi-structured interviews will be presented. A sociocultural approach was used to analyze the data since the principals' values and mediated actions toward CS were influenced by the socially situated environment of the schools they lead

Near-infrared (NIR) spectroscopy techniques have been widely used to classify tobacco cultivation regions. NIR spectroscopy of tobacco leaves involves a large number of correlated features, so it is difficult to find the connection between spectral data and tobacco cultivation regions. This paper proposes a novel classification model of tobacco cultivation regions that integrates residual network (ResNet) and NIR spectroscopy techniques. As the number of neural network layers increases, the network may have issues such as network degradation, gradient disappearance, and the reduction of sample recognition rate. The proposed model applies a residual module to a neural network which effectively solves or alleviates the vanishing gradient issues caused by the increase of network depth. This paper also adds balance and suppression factors to the loss function to solve the issues caused by uneven sizes of tobacco samples collected from different cultivation regions in the training process. In the proposed method, tobacco samples are marked as internal and external samples respectively during the training process. Internal samples are collected from the corresponding cultivation regions in the north, northeast, and northwest of Guizhou Province, China. External samples are collected from other cultivation regions. The weight distributions of internal and external samples can be adjusted by experimental results to improve the identification accuracy of the proposed solution. The size of training samples determines the generalization ability of the network and affects the experimental results. A parametric rectified linear unit (PReLU) function is integrated into the network, in which the parameters of a linear unit are adaptively learned to further improve the identification accuracy of the proposed solution. Compared with current mainstream methods, the experimental results confirm that the proposed model is superior in accurately identifying different cultivation regions of tobacco leaves.

The poster describes an innovative approach to help secondary school teachers enhance their computer science (CS) knowledge through the Google funded CS4HS (Computer Science for High School) program. Through a 4-day professional training workshop teachers learn different computational thinking skills, CS concepts and related tools in an attempt to promote CS education by establishing a computer club and eventually teaching CS courses in their schools. The training includes units from the Exploring Computer Science curriculum and brainstorming sessions on starting clubs, club activities, and strategies for recruiting more girls and minorities in clubs. Participating teachers are invited back during the school year to participate in events including a CS conference and a competition and showcase for their students to continue the momentum started by the workshop. Teachers share the barriers to establishing clubs and success stories of being the first teachers to introduce computer science into their schools. More than 150 teachers from more than 50 secondary schools have participated in the CS4HS workshops since the program"s inception. The result is that many of the participating teachers now have established computer clubs; many teach CS courses and many bring their club students to participate in the annual CS4HS Showcase and Competition event at Buffalo State College; all contributing to the goals of CS4HS which is to promote CS education in every secondary schools of Western New York. This will create a pipeline of aspiring CS students and help to alleviate the current and predicted shortage of CS professionals.