Search

Data representation learning is one of the most important problems in machine learning. Unsupervised representation learning becomes meritorious as it has no necessity of label information with observed data. Due to the highly time-consuming learning of deep-learning models, there are many machine-learning models directly adapting well-trained deep models that are obtained in a supervised and end-to-end manner as feature abstractors to distinct problems. However, it is obvious that different machine-learning tasks require disparate representation of original input data. Taking human action recognition as an example, it is well known that human actions in a video sequence are 3-D signals containing both visual appearance and motion dynamics of humans and objects. Therefore, the data representation approaches with the capabilities to capture both spatial and temporal correlations in videos are meaningful. Most of the existing human motion recognition models build classifiers based on deep-learning structures such as deep convolutional networks. These models require a large quantity of training videos with annotations. Meanwhile, these supervised models cannot recognize samples from the distinct dataset without retraining. In this article, we propose a new 3-D deconvolutional network (3DDN) for representation learning of high-dimensional video data, in which the high-level features are obtained through the optimization approach. The proposed 3DDN decomposes the video frames into spatiotemporal features under a sparse constraint in an unsupervised way. In addition, it also can be regarded as a building block to develop deep architectures by stacking. The high-level representation of input sequential data can be used in multiple downstream machine-learning tasks, we evaluate the proposed 3DDN and its deep models in human action recognition. The experimental results from three datasets: 1) KTH data; 2) HMDB-51; and 3) UCF-101, demonstrate that the proposed 3DDN is an alternative approach to feedforward convolutional neural networks (CNNs), that attains comparable results.

In the field of computer vision, Video captioning is a very important and meaningful task, which could automatically generate textual descriptions of contents from videos. It is a challenging problem due to the difficulties of understanding the objects and activities in a video. Benefit from the rapid development of deep learning technology, e.g. sequence to sequence model, video captioning task has achieved very accurate results. However, there are two serious flaws, the first is that the pre-trained deep models are often used as visual feature abstractors as the training is highly time-consuming, so the feature generalization performance generated by these pre-trained Encoder is limited when we directly employ those networks in video captioning tasks. The second is that each frame in the video is processed separately, ignoring the correlation of video data in the time dimension. In this work, we propose video captioning model with attention-memory module to explore the role of capturing temporal correlations which with sequence to sequence model as the background and showing the importance of temporal structure to vision tasks by adding the correlation of videos when extracting features and enhancing the time-memory capability. Our experiments are based on two most famous benchmark datasets in the field of video captioning: MSVD and MSR-VTT. Then employ BLEU and METEOR to evaluate the accuracy of the description generated by different methods. Finally, the experimental results confirm that the proposed model could make significant improvements in description results compared with the baseline models.

When multiple trace contaminants of significantly different chemical properties are present in a single source of contaminated water, designing an engineered sorbent for their simultaneous removal poses a major challenge. Physical–chemical properties of the sorption sites need to be tailored and expanded for preferential binding of more than one contaminant in such cases. The scientific challenge becomes increasingly complex when the sorbent requires to be reusable through intermittent regenerations. In this study, hydrated Fe(III) oxide or HFO nanoparticles were dispersed within an ion exchange fiber containing covalently attached quaternary ammonium functional groups. The resulting hybrid anion exchange fiber (HAIX-F) showed very high sorption affinity for both perchlorate and arsenate in the presence of orders of magnitude greater concentrations of competing sulfate and chloride anions. A series of experimental studies validated that relatively hydrophobic perchlorate was selectively bound to ...

Separation processes using ion exchange materials are ubiquitous regarding the selective removal of contaminants of environmental concern. Recently, highly regulated contaminants, such as arsenic, have gained notoriety on account of carcinogenic effects and subsequent promulgation of new drinking water standards by the United States Environmental Protection Agency. Other nonregulated compounds such as hardness (e.g., Ca2+, Mg2+), pose a particular concern to avoid scaling in heat-transfer equipment, foulingz in membranes, and high consumption of detergents and sequestering chemicals in cooling and wash water. In general, ion exchange processes used to remove hardness generate concentrated brine or mineral acid as a waste regenerant stream. Residuals management and long-term sustainability issues will continue to be major concerns with these processes. The subject paper reports and discusses the results and attributes of two new separation processes using ion exchange fibers (IX-fibers). The first process involves the selective removal of arsenic using hybridized IX-fibers that contain dispersed hydrated ferric oxide (HFO) nanoparticles. Anion-exchanger-supported HFO particles offered a high arsenic removal capacity; less than 10% of influent arsenic broke through after 30,000 bed volumes. Hybrid fibers were also amenable to efficient regeneration with 2% NaOH and 2% NaCl and capable of simultaneous removal of both arsenic(V) and arsenic(III). The second process involves the environmentally benign removal of hardness. Most importantly, this process uses harvested snowmelt (or rainwater) sparged with carbon dioxide as the regenerant. Consequently, the spent regenerant does not contain a high concentration of aggressive chemicals such as sodium chloride or acid like traditional ion-exchange processes nor does the process produce voluminous sludges as does lime softening. The bulk of carbon dioxide consumed during regeneration remains sequestered in the aqueous phase as alkalinity. For both treatment strategies, IX-fibers form the heart of the process. They are essentially thin cylindrical polymeric strands 10–20 μm in diameter with functional groups residing near to the fiber surface. Low intraparticle diffusional resistance is the underlying reason why calcium loaded weak acid IX-fibers are amenable to efficient regeneration using either snowmelt or rainwater sparged with carbon dioxide. Additionally, for hybrid IX-fibers, enhanced adsorption kinetics may offer the possibility for certain point of use applications, which are unavailable to their resin counterparts. © 2006 American Institute of Chemical Engineers Environ Prog, 2006

Software testability is becoming an important factor to be considered during software development and assessment, especially for critical software. We give software testability, previously defined by Voas, a new model and measurement which is done before random black-box testing with respect to a particular input distribution. We also compare our measurement results with the results simulated according to Voas's model. It showed that our rough testability estimate provides enough information and will be used as guidelines for software development.