Combining information from various data sources has become an important research topic in machine learning with many scientific applications. Most previous studies employ kernels or graphs to integrate different types of features, which routinely assume one weight for one type of features. However, for many problems, the importance of features in one source to an individual cluster of data can be varied, which makes the previous approaches ineffective. In this paper, we propose a novel multi-view learning model to integrate all features and learn the weight for every feature with respect to each cluster individually via new joint structured sparsity-inducing norms. The proposed multi-view learning framework allows us not only to perform clustering tasks, but also to deal with classification tasks by an extension when the labeling knowledge is available. A new efficient algorithm is derived to solve the formulated objective with rigorous theoretical proof on its convergence. We applied our new data fusion method to five broadly used multi-view data sets for both clustering and classification. In all experimental results, our method clearly outperforms other related state-of-the-art methods.
Recently, realistic image generation using deep neural networks has become a hot topic in machine learning and computer vision. Images can be generated at the pixel level by learning from a large collection of images. Learning to generate colorful cartoon images from black-and-white sketches is not only an interesting research problem, but also a potential application in digital entertainment. In this paper, we investigate the sketch-to-image synthesis problem by using conditional generative adversarial networks (cGAN). We propose the auto-painter model which can automatically generate compatible colors for a sketch. The new model is not only capable of painting hand-draw sketch with proper colors, but also allowing users to indicate preferred colors. Experimental results on two sketch datasets show that the auto-painter performs better that existing image-to-image methods.
Software-defined networking (SDN) offers a novel paradigm for effective network management by decoupling the control plane from the data plane thereby allowing a high level of manageability and programmability. However, the notion of a centralized controller becomes a bottleneck by opening up a host of vulnerabilities to various types of attacks. One of the most harmful, stealthy, and easy to launch attacks against networked systems is the link flooding attack (LFA). In this paper, we demonstrate the vulnerability of the SDN control layer to LFA and how the attack strategy differs when targeting traditional networks which primarily involves attacking the links directly. In LFA, the attacker employs bots to surreptitiously send low rate legitimate traffic on the control channel which ultimately results in disconnecting control plane from the data plane. Mitigating LFA on the control channel remains a challenge in the network security paradigm with the use of network traffic filtering only. To address this challenge, we propose CyberPulse, a novel effective countermeasure, underpinning a machine learning-based classifier to alleviate LFA in SDN. CyberPulse performs network surveillance by classifying network traffic using deep learning techniques and is implemented as an extension module in the Floodlight controller. CyberPulse was evaluated for its accuracy, false positive rate, and effectiveness as compared to competing approaches on realistic networks generated using Mininet. The results show that CyberPulse can classify malicious flows with high accuracy and mitigate them effectively.
Neural tube defects (NTDs) represent a prevalent and severe category of congenital anomalies in humans. Cadmium (Cd) is an environmental teratogen known to cause fetal NTDs. However, its underlying mechanisms remain elusive. This study aims to investigate the therapeutic potential of lipophagy in the treatment of NTDs, providing valuable insights for future strategies targeting lipophagy activation as a means to mitigate NTDs.We successfully modeled NTDs by Cd exposure during pregnancy. RNA sequencing was employed to investigate the transcriptomic alterations and functional enrichment of differentially expressed genes in NTD placental tissues. Subsequently, pharmacological/genetic (Atg5
Domestic violence (DV) is not only a major health and welfare issue but also a violation of human rights. In recent years, domestic violence crisis support (DVCS) groups active on social media have proven indispensable in the support services provided to victims and their families. In the deluge of online-generated content, the significant challenge arises for DVCS groups' to manually detect the critical situation in a timely manner. For instance, the reports of abuse or urgent financial help solicitation are typically obscured by a vast amount of awareness campaigns or prayers for the victims. The state-of-the-art deep learning models with the embeddings approach have already demonstrated superior results in online text classification tasks. The automatic content categorization would address the scalability issue and allow the DVCS groups to intervene instantly with the exact support needed. Given the problem identified, the study aims to: 1) construct the novel "gold standard' dataset from social media with multi-class annotation; 2) perform the extensive experiments with multiple deep learning architectures; 3) train the domain-specific embeddings for performance improvement and knowledge discovery; and 4) produce the visualizations to facilitate models analysis and results in interpretation. The empirical evidence on a ground truth dataset has achieved an accuracy of up to 92% in classes prediction. The study validates an application of cutting edge technology to a real-world problem and proves beneficial to DVCS groups, health care practitioners, and most of all victims.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
