In this study, we propose a machine-learning-based approach to identify the modal parameters of the output only data for structural health monitoring (SHM) that makes full use of the characteristic of independence of modal responses and the principle of machine learning. By taking advantage of the independence feature of each mode, we use the principle of unsupervised learning, making the training process of the deep neural network becomes the process of modal separation. A self-coding deep neural network is designed to identify the structural modal parameters from the vibration data of structures. The mixture signals, that is, the structural response data, are used as the input of the neural network. Then we use a complex cost function to restrict the training process of the neural network, making the output of the third layer the modal responses we want, and the weights of the last two layers are mode shapes. The deep neural network is essentially a nonlinear objective function optimization problem. A novel loss function is proposed to constrain the independent feature with consideration of uncorrelation and non-Gaussianity to restrict the designed neural network to obtain the structural modal parameters. A numerical example of a simple structure and an example of actual SHM data from a cable-stayed bridge are presented to illustrate the modal parameter identification ability of the proposed approach. The results show the approach s good capability in blindly extracting modal information from system responses.

Neural networks are the pinnacle of Artificial Intelligence, as in recent years we witnessed many novel architectures, learning and optimization techniques for deep learning. Capitalizing on the fact that neural networks inherently constitute multipartite graphs among neuron layers, we aim to analyze directly their structure to extract meaningful information that can improve the learning process. To our knowledge graph mining techniques for enhancing learning in neural networks have not been thoroughly investigated. In this paper we propose an adapted version of the k-core structure for the complete weighted multipartite graph extracted from a deep learning architecture. As a multipartite graph is a combination of bipartite graphs, that are in turn the incidence graphs of hypergraphs, we design k-hypercore decomposition, the hypergraph analogue of k-core degeneracy. We applied k-hypercore to several neural network architectures, more specifically to convolutional neural networks and multilayer perceptrons for image recognition tasks after a very short pretraining. Then we used the information provided by the hypercore numbers of the neurons to re-initialize the weights of the neural network, thus biasing the gradient optimization scheme. Extensive experiments proved that k-hypercore outperforms the state-of-the-art initialization methods.

Chip maker Intel has been chosen to lead a new initiative led by the U.S. military's research wing, DARPA, aimed at improving cyber-defenses against deception attacks on machine learning models. Machine learning is a kind of artificial intelligence that allows systems to improve over time with new data and experiences. One of its most common use cases today is object recognition, such as taking a photo and describing what's in it. That can help those with impaired vision to know what's in a photo if they can't see it, for example, but it also can be used by other computers, such as autonomous vehicles, to identify what's on the road. But deception attacks, although rare, can meddle with machine learning algorithms.

Digital health company Medopad today announced that it's rebranding to Huma and acquiring two companies -- BioBeats and Tarilian Laser Technologies (TLT) -- to add support for new biomarkers to its AI-powered patient monitoring platform. When contacted for comment, a Huma spokesperson declined to disclose the purchase price for the two companies. The acquisitions would appear to be strategic -- increasingly, health systems and hospitals are employing AI-enabled telemedical services to triage and treat patients potentially infected with COVID-19. Huma previously leveraged AI to identify signs of chronic diseases like Parkinson's disease, in partnership with Tencent, but the incorporation of BioBeats' and TLT's technologies will enable it to analyze mental and cardiovascular health data. The thinking goes that the more holistic Huma's platform becomes, the better health outcomes are likely to be.

In 2008, the UK published its first national risk register, allowing a public sense of the national security priorities for civil emergencies. The report measured risks along two dimensions--relative impact and relative likelihood--with the possibility of a pandemic influence topping the list. A year later the world saw the swine flu pandemic, causing hundreds of thousands of deaths. While the UK saw hundreds of thousands of cases, they saw relatively few deaths. From the perspective of governments, pandemics are not black swans. The issue is not whether a country foresees a pandemic and prepares accordingly, it's whether the systems in place can function under the level of stress resulting from a pandemic.

Artificial intelligence (AI) has been a hot topic for a decade now. The concepts that were once taught in the books are now turned into reality, and we are experiencing its existence in our routine life. AI-powered personal assistance in the smartphone has simplified the user experience that an illiterate can browse the web and find his or her favorite song, celebrity, movie, or brand. The ability to automating the simplest to complex tasks, AI has been a victim of controversy. The debate started with some of the people admiring its applications, while others fear the loss of jobs.

In a paper published on the preprint server Arxiv.org this week, researchers at Uber's Advanced Technologies Group (ATG) propose an AI technique to improve autonomous vehicles' traffic movement predictions. It's directly applicable to the driverless technologies that Uber itself is developing, which must be able to detect, track, and anticipate surrounding cars' trajectories in order to safely navigate public roads. It's well-understood that without the ability to predict the decisions other drivers on the road might make, vehicles can't be fully autonomous. In a tragic case in point, an Uber self-driving prototype hit and killed a pedestrian in Tempe, Arizona two years ago, partly because the vehicle failed to detect and avoid the victim. ATG's research, then -- which is novel in that it employs a generative adversarial network (GAN) to make car trajectory predictions as opposed to less complex architectures -- promises to advance the state of the art by boosting the precision of predictions by an order of magnitude.

Even with the best protocols in place, treating COVID-19 patients is inherently dangerous for health professionals. But what if there was a way to monitor patients from a safe distance? This week a clinical team in Boston has reported being able to monitor a COVID-19 patient remotely, thanks to a device developed at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) that can monitor a patient's breathing, movement and sleep patterns using wireless signals. The CSAIL team's device, which they call "Emerald," has been used in multiple hospitals and assistive-care facilities, including with a COVID-19 patient at Heritage Assisted Living in the Boston suburb of Framingham. Developed by MIT professor Dina Katabi and her research group at CSAIL, Emerald is a WiFi-like box that analyzes the wireless signals in the environment using artificial intelligence to infer people's vital signs, sleep, and movement.

We have seen rapid advancements in Artificial Intelligence and related technologies in recent times. Use of AI applications for - Automated customer support systems, chatbots, and personalized shopping experience with product recommendations are common examples. With the growth of Artificial Intelligence industry, we have also seen increase in demand of professionals who are skilled in this technology. The demand for AI professionals are more in - product companies for services like - chatbots, AI_powered visual search, and recommendation engines; companies that offer either offshore, recruitment or training services. Business have realised the potential of AI to devise new products and process to gain a competitive advantages by saving costs and time.

"I would love to see a future where looking inside the body becomes as routine as a blood pressure cuff measurement," says Charles Cadieu '04, MEng '05. As president of the medical technology startup Caption Health, he sees that future in reach--with the help of artificial intelligence. Cadieu still remembers the "lightbulb moment" during his postdoctoral research at MIT when he realized that the field of AI would never be the same. He was working in the lab of James DiCarlo (now the Peter de Florez Professor of Neuroscience) on neural networks--AI systems made up of deep-learning algorithms that emulate the dense networks of neurons in the brain. Until then, neural networks had been unable to perform even simple visual tasks that the brain handles with ease.