Collaborating Authors

internal medicine

Initialization methods of convolutional neural networks for detection of image manipulations


Fake images and videos have engulfed mass communication media. This is not something recent, manipulations and forgeries have occurred since the advent of photography itself. These alterations can go from innocent retouches in an attempt to make an image visually attractive to the spread of misleading information or even the use of false media in legal instances. Accordingly, the creation of methods that can help us assure the authenticity of an image presented as non-modified is of paramount importance. In this thesis, we aim at detecting image manipulation operations using deep learning techniques. We present three methods showing the progression of our work under one common objective, i.e, the design and test of Convolutional Neural Network (CNN) initialization methods for image forensic problems with a variance stability focus for the output of a CNN layer.First, we carry out an extensive review of the state of the art in deep-learning-based methods for image forensics. From this review we can confirm that the first layer of a CNN has big impact on the final performance. Specifically, the initialization used on the first-layer filters plays an important role that should be in line with the image forensic task in hand.As our first attempt to address this research problem, we propose a low-complexity initialization method for CNNs. Taking advantage of previous methods designed for the computer vision field, we extend the popular Xavier method to design a filter that would provide variance stability after a convolution operation. This method generates a set of random high-pass filters for the initialization of a CNN's first layer. These filters allow us to better identify forensic traces which usually lie towards the high-frequency part of the image.This first approach constitutes a good staring point of our work. However, a wrong assumption, largely utilized in the research community, was made. This is corrected in our second method where we follow a different data-dependent approach and take into consideration the real statistical properties of natural images. Accordingly, we propose a scaling method for first-layer filters which can cope well with different CNN initialization algorithms. The objective remains in keeping the stability of the variance of data flow in a CNN. We also present theoretical and experimental studies on the output variance for convolutional filter, which are the basis of our proposed data-dependent scaling.Next we describe a revisited version of our first proposal now with a corrected assumption on the statistics of natural images. More precisely, we propose an improved random high-pass initialization method which does not explicitly compute the statistics of input data. We believe that such a ``data-independent'' approach has higher flexibility and broader application range than our second method in situations where the computation of input statistics is not possible.Our proposed methods are tested over several image forensic problems and different CNN architectures.Finally, during all this thesis work we took part in a challenge competition of image forgery detection organized by the French National Research Agency and the French Directorate General of Armaments. We explain in the Appendix the objectives of the challenge along with a brief description of our work conducted for the competition.

GPs to use artificial intelligence to help manage elective care waiting list


The Government has said that artificial intelligence (AI) in GP practices will help manage patients in the elective care backlog. It today announced that new technology and innovation will allow the NHS to treat 30% more elective care patients by 2023/24. It added that NHS'come forward with a delivery plan for tackling the backlog'. In March, NHS England suggested that GPs could be asked to review hospital waiting lists for elective care to help prioritise and manage patients from the following month. Details were limited, but NHS England later told GPs that they must'jointly manage' patients stuck in the backlog of care caused by the Covid pandemic with hospitals. Meanwhile, Pulse revealed in June that NHSX and NHS England were considering the viability of a wider roll out of an artificial intelligence triage model based on that used by Babylon.

Going deeper into Deep Learning


I'd love the thank my friends who gave me permission to use their handsome faces in the name of artificial intelligence science! We can definitely tell that this fine gentleman has brown eyes. On the other hand, the model is pretty certain that this individual has blue eyes with a probability greater than 90%. We have a correct prediction but a not very confident probability of 69% (and that's no coincidence). Finally, we try it on me… not so handsome and no so great prediction confidence.

The Third Revolution in Warfare

The Atlantic - Technology

On the 20th anniversary of 9/11, against the backdrop of the rushed U.S.-allied Afghanistan withdrawal, the grisly reality of armed combat and the challenge posed by asymmetric suicide terror attacks grow harder to ignore. But weapons technology has changed substantially over the past two decades. And thinking ahead to the not-so-distant future, we must ask: What if these assailants were able to remove human suicide bombers or attackers from the equation altogether? As someone who has studied and worked in artificial intelligence for the better part of four decades, I worry about such a technology threat, born from artificial intelligence and robotics. Autonomous weaponry is the third revolution in warfare, following gunpowder and nuclear arms.

Palindrome creates SA-first smart HIV patient and practitioner care solution


Palindrome Data, a data science implementer that specialises in alternative data and machine learning tools for community development, has created what it believes to be South Africa's first suite of digital and paper-based HIV tools backed by machine learning, designed to help frontline healthcare workers triage at-risk patients. The solution, leveraging machine learning and multiple data sources, is designed to be used in both digital and paper-based environments so that healthcare workers can identify and manage high-risk patients and relevant interventions to increase HIV treatment retention and mitigate the risk of loss to follow-up (LTFU). The solution can correctly predict a patient's viral load (suppressed versus unsuppressed) for three out of four patients; and can anticipate two out of three times when a patient will drop out of care. "The biggest obstacle facing HIV patients is dealing with an overburdened healthcare system that can't afford to take the time to deal with their unique challenges," says Lucien De Voux, director of market strategy at Palindrome Data. "There is a need to retain and engage patients in a relevant way.

Designers as Stewards of AI


We have a lot to be grateful for. The average life expectancy in Liverpool during the industrial revolution was 28 years old. Nowadays, we have extraordinary advances in technology that have resulted in artificial hearts and mRNA Covid vaccines; the internet, self-driving cars, and personal computing. Within the next decade, the AI (artificial intelligence) revolution will propagate through everything, and it is predicted by some that it will be a more dramatic shift in technology than the use of the personal computer. However, AI has become an over-hyped buzzword across many industries, and the design world is no exception.

SimpliSafe unveils its first proper outdoor cam


For years, SimpliSafe's only option for outdoor video monitoring (other than the Video Doorbell Pro) was its indoor-only SimpliCam wrapped in a weatherproof rubber sleeve. Now, the company is finally offering a proper, battery-powered outdoor cam, complete with a weatherized shell, a spotlight, and people detection. Available now for $170, the SimpliSafe Wireless Outdoor Security Camera is a svelte, cylindrical camera with a swiveling magnetic base, Wi-Fi connectivity, Alexa and Google Assistant support, and a rechargeable, replaceable battery that promises to deliver between 3 and 6 months of battery life on a single charge. Equipped with two antennas, the new SimpliFi outdoor cam is capable of connecting to 2.4GHz Wi-Fi networks, but it won't work without a SimpliSafe base station. To get a base station, you'll need to purchase one of SimpliSafe's alarm systems, which start at $230 for a four-piece kit.

Deep Learning: Data and Hardware


In past few years, We have seen so much advancement in field of Machine learning as well as in Deep Learning. Deep Learning is a subfield of Machine Learning. Any Good Deep Learning Model majorly depends on two factors viz Data and Hardware. Francois Chollet, Creator of Keras explained the importance of Data in Deep Learning:- If deep learning is steam engine of AI revolution, then data is its coal. More training data we have, more accuracy model will have.

Bang & Olufsen Beosound Level review: A top-tier portable music streamer


Without a doubt, the Bang & Olufsen Beosound Level is the prettiest and best-sounding wireless streaming speaker I've encountered that operates on both AC and battery power. It holds true to the aesthetic spirit that's long driven this legendary Danish electronics brand, ever striving for a magical fusion of design and technology. But be forewarned, buying into this functional work of art isn't for the financially faint of heart: A single Beosound Level costs either $1,499 or $1,799, depending on which model you choose. You might need to rationalize this luxury indulgence as a long-term investment; like the pitch proffered for a Rolex timekeeper, or an exotic Euro sports car. And like those rare goods, the Beosound Level has a sensitive nature that in some ways demands a bit of coddling (more on that in a bit). At the heart of this device (and a few of B&O's other Wi-Fi-enabled speakers) is a new, modular circuit core called Mozart, which the manufacturer says can be swapped out for another if the onboard upgradability ever reaches its limit.

Convolutional Neural Network


Today the topic of discussion is Convolutional Neural Network(CNN). We earlier discussed the Feedforward Neural Network where an output of one linear layer was fed to the next layer with an activation layer sandwiched between the two. Here is the link to the article. The CNN is good at identifying the images and classifying them in different classes. Basically a 2D convolution is the sliding of one smaller matrix over the other bigger matrix.