Tiny Vision Processing Chip, EQSCALE Finally developed

                            

        A team of researchers from the National University of Singapore (NUS) has developed a novel microchip, named EQSCALE, which is capable of capturing visual details from video frames at extremely low power consumption. The video feature extractor uses 20 times less power than existing best-in-class chips, and hence requires 20 times smaller battery, and could reduce the size of smart vision systems down to the millimetre range. For example, it can be powered continuously by a millimetre-sized solar cell without the need for battery replacement.

Led by Associate Professor Massimo Alioto from the Department of Electrical and Computer Engineering at the NUS Faculty of Engineering, the team's discovery is a major step forward in developing millimetre-sized smart cameras with near-perpetual lifespan. It will also pave the way for cost-effective Internet of Things (IoT) applications, such as ubiquitous safety surveillance in airports and key infrastructure, building energy management, workplace safety, and elderly care.

"IoT is a fast-growing technology wave that uses massively distributed sensors to make our environment smarter and human-centric. Vision electronic systems with long lifetime are currently not feasible for IoT applications due to their high power consumption and large size. Our team has addressed these challenges through our tiny EQSCALE chip and we have shown that ubiquitous and always-on smart cameras are viable. We hope that this new capability will accelerate the ambitious endeavour of embedding the sense of sight in the IoT, said Assoc Prof Alioto.

Tiny vision processing chip that works non-stop

A video feature extractor captures visual details taken by a smart camera and turns them into a much smaller set of points of interest and edges for further analysis. Video feature extraction is the basis of any computer vision system that automatically detects, classifies and tracks objects in the visual scene. It needs to be performed on every single frame continuously, thus defining the minimum power of a smart vision system and hence the minimum system size.

The power consumption of previous state-of-the-art chips for feature extraction ranges from various milliwatts to hundreds of milliwatts, which is the average power consumption of a smartwatch and a smartphone, respectively. To enable near-perpetual operation, devices can be powered by solar cells that harvest energy from natural lighting in living spaces. However, such devices would require solar cells with a size in the centimetre scale or larger, thus posing a fundamental limit to the miniaturisation of such vision systems. Shrinking them down to the millimetre scale requires the reduction of the power consumption to much lesser than one milliwatt.

The NUS Engineering team's microchip, EQSCALE, can perform continuous feature extraction at 0.2 milliwatts -- 20 times lower in power consumption than any existing technology. This translates into a major advancement in the level of miniaturisation for smart vision systems. The novel feature extractor is smaller than a millimetre on each side, and can be powered continuously by a solar cell that is only a few millimetres in size.

Assoc Prof Alioto explained, "This technological breakthrough is achieved through the concept of energy-quality scaling, where the trade-off between energy consumption and quality in the extraction of features is adjusted. This mimics the dynamic change in the level of attention with which humans observe the visual scene, processing it with different levels of detail and quality depending on the task at hand. Energy-quality scaling allows correct object recognition even when a substantial number of points of interests are missed due to the degraded quality of the target."

Next steps

The development of EQSCALE is a crucial step towards the future demonstration of millimetre-sized vision systems that could operate indefinitely. The NUS research team is looking into developing a miniaturised computer vision system that comprises smart cameras equipped with vision capabilities enabled by the microchip, as well as a machine learning engine that comprehends the visual scene. The ultimate goal of the NUS research team is to enable massively distributed vision systems for wide-area and ubiquitous visual monitoring, vastly exceeding the traditional concept of cameras.

Ai predicts corruption

Researchers from the University of Valladolid (Spain) have created a computer model based on neural networks which provides in which Spanish provinces cases of corruption can appear with greater probability, as well as the conditions that favor their appearance. This alert system confirms that the probabilities increase when the same party stays in government more years.

Two researchers from the University of Valladolid have developed a model with artificial neural networks to predict in which Spanish provinces corruption cases could appear with more probability, after one, two and up to three years.

The study, published in Social Indicators Research, does not mention the provinces most prone to corruption so as not to generate controversy, explains one of the authors, Ivan Pastor, to Sinc, who recalls that, in any case, "a greater propensity or high probability does not imply corruption will actually happen."

The data indicate that the real estate tax (Impuesto de Bienes Inmuebles), the exaggerated increase in the price of housing, the opening of bank branches and the creation of new companies are some of the variables that seem to induce public corruption, and when they are added together in a region, it should be taken into account to carry out a more rigorous control of the public accounts.

"In addition, as might be expected, our model confirms that the increase in the number of years in the government of the same political party increases the chances of corruption, regardless of whether or not the party governs with majority," says Pastor.

"Anyway, fortunately -- he adds -, for the next years this alert system predicts less indications of corruption in our country. This is mainly due to the greater public pressure on this issue and to the fact that the economic situation has worsened significantly during the crisis."

To carry out the study, the authors have relied on all cases of corruption that appeared in Spain between 2000 and 2012, such as the Mercasevilla case (in which the managers of this public company of the Seville City Council were charged) and the Baltar case (in which the president of the Diputación de Ourense was sentenced for more than a hundred contracts "that did not complied with the legal requirements").

The collection and analysis of all this information has been done with neural networks, which show the most predictive factors of corruption. "The use of this AI technique is novel, as well as that of a database of real cases, since until now more or less subjective indexes of perception of corruption were used, scorings assigned to each country by agencies such as Transparency International, based on surveys of businessmen and national analysts," highlights Pastor.

The authors hope that this study will contribute to better direct efforts to end corruption, focusing the efforts on those areas with the greatest propensity to appear, as well as continuing to move forward to apply their model internationally.