Commodity Chemicals


Band Target Entropy Minimization and Target Partial Least Squares for Spectral Recovery and Calibration

arXiv.org Machine Learning

The resolution and calibration of pure spectra of minority components in measurements of chemical mixtures without prior knowledge of the mixture is a challenging problem. In this work, a combination of band target entropy minimization (BTEM) and target partial least squares (T-PLS) was used to obtain estimates for single pure component spectra and to calibrate those estimates in a true, one-at-a-time fashion. This approach allows for minor components to be targeted and their relative amounts estimated in the presence of other varying components in spectral data. The use of T-PLS estimation is an improvement to the BTEM method because it overcomes the need to identify all of the pure components prior to estimation. Estimated amounts from this combination were found to be similar to those obtained from a standard method, multivariate curve resolution-alternating least squares (MCR-ALS), on a simple, three component mixture dataset. Studies from two experimental datasets demonstrate where the combination of BTEM and T-PLS could model the pure component spectra and obtain concentration profiles of minor components but MCR-ALS could not.


Rapid Bayesian optimisation for synthesis of short polymer fiber materials

arXiv.org Machine Learning

The discovery of processes for the synthesis of new materials involves many decisions about process design, operation, and material properties. Experimentation is crucial but as complexity increases, exploration of variables can become impractical using traditional combinatorial approaches. We describe an iterative method which uses machine learning to optimise process development, incorporating multiple qualitative and quantitative objectives. We demonstrate the method with a novel fluid processing platform for synthesis of short polymer fibers, and show how the synthesis process can be efficiently directed to achieve material and process objectives.


Prediction of amino acid side chain conformation using a deep neural network

arXiv.org Machine Learning

A deep neural network based architecture was constructed to predict amino acid side chain conformation with unprecedented accuracy. Amino acid side chain conformation prediction is essential for protein homology modeling and protein design. Current widely-adopted methods use physics-based energy functions to evaluate side chain conformation. Here, using a deep neural network architecture without physics-based assumptions, we have demonstrated that side chain conformation prediction accuracy can be improved by more than 25%, especially for aromatic residues compared with current standard methods. More strikingly, the prediction method presented here is robust enough to identify individual conformational outliers from high resolution structures in a protein data bank without providing its structural factors. We envisage that our amino acid side chain predictor could be used as a quality check step for future protein structure model validation and many other potential applications such as side chain assignment in Cryo-electron microscopy, crystallography model auto-building, protein folding and small molecule ligand docking.


How to use machine learning to identify "good" customers vs "bad" customers - BDO Canada - IT Solutions

#artificialintelligence

Good profitable customers rarely become unprofitable. It is more likely that they were unprofitable from the onset. Determining an approach to define customer value can be a complex decision. Traditionally, we use gross margin in identifying good and bad customers. For example, if your overhead costs are 25% of gross revenue, a good customer is anyone with a gross margin over 25%.


Carbon Black warns that artificial intelligence is not a silver bullet

#artificialintelligence

The research, which Carbon Black says looked "Beyond the Hype" found that the roles of AI and ML in preventing cyber-attacks have been met with both hope and skepticism. The vast majority (93 percent) of the 400 security researchers interviewed while conducting this research said non-malware attacks pose more of a business risk than commodity malware attacks, and more importantly that these are often not stopped by traditional anti-virus offerings. Mike Viscuso, co-founder and CTO of Carbon Black told SC Media UK: "Researchers have reported seeing an increase in the number, and sophistication, of non-malware attacks. These attacks are specifically designed to evade file-based prevention mechanisms and leverage native operating system tools to keep attackers under the radar." One respondent explained: "Most users seem to be familiar with the idea that their computer or network may have accidentally become infected with a virus, but rarely consider a person who is actually attacking them in a more proactive and targeted manner."


Artificial Intelligence: BASF partner with Nuritas on 'next gen' functional peptides

#artificialintelligence

The first step of the partnership will see Nuritas, a biotech and R&D start-up that uses artificial intelligence and new technologies for the discovery of novel food and health ingredients, grant an exclusive royalty-based license to BASF to commercialise one of its existing peptides. A second part of the deal will focus on the discovery of new functional peptides, based on health areas that are strategically important to BASF, using Nuritas' technological expertise and AI platform. According to BASF, peptide networks of focus in the collaboration will be natural, food-derived, patented and of significant benefit to health – including peptides that bring about anti-inflammatory responses. "Cooperating with an innovative and agile start-up like Nuritas enables us to further expand our already broad portfolio of health solutions," commented Saori Dubourg, head of BASF's Nutrition & Health Business. Nuritas' unique platform combines DNA analysis and artificial intelligence (AI) to predict, unlock, and validate peptides from natural sources.


Headlines for the Next 50 Years : Plastics Technology

AITopics Original Links

As micro-molding gives way to "nano-molding," processors will need creative answers to the problems of handling flyspeck-sized parts. Farms may replace oil wells as the source of new plastics. Biopolymers made from cornstarch or other renewable feedstocks will supple-ment petrochemical-derived polymers in a wide range of applications. What if you could change the color of every part right at the machine? Instant color changes may be part of the coming era of "mass customization." New methods of polymer production will allow custom materials to be "programmed" for individual applications. Say Hello to Nano Molding The new frontier of injection molding is "shrinking," says Carl Schiffer, managing partner at Dr. Boy GmbH in Germany. Miniaturization in electronic and medical parts will help push today's micro-molding toward "nano"-size parts. Machinery will need to evolve to meet the "nano" challenge. Shot sizes must become smaller, and screw diameters are already shrinking from the standard lower limit of 14 mm.


The Care and Feeding of Machine Learning - Carbon Black

#artificialintelligence

The output of this task is a series of predictions about binaries' potential maliciousness and relationships to known malware families. These predictions are validated against outside intelligence.


Use of 3D Vision and Artificial Intelligence Predicted to Drive the Global Industrial Robotics Market in the Rubber and Plastic Industries Until 2020, Says Technavio

#artificialintelligence

The industrial robotics market in the rubber and plastic industry for material handling application was valued USD 1.06 billion in 2015. The industrial robotics market in the rubber and plastic industry for assembling and the disassembling application was valued USD 480.9 million in 2015. The industrial robotics market in the rubber and plastic industry for dispensing and painting application was valued at USD 412.4 million in 2015. Manual gluing, painting, and adhesive-dispensing operations demand high precision and consistent quality.


These futuristic driverless pods will run on Singapore's roads by end of the year

Mashable

The pods run on electricity, and are able to travel autonomously on smaller roads, such as those within a gated community or school campus. The pods look like they're going to be larger versions of the ones that already run in Abu Dhabi's cleantech business park, Masdar City -- also produced by 2getthere and SMRT back in 2010. The futuristic petrol car-free park has 10 electric pods, which seat between four and six passengers each, and the system marked its millionth passenger carried in 2014. In this video, you can see Masdar City's pods in operation, exiting their charging blocks and moving seamlessly to the next station.