by nurazaliah | Dec 4, 2018 | PhD, research, scholarship
Project Description
Applications are invited for a fully-funded three year PhD to commence in October 2019.
The PhD will be based in the Faculty of Business and Law, and will be supervised by Professor Alessio Ishizaka and Dr Giovanni Pino.
The work will look at:
-developing a state-of-the art review of existing data-driven multi-criteria decision methods;
-developing a data-driven multi-criteria decision method based on sentiment analysis;
-validating the method in a marketing context.
Project description
It is well known that optimal decisions are fundamentals for companies but also for individuals. Thus, it is not surprising that multi-criteria decision analysis has undergone a considerable expansion in recent years (Figueira et al. 2016), as a large number of methodologies have been developed and used in multiple contexts (lshizaka and Nemery 2013). However, these methods require a direct input from the decision-maker. If a decision-maker is unavailable, the multi-criteria decision method cannot be used. Furthermore, if the decision applies to a large group of people (e.g. which product to launch on the market), it is unlikely that a single decision-maker can represent all the parties. It is, therefore, important to develop new data-driven techniques based on secondary data, which do not require a direct input of a decision-maker.
To this end, we propose to use sentiment analysis to extract consumer preferences from social networks. Previous research has investigated how multi-criteria ratings allow consumers to assess whether or not a product or a service matches their expectations. However, previous research has rarely investigated how companies may employ such ratings to develop new products or services (Lin 2018). In particular, very little effort has been made so far to assess whether consumer emotions, as expressed through text, images, or videos, on the social media, may provide guidance for multi-criteria decision making related to the development of new products and services (Jannach et al. 2014). This research aims to enhance the field of multiple criteria decision analysis by incorporating sentiment analysis from social media.
The new methodology will be validated with a marketing case study. Secondary data will be collected from social media, which has two advantages: i) individuals can express themselves freely, and ii) data is available in large quantities. Multi-criteria decision-making literature (Bous et al. 2010) shows that consumers consider a variety of attributes in a holistic manner to arrive at a decision compatible with their preferences. Thus, because multiple attributes shape consumer decisions to adopt or resist new products, companies could benefit from a decision method that considers these attributes and their relative importance. Such a method may, in fact, help them design or improve different aspects of their offerings.
Entry Requirements
General admissions criteria
You’ll need a good first degree from an internationally recognised university (minimum second class or equivalent, depending on your chosen course) or a Master’s degree in an appropriate subject. In exceptional cases, we may consider equivalent professional experience and/or qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.
Specific candidate requirements
Successful candidates should demonstrate a significant interest in social media marketing and Internet technologies.
How to Apply
We’d encourage you to contact Professor Alessio Ishizaka (alessio.ishizaka@port.ac.uk) to discuss your interest before you apply, quoting the project code.
When you are ready to apply, you can use our online application form and select ‘Business and Management’ as the subject area. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. Our ‘How to Apply’ page offers further guidance on the PhD application process.
https://www.port.ac.uk/study/postgraduate/postgraduate-research/how-to-apply
If you want to be considered for this funded PhD opportunity you must quote project code BUSM4510219 when applying.
Funding Notes
Successful applicants will receive a bursary to cover tuition fees at the UK/EU rate for three years and a stipend in line with the RCUK rate (£14,777 for 2018/2019). As part of the bursary the Faculty of Business and Law may fund fieldwork expenses (currently £2,000) over the total period of PhD study. We also offer funding to attend conferences (currently £450), training (currently £450), and a work-based placement (currently a maximum of £3,000 tied up to the period of 12 weeks).
References
Ishizaka, A., and Nemery, P. (2013). Multi-Criteria Decision Analysis. Chichester (United Kingdom), John Wiley & Sons Inc.
Jannach, D., Zanker, M., and Fuchs, M. (2014). “Leveraging multi-criteria customer feedback for satisfaction analysis and improved recommendations.” Information Technology & Tourism 14(2): 119-149.
Lin, K. (2018). “A text mining approach to capture user experience for new product development.” International Journal of Industrial Engineering 25(1): 108-121.
—
—–8<———————————
Prof Dr Alessio Ishizaka
Professor in Decision Analysis
University of Portsmouth
PBS, Operations & Systems Management
Portsmouth PO1 3DE
United Kingdom
Tel: 0044(0)23 9284 4171
Email: Alessio.Ishizaka@port.ac.uk
Webpage:
http://www.port.ac.uk/operations-and-systems-management/staff/alessio-ishizaka.html
by nurazaliah | Oct 8, 2018 | knowledge, research
In this profile series, we interview AI innovators on the front-lines – those who have dedicated their life’s work to improving the human condition through technology advancements.
Meet Damian Borth, chair in the Artificial Intelligence & Machine Learning department at the University of St. Gallen (HSG) in Switzerland, and past director of the Deep Learning Competence Center at the German Research Center for Artificial Intelligence (DFKI). He is also a founding co-director of Sociovestix Labs, a social enterprise in the area of financial data science. Damian’s background is in research where he focuses on large-scale multimedia opinion mining applying machine learning and in particular deep learning to mine insights (trends, sentiment) from online media streams.
Damian talks about his realization in deep learning and shares why integrating his work with deep learning is an important part to help prevent future natural disasters.
What has your journey been like in deep learning? How did you end up at DFKI?
I spent two years in Taiwan, went to the University of Kaiserslautern, Germany for my PhD while having a stopover at Columbia University, and did my post-doctoral at UC Berkeley and the International Computer Science Institute in Berkeley. In Berkeley, I spent my time on deep learning network architectures and got really into it. That was a really great time. After my stay in the US, I went back to the DFKI to found the Deep Learning Competence Center. Now, I am helping the University of St. Gallen to establish a lab in Artificial Intelligence and Machine Learning and hopefully soon the buildup of a new computer science faculty.
What made you become a DL believer?
I was actually a “non-believer” in deep learning, until I started my post-doc at UC Berkeley. It’s very hard to train a neural network efficiently without sufficient data and at the time that I started by PhD, neural networks were not trusted as the go-to method. Instead, we looked at support vector machines for classification. But then AlexNet came along and showed neural networks do, in fact, work consistently. Then people began to download the Caffe framework, use it, improve it, and outperform other architectures.
What did you do in Berkeley?
I continued the work we have started at Columbia in sentiment analysis for pictures. It could classify objects like e.g. animals such as a dog or a cat. We attached adjectives to the noun and made the analysis differentiate between a scary dog or a cute dog. The vocabulary was roughly 2,000 adjectives noun pairs (ANP). By conditioning the noun with an adjective, we were able to move a very objective judgement to a subjective assessment. Doing so we were able to derive a link from this mid-level representation to a higher level of sentiment representation. The positive image of a cute dog or a laughing baby could flip to a negative sentiment when it saw a dark street or a bloody accident. This mid-level representation proved to be also very successful beyond sentiment analysis and was applied to aesthetics and emotion detection. It created a bridge between the objective world and the subjective world of visual content. In Berkeley I was also part of the team creating the YFCC100m dataset the largest curated image dataset at that time. Having such a dataset with 100 million creative common images and videos from Flickr helps if you want to train a very deep neural network architecture.
Did you continue your sentiment analysis work with DFKI?
We call it Multimedia Opinion Mining (MOM), because we want it to consider different modalities such as video and audio. Currently we’re extending deep learning architectures towards multi-model signal processing. The goal is to take different modalities as an input and move them all into one architecture. If you have a self-driving car, you’re not only detecting the visual signal of the camera, but also the radar data from an audio signal and others in one network. Working with different architectures such as late fusion, infusion, and in some work on early fusion demonstrated to improve system performance. In particular early fusion has been successfully used in satellite image analysis for remote sensing where a lot of information is multi-model. This is really a game changer for disaster recovery. Using this information, we can help with flooding and wildfires disasters where emergency response teams on the ground can get immediate information from satellites to find where the fire is, what the flooding looks like, or how many buildings can be affected and is it accessible by road or by boat.
Can you elaborate on the disaster response case? How can your work help these first responders?
We were analyzing data collected from a wildfire case at Fort McMurray. When we looked at the data, initially we saw that the area around the fire, in particular the vegetation and already burned area was a strong indicator for the direction of the fire spread. Once the wind changed the fire changed its course as well which caused more damage. This analysis would have predicted that change of how the fire develops much earlier. Such information is very valuable to the first responders and their work on the ground. Another case we’re currently working on is with flooding. We started a benchmark challenge to foster collaboration to build up a community with MediaEval Satellite Task. In the first year 16 teams from around the world have been participating. The teams submit their neural networks results and we compare the performance on the test data set to figure out which one provides the best predictions. This way we know very quickly which approaches work and which not.
Is there a specific natural disaster you’re analyzing to prevent in the future?
Minimizing the impact of natural disasters was one of my main research areas at DFKI, and wildfire and flooding are just a few of the disasters the United Nations is monitoring worldwide. We’re seeing a general rise in natural disasters and we want to help emergency response teams on the ground get immediate information from satellites about their impact. For example, where the fire is, how the flood is moving, or how many buildings are affected. However, there are
other disaster we would like to continue our work such as earthquakes or landslides. The goal is to have a system that learns from data of previously seen disasters automatically.
Is there a reason why you went into the disaster space?
I’m a huge advocate of AI for public good working closely with the AI for Good Foundation. The foundation investigates ways how AI can help humanity in areas like agriculture, natural disaster recovery, and the sustainable development goals. It’s currently difficult to motivate students to stay with academia because there are so many great opportunities in the industrial sectors. But if you have someone who’s talented, it’s important to show him or her how their work can help people – then they will stay to work on the problem and try to solve it. It’s not just about money in AI research – we have the ability to do something good.
Was there a natural disaster that happened to you as a child growing up wishing you had this type of technology to help prevent it?
Not exactly. I was born in Poland and before the Iron Curtain fell we moved to Germany. The Chernobyl disaster happened, so it affected the area partially through the contaminated rain. You couldn’t help prevent that, but it’s definitely something to think about.
Is there any advice you’d like to give to researchers who want to follow in the same space?
Take your time, read the literature, and try to understand the material thoroughly. You don’t want to be overwhelmed by the velocity of papers being published. You also don’t need to publish about all the conferences that are currently happening. Focus on solving problems, because you want to prioritize what’s important rather than splitting yourself to do multiple things.
If you could go back in time and bring this technology with you, what would you have wanted to prevent?
Maybe Fukushima with the tsunamis. If I could help the disaster in real time, then we would get the emergency response team in the right spot. Analyze the surface structure and maybe prevent the outcome of a natural disaster such as flooding in a way that it would have less damage or prevent more victims from the disaster. It’s something that I think is very important, and not enough people are working on preventing that.
Register now for the ‘Earth Observation from Space: Deep Learning Based Satellite Image Analysis’ webinar with Damian Borth discussing the challenges of land use and land cover classification using remote sensing satellite images.
Resources:
Read how DFKI finds meaningful insights from enormous data sets to make better decisions.
Learn how AI and Deep Learning are fueling all areas of business.
Check out how you can implement AI for public good.
https://www.forbes.com/sites/nvidia/2018/09/19/ai-innovators-this-researcher-uses-deep-learning-to-prevent-future-natural-disasters/#773d6c026cd1
by nurazaliah | Aug 30, 2018 | knowledge, research
What is Industry 4.0? It’s simply a way to efficiently and effectively leverage new digital and robotic techniques into the manufacturing process.
Such technologies include cloud services, IoT sensors and activators, robotics, wireless networking and more. These would be intelligently combined with manufacturing machines to create what one might call a “smart factory”.
Could 3D printing fit into this paradigm?
Absolutely it could. In fact, 3D printing is perhaps one of the most “flexible” means of manufacturing, as literally each print could be unique. Of course, it’s more expensive than mass manufacturing, but there are many working on that problem.
Currently, however, most 3D printing equipment is more or less “standalone” and provides only simple, if any, interfaces to a larger manufacturing ecosystem.
I believe that 3D printers could be a significant part of Industry 4.0 implementations if they were able to add on control and operational mechanisms to make the printers more “independent” and thus more able to fit into a smart factory.
and amazingly..this 3D printing is applied as a makeup!…Wow it is such a great invention. Less hassle for ladies and everyone can be pro make up artist now!!!! awesome
Recent Comments