The 2020 report of The Lancet Countdown on health and climate change: responding to converging crises.

Over the past two decades, a large amount of research effort has been devoted to developing algorithms that generate recommendations. The resulting research progress has established the importance of the user-item (U-I) matrix, which encodes the individual preferences of users for items in a collection, for recommender systems. The U-I matrix provides the basis for collaborative filtering (CF) techniques, the dominant framework for recommender systems. Currently, new recommendation scenarios are emerging that offer promising new information that goes beyond the U-I matrix. This information can be divided into two categories related to its source: rich side information concerning users and items, and interaction information associated with the interplay of users and items. In this survey, we summarize and analyze recommendation scenarios involving information sources and the CF algorithms that have been recently developed to address them. We provide a comprehensive introduction to a large body of research, more than 200 key references, with the aim of supporting the further development of recommender systems exploiting information beyond the U-I matrix. On the basis of this material, we identify and discuss what we see as the central challenges lying ahead for recommender system technology, both in terms of extensions of existing techniques as well as of the integration of techniques and technologies drawn from other research areas.

Collaborative Filtering beyond the User-Item Matrix: A Survey of the State of the Art and Future Challenges

A method, related system and apparatus are disclosed. The method is implemented by an operative set of processor executable instructions configured for execution by a processor. The method includes the acts of: determining if a monitoring client is connected to a base through a physical connection; establishing a first communications link between the monitoring client and the base through the physical connection; updating, if necessary, the interface program on the monitoring client and the base through the first communications link; establishing a second communications link between the monitoring client and the base using the first communications link; and communicating data from the base to the monitoring client using the second communications link.

System, method, and apparatus for electronic patient care

Transformer-based models have pushed state of the art in many areas of NLP, but our understanding of what is behind their success is still limited. This paper is the first survey of over 150 studies of the popular BERT model. We review the current state of knowledge about how BERT works, what kind of information it learns and how it is represented, common modifications to its training objectives and architecture, the overparameterization issue and approaches to compression. We then outline directions for future research.

/pdf/a-primer-in-bertology-what-we-know-about-how-bert-works-2v8af1zw7o.pdf

A Primer in BERTology: What We Know About How BERT Works

A Primer in BERTology: What we know about how BERT works

Photo sharing is one of the most popular Web services. Photo sharing sites provide functions to add tags and geo-tags to photos to make photo organization easy. Considering that people take photos to record something that attracts them, geo-tagged photos are a rich data source that reflects people's memorable events associated with locations. In this paper, we focus on geo-tagged photos and propose a method to detect people's frequent trip patterns, i.e., typical sequences of visited cities and durations of stay as well as descriptive tags that characterize the trip patterns. Our method first segments photo collections into trips and categorizes them based on their trip themes, such as visiting landmarks or communing with nature. Our method mines frequent trip patterns for each trip theme category. We crawled 5.7 million geo-tagged photos and performed photo trip pattern mining. The experimental result shows that our method outperforms other baseline methods and can correctly segment photo collections into photo trips with an accuracy of 78%. For trip categorization, our method can categorize about 80% of trips using tags and titles of photos and visited cities as features. Finally, we illustrate interesting examples of trip patterns detected from our dataset and show an application with which users can search frequent trip patterns by querying a destination, visit duration, and trip theme on the trip.

Mining people's trips from large scale geo-tagged photos

Techniques for determining a status of a user are described A mobile device equipped with sensors may collect sensor data pertaining to transportation modes of the user, tracking locations of the user, identifying environmental noise levels surrounding the user, or speech being spoken in proximity to the user Features of the collected sensor readings are then used to infer activities the user may be performing Based at least in part on the multiple inferred activities, a status of the user is determined

Identifying Status Based on Heterogeneous Sensors

According to the growth of mobile devices equipped with a GPS receiver, a variety of location-based services (LBSs) have been launched. Since location information may reveal private information, preserving location privacy has become a significant issue. Previous studies proposed methods to preserve a users’ privacy; however, most of them do not take physical constraints into consideration. In this paper, we focus on such constraints and propose a location privacy preservation method that can be applicable to a real environment. In particular, our method anonymizes the user’s location by generating dummies which we simulate to behave like real human. It also considers traceability of the user’s locations to quickly recover from an accidental reveal of the user’s location. We conduct an experiment using five users’ real GPS trajectories and compared our method with previous studies. The results show that our method ensures to anonymize the user’s location within a pre-determined range. It also avoids fixing the relative positions of the user and dummies, which may give a hint for an LBS provider to identify the real user. In addition, we conducted a user experiment with 22 participants to evaluate the robustness of our method against humans. We asked participants to observe movements of a user and dummies and try to find the real user. As a result, we confirmed that our method can anonymize the users’ locations even against human’s observation.

Dummy-Based User Location Anonymization Under Real-World Constraints

A variety of services utilizing users' positions have become available because of rapid advances in Global Positioning System (GPS) technologies. Since location information may reveal private information, preserving location privacy has become a significant issue. We proposed a dummy-based method of anonymizing location to protect this privacy in our previous work that generated dummies based on various restrictions in a real environment. However, the previous work assumed a simplified mobility model in which users kept moving and did not stop. If we assume a more realistic mobility model in which users often pause to visit various attractions, it becomes increasingly more difficult to generate dummies that will move naturally. In this paper, we assumed that the users' movements are known in advance and propose a dummy-based anonymization method based on user movements, where dummies move naturally while stopping at several locations. We simulated user movements on real map information and verified the method we propose was more effective than the previous one.

A dummy-based anonymization method based on user trajectory with pauses

We propose discriminative methods to generate semantic distractors of fill-in-theblank quiz for language learners using a large-scale language learners’ corpus. Unlike previous studies, the proposed methods aim at satisfying both reliability and validity of generated distractors; distractors should be exclusive against answers to avoid multiple answers in one quiz, and distractors should discriminate learners’ proficiency. Detailed user evaluation with 3 native and 23 non-native speakers of English shows that our methods achieve better reliability and validity than previous methods.

Yuki Arase

Papers

Mining people's trips from large scale geo-tagged photos

Identifying Status Based on Heterogeneous Sensors

Dummy-Based User Location Anonymization Under Real-World Constraints

A dummy-based anonymization method based on user trajectory with pauses

Discriminative Approach to Fill-in-the-Blank Quiz Generation for Language Learners