Neural Matrix Factorization Recommendation for User Preference Prediction Based on Explicit and Implicit Feedback

Explicit feedback and implicit feedback are two important types of heterogeneous data for constructing a recommendation system. The combination of the two can effectively improve the performance of the recommendation system. However, most of the current deep learning recommendation models fail to fully exploit the complementary advantages of two types of data combined and usually only use binary implicit feedback data. Thus, this paper proposes a neural matrix factorization recommendation algorithm (EINMF) based on explicit-implicit feedback. First, neural network is used to learn nonlinear feature of explicit-implicit feedback of user-item interaction. Second, combined with the traditional matrix factorization, explicit feedback is used to accurately reflect the explicit preference and the potential preferences of users to build a recommendation model; a new loss function is designed based on explicit-implicit feedback to obtain the best parameters through the neural network training to predict the preference of users for items; finally, according to prediction results, personalized recommendation list is pushed to the user. The feasibility, validity, and robustness are fully demonstrated in comparison with multiple baseline models on two real datasets.

Process-based flood damage modelling relying on expert knowledge: a methodological contribution applied to agricultural sector

Flood damage assessment is crucial for evaluating flood management policies. In particular, properly assessing damage to the agricultural assets is important because they may have greater exposure and are complex economic systems. The modelling approaches used to assess flood damage are of several types and can be fed by damage data collected post-flood, from experiments or based on expert knowledge. The process-based models fed by expert knowledge are subject of research and also widely used in an operational way. Although identified as potentially transferable, they are in reality often case-specific and difficult to reuse in time (updatbililty) and space (transferability). In this paper, we argue that process-based models are not doomed to be context specific as far as the modelling process is rigorous. We propose a methodological framework aiming at verifying the conditions necessary to develop these models in a spirit of capitalisation by relying on four axes which are: i/ the explicitation of assumptions, ii/ the validation, iii/ the updatability, iv/ the transferability. The methodological framework is then applied to the model we have developed in France to produce national damage functions for the agricultural sector. We show in this paper that the proposed methodological framework allows an explicit description of the modelling assumptions and data used, which is necessary to consider a reuse in time or a transfer to another geographical area. We also highlight that despite the lack of feedback data on post-flood damages, the proposed methodological framework is a solid basis to consider the validation, transfer, comparison and capitalisation of data collected around process-based models relying on expert knowledge. In conclusion, we identify research tracks to be implemented to pursue this improvement in a spirit of capitalisation and international cooperation.

Intentional Connection

This chapter details how learning-based course design promotes meaningful student connections with course content, course goals, and connections with peers, faculty, and student self-awareness. No matter the modality, the learning-based course design model provides a pathway for faculty and instructional designers to use backward design to create courses that embrace significant learning, valuable practice, and feedback opportunities. With an emphasis on authentic activities that are aligned to learning outcomes, learning-based course design avoids busywork and reduces rote memorization of facts and figures. Educational technologies can strengthen the faculty and student course experience, provided that these are purposefully integrated into the course. Courses designed with close attention to student learning provide skill growth that strengthens students' professional lives. Course feedback data allows faculty to refine the course and programs and institutions to develop stronger alignment to their stated goals.

Biophysical and Subject-Based Assessment of the Effects of Topical Moisturizer Usage on Xerotic Skin—Part I: EpsilonTM 2D Skin Hydration

As new biophysical methods become available to the skin researcher, it is important to understand the type of information that they are capable of measuring, and how it relates to consumer perception of topical moisturizing products. This work was aimed at understanding how two-dimensional (2D) skin hydration mapping can be used to describe skin properties beyond the traditional ‘single number’ approach to skin hydration. Two-dimensional skin hydration measurement data were collected at baseline and after 1 week of in vivo usage of a topical moisturizing product. In addition, subject feedback regarding their skin condition obtained during the study was collected and assessed. Dividing the 2D hydration measurement device images into zones of different electrical permittivity scores enabled analysis of different aspects of the skin compared with traditional electrical skin hydration measurements. Improvement in skin flexibility as a result of use of the topical test product was demonstrated. Complete description of the skin’s hydration state through the creation of hydration histograms to describe its electrical characteristics was performed. Subject feedback data showed improvements in aspects of skin assessed using 2D hydration measurement.

Using Real-Time Data to Develop and Improve Teaching of Clinical Skills in Virtual Nursing Simulation Laboratories During COVID-19 Pandemic

During COVID-19 pandemic public health measures, face-to-face simulation laboratories were cancelled. A rapid transition to online teaching environments required staff and students to rapid upskilling in digital literacy. The purpose of this article is to describe a model of virtual nursing simulation laboratory implemented in graduate entry to practice Master’s nursing program to teach clinical skills. The model used cloud-based communication app Zoom and real time feedback data to improve content delivery, student engagement and confidence in skill development. This model was co-designed with the student cohort to ensure students, as stakeholders, had a voice in having their education needs met during these challenging times.

Feasibility, Acceptability, and Impact of a Self-guided e-Learning Memory Program for Older Adults

Clinician-led memory interventions have been shown to increase knowledge, reduce anxiety, promote memory-strategy use, and increase brain-healthy lifestyle behaviours in older adults with normal age-related memory changes. A self-guided, e-learning version of the Baycrest Memory and Aging Program® was recently developed to increase accessibility to memory interventions. The objectives of the current study were to assess program feasibility (retention rate), acceptability (satisfaction), and participant-reported impact (memory concerns, behaviour change, goal attainment). As part of a larger study, participants were 139 healthy older adults (mean age: 73±7, 73% female). Ninety-two individuals completed the program (retention rate=66%). Anonymous feedback data indicated a high level of satisfaction with the program overall (98%), the pace and clarity of the learning modules (100%), and the organization and navigation of the interface (92%). Suggested improvements included offering more interaction with others and addressing minor platform glitches. There was a decrease in the level of concern about memory change, with 64% expressing concern at a level consistent with the Jessen et al. (2014) criteria for Subjective Cognitive Decline at baseline, and 23% expressing the same at post-test. The majority of participants reported increases in using memory-strategies (63-97%) and lifestyle-promoting behaviours (40-72%). All participants reported moderate to high satisfaction with personal goal attainment. Results support feasibility, acceptability, and impact of a self-guided e-learning adaptation of memory intervention. E-learning tools may be a promising avenue to deliver accessible brain health promotion in later life, especially in the context of the shift to virtual care during and beyond COVID-19.

Design and Research on the Foul Detector of a Long Jump Jumping Line Based on a Vision Sensor

Long jump is one of the important events of modern track and field sports, and it is also one of the regular events of major events. Due to the complexity and technicality of the project, the determination of the results in a formal competition is also very complicated. It is easy for athletes to invalidate their results due to fouls by stepping on the jump line. Therefore, it is very necessary to detect fouls. This paper uses a visual sensor technology to design and develop a foul detector for the situation of athletes stepping on the jump line in a long jump, which can detect fouls well. In the formal competition process, because the long jump time is relatively short, the referee is interfered by many factors and it is easy to misread the movements of the athletes and cause misjudgment. Therefore, on this basis, in order to improve the fairness of the game and create a good competition environment, the design is designed. The long jump stepping line foul detector is studied, and the visual sensor technology is used, which can judge the long jump stepping fouls during the long jump based on the feedback data.

Data Collection Smart and Simple: Evaluation and Metanalysis of Call Data From Studies Applying the 5Q Approach

Agricultural development projects often struggle to show impact because they lack agile and cost-effective data collection tools and approaches. Due to the lack of real-time feedback data, they are not responsive to emerging opportunities during project implementation and often miss the needs of beneficiaries. This study evaluates the application of the 5Q approach (5Q). It shows findings from analyzing more than 37,000 call log records from studies among five countries. Results show that response rate and completion status for interactive voice response (IVR) surveys vary between countries, survey types, and survey topics. The complexity of question trees, the number of question blocks in a tree, and the total call duration are relevant parameters to improve response and survey completion rate. One of the main advantages of IVR surveys is low cost and time efficiency. The total cost for operating 1,000 calls of 5 min each in five countries was 1,600 USD. To take full advantage of 5Q, questions and question-logic trees must follow the principle of keeping surveys smart and simple and aligned to the project's theory of change and research questions. Lessons learned from operating the IVR surveys in five countries show that the response rate improves through quality control of the phone contact database, using a larger pool of phone numbers to reach the desired target response rate, and using project communication channels to announce the IVR surveys. Among other things, the respondent's first impression is decisive. Thus, the introduction and the consent request largely determine the response and completion rate.

Pre-scaling up of improved finger millet (Kako-1) variety, at Weyira district, under Halaba zone in Ethiopian

Pre-scaling up of improved finger millet variety (kako-1) was conducted in 2019/20 mehere season in Halaba Zone, two selected kebeles under Weyira District,southern Ethiopia under rain fed conditions through involvement of farmers in participatory demonstration. The demonstration was carried out with the specific objectives:to popularize and demonstrate improved Finger millet technology (Kako-1) and to collect farmers feedback on improved finger millet variety. The demonstration was conducted at layignawu Badana and kufe kebele on farmers field of Weyira Districts on 10ha land coverage totally 20 beneficiary farmers field .Site and beneficiary farmers selection criteria were conducted purposively by cooperating with woreda and kebele extension personnel by willingness to accept technology, land availability and accessibility of the area. Training was given by focusing on agronomic practices and awareness creation for all selected beneficiary farmers and concerned extension personnel. Also, all necessary inputs (10kg/h kako-1 seed,100kg/h NPSB and 150 kg /h Urea) were provided from Hawassa agricultural research center.Yield and farmers feedback data were collected and analyzed by using descriptive statistics applying on SPSS software Accordingly, 2.7 tone/ha average mean grain yield was obtained. According to farmers’ feedback, the variety kako-1 has high tilling capacity, high grain yield, early maturity, high biomass yield and quality Therefore the variety need to extended to wide area.So, all concerned bodies need to work to facilitation of further extension of kako-1 variety for Halaba zone and other similar agro-ecological zones to improve finger millet production and productivity of smallholder farmers.