Improving Customer Value Index and Consumption Forecasts using a Weighted RFM Model and Machine Learning Algorithms

Collecting and mining customer consumption data are crucial to assess customer value and predict customer consumption behaviors. This paper proposes a new procedure, based on an improved Random Forest Model by: adding a new indicator, joining the RFMS-based method to a K-means algorithm with the Entropy Weight Method applied in computing the customer value index, classifying customers to different categories, and then constructing a consumption forecasting model whose RMSE is the smallest in all kinds of data mining models. The results show that identifying customers by this improved RMF model and customer value index facilitates customer profiling, and forecasting customer consumption enables the development of more precise marketing strategies.

Improving Customer Value Index and Consumption Forecasts Using a Weighted RFM Model and Machine Learning Algorithms

Collecting and mining customer consumption data are crucial to assess customer value and predict customer consumption behaviors. This paper proposes a new procedure, based on an improved Random Forest Model by: adding a new indicator, joining the RFMS-based method to a K-means algorithm with the Entropy Weight Method applied in computing the customer value index, classifying customers to different categories, and then constructing a consumption forecasting model whose RMSE is the smallest in all kinds of data mining models. The results show that identifying customers by this improved RMF model and customer value index facilitates customer profiling, and forecasting customer consumption enables the development of more precise marketing strategies.

Systematic review of metrics used to characterize dietary nutrient supply from household consumption and expenditure surveys

Objective: To review existing publications using Household Consumption & Expenditure Survey (HCES) data to estimate household dietary nutrient supply to (1) describe scope of available literature, (2) identify the metrics reported and parameters used to construct these metrics, (3) summarize comparisons between estimates derived from HCES and individual dietary assessment data, and (4) explore the demographic and socioeconomic sub-groups used to characterize risks of nutrient inadequacy. Design: This study is a systematic review of publications identified from online databases published between 2000 to 2019 that used HCES food consumption data to estimate household dietary nutrient supply. Further publications were identified by “snowballing” the references of included database-identified publications. Setting: Publications using data from low- and lower middle income countries Results: In total, 58 publications were included. Three metrics were reported that characterized household dietary nutrient supply: apparent nutrient intake per adult-male equivalent per day (n=35), apparent nutrient intake per capita per day (n=24), and nutrient density (n=5). Nutrient intakes were generally overestimated using HCES food consumption data, with several studies finding sizeable discrepancies compared to intake estimates based on individual dietary assessment methods. Sub-group analyses predominantly focused on measuring variation in household dietary nutrient supply according to socioeconomic position and geography. Conclusion: HCES data are increasingly being used to assess diets across populations. More research is needed to inform the development of a framework to guide the use of and qualified interpretation of dietary assessments based on these data.

Improved Routing Protocol Based on Multiobjective Optimization in Industrial Robot Networks

This paper decomposes the routing process of industrial robot network using the application of analytic hierarchy process in decision-making. The influence of four factors, such as path length, data integrity, energy consumption, and receiving delay, on routing effect is analyzed. Simultaneous interpreting routes are selected to achieve the purpose of routing. Simulation results show that this method can more comprehensively consider the factors affecting routing and is superior to the existing methods in terms of energy consumption, data integrity, and transmission delay.

Increasing Seaweed Consumption in the Netherlands and Portugal and the Consequences for the Intake of Iodine, Sodium, and Exposure to Chemical Contaminants: A Risk-Benefit Study

Background: Seaweed has a high potential for nourishing the future planet. However, besides being beneficial, it also contains adverse components; this poses the question whether consumption of seaweed foods overall contributes beneficially or detrimentally to human health, and hence if their consumption should be promoted or restricted.Methods: This study evaluated the impact of substituting regular foods with seaweed foods in the diet, both in terms of nutritional quality (via iodine and sodium) and food safety (via arsenic, cadmium, lead, and mercury). Food consumption data from the Netherlands and Portugal (adults aged >18 years) were used, in which 10% of the amounts of pasta, bacon, and lettuce consumed were replaced by seaweed-derived products made from kelp (Saccharina latissima). Using Monte Carlo Risk Assessment software (MCRA), long-term nutrient intake and exposure to contaminants were assessed. The results obtained for the Netherlands and Portugal were compared with data from Japan, a country that has a high natural consumption of seaweed.Results: This low-tier risk-benefit study reveals that an increased seaweed consumption (as assessed by the 10% replacement with seaweed products) has no consequences in terms of intake of sodium and exposure to cadmium, lead, and mercury, and the associated (absence of) adverse health aspects. The alternative scenario almost doubled the mean iodine intake in the Netherlands (to 300 μg/day) and Portugal (to 208 μg/day) and increased the average exposure to arsenic levels in the Netherlands (to 1.02 μg/kg bw/day) and Portugal (to 1.67 μg/kg bw/day).Conclusion: The intake of iodine and exposure to arsenic in the Netherland and Portugal were certainly higher due to the modeled increase of seaweed foods. If seaweed consumption increases close to the 10% substitution, the public health consequences thereof may trigger further research.

The Intake of Phosphorus and Nitrites through Meat Products: A Health Risk Assessment of Children Aged 1 to 9 Years Old in Serbia

This study provides the data on dietary exposure of Serbian children to nitrites and phosphorus from meat products by combining individual consumption data with available analytical data of meat products. A total of 2603 and 1900 commercially available meat products were categorized into seven groups and analysed for nitrite and phosphorous content. The highest mean levels of nitrite content, expressed as NaNO2, were found in finely minced cooked sausages (40.25 ± 20.37 mg/kg), followed by canned meat (34.95 ± 22.12 mg/kg) and coarsely minced cooked sausages (32.85 ± 23.25 mg/kg). The EDI (estimated daily intake) of nitrites from meat products, calculated from a National Food Consumption Survey in 576 children aged 1–9 years, indicated that the Serbian children population exceeded the nitrite ADI (acceptable daily intake) proposed by EFSA (European Food Safety Authority) in 6.4% of children, with a higher proportion in 1–3-year-old participants. The mean phosphorus concentration varied from 2.71 ± 1.05 g/kg to 6.12 ± 1.33 g/kg in liver sausage and pate and smoked meat products, respectively. The EDI of phosphorus from meat products was far below the ADI proposed by EFSA, indicating that the use of phosphorus additives in Serbian meat products is generally in line with legislation.

Smart water meter for automatic meter reading

Clean water is one of the main sectors in smart city that need well management. One of the clean water management is utilization of water meters. The smart meter is more suitable applied for smart city. Recent Smart Water Meter allows water authorities to obtain water consumption data remotely. It also provides ability to collect and record the data in real time that can be utilised for multipurpose. However, in Indonesia, the water meters are used only to measure the total volume of clean water consumption for billing purpose only using mechanical water meter and requires labour intensive manual. Currently, many researches on smart meter design have been developed. However, the smart meter only measure and record the water consumption, without ability in which customer can determine the amount of water as needed. This paper describes design and development of smart water metering with Internet of Things. Flow meter is used as a sensor of water flowing through the pipe. The ability of the proposed smart meter is not only to measure and to record the volume water consumed, but also the customer can determine the water desired and required. The volume of water measured by the smart meter is compared with the manual measurement. The result shows that the water measured manually differs slightly from smart meter measurement using water flow sensor. The maximum difference, error, is 0.03 litres. The proposed smart meter has ability to close the main valve once the determined amount of water is reached.

Level of Anxiety-State as a factor in changing eating patterns in college students: NUTSAU Study

With the purpose of identifying eating patterns of university students at a federal university in the state of Rio de Janeiro, a cross-sectional analysis of food consumption data was stratified by anxiety symptom scores of 147 students enrolled in the second semester of several undergraduate courses in the second semester of 2015. The State-Trait Anxiety Inventory determined the anxiety symptoms scores. A food frequency questionnaire was applied to obtain food consumption data. Students were stratified into two groups, using the median state anxiety score as cutoff point. For each group, some dietary patterns were derived by the application of the principal component analysis. Statistical analysis was performed using the SPSS software. The university students presented a median state-anxiety score of 43 points, and it was significantly higher in women. Three dietary patterns were identified for each group according to their nutritional characteristics, among which “Mixed 1”, “Healthy” and “Rice and Beans” for the less anxious students and “Western”, “Mixed 2” and “Rice and Beans” for the most anxious students. The results showed that it was possible to identify consistent food patterns for both, using a factorial analysis method. Students with the highest anxiety-state scores had a pronounced Western eating pattern, and those least anxious students had higher consumption of healthier food groups and lower consumption of caffeinated beverages. Although this is a cross-sectional analysis, it can contribute to optimize nutritional intervention for this population.