• International Journal of Computer Science & Network Security
• /
• v.23 no.9
• /
• pp.1-7
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.210-216
• /
• 2023

Demand prediction is an essential component of any business or supply chain. Large retailers need to keep track of tens of millions of items flows each day to ensure smooth operations and strong margins. The demand prediction is in the epicenter of this planning tornado. For business processes in retail companies that deal with a variety of products with short shelf life and foodstuffs, forecast accuracy is of the utmost importance due to the shifting demand pattern, which is impacted by an environment of dynamic and fast response. All sectors strive to produce the ideal quantity of goods at the ideal time, but for retailers, this issue is especially crucial as they also need to effectively manage perishable inventories. In light of this, this research aims to show how Machine Learning approaches can help with demand forecasting in retail and future sales predictions. This will be done in two steps. One by using historic data and another by using open data of weather conditions, fuel, Consumer Price Index (CPI), holidays, any specific events in that area etc. Several machine learning algorithms were applied and compared using the r-squared and mean absolute percentage error (MAPE) assessment metrics. The suggested method improves the effectiveness and quality of feature selection while using a small number of well-chosen features to increase demand prediction accuracy. The model is tested with a one-year weekly dataset after being trained with a two-year weekly dataset. The results show that the suggested expanded feature selection approach provides a very good MAPE range, a very respectable and encouraging value for anticipating retail demand in retail systems.

• Journal of Bio-Environment Control
• /
• v.26 no.4
• /
• pp.411-417
• /
• 2017

Environmental and growth factors such as light intensity, vapor pressure deficit, and leaf area index are important variables that can change the transpiration rate of plants. The objective of this study was to compare the transpiration rates estimated by modified Penman-Monteith model and artificial neural network. The transpiration rate of paprika (Capsicum annuum L. cv. Fiesta) was obtained by using the change in substrate weight measured by load cells. Radiation, temperature, relative humidity, and substrate weight were collected every min for 2 months. Since the transpiration rate cannot be accurately estimated with linear equations, a modified Penman-Monteith equation using compensated radiation (Shin et al., 2014) was used. On the other hand, ANN was applied to estimating the transpiration rate. For this purpose, an ANN composed of an input layer using radiation, temperature, relative humidity, leaf area index, and time as input factors and five hidden layers was constructed. The number of perceptons in each hidden layer was 512, which showed the highest accuracy. As a result of validation, $R^2$ values of the modified model and ANN were 0.82 and 0.94, respectively. Therefore, it is concluded that the ANN can estimate the transpiration rate more accurately than the modified model and can be applied to the efficient irrigation strategy in soilless cultures.

• Journal of Korea Multimedia Society
• /
• v.17 no.8
• /
• pp.1020-1024
• /
• 2014

The environment information such as dust, temperature, humidity, illumination and gas are very important in daily life. We implemented multi-sensor system which made for measuring an environment by using Arduino, ZigBee, and Appinventor. We also designed a packet for transmitting environment data. The data are sent to the server via ZigBee and then it communicates to a smart phone via WI-Fi. In this study, we added divers sensors, designed a protocol which made for transfer several kinds of data and improve mobility for real time monitoring by using smart phones. The system was worked well and the data was transmitted correctly to the smart phone.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3417-3421
• /
• 2010

USN, all things are given to the computing and networking capabilities and by enabling the best service through awareness of environment and situation is a technology to improve the convenience and safety of human life. In this paper, we develop learning support system based on embedded system using USN technology which collect learner's learning environment based on real time and makes the best learning environment. In addition, simulations of these systems to improve the learners' learning efficiency was identified.

• Journal of Dairy Science and Biotechnology
• /
• v.25 no.2
• /
• pp.29-32
• /
• 2007

An understanding functional properties and molecular interactions of milk proteins was critical to improve qualities of fermented dairy products including yogurts and cheeses. Extensive rearrangements of casein particles were important factors to enhance whey separation in yogurt gel network. The use of high hydrostatic pressure treated whey protein as an ingredient of low fat processed cheese food resulted in the production of low fat processed cheese food with acceptable firmness and enhanced meltabilities. Milk protein-based nano particles produced by self-association of proteins could be better nutrient delivery vehicle than micro particle since particle size reduction in nano particles could lead to increased residence time and surface area available in GI tract.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.261-263
• /
• 2006

Nowadays, technologies such as RFID, sensor network makes our life comfortable more and more. In this paper we propose a wearable computing system for blind and deaf person who can be easily out of sight from our technology. We are making a wearable computing system that is consisted of embedded board to processing data, ultrasonic sensors to get distance data and motors that make vibration as a signal to see the screen for a deaf person. This system offers environmental informations by text and voice. For example, distance data from a obstacle to a person are calculated by data compounding module using sensed ultrasonic reflection time. This data is converted to text or voice by main processing module, and are serviced to a handicapped person. Furthermore we will extend this system using a voice recognition module and text to voice convertor module to help communication among the blind and deaf persons.

• Fisheries and Aquatic Sciences
• /
• v.10 no.3
• /
• pp.159-169
• /
• 2007

The complex 2-dimensional movements of fish during an annual migration circuit were generated and simulated by a chaotic model of fish movement, which was expanded from a small-scale movement model. Fish migration was modeled as a neural network including stimuli, central decision-making, and output responses as variables. The input stimuli included physical stimuli (temperature, salinity, turbidity, flow), biotic factors (prey, predators, life cycle) and landmarks or navigational aids (sun, moon, weather), values of which were all normalized as ratios. By varying the amplitude and period coefficients of the klinokinesis index using chaotic equations, model results (i.e., spatial orientation patterns of migration through time) were represented as fish feeding, spawning, overwintering, and sheltering. Simulations using this model generated 2-dimesional annual movements of sea bream migration in the southern and western seas of the Korean Peninsula. This model of object-oriented and large-scale fish migration produced complicated and sensitive migratory movements by varying both the klinokinesis coefficients (e.g., the amplitude and period of the physiological month) and the angular variables within chaotic equations.

• 한국유가공학회:학술대회논문집
• /
• 2007.09a
• /
• pp.31-37
• /
• 2007

An understanding functional properties and molecular interactions of milk proteins was critical to improve qualities of fermented dairy products including yogurts and cheeses. Extensive rearrangements of casein particles were important factors to enhance whey separation in yogurt gel network. The use of high hydrostatic pressure treated whey protein as an ingredient of low fat processed cheese food resulted in the production of low fat processed cheese food with acceptable firmness and enhanced meltabilities. Milk protein-based nano particles produced by self-association of proteins could be better nutrient delivery vehicle than micro particle since particle size reduction in nano particles could lead to increased residence time and surface area available in GI tract.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.2156-2162
• /
• 2008

To reduce the cost and the time of transport in Eurasian railroad networks such as TKR, TCR and TSR owing to the problem of different track gauges (narrow/standard/broad gauge), it is important to develop the gauge - adjustable wheelset system to adapt easily to these gauges. The gauge - adjustable wheelset system in the transcontinental railway have been proposed as a more effective way in comparison with other techniques for overcoming difference in track gauges. Assume that the freight train with gauge adjustable wheelset system is running from domestic train network to TCR, TSR in Eurasian continent, it is necessary to estimate the safety of this system. This study is evaluated at examination of safety for freight train with gauge adjustable wheelset system by simulated durability analysis. Moreover, the predicted fatigue life at running track using the durability simulator was verified by the durability test according to UIC standard.