Neural network models for predicting perishable food temperatures along the supply chain

Mercier, Samuel; Uysal, Ismail

doi:10.1016/j.biosystemseng.2018.04.016

Cited by 43 publications

(27 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To that end, sensors can be used not only to enable visibility during agricultural production, but also to provide end-to-end traceability in food supply chains, particularly in the case of cold chains [23]. The retrieved data and information could inform efficient and responsive supply chain management interventions to mitigate food safety risks, improve inventory management, reduce waste and losses, as well as allow for dynamic pricing systems [24]. Recently, due to the improvement, accuracy, technical feasibility and economic viability of sensors, the use of wireless sensor networks in the agricultural sector is becoming the norm [25].…”

Section: Sensor-focused Decision Making In Food Supply Networkmentioning

confidence: 99%

Sensor Applications in Agrifood Systems: Current Trends and Opportunities for Water Stewardship

Tsolakis

Aivazidou

Srai

2019

Climate

View full text Add to dashboard Cite

Growing global food demand and security concerns dictate the need for state-of-the-art food production technologies to increase farming efficiency. Concurrently, freshwater overexploitation in agriculture, especially in arid and water-scarce areas, emphasises the vital role of appropriate water-saving irrigations techniques to ensure natural resources sustainability in food supply networks. In line with the development of automated systems, the use of sensors for water monitoring, indicatively in the cases of smart farming or precision agriculture, could further promote the preservation of freshwater resources. To this end, this research first provides a review of sensor applications for improving sustainability in agrifood systems. We then focus on digital technologies applied for monitoring and assessing freshwater utilisation in the food commodities sector based on academic literature and real-world business evidence. A contextual map is developed for capturing the main technical, environmental and economic factors affecting the selection of sensors for water monitoring and stewardship during agricultural production. This first-effort framework, in terms of sensor-based freshwater monitoring, aims at supporting the agrifood system’s decision makers to identify the optimal sensor applications for improving sustainability and water efficiency in agricultural operations.

show abstract

Section: Sensor-focused Decision Making In Food Supply Networkmentioning

confidence: 99%

Sensor Applications in Agrifood Systems: Current Trends and Opportunities for Water Stewardship

Tsolakis

Aivazidou

Srai

2019

Climate

View full text Add to dashboard Cite

show abstract

“…The neural network (NN) has been widely used in agricultural technologies (Samuel & Ismail, 2018;Shi, Zhao, Zhang, & Ren, 2009;Silva et al, 2012;Takahashi et al, 2015;Tetyana, Cassinao, Joerg, & Bernd, 2016). It can make a better identification of seeds with its non-linear ability (Lin et al, 2018).…”

Section: Weight Balanced Backpropagation Neural Networkmentioning

confidence: 99%

A data transfer method for improving seed identification of maize (Zea mays) haploid breeding based on genetic similarity

Lin

et al. 2019

Plant Breeding

View full text Add to dashboard Cite

Maize haploid breeding technology is able to identify haploid seeds non‐destructively, rapidly and at low cost with the help of Near‐infrared (NIR) spectral analysis. However, due to the hybridization of numerous parents and the low production rate of haploid, the haploid data collection becomes a burden for engineering this technology. Biologically, there are considerable similarities between the progeny of the same female parent and different male parents. Based on this advantage, similar spectral data can be transferred when the NIR technology is employed. A revised method of Transfer adaptive boost (TrAdaBoost) is proposed to improve identifying for the backpropagation neural network (BPNN) classifier. To avoid the negative transfer, a screening thresh is used to select out similar data, and the amount of these data are limited to join current training. The results show that the identification performances are improved significantly when the data amount is small. This method shows a high ability to make the seed identification more convenient for engineering maize haploid breeding.

show abstract

“…These unsupervised NN have been used also for network management, 39 for intrusion detection systems, 40 or for predicting perishable food temperatures along the supply chain. 41 Our purpose is not to propose a new algorithm based on SOM. However, our purpose is to identify patterns within the SPI studies context.…”

Section: Very Small Entitiesmentioning

confidence: 99%

“…These NN have been used to extract patterns in several environments, such as Resta et al where authors used SOM for supporting bed capacity planning in an emergency department. These unsupervised NN have been used also for network management, for intrusion detection systems, or for predicting perishable food temperatures along the supply chain …”

Section: Introductionmentioning

confidence: 99%

Correlations study and clustering from SPI experiences in small settings

Larrucea

Santamaría

2018

J Software Evolu Process

View full text Add to dashboard Cite

Software Process Improvement (SPI) initiatives have been applied in a wide set of organisations including very small entities (VSE). In fact, this kind of organisations is facing several hurdles when overarching a SPI initiative. In this context, the ISO/IEC 29110 has been used as a lightweight reference model for steering VSEs in their SPI initiatives. The inherent uncertainty behind the SPI curtains blocks the organisations in their investments. Due to these reasons, we need to identify relationships and similarities in order to predict whether a SPI will succeed or not. We propose the use of Self‐Organising Maps for identifying patterns from these SPI studies. The aim of this paper is to identify correlations among SPI studies and to discover patterns from them.

show abstract

Neural network models for predicting perishable food temperatures along the supply chain

Cited by 43 publications

References 19 publications

Sensor Applications in Agrifood Systems: Current Trends and Opportunities for Water Stewardship

Sensor Applications in Agrifood Systems: Current Trends and Opportunities for Water Stewardship

A data transfer method for improving seed identification of maize (Zea mays) haploid breeding based on genetic similarity

Correlations study and clustering from SPI experiences in small settings

Contact Info

Product

Resources

About