Decision support systems in Food Industry

Decision support system (DSS) is a computerized program that is used to support judgment and course of action in a business or an organisation. This report will discuss comprehensive information on such systems. DSS usually analyses massive amount of data, information, and compile comprehensive information (Arason, et al., 2010), to take decisions. However, some systems are rule based and based on heuristic decisions can also be undertaken by the systems. The output generated by these systems provide information for decision making or to solving the critical issues in the industries. One particular example, where DSS systems are more prominent is the food industry, and it is extensively used in business management as well as in various stages of food processing. One of the important features of DSS in business management is able to enable the identification of negative trends, better resources allocation and improving faster decision making (Shim, et al., 2002). Therefore, this report, in the present work, considers discussing the importance of DSS in the food processing industry, and particularly within the seafood industry. 

DSS's integrated platform enables its users in the seafood industry to perform reliable and sophisticated analysis, and generate analytical reports that help the users to take informed and better decisions (Amara, et al., 2007; Hayen, et al., 2004).

Organisation of the Report of support systems in Food Industry

This reports discusses how DSS is used at seafood industry, how are the decisions supported through DSS systems.Next, what type of algorithms are being used in DSS. Follwed by new technologies and improvisation of DSS.

Decision Support Systems at Seafood Industry

In the past years, the food industry has changed dramatically, merging retailers, and selling huge composition of their products. Therefore, the industry itself is rising high, earning huge consumer base and sustaining in the market. The main involvement of DSS in the food industry is right from defining the raw materials to processing the food and finally packaging the food and delivering to the markets (Shim, et al., 2002; Amara, et al., 2007). 

Figure 1 Stages of value of chain in seafood industry. The stages are inter connecte

DSS in Raw Materials stage

The demand from the consumer market defines the need for the amount of raw materials. Therefore, a DSS is needed here for optimising the right volume to be ordered without any wastage of money or resources. In particular, raw material supply chain is considered as constraint for optimisation. especially, the raw material constraint deal with the supply of raw material properties. However, on the other hand, there could be several other parameters within the value chain of seafood industry; such as fishing, processing, labor allocations, marketing of services and products, and vessel scheduling, which may be optimised for the cost. All the aforementioned activities may have DSS models of their own that could potentially play an active role in providing quality of services and products, logistics, handling of raw material, and schedule processing. For instance, in the case of handling of raw materials, improper cooling and icing, increase higher temperature of flesh, which in turn influences the growth of bacteria (Amara, et al., 2007). The increased growth of bacteria can spoil the food and can incur a huge loss to the industry. Since the food gets spoilt if no care is taken, DSS plays an important role in maintaining the quality of the final product thereby optimising the parameters efficiently that can preserve the food with low cost optimisation. The life span/expiry dates for raw material is also required for the time plan and the processing of products. 

DSS in Processing stage of support systems in Food Industry

The DSS in the seafood industry can help optimise the cost of food processing, energy consumption, manpower utilisation, and improve transport efficiency. The first processing stages have a wide range of options for processing and a flexible workforce. The DSS systems are mostly used for optimizing the intensive processes. Especially in the seafood industry, the descaling, removing the skin and removing the bones to extract the fish fillets are very intensive. (Arason, et al., 2010; Chaudhuri, et al., 2019).  

A lot of labour force is scheduled to work on the aforementioned processing task.  Some workers are more skilled than others and the pace at they work also varies. The DSS system here can help to log the working patterns of the workers and optimize the wages based on the high speed and accuracy with which they work. This can help industry to optimise the costs as well as to make working more efficient and improvise quality. 

DSS in Market stage of support systems in Food Industry

The final stage is food packaging and delivering it to the markets. DSS here can help the industry by locating the markets where there is demand for their product. On the other hand, it can also help in finding out the causes why their products are not successful in some markets. The next section will deal with how the decisions are supported through the DSS.

Example of how a decision problem is supported

The seafood industry especially in the Nordic countries is highly sophisticated. They use technology right from fishing to processing to markets. In the fishing, DSS is integrated to the radar system that helps find the fish, including its precise location. (Boute, et al., 2007). The DSS is integrated at every stage right about the raw material, properties of the material, and the information about the markets. 

The biggest challenge faced by the DSS is the availability of relevant data, which influences the decision (Chaudhuri, et al., 2019; Amara, et al., 2007). Few cases where decisions are supported by DSS are given as follows:

Identifying product based on the quality of standards.

In improving the process control including the right amount workers needed for a task. 

Optimisating the amount of raw materials and incentives to maintain inherent material quality (Arason, et al., 2010).

In the management, providing decisions in the audits of quality management of the food industry (Hayen, et al., 2004).

Decisions on procedures that can minimise the losse and to achieve best quality for the product. 

Major algorithms used for the system

Major algorithms used in this particular industry are mostly optimisation algorithms. Ranging from linear programming, to quadratic programming and genetic and evolutionary algorithm.

Different parameters used in the DSS model for the fish industry include, fishing area, ship/boat, fish type, season, and etc. Using linear programming, to maximise the total profit, using those parameters can be given by

profit =  optimise(fish_type,season,fishing_cost,fishingarea_distance)

 This equation is also known as the general form of the linear model that contain some variables of the model. The c_i and the cost coefficient and data parameter of a_(n i,j)  and b_( j).

Maximize subject to 

c_( 1) 〖 x〗_( 1)  + c_( 2)  x_( 2)   +  .  .  .  .  .  .  .  .  +  c_( n)  x_( n)   (objective function)

Subject to 〖 a〗_( 11) 〖 x〗_( 1)  + a_( 12)  x_( 1)   +   .  .  .  .  .  .  .  .  +  a_( 1n) 〖 x〗_( n)  ≤  b_( 1)  (constraint 1)

a_( 21)  x_( 1)   +  a_( 22) 〖 x〗_( 1)   +  .  .  .  .  .  .  .  .  +  a_( 2n) 〖 x〗_( n)   ≤  b_( 2)   (constraint 2)

 a_( m1) 〖 x〗_( 1)   +  a_( m2) 〖 x〗_(  1 )    + .  .  .  .  .  .  .  .+  a_( mn) x_( n)   ≤〖 b〗_( m)  (constraint m)

x_1,x_2,.  .  .  .  .  .  .  .x_n  ≥ 0

This model is solvable in which all the objective function and constraints are linear (Arason, et al., 2010). It can be used to solve the linear optimization problems in which their size is not huge. Irf we optimise those parameters with respect to the constrainst, profits can be maximized.(Amara, et al., 2007).

Capitalization of new technologies of support systems in Food Industry

 It can be noted that artificial intelligence is not able to replace humans from this food industry. The reason is that humans are always required to supervise all operations and maintain and repair all equipment in a proper way. Only humans are able to introduce creative technologies. These new technologies are able to increase efficiency and also improve the performance of the required operations for the preparation of food. 

However, there is about four major application of artificial intelligence that is used in the food industry. 

Sorting of food of support systems in Food Industry

One of the most difficult task for the human is to sort out the fresh food for manufacturing the different product. This can be explained by the help of an example when the organization wanted to make new products made from potatoes. In the first step, all new potatoes will be sorted out, and proper ripe will be selected for making chips and other products. 

In the food industry, one of the most important applications is related to TOMRA sorting food. This application is involved in using the sensor-based optical storing that is combined with the functions of machine learning. This technology is using the cameras that contain high-quality infrared sensors for watching the food properly, like the customers. This equipment is sorting the products, and it will help to save money and time and also enhance the quality of the food. 

Enhance the supply chain of food 

The AI is also involved in managing the supply chain for the safety of food. The reason is that rules for safe food become extremely strict and due to this companies are required to enhance their main operations. In this case, the companies are using different technologies that are involved in testing the quality of food at each step of the supply chain. This technology is also helping them to forecast the inventory and also manage the prices of their products. Another thing is that Food Company are also involved in transporting the food in a safe way. It can be seen that the Symphony RetailAI is that company that is using AI for monitoring the demand in an efficient way. 

Work for improving personal hygiene

AI is also working on improving personal hygiene in food products. They are working on making a better environment in the kitchen. These systems are also ensuring all complaints according to the regulations. For that case, KanKan is that organization that is involved in giving proper solutions for enhancing hygiene in the companies. Now, this system is used in many organizations. This system is monitoring every worker in the kitchen with the help of cameras. 

Equipment for cleaning processing 

There is another AI element the organizations are using for maintaining better health standards in the food industry. Nottingham University researchers are developing some systems that are involved in reducing the cleaning time and other resources. These new systems are saving more than 100 million euros per year. This AI is also known as SOCIP. This system is using Ultrasound sensors and optical lights for gaining the perfect image of the food (Utermohlen, 2017). 

How to improve the decision-making process

Conclusion of support systems in Food Industry

In the modern food industry, the business is consistently under pressure to improve the inventory, supply chain and level of services. The modern models of DSS cut down the cost of production and the timeframe for services. The decision support system has proved that the services and tools are considered as essential to improving the competition in the food industry. The processing and production of fish meat are becoming a difficult part of the food industry. The biggest challenge is to predict demand, maintain traceability, and dated products that are required for special attention and handling (Arason, et al., 2010). The potential benefits of using DSS models is to help manage the value chain process by providing smart decisions.

References of support systems in Food Industry

Amara, S., Youbi-Idrissi, M., Moureh, J. & Guipart, J., 2007. Numerical simulation of air humidity distribution in a refrigerated truch enclosure. Proceedings IIF-IIR international congress of refrigeration, 02(05), pp. 01-16.

Arason, S. et al., 2010. Decision Support Systems for the Food Industry. Intelligent Systems Reference Library, 01(01), pp. 01-10.

Boute, R., Disney, S., Lambrecht, M. & Houdt, B., 2007. An integrated production and inventory model to dampen upstream demand variability in the supply chain. European Journal of Operational Research, 178(01), pp. 121-142.

Chaudhuri, S., Dayal, U. & Ganti, V., 2019. Database technology for decision support systems. Journal of computer, 34(12), pp. 1105-1110.

Hayen, R. L., Holmes, M. C. & Scott, J. P., 2004. DECISION SUPPORT SYSTEMS IN INFORMATION TECHNOLOGY ASSIMILATION. Issues in Information Systems, 02(02), pp. 481-450.

Shim, J. P., Warkentin, M., Courtney, J. F. & Power, D. J., 2002. Past, Present, and Future of Decision Support Technology. Decision Support Systems, 33(02), pp. 111-126.

Zuritz, C. & Sastry, S., 1986. Effect of packaging materials on temperature fluctuations in frozen foods: mathematical model and experimental studies. Journal of food science, 51(04), pp. 105-1056.