Recep Benzer, Semra Benzer, Alternative approaches to traditional methods for growth parameters of fisheries industry: Artificial Neural Networks in:

Alptekin Erkollar (Ed.)

Enterprise & Business Management, page 317 - 346

A Handbook for Educators, Consultants, and Practitioners

1. Edition 2020, ISBN print: 978-3-8288-4255-7, ISBN online: 978-3-8288-7230-1,

Series: Enterprise & Business Management

Tectum, Baden-Baden
Bibliographic information
Recep Benzer, Semra Benzer Alternative approaches to traditional methods for growth parameters of fisheries industry: Artificial Neural Networks Learning Objectives The objectives of this chapter effects of ANNs on predicting statistical growth in fishery industry are investigated. Besides comparisons with conventional method are performed. Once you have mastered the materials in this chapter, you will be able to: – Discuss the growth models with artificial neural networks for crayfish. – Understand the difference traditional and artificial intelligence in fisheries. – Identify the information data with Matlab application. – Conversion and evaluation of crayfish measurements into data. – Supporting decision makers in the fishing industry. Chapter Outline The aim of the fishing industry is to protect the natural habitat and fish and crayfish maintenance of stocks. For this reason, all studies in fisheries must be done using new approaches on mathematical models. This design should be established in the fishing industry. A defect will occur when it is fail to meet the intended design. Hence, prediction methods play an important role to forecast the number of product crayfish growth. For this study, Artificial Neural Network (ANNs) used to forecast in crayfish growth in in order to develop a well suit ANNs model for prediction and obtain an accurate prediction for decision making. Therefore, data of crayfish was collected and the analysis pro- 317 cess carried out by Matlab R2015a application using the neural network toolbox. The neural network framework for the some metric data prediction was developed with the minimum error. The fisheries industry is able to conduct prediction process with the framework and make a better decision based on the result in order to reach their goal. Keywords Artificial neural networks, crayfish, fisheries industry, traditional methots, modern methods, Matlab. Introduction Terms such as; “Digital Revolution”, “Industrial Revolution”, “Industry 4.0” conceptualize the same meaning: “Technological Revolution”. Technological Revolution aims improving human abilities with cyberphysical systems, creating factories based on artificial intelligence (AI), making interactions among objects and also with human-beings and providing decisions based on data processing. Researchers addressing interdisciplinary fields, experts have deep knowledge in wide-range of branches and collaboration facilities between them have utmost importance in the course of revolutionizing technology. Industry 4.0, 4th industry revolution, is the project of encouraging industrial improvements based on computer science and equipping industry with state-ofthe-heart technology. AI is the most significant tool for extracting information from data and for making decisions. At this point, in fishery industry applying modern techniques related to AI instead of conventional methods is gaining importance. Nowadays thanks to high computer technology human-beings are trying not only to resolve unsolved problems but to contribute novel approaches. From this point of view, the idea enabling intelligent machines in 1980s evolved and improved with ANNs in 1990s. In particular ANNs, a branch of AI, attracted interests of various academics and researchers. ANNs provide generalized learning based on training process (Bon and Hui 2017). Thus, ANNs has non-linear structure. Besides, ANNs outperform conventional methods in terms of performance measures and they can detect non-linear relations without any hypothesis (Türeli et al. 2011; 1 Alternative approaches to traditional methods for growth parameters of fisheries industry 318 Benzer 2015; Benzer and Benzer 2015; Benzer et al. 2015; Benzer and Benzer 2016; Benzer et al. 2016; Benzer et al. 2017; Benzer and Benzer 2017; Benzer et al. 2017; Benzer and Benzer 2018). Furthermore, ANNs enables using infinite variables. Companies that encounter difficulties while decision-making processes are to develop appropriate and well-planned solutions to maintain their existing situation and to forecast events in the future. Aim of prediction is not only to forecast their statutes in the future but to take measures against problems that do not currently exist. Stoke and growth problem has also the same aim. In terms of sustainability of any business, prediction has invaluable importance. Predictions supports business managers to make decisions parallel to company objectives. Predictions are forecasts to reveal unclear events' occupations, duration and impacts. Product managers occasionally deal with predictions on request forecasts prepared by (or with) marketing functions. However, managers use relational predictions to forecast payments of raw materials, to plan human powers and to decide on stock level. Thus, they can serve customers in better conditions, use capacity of their companies efficiently, and also enhance stability (Sharda and Patil 1992; Kaastra and Boyd 1996). Conventional statistical methods provide prediction of requests after analyzing past request status, factors affecting requests and economic indicator relations. Forecasts about the future is implemented using statistical methods that examine past events. Some of the most prominent statistical methods in prediction are given as follows; regression method, correlation method, curve fitting method, time series analysis method, moving averages method (Tekin 2008). Regression and von Bertalanffy are among the conventional methods used in Fishery Industry. Box – Jenkins Methods (AR-MA Model, ARIMA Model, and Simulation Model), fuzzy logic and artificial neural networks can be listed as modern estimation methods. Even structure and properties of ANNs are specific for problem, it is observed that performance results of ANNs are higher than that of conventional data processions methods. With the structure of the ANNs and the feature of imitating the intuition ability of human-beings, companies use ANNs in almost every vital decision-making process nowadays. Information systems are one of the main pillars of the information society and clearly show that machines can interpret, prioritize, solve problems, produce solutions to 1 Introduction 319 complex problems that computers can not solve under normal conditions, perceive and prioritize events. With the concept of Industry 4.0, a rapid digital transformation is triggered in communities. In this context, it is obvious that the possible developments are examined that digital domination makes one feel more and more in industrial life at any moment itself, at the same time it leads to important developments in the social sense. Digitization is great importance when considering the big data, intelligent robots, simulation, vertical and horizontal system organization, internet of objects, cyber security, cloud, joint production and enriched reality. In terms of data, information, knowledge, understanding and comprehension, Industry 4.0 has emerged as a strategic step in the direction of businesses. Environmental sustainability, product variety, branding by increasing the competitiveness in international markets and some kind of IT support including all kinds of classical and modern computing approaches are gaining importance in terms of digitalization in aquaculture. Also it will be accelerated by automating the production, processing and distribution chain by transforming the obtained data into decisions (Dopico et al. 2016). In the aquaculture industry, there will be no innovation without interdisciplinary work, it will not be possible to produce value-added ideas in complex socio-technical fields through various interdisciplinary collaborations and the engineers should be equipped with the skills they have adopted modern approaches to provide interdisciplinary thinking and access to excellence. In this study, effects of ANNs on predicting statistical growth in fishery industry are investigated. Besides comparisons with conventional method are performed. Methodology Study area The Lake Yeniçaga is located in in west Black Sea region of Turkey (40º 46' 45" N, 32º 01' 33" E), within the borders of the city Bolu and in the north of the town Yeniçağa (Fig. 1). Lake Yeniçağa is a shallow eutrophic freshwater lake with maximum depth of 5.2 m (Saygı and 2 2.1 Alternative approaches to traditional methods for growth parameters of fisheries industry 320 Demirkalp 2004), 989 m above sea level, and covers surface area of about 260 ha (Kılıç and Becer 2013). The study area (Yeniçağa Lake). Data collection Crayfish (Astacus leptodactylus) shows a widespread distribution within inland waters of Turkey. It was the most important inland water product between 1970 and 1985. However, there was a dramatic decrease in its population due to the crayfish plague, which was recorded in Turkey in 1984 (Furst 1988; Baran and Soylu 1989; Rahe and Soylu 1989). In Turkey, crayfish production was 7936 tonnes in 1984. It dropped to 1565 tonnes in 1987 and 320 tonnes in 1991 (TÜİK 1984– 1991). Furthermore, there have been some fluctuations in crayfish production in the last 25 years. Production was 324 tonnes in 1992, which increased to nearly 1500 tonnes in 1998. While production was 1372 tonnes in 1999, it reached 2317 tonnes in 2004. However, it diminished to 816 tonnes in 2007, 1030 tonnes in 2010, 609.6 tonnes in 2011, 492 tonnes in 2012, 532.1 tonnes in 2013, 582 tonnes in 2014, 532 tonnes in 2015 and 544 tonnes in 2016 (TÜİK 2018). Crayfish samples were Fig. 1. 2.2 2 Methodology 321 collected from Yeniçağa Lake. During the study, 455 crayfish specimens (260 females and 195 males) were caught between 2015 and 2016. The total length (TL), total weight (TW), carapace length (CL), carapace width (Cw), abdomen length (AL) and abdomen width (Aw), chela length (ChL) and chela width (Chw) of each specimen were measured. The parameters related to length and width were measured with a digital calliper to the nearest 0.1 mm, while the weight related ones were measured to the nearest 0.01 g, and sex determination was carried out for each specimen (Rhodes & Holdich 1979). The crayfish obtained from the lake were immediately transported to the laboratory. Sex, maturity, mating, spawning and hatching statuses were recorded during the study. Sex and length composition, the average length and weight, and the length-weight relationship for each sex and combined sexes were determined. Length–weight relationship (LWR) equation LWR equation is a traditional method used for the determination of the growth features of populations. From the collected samples; sex and length composition, the average length and weight weight, and the length–weight relationship for each sex and combined sexes were identified. The relationship between length (L) and body weight (W) for nearly all species of fish can normally be represented by the "lengthweight relationship" following equation: Where W is the body weight of fish (in g), L is the length (in cm) and 'a' and 'b' are constants. The parameter 'b' (also known as the allometry coefficient) has an important biological meaning, indicating the rate of weight gain relative to growth in length or the rate at which weight increases for a given increase in length. If b is equal to 3, isometric pattern of growth takes places, if b is not equal to 3, then allometric pattern of growth takes places, it may be positive if it is greater than 3 or negative otherwise (Ricker 1973). The q and b constants could be esti- 2.3 Alternative approaches to traditional methods for growth parameters of fisheries industry 322 mated from linear functions. However, many functional relationships observed in fishery biology such as length-weight relationship are not linear. Fortunately, such curvilinear functions can often be transformed into linear functions by taking the logarithm or the natural logarithms of both sides: This equation is equivalent the regression equation: This mean that; y is equivalent to ln W, a which represents the y-intercept (the point where the line crosses the y axis) of the regression line is equivalent to ln a, b is the slope of the line, and x is equivalent to ln L. Artificial Neural Networks (ANNs) ANNs are computational systems that simulate biological neural networks and can be defined as a specific type of parallel processing system based on distributional or connectionist methods (Andrews et al. 1995; Hopgood 2000). Artificial Neural Networks (ANNs) are used in three basics methods: – As biological nervous system models and intelligence. – As real time adaptive signal processing controllers implemented in hardware for applications such as robots. – As methods of data analytic. 2.4 2 Methodology 323 In several years of artificial neural models (ANNs) network has developed to predict. There are threefeatured steps in developing an ANNs based solution: – Scaling or data transformation. – Definition of Network architecture as in Fig. 2, when the number of hidden layers, the number of nodes in each layer and connectivity between the nodes and set, learning algorithm construction in order to train the network. Artificial Neural Networks model diagram That contain of an input layer, a series of hidden layer, an output layer and connections between them. Nodes in the input layer represent possible influential factors that affect the network output and have no computational activities, while the layer of output contains one or more nodes that produce the output of network. Hidden layer may consist a large number of hidden processing nodes. A feed -forward back–propagation network propagates the information from the input layer to the output layers, compares the network output with known target, and propagates the error term from the layer of output back to the layer of input, by using a learning mechanism to adjust the biases and weights. ANNs are simulations of biological nervous systems using mathematical models. They are networks with simple processor units, interconnections, adaptive weights and scalar measurement functions (e.g., summation and activation functions) (Rumelhart et al. 1986). ANNs mathematical expression is seen in Fig. 3. Y is the neu- Fig. 2. Alternative approaches to traditional methods for growth parameters of fisheries industry 324 ron’s output, x is the vector of inputs, and w is the vector of synaptic weights. Biological and Mathematical explanation for ANNs design In case of biological neuron information comes into the neuron via dendrite, soma processes the information and passes it on via axon. In case of artificial neuron the information comes into the body of an artificial neuron via inputs that are weighted (each input can be individually multiplied with a weight). The body of an artificial neuron then sums the weighted inputs, bias and “processes” the sum with a transfer function. At the end an artificial neuron passes the processed information via output(s). Benefit of artificial neuron model (Krenker et al. 2011) simplicity can be seen in its mathematical description below: Where: – wi (k) is weight value in discrete time k where i goes from 0 to m, – xi (k) is input value in discrete time k where i goes from 0 to m, – F is a transfer function, – yi (k) is output value in discrete time k. As seen from a model of an artificial neuron and its equation (5) the major unknown variable of our model is its transfer function. Transfer function defines the properties of artificial neuron and can be any mathematical function. Fig. 3. 2 Methodology 325 Normalization The supervised learning method trained with the network structure (Back-propagation Networks) will be used to solve problems in this study. The transfer function (6), (VN is normalized data, VN is data to be normalized, Vmin is the minimum value of the data, Vmax is the maximum value of the data) mostly used a sigmoid or a logistic function, gives values in the range of [0,1] and can be described as (normalization): Estimation Accuracy Validation For this research, the Mean Absolute Percentage Error (MAPE) is used for estimation accuracy. MAPE is defined as: Comparisons can be made with more than one method by MAPE, because it is easy to interpret with its relative measurements. The smaller the values of MAPE, the closer are the forecasted values to the actual values. MAPE is the preferred error measure of the software measurement (MATLAB) researches. 2.5 2.6 Alternative approaches to traditional methods for growth parameters of fisheries industry 326 Statistics The MAPE benchmark refers to forecast errors as a percentage, and can therefore negate the disadvantages that may arise when correlating models developed for examines with different values. These features of MAPE are considered to be superior to those of other evaluation statistics. The MAPE results were assessed according to literature (0%– 10%: Very Good, 10%–20%: Good, 20%–50%: Acceptable, 50%–100%: Wrong and Faulty) (Witt and Witt 1992; Lewis 1982). The coefficient correlation (R2) calculated by the LWR regression model was 0.971. When the coefficient correlation (R2) was evaluated in both ANNs and LWR model, the results of ANNs were better, although they did not seem close to each other. It is evaluated that comparing the MAPE values together with R2 values can give a healthy result (Gentry et al. 1995). Data Editing for MATLAB Neural Network Toolbox of MATLAB was used for the ANNs calculations. This study was performed on 540 crayfish (270 females and 270 males) caught between 2015 and 2016 in Uluabat Lake. The data were divided into three equal parts: training, validation and test sets. The Matlab functions were used for “training”, “testing”, and “validation”. They were used randomly; 70% in training, 15% in testing, and 15% in the validation of the crayfish. Literature Review It is well acknowledged that Astacus leptodactylus is of great element in the food webs of freshwater habitats and their examination provides advantageous information on the comprehensive water systems (Hogger 1988; Momot 1995; Nyström 2002; Füreder et al. 2003). The crayfish, which is examined as eutrophic water scavengers, is one of the aquatic creatures with high nutritional and economic values. Therefore, it has long attracted interests in scientific research (Holdich and 2.7 2.8 3 3 Literature Review 327 Lowery 1988). Crayfish (Astacus leptodactylus), is a common species distributed throughout Europe, Middle East and Eastern Russia (Harlioglu 1996, Gutierrez-Yurrita et al. 1999; Souty-Grosset et al. 2006). It can be found in 27 countries around the world (Skurdal and Taugbol 2001; Parvulescu et al. 2012; Azari et al. 2014; Azari et al. 2015). A. leptodactylus is naturally and widely distributed in freshwaters throughout Turkey (Harlioğlu 2004; Harlioğlu and Harlioğlu 2005; Yüksel and Duman 2011; Bolat et al. 2011; Bök et al. 2013; Aydın et al. 2015; Benzer et al. 2015; Benzer and Benzer 2015; Demirol et al. 2015; Aksu and Harlioğlu 2016). Length˗weight relationships (LWR) is a widely used method, namely, in fish biology, ecology and fisheries studies. It is widely used in the determination of fishery measurement when sampling large species, mostly because of the difficulty and time required to record weight in the field (Andrade and Campos 2002). LWR for fish are predicted using the average length and weight (Mendes et al. 2004; Tosunoğlu et al. 2007). The LWR describes the correlation mathematically between the length and weight of the fish as well as the estimated values (Beyer 1991) of its length and weight. LWR are beneficial for the conversion of length equations to weight for use in stock calculation models (Lindqvist and Lathi 1983; Deval et al. 2007) and in predicting stock biomass with narrow sample (Verdiell˗Cubedo et al. 2006). These results also let scientists make identifications on morphological properties among species or among populations of the same species from various habitats (Moutopoulos and Stergiou 2002; Etchison et al. 2012). Critically, LWR were used to inform on the condition of freshwater samples and to evaluate whether somatic growth was isometric or allometric (Ricker 1973). The prediction of the relationship parameters between a and b can explain the connection regarding ecological events and life history. Environmental causes may affect crayfish growth by feeding and food resources. Length˗weight values may probably demonstrate the differences in growth that may be correlated with environmental stress across the species (Westman and Savolainen 2002; Olsson 2008). The most frequently researched dimensions for crustaceans are carapace length, body length, total length, body width, and wet weight (Primavera et al. 1998). Differences in length between individual body parts are used to Alternative approaches to traditional methods for growth parameters of fisheries industry 328 demonstrate the morphological changes between the male and female crayfish species (Lindqvist and Lahti 1983). These differences are also utilized in determing crayfish populations, its relative growth, comparing the populations of the same species, the morphology of crayfish species and the systematic assignment of crayfish (Lindqvist and Lahti 1983; Skurdal and Qvenild 1986; Gillet and Laurent 1995). The dimensions may be favorable to be able to convert into the desired length values when only one of the other length measurements is known and the LWR may be used to predict length from weight (Tosunoğlu et al. 2007). ANNs has been used in biology and in different disciplines of fisheries rather than in sciences (Tureli Bilen et al. 2011). Exercises of ANNs has included forecast the fish species distributions (Maravelias et al., 2003), fish predicting in a river (Mastrorillo et al., 1997), predicting macro invertebrate diversities (Park et al. 2003), population of aquatic insects (Obach et al. 2001), modeling freshwater fish (Joy and Death, 2004), fish population modeling (Benzer et al. 2016; Benzer and Benzer 2016). There are many publications on management information systems approaches in fisheries, biology and similar research areas (Fish et al. 1995; Lek and Guégan 1999; Olden and Jackson 2001; Teles et al. 2006; Goethals et al. 2007; Cabreira et al. 2009; Sholahuddin et al. 2015; Rocha et al. 2017; Ouali et al. 2017). Compared to traditional methods, ANNs has supported better conclusions in the evaluation of future data (Suryanarayana et al. 2008; Tureli Bilen et al. 2011). For limited values, the normality and their independence from the predicted values, ANNs is asserted to be an excellent model which gives excellent predictions. ANNs is also recorded to have accomplishment compared to linear regressions (Sun et al. 2009). Besides, ANNs is more favorable for its speed and flexibility (Brosse et al. 2009). Results There were about 57.14 % females, 42.86 % males (260 female, 195 male). The female: male ratio was found to be 1:0.75 for the general population. The length and weight (minimum-maximum) of the crayfish were 89–163 mm and 15.82 – 105.60 g. The average length and weight of samples were 122.154 ± 18.10 mm and 49.09 ± 19.38 g for 4 4 Results 329 male, 118.17 ± 15.50 mm and 42.04 ± 14.82 g for females and 118.98 ± 16.81 mm and 45.06 ± 17.07 g for the combined sex, respectively (Table 1). We organized the length-weight relation formaulation data as a TL-TW, CL-ChL, CL-AL. Total length total weight relation (TL-TW) for the crayfish in Yeniçağa Lake were found as W = 0.12949911 L2.3258 for females, W = 0.18113315 L2.2176 for males and W= 0.14162875 L2.3010 for both sexes. The carapace length chela length relations (CL- ChL) for the crayfish in Yeniçağa Lake were found as W = 1.31828102 L0.9788 for females, W= 2.21471042 L0.7544 for males and W = 1.48781344 L0.9378 for both sexes. The carapace length abdomen length relations (CL-AL) for the crayfish in Yeniçağa Lake were found as W = 1.02962529 L0.8497 for females (Table 2 and Fig. 4). Some metric properties for crayfish data Metric Species Sex Median ± Sx Min – Max t test TL ♀ ♂ ♀♂ 118.17 ± 15.57 122.15 ± 18.13 119.87 ± 16.81 89–150 89–163 89–163 P<0.05 TW ♀ ♂ ♀♂ 42.04 ± 14.44 49.09 ± 19.38 45.06 ± 17.07 15.82 – 80.0 18.01 – 105.6 15.82 – 105.6 P<0.05 CL ♀ ♂ ♀♂ 57.21 ± 8.6 61.89 ± 11.51 59.22 ± 10.2 42–75 40–90 40–90 P<0.05 AL ♀ ♂ ♀♂ 45.51 ± 7.3 45.22 ± 6.1 45.40 ± 6.93 25–60 35–60 25–60 P<0.05 ChL ♀ ♂ ♀♂ 73.09 ± 13.83 91.59 ± 27.45 81.02 ± 22.7 45–130 15–155 15–155 P<0.05 Sx: Standard deviation Some metric properties for crayfish data Species Sex Relationship r2 TL – TW ♀ ♂ ♀♂ W = 0.12949911 L 2.3258 W = 0.18113315 L 2.2176 W = 0.14162875 L 2.3010 0.975 0.964 0.968 CL – ChL ♀ ♂ ♀♂ W = 1.31828102 L 0.9788 W = 2.21471042 L 0.7544 W = 1.48781344 L 0.9378 0.994 0.974 0.980 CL – AL ♀ ♂ ♀♂ W = 1.02962529 L 0.8497 W = 1.46177399 L 0.6202 W = 1.31682998 L 0.6947 0.995 0.994 0.994 Table 1. Table 2. Alternative approaches to traditional methods for growth parameters of fisheries industry 330 Pearson correlation coefficient is a dimensionless measure that determines a linear relation between two variables. Its value varies from -1, when there is a perfect negative linear relation, to +1, when there is a perfect positive linear relation. The closer this value to zero, the smaller is the degree of linear relation. From the Pearson correlation coefficient, many other statistics are calculated, such as partial correlation, direct and indirect effects between variables in track analysis, and canonical correlation (Sari et al. 2017). Thus, the precision of these statistics depends on accuracy of the estimate of Pearson’s correlation coefficient. In the present study, Table 3 showed that there is no negative pearson correlation between all parameters. Apart from these results, TW – TL, ChL – TL, AL – TL, CL – TW have a high correlation. ..\Bilder\abb.jpg LWR relations for TL-TW (Yeniçağa Lake). Table 3. Pearson correlation coefficients between metric characteristics. TL TW CL ChL AL TL 1.000 TW 0.850 1.000 CL 0.955 0.831 1.000 ChL 0.648 0.703 0.683 1.000 AL 0.903 0.742 0.760 0.497 1.000 All correlation is significant at the 0.01 level. If we examine the example problem in question as a multi-layer neural networks; the following objectives will be achieved. – With a single, suciently large hidden layer, it is possible to represent any continuous function of the inputs with arbitrary accuracy, – As a consequence, given a particular learning problem, it is unknown how to choose the right number of hidden units in advance, – We need to consider multiple output units for multi-layer networks. Let (x, y) be a single sample with its desired output labels y = {y1,...,yi,...,yM}, Fig. 4. 4 Results 331 – The error at the output units is just y- hW(x), and we can use this to adjust the weights between the hidden layer and the output layer, – A term equivalent to the error at the hidden layer, i.e. the error at the output layer is back-propagated to the hidden later, – This is subsequently used to update the weights between the input units and the hidden layer. A multilayer feed-forward neural network was used for the ANNs. The following three steps will be carried out for this. 1. Update the weights between the hidden and output layers. – Let Erri  be the i-th component of the error vectory − ℎW x   – Define∆i = Errix g′ ini   – The weight-update rule becomesWj, i  Wj, i+ ∝ x aj  x  ∆i  2. Back-propagate the error to the hidden layer. – The idea is that the hidden node j is “responsible” for some fraction of the error ∆i  in each of the output nodes to which it connects. – Thus the ∆i  values are divided according to the strength (weight) of the connection between the hidden node and the output node∆j =  gi  inj  ∑iWj, i ∆i  – Again, this is similar to weight-updates in perceptrons:Wk, j  Wk, j+   ∝ x ak x ∆j    A schematic representation of a typical ANNs was shown in Fig. 2. Fig. 5 illustrates graphical presentation of the fit between the actual and predicted values. Performance of the ANNs between forecast values for TL TW was seen in Fig. 6. ..\Bilder\abb5.jpg Relationship between of artificial neural networks for TL-TW (Yeniçağa Lake). ..\Bilder\abb Performance of artificial neural networks for TL – TW (Yeniçağa Lake). Fig. 7 shows the distribution of fish data collected from the Yeniçağa Lake by total length (TL) and total weight (TW). Fig. 8 shows the distribution of the actual data with estimation (estimation) data for the Fig. 5. Fig. 6. Alternative approaches to traditional methods for growth parameters of fisheries industry 332 results of the regression on learning, validation and test clusters in Matlab. Distribution of fish data collected for TL – TW (Yeniçağa Lake). The average absolute error and average error squares of error functions used in both training and test data are calculated with Matlab coding. In the training data MAE 0.1585, RMSE 0.2122; in the test data, MAE was found to be 0.2158 RMSE 0.2689. The actual values of the fishes obtained from natüre (Yeniçağa Lake), as seen in Fig. 4, are well predicted. Actual and predictive data The values observed, ANNs and length-weight relation data are presented in Table 4. The observed data, which is collected from the Fig. 7. Fig. 8. 4 Results 333 Yeniçağa Lake, were presented according to the gender of group with lenght and weight. The calculated data observed from the artificial neural networks, length-weight relations. Table 4 were prepared for comparison of data of the crayfish in Yeniçağa Lake with length-weight relation and ANNs method. Observed and calculated values for ANNs, length-weight relation Type (1) – (2) Sex ACTUAL DATA FORECAST MAPE (%) LWR MAPE (%) 1 2 1 2 1 2 1 2 1 2 TL (1) TW (2) Female 11.81 7 42.04 7 11.99 3 43.59 2 1.491 3.685 12.01 7 40.43 3 1.695 3.828 Male 12.21 5 49.09 5 11.99 9 46.78 2 1.768 4.710 12.50 7 46.59 2 2.391 5.098 All 11.98 8 45.06 5 11.99 6 45.58 5 0.064 1.153 12.23 6 42.99 0 2.069 4.603 CL (1) ChL (2) Female 5.721 7.310 5.807 7.407 1.505 1.329 5.754 7.269 0.572 0.557 Male 6.190 9.159 6.065 9.055 2.023 1.134 6.565 8.761 6.070 4.347 All 5.922 8.103 5.910 8.190 0.214 1.084 6.093 7.888 2.896 2.640 CL (1) AL (2) Female 5.721 4.552 5.807 4.570 1.505 0.391 5.754 4.532 0.572 0.428 Male 6.190 4.526 6.065 4.537 2.023 0.252 6.565 4.526 6.070 0.042 All 5.922 4.541 5.909 4,540 0.214 0.015 6.093 4.531 2.896 0.222 Discussion Environmental factors such as behavior, foraging efficiency, feeding and the availability and quality of food resources might widely influence variation in morphometric traits (Lindqvist and Lahti 1983). Crustacean growth is affected by the environmental conditions by influencing molt intervals and incremental rises in length and weight. In fishery studies, the relationship between bodies length – weight is an essential and extensively used equation and the simplest parameter to measure is the fish length. Crustaceans experience different stages in their life history which are defined by different length˗weight relationships. The parameter b is characteristic of species and usually does not show a significant change throughout the year, unlike the parameter, which may change on a daily basis, seasonally, between different environments, water temperature and salinity, gender, availability of food, Table 4. 5 Alternative approaches to traditional methods for growth parameters of fisheries industry 334 diversity in the number of specimens analyzed, as well as in the observed length ranges of the species caught (Tesch 1971). The morphological differences are used in determining the growth characteristics of the freshwater crayfish population, comparing populations of the same species with different regions and classifying freshwater crayfish systematically (Harlioğlu 1999). The calculated LWR is model dependent; as a result, model selection uncertainty may be quite higher in certain data sets. Ignoring model selection uncertainty may cause substantial overestimation of the precision and estimation of the confidence intervals of the parameters below the nominal level. This uncertainty has serious implications, e.g., in the case of comparing the growth parameters of different crayfish populations. The average lengths and weight of the males were higher than the females in this study. It was generally found that TL and TW of all sex was longer and weight than that of all the literature (Table 5). Comparison of crayfish parameters in different locations. Referee Sex TL TW Regression parameters Sex ratio (♀/♂)a b r 2 Harlioğlu (1999) Keban Dam Lake ♀ ♂ 106.79 108.14 - 0.00159 0.00093 2.52 2.67 0.88 0.92 1.16:1 Harlioğlu and Harlioğlu (2005) Eğirdir Lake İznik Lake Hirfanli Dam Lake ♀ ♂ 103.29 101.81 32.17 33.07 - 2.11 2.51 0.82 0.92 1.14:1 ♀ ♂ 104.54 100.47 29.19 29.34 - 2.66 2.72 0.94 0.94 1.15:1 ♀ ♂ 105.93 104.76 19.36 20.17 - 2.22 3.66 0.78 0.89 0.82:1 Balık et al. (2005) Demirköprü Dam Lake ♀ ♂ 92.88 90.18 24.19 25.43 0.00002 0.00001 3.06 3.27 0.97 0.98 0.49:1 Berber and Balık (2006) Manyas Lake ♀ ♂ 89.07 82.12 21.85 19.57 0.0003 0.0003 2.94 2.98 0.99 0.97 Berber and Balık (2009) Apolyont Lake ♀ ♂ - 20.62 21.92 0.0003 0.0002 2.96 3.03 0.94 0.95 0.68:1 Deniz et al. (2013) Inland water in Turkey Eğirdir Lake Hirfanli Dam Lake Keban Dam Lake Porsuk Dam Lake ♀ ♂ - - 0.00003 0.00003 2.96 2.97 0.87 0.88 0.84:1 ♀ ♂ - - 0.00007 0.00001 2.78 3.21 0.88 0.93 0.91:1 ♀ ♂ - - 0.0001 0.000008 2.71 3.28 0.90 0.92 0.57:1 ♀ ♂ - - 0.0001 0.000005 2.42 3.38 0.75 0.83 0.87:1 Benzer et al. (2015) Mogan Lake ♀ 108.71 28.64 0.00220024 2.021 0.99 0.14:1♂ 102.93 32.49 0.00095247 2.229 0.99 Table. 5 5 Discussion 335 Benzer and Benzer (2015) Dikilitaş Pond ♀ ♂ 110.6 113.5 38.52 50.02 0.03105469 0.05958618 2.98 2.76 0.98 0.99 0.68:1 Aydın et al. (2015) İznik Lake ♀ ♂ 104.17 95.71 32.50 28.82 0.00003 0.000008 3.01 3.30 0.97 0.97 0.89:1 Benzer and Benzer (2018) Uluabat Lake ♀ ♂ ♀♂ 118.72 117.80 118.26 40.86 45.43 43.16 0.04059605 0.02999258 0.03634341 2.775 2.947 2.845 0.968 0.959 0.961 1:1 This Study ♀ ♂ ♀♂ 118.17 122.15 119.88 42.04 49.09 45.06 0.12949911 0.18113315 0.14162875 2.326 2.218 2.301 0.975 0.964 0.968 1:0.75 ♀:Female; ♂:Male; ♀♂:Female+Male. Some researchers have indicated that the females have a larger size than the males (Benzer and Benzer 2018; Benzer et al. 2015; Aydın et al. 2015; Balık et al. 2005; Berber and Balık 2006), while some researchers have indicated that male females are longer than female females (Harlioğlu 1999; Berber and Balık 2009; Benzer and Benzer 2016). In some studies, it is stated that females are heavier than males (Berber and Balık 2006; Aydın et al. 2015), and some studies indicate that males are heavier than females (Benzer and Benzer 2018; Benzer et al. 2015; Benzer and Benzer 2016; Balık et al. 2005; Berber and Balık 2009). It was found that b values for male and female were lower than the values found in the study by Harlioğlu (1999), Harlioğlu and Harlioğlu (2005) (Eğirdir and İznik) for female, Benzer et al. (2015), Aydın et al. (2015), Benzer and Benzer (2015), Deniz et al (2013) (Eğirdir, Hirfanlı, Keban and Porsuk). It was found that b values were higher than the values found in the study by Benzer et al. (2015) for all individuals and Harlioğlu and Harlioğlu (2005) (Eğirdir, İznik and Hirfanlı – male) for anly males (Table 5). The differences may result from the environmental factors, food, density of the population and the selectivity of the traps or fykenets used in the studies. For example, male crayfish were found heavier than females in a previous study. This disparity is said to be a result of the increasing development of the male chela with sexual maturity; however, the chela of the females remain isometric during their life (Romaire et al. 1977). Furthermore, males were found rougher and more thick-set than females in another study (Skurdal and Qvenild 1986). The TL – TW relationship, which shows the estimate power of the developed ANNs, was found to be 0.90297 as the r2 (for all individuals) values. Success is considered high when r2 values are between 0.95 – 1 (Ekici and Aksoy 1993). The coefficient Alternative approaches to traditional methods for growth parameters of fisheries industry 336 correlation (r2) calculated by the LWR regression model (for all individuals) was 0.968. When the coefficient correlation (r2) was evaluated in both ANNs and LWR model, the results of LWR were better, although they did not seem close to each other. The calculated SSE and MSE value for actual data, ANNs, length-weight relations are given in Table 6. It is evaluated that comparing the MAPE values together with r2, SSE and MSE values can give a healthy result (Gentry et al. 1995). SSE and MSE values for actual data, ANNs, length-weight relations Actual data ANNs Length-weight Relations Length Weight Length Weight Length Weight SSE 381.78 12307.66 233.57 28105.12 458.01 28124.96 MSE 2.74 223.77 1.68 201.50 3.29 202.33 When MAPE results of length-weight relation and ANNs were compared, it was found that MAPE value of the forecast of ANNs was 0.164 and 0.750, and the value of length-weight relationship was 2.620 and 2.488 for length–weight of all genders. ANNs gives better results than length-weight relation (Table 4). In the literature, it is reported that ANNs MAPE ratios are low (Tureli Bilen et al. 2011; Benzer and Benzer 2016; Benzer et al. 2015, 2016, Benzer and Benzer 2018). The most important result of this research is that it is done with artificial neural networks instead of the traditional approach methods used in businesses administration of fisheries thus providing the necessary environment for decision makers to make decisions more easily and quickly. By using the developments in the field of informatic in prediction approaches, plans will be made more comfortable and easier for the coming years, without forcing the populations existing in the fishing industry. Especially in the European Union countries, it is evaluated that the use of information software and hardware tools can be used more effectively and that inventory control and product efficiency can reach maximum levels through the use of modern fisheries. Taking into consideration that timing, effort and cost are the three most important elements of a successful project management, the results obtained with modern predict methods will lead to making healthier decisions based on case evaluation reports in business. Modern methods of pre- Table 6. 5 Discussion 337 dict will gain competitive advantage when judged to be more difficult in case of uncertainty. With the industrial revolution of the industry 4.0, it will be possible to automate all kinds of business sectors faster and less costly by using modern methods. In this paper, the use of the neural networks approach was examined for regression problem with the aim of analyzing the level of relationships between length and weight variables in Yeniçağa Lake by using the crayfish. References Aksu, Ö. and Harlioğlu, M.M., The Effect of Placing Hides into the Natural Habitat on Astacus Leptodactylus (Eschscholtz, 1823) Harvest. Ecological Life Sciences, 11(2), 1–10. 2016. Andrade, H.A. and Campos, R.O., Allometry coefficient variations of the lengthweight relationship of skipjack tuna (Katsuwonus pelamis) caught in the southwest South Atlantic. Fish.Res., 55: 307–312. 2002. Andrews, R., Diederich, J., & Tickle, A. B. Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowledge-based systems, 8(6), 373–389. 1995. Aydin, H., Harlioğlu, M.M. and Deniz, T., An investigation on the population parameters of freshwater crayfish (Astacus leptodactylus Esch., 1823) in Lake İznik (Bursa). Turkish Journal of Zoology, 39(4), 660–668. 2015. Azari, M.A., Seidgar, M. and Mohebbi, F., Population dynamics of freshwater crayfish (Astacus leptodactylus) in Aras reservoir, Iran. Environ. Resourc. Res., 3: 15–26. 2015. Azari, S., Jhin, G., Papini, M. and Spelt, J.K., Fatigue threshold and crack growth rate of adhesively bonded joints as a function of load/displacement ratio. Composites Part A 57, 59–66. 2014. Balık, S., Ustaoğlu, M.R., Sarı H.M., Berber, S., Determination of traits some growth and morphometric of crayfish (Astacus leptodactylus Eschscholtz, 1823) at Demirköprü Dam Lake (Manisa). EU Journal of Fisheries & Aquatic Sciences, 22(1–2): 83–89. 2005. Baran İ, Soylu E., Crayfish plague in Turkey (short communication). J Fish Dis 12: 193–197. 1989. Benzer, R. Population Dynamics Forecasting Using Artificial Neural Networks. Fresenius Environmental Bulletin, 24(2), 460–466. 2015. Benzer, S and Benzer, R., Determine Some Morphological Characteristics of Crayfish (Astacus Leptodactylus Eschscholtz, 1823) with Tradional Methods and Artificial Neural Networks in Dikilitas Pond, Ankara, Turkey. Fresenius Environmental Bulletin, 24 (11A):3727–3735. 2015. 6 Alternative approaches to traditional methods for growth parameters of fisheries industry 338 Benzer, S., Karasu Benli, Ç., Benzer, R., The comparison of growth with lengthweight relation and artificial neural networks of crayfish, Astacus leptodactylus, in Mogan Lake. J. Black Sea/Mediterranean Environment, 21(2):208–223. 2015. Benzer, S and Benzer, R., Evaluation of growth in pike (Esox lucius L., 1758) using traditional methods and artificial neural networks. Applied Ecology and Environmental Research; 14(2), 543–554. 2016. Benzer, S, Benzer, R and Gül A., Developments in Science and Engineering. St. Kliment Ohridski University Presssofia, Chaper 5: Artificial Neural Networks Application for Biological Systems: The Case Study of Pseudorasbora parva.; A. ISBN 978–954–07–4137–6. 2016. Benzer, S., Benzer, R., and Günal, A. Ç. Artificial Neural Networks approach in morphometric analysis of crayfish (Astacus leptodactylus) in Hirfanlı Dam Lake. Biologia, 72(5), 527–535. 2017. Benzer, S. and Benzer, R. New Perspectives for Predicting Growth Properties of Crayfish (Astacus leptodactylus Eschscholtz, 1823) in Uluabat Lake. Pakistan J. Zool. 50(1):35–45. 2018. Berber, S. and Balık, S., Determination of traits some growth and morphometric of crayfish (Astacus leptodactylus Eschscholtz, 1823) at Manyas Lake (Balıkesir), EU Journal of Fisheries & Aquatic Sciences, 23(1–2):83–91. 2006. Berber, S. and Balık, S., The length-weight relationships, and meat yield of crayfish (Astacus leptodactylus Eschcholtz, 1823) population in Apolyont Lake (Bursa, Turkey). J Fish Sci., 3(2):86–99. 2009. Beyer, J.E., On length˗weight relationships: Part II. Computing mean weights from length statistics. Fishbyte, 9: 50˗54. 1991. Bolat, Y., Mazlum, Y., Demirci, A., & Koca, H. U. Estimating the population size of Astacus leptodactylus (Decapoda: Astacidae) by mark-recapture technique in Egirdir lake, Turkey. African Journal of Biotechnology, 10(55), 11778. 2011. Bon, A.T., Hui, H.S. Industrial Engineering Solution in the Industry: Artificial Neural Network Forecasting Approach. Proceedings of the International Conference on Industrial Engineering and Operations Management Rabat, Morocco, April 11–13, 2017. Bök, T. D., Aydın, H., & Ateş, C. A study on some morphological characteristics of Astacus leptodactylus (Eschscholtz 1823) in seven different inland waters in Turkey. Journal of Black Sea/Mediterranean Environment, 19(2). 2013. Brosse, S., Guegan, J., Tourenq, J. and Lek S., The Use of Artificial Neural Networks to Assess Fish Abundance and spatial occupancy in the littoral zone of a mesotrophic lake. Ecol Model., 120(2–3):299–311. 1999. Cabreira, A. G., Tripode, M., Madirolas, A. Artificial neural networks for fishspecies identification. ICES Journal of Marine Science, 66(6), 1119–1129. 2009. 6 References 339 Demirol, F., Gündüz, F., Yüksel, F., Çoban, M.Z., Abdulmutalip, B.E.R.İ., Kurtoğlu, M. and Küçükyilmaz, M., The Investigation of By-catch and Discard Rates in Crayfish (Astacus leptodactylus Eschscholtz, 1823) Catching in the Keban Dam Lake. Journal of Limnology and Freshwater Fisheries Research, 1(2), 69–74. 2015. Deniz, T.B., Aydın, C. and Ateş, C., A study on some morphological characteristics of Astacus leptodactylus (Eschscholtz 1823) in seven different inland waters in Turkey. J Black Sea/Mediterranean Environment., 19(2):190˗205. 2013. Deval, M. C., Bök, T., Ateş, C., & Tosunoğlu, Z. Length-based estimates of growth parameters, mortality rates, and recruitment of Astacus leptodactylus (Eschscholtz, 1823)(Decapoda, Astacidae) in unexploited inland waters of the northern Marmara region, European Turkey. Crustaceana, 80(6), 655–665. 2007. Dopico, M., Gomez, A., De la Fuente, D., García, N., Rosillo, R., & Puche, J. A vision of industry 4.0 from an artificial intelligence point of view. In Proceedings on the International Conference on Artificial Intelligence (ICAI) (p. 407). The Steering Committee of The World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp). 2016. Ekici, B.B. and Aksoy, U.T., Prediction of building energy consumption by using artificial neural networks, Advances in Engineering Software, 40: 356–362. 1993. Etchison, L., Jacquemin, S. J., Allen, M., Pyron, M. Morphological variation of rusty crayfish Orconectes rusticus (Cambaridae) with gender and local scale spatial gradients. International Journal of Biology 4 (2): 163˗171. 2012. Fish, K. E., Barnes, J. H., & AikenAssistant, M. W. Artificial neural networks: a new methodology for industrial market segmentation. Industrial Marketing Management, 24(5), 431–438. 1995. Furst, M., Future perspectives for Turkish crayfish fishery. I Unv J Fish Aquat Sci 2: 139–147. 1988. Füreder, L., Oberkofler, B., Hanel, R., Leiter J. and Thaler, B., The freshwater crayfish Austropotamobius pallipes in South Tyrol: Heritage species and bioindicator. B Fr Peche Piscic., 370–371:79−95. 2003. Gentry, T.W., Wiliamowski B.M. and Weatherford L.R., A comparison of traditional forecasting techniques and neural networks. Intelligent Engineering Systems Through Artificial Neural Networks, 5, 765–770. 1995. Gillet, C. and Laurent, P.J., Tail length variations among noble crayfish (Astacus astacus (L)) populations. Freshwater Crayfish, 10: 31–36. 1995. Goethals, P. L., Dedecker, A. P., Gabriels, W., Lek, S., & De Pauw, N. Applications of artificial neural networks predicting macroinvertebrates in freshwaters. Aquatic Ecology, 41(3), 491–508. 2007. Alternative approaches to traditional methods for growth parameters of fisheries industry 340 Gutiérrez-Yurrita, P.J., Martínez, J.M., Bravo-Utrera, M.A., Montes, C., Ilhéu M. and Bernardo, J.M., The status of crayfish populations in Spain and Portugal. Pages 161–192 in F. Gherardi, and D. M. Holdich, editors. Crayfish in Europe as alien species: how to make the best of a bad situation? A. A. Balkema, Rotterdam, Netherlands. 1999. Harlioğlu, M. M. Comparative biology of the signal crayfish, Pacifastacus leniusculus (Dana), and the narrow-clawed crayfish, Astacus leptodactylus Eschscholtz (Doctoral dissertation, University of Nottingham). 1996. Harlioğlu, M.M., The Relationships between Length-Weight, and Meat Yield of Freshwater Crayfish, Astacus leptodactylus Eschscholtz, in the Ağın Region of Keban Dam Lake. Turk J Zool., 23: 949–958. 1999. Harlioğlu, M.M., The present situation of freshwater crayfish, Astacus leptodactylus (Eschscholtz, 1823) in Turkey. Aquaculture, 230:181–187. 2004. Harlioğlu, M.M. and Harlioğlu, A.G., The comparison of morphometric analysis and meat yield contents of freshwater crayfish, Astacus leptodactylus (Esch 1823) caught from İznik, Eğirdir Lakes and Hirfanlı Dam Lake, Science and Engineering Journal of Fırat University, 17(2):412–423. 2005. Hogger, J. B., Ecology, population biology and behaviour, In: D.M. Holdich and R.S. Lowery (eds.), Freshwater Crayfish, Biology, Menagement and Exploitation, Cambridge, 114–144. 1988. Holdich, D.M. and Lowery, R.S., Freshwater Crayfish – Biology, Management and Exploitation. Chapman and Hall, London. 498 p. 1988. Hopgood A.A. Intelligent Systems for Engineers and Scientists. CRC Press, Florida, 461 pp. 2000. Joy, K.M. and Death, R.G., Predictive modelling and spatial mapping of freshwater fish and decapod assemblages using GIS and neural Networks. Freshwater Biol., 49(8):1306–1052. 2004. Kaastra, I., Boyd, M. Designing a neural network for forecasting financial and economic time series. Neurocomputing, 10(3), 215–236. 1996. Kılıç, S., Becer, Z. A. Some Growth Characters of Tench (Tinca tinca L., 1758) in Lake Yeniçaga, Bolu, Turkey. Journal of Applied Biological Sciences, 7(3). 2013. Krenker, A., BešTer, J. and Kos, A., Introduction to the Artificial Neural Networks, Artificial Neural Networks – Methodological Advances and Biomedical Applications, Prof. Kenji Suzuki (Ed.)., ISBN: 978–953–307–243–2. 2011. Lek, S., & Guégan, J. F. Artificial neural networks as a tool in ecological modelling, an introduction. Ecological modelling, 120(2–3), 65–73. 1999. Lewis, C.D. Industrial and business forecasting methods. London: Butterworths. 1982. Lindqvist, O.V. and Lahti, E., On the sexual dimorphism and condition index in the crayfish Astacus astacus L. in Finland. Freshwater Crayfish., 5: 3–11. 1983. 6 References 341 Maravelias, C.D., Haralabous, J. and Papaconstantinou, C., Predicting demersal fish species distributions in the Mediterranean Sea using artificial neural networks. Mar Ecol., 255:249–258. 2003. Mastrorillo, S., Lek, S., Dauba, F. and Belaud, A., The use of artificial neural networks to predict the presence of small-bodied fish in river. Freshwater Biol., 38: 237–246. 1997. Mendes, B., Fonseca, P. and Campos, A., Weight length relationships for 46 fish species of the Portuguese west coast. J. Appl. Ichthyol., 20: 355–361. 2004. Momot, W. T. Annual production and production/biomass of the crayfish, Orconectes virilis in two northern Ontario Lakes. Trans. Am. Fish. Soc., 96: 202– 209. 1978. Moutopoulos, D. K., Stergiou, K. I. Length˗weight and length˗length relationships of fish species from Aegean Sea (Greece). J. Appl. Ichthyol. 18: 200˗203. 2002. Nystrom, P. Ecology. In: Biology of Freshwater Crayfish (ed. D. M. Holdich), pp. 192–235. Blackwell Science, Oxford. 2002. Obach, M., Wagner, R., Werner, H. and Schmidt, H.H., Modelling population dynamics of aquatic insects ith artificial neural networks. Ecol Model., 146:207– 217. 2001. Olden, J. D., & Jackson, D. A. Fish–habitat relationships in lakes: gaining predictive and explanatory insight by using artificial neural networks. Transactions of the American Fisheries Society, 130(5), 878–897. 2001. Olsson, K., Dynamics of omnivorous crayfish in freshwater ecosystems. Ph.D. thesis. Department of Ecology, Limnology, Lund Univ., 119 pp. 2008. Ouali, D., Chebana, F., & Ouarda, T. B. Fully nonlinear statistical and machine‐ learning approaches for hydrological frequency estimation at ungauged sites. Journal of Advances in Modeling Earth Systems, 9(2), 1292–1306. 2017. Park, Y.S., Verdonschot, P.F.M., Chon, T.S. and Lek, S., Patterning and predicting aquatic macro invertabrate diversities using artificial neural network. Water Res., 37: 1749–1758. 2003. Pârvulescu L., Schrimpf A., Kozubíková E., Cabanillas Resino S., Vrålstad T., Petrusek A & Schulz R. Invasive crayfish and crayfish plague on the move: first detection of the plague agent Aphanomyces astaci in the Romanian Danube. Diseases of Aquatic Organisms 98: 85–94. 2012. Primavera, J.H., Parado-Estepa, F.D. and Lebata, J.L., Morphometric relationship of length and weight of giant tiger prawn Penaeus monodon according to life stage, sex and source. Aquaculture, 164: 67–75. 1998. Rahe R, Soylu E. Identification of the pathogenic fungus causing destruction to Turkish crayfish stocks (Astacus leptodactylus). J Invertebr Pathol 54: 10–15. 1989. Alternative approaches to traditional methods for growth parameters of fisheries industry 342 Rhodes, C.P. and Holdich, D.M., On size and sexual dimorphism in Austropotamobius pallipes (Lereboullet) – A step in assessing the commercial exploitation potential of the native British freshwater crayfish. Aquaculture, 17: 345–358. 1979. Ricker, W.E., Linear regressions in fishery research. J Fish Res Board Can., 30:409– 434. 1973. Rocha, J. C., Passalia, F. J., Matos, F. D., Takahashi, M. B., de Souza Ciniciato, D., Maserati, M. P., ... Nogueira, M. F. G. A method based on artificial intelligence to fully automatize the evaluation of bovine blastocyst images. Scientific Reports, 7(1), 7659. 2017. Romaire, R.P., Forester J.S. and Avault, J.W., Length˗weight relationships of two commercially important crayfishes of the genus Procambarus. Freshwater Crayfish, 3:463˗470. 1977. Rumelhart, D.E., Hinton, G.E. and Williams, R.J., Learning internal representations by error propagation in Parallel Distributed Processing. Explorations in the Microstructure of Cognition MIT Press, 1:318–362. 1986. Sari, B. G., Lúcio, A. D. C., Santana, C. S., Krysczun, D. K., Tischler, A. L., & Drebes, L. Sample size for estimation of the Pearson correlation coefficient in cherry tomato tests. Ciência Rural, 47(10):1–6. 2017. Saygı B.Y, Demirkalp, F.Y. Trophic status of shallow Yeniçağa Lake (Bolu, Turkey) in relation to physical and chemical environment. Fresenius Environmental Bulletin. 13:385 -393. 2004. Sharda, R., Patil, R. B. Connectionist approach to time series prediction: an empirical test. Journal of Intelligent Manufacturing, 3(5), 317–323. 1992. Sholahuddin, A., Ramadhan, A. P., & Supriatna, A. K. The Application of ANN- Linear Perceptron in the Development of DSS for a Fishery Industry. Procedia Computer Science, 72, 67–77. 2015. Skurdal, J. and Qvenild, T. Growth, maturity and fecundity of Astacus astacus in Lake Steinsfjorden, In: Freshwater Crayfish (Eds., J. Skurdal and T. TougbØl), Norway, pp. 182–186. 1986. Skurdal, J. and Taugbol, T., Crayfish of commercial importance-Astacus. In: D.M. Holdich (Ed.), Biology of Freshwater Crayfish. Blackwell Science, Oxford: 467– 510. 2001. Souty-Grosset, C., Holdrich, D.M., Noel, P.Y., Reynolds, J.D. and Haffner, P., Atlas of crayfish in Europe. Publications Scientifiques du MNHN-Paris. 2006. Sun, L., Xiao, H., Li, S. and Yang, D., Forecating fish stock recruitment and planning optimal harvesting strategies by using neural network. Journal of Computers, 4(11):1075–1082. 2009. Suryanarayana, I., Braibanti, A., Rao, R.S., Ramamc, V.A., Sudarsan, D. and Rao, G.N., Neural networks in fisheries research. Fish Res., 92:115–139. 2008. Tekin, M. Numerical Methods (Computer Analysis). (Updated 6. Edition). Konya: Günay Ofset. (Turkish). 2008. 6 References 343 Teles, L. O., Vasconcelos, V., Pereira, E., & Saker, M. Time series forecasting of cyanobacteria blooms in the Crestuma Reservoir (Douro River, Portugal) using artificial neural networks. Environmental Management, 38(2), 227–237. 2006. Tesch, F.W., Age and growth. In: Methods for Assessment of Fish Production in Fresh Waters (ed., W. E. Ricker), Blackwell Scientific Publications, Oxford, 99˗130. 1971. Tosunoğlu, Z., Aydın, C., Özaydın, O. and Leblebici, S., Trawl codend mesh selectivity of braided PE material for Parapenaeus longirostris (Lucas, 1846) (Decapoda, Penaeidae). Crustaceana, 80: 1087–1094. 2007. Tureli Bilen, C., Kokcu, P. and Ibrikci, T., Application of Artificial Neural Networks (ANNs) for Weight Predictions of Blue Crabs (Callinectes sapidus Rathbun, 1896) Using Predictor Variables. Medit Mar Sci., 12(2):439–446. 2011. TÜİK Aquaculture Statistics. Ankara, Turkey: Turkey Statistical Institute Publications (in Turkish). 2018. TÜİK, Aquaculture Statistics (1984–1991). Ankara, Turkey: Turkey Statistical Institute Publications (in Turkish). 1984–1991. Verdiell-Cubedo, D., Oliva-Paterna, F.J. and Torralva, M., Length-weight relationships for 22 fish species of the Mar Menor coastal lagoon (Western Mediterranean Sea). Journal of Applied Ichthyology, 22: 293–294. 2006. Westman, K., Savolainen, R., Growth of the signal crayfish Pacifastacus leniusculus, in a small forest lake in Finland. Boreal Environ. Res. 7, 53–61. 2002. Witt, S.F. and Witt C.A. Modeling and Forecasting Demand in Tourism. Londra: Academic Press. 1992. Yüksel, F., and Duman, E. The investigation of the crayfish (Astacus leptodactylus Eschscholtz, 1823) population amplitude in Keban Dam Lake. Journal of FisheriesSciences. com, 5(3), 226. 2011. Key Terms Artificial neural networks crayfish Decision Growth Traditional methods Fisheries industry Artificial intelligent Lake Modern methods Matlab Questions for Further Study Describe the principal steps in the planning phase. What are the major deliverables? 7 8 Alternative approaches to traditional methods for growth parameters of fisheries industry 344 Compare modern methodologies and traditional methodologies. What does normalization mean in artificial neural networks? How do error comparisons be made in artificial neural networks? Exercises In the fisheries industry, you can use the traditional methods for the samples taken from ecosystems. Find the growh models and draw growh curve. What do you say? In the fisheries industry, you can use the modern methods (artificial neural networks) for the samples taken from ecosystems. Find the growh models and draw growh curve. What do you say? Compare the traditional methods and modern methods (artificial neural networks). According to the error rates, which method gave better results. What do you say about ecosystem? Artificial neural networks can be used in other areas of the industry. discuss Further Reading Franceschini, S., Tancioni, L., Lorenzoni, M., Mattei, F., & Scardi, M. 2019. An ecologically constrained procedure for sensitivity analysis of Artificial Neural Networks and other empirical models. PloS one, 14(1), e0211445. Kaveh, M., Sharabiani, V. R., Chayjan, R. A., Taghinezhad, E., Abbaspour-Gilandeh, Y., & Golpour, I. 2018. ANFIS and ANNs model for prediction of moisture diffusivity and specific energy consumption potato, garlic and cantaloupe drying under convective hot air dryer. Information Processing in Agriculture, 5(3), 372–387. Rohani, A., Taki, M., & Bahrami, G. 2019. Application of artificial intelligence for separation of live and dead rainbow trout fish eggs. Artificial Intelligence in Agriculture.2019: 27–34. Walczak, S. 2019. Artificial neural networks. In Advanced Methodologies and Technologies in Artificial Intelligence, Computer Simulation, and Human- Computer Interaction (pp. 40–53). IGI Global. 9 10 10 Further Reading 345 Zhang, X., Xue, T., & Stanley, H. E. 2019. Comparison of Econometric Models and Artificial Neural Networks Algorithms for the Prediction of Baltic Dry Index. IEEE Access, 7, 1647–1657. Alternative approaches to traditional methods for growth parameters of fisheries industry 346

Chapter Preview



Organizations have always been dependent on communication, information, technology and their management. The development of information technology has sped up the importance of management information systems, which is an emerging discipline combining various aspects of informatics, information technology, and business management. Understanding the impact of information on today’s organizations requires technological and managerial views, which are both offered by management information systems.

Business management is not only about generating greater returns and using new technologies for developing businesses to reach future goals. Business management also means generating better revenue performance if plans are diligently followed.

It is part of business management to have an ear to the ground of global economic trends, changing environmental conditions and preferences, as well as the behavior of value chain partners. While, until now, business management and management information systems are mostly treated as independent fields, this publication takes an interest in the cooperation of the two. Its contributions focus on both research areas and practical approaches, in turn showing novelties in the area of enterprise and business management.

Main topics covered in this book are technology management, software engineering, knowledge management, innovation management and social media management.

This book adopts an international view, combines theory and practice, and is authored for researchers, lecturers, students as well as consultants and practitioners.