1 Introduction

Social image hosting websites have recently become very popular. On these sites, users can upload and tag images for sharing their travelling experiences. The geotagged images are widely used in landmark recognitions and trip recommendations. Large amount of information generated from these location-based social services covers not only popular locations but also obscure ones. Since personalized tours are becoming popular, more attention is focusing on obscure sightseeing locations that are less well-known while still worth visiting. In Fig. 1 are show two dimensions of diverse sightseeing resources. The evaluation can be done using the sightseeing quality and popularity [1,2,3,4,5].

Fig. 1.
figure 1

Two dimensions of diverse sightseeing resources.

Full size image

In this work, we use Fuzzy Logic (FL) for decision of sightseeing spots. The FL is the logic underlying modes of reasoning which are approximate rather then exact. The importance of FL derives from the fact that most modes of human reasoning and especially common sense reasoning are approximate in nature [6]. FL uses linguistic variables to describe the control parameters. By using relatively simple linguistic expressions it is possible to describe and grasp very complex problems. A very important property of the linguistic variables is the capability of describing imprecise parameters.

The concept of a fuzzy set deals with the representation of classes whose boundaries are not determined. It uses a characteristic function, taking values usually in the interval [0, 1]. The fuzzy sets are used for representing linguistic labels. This can be viewed as expressing an uncertainty about the clear-cut meaning of the label. But important point is that the valuation set is supposed to be common to the various linguistic labels that are involved in the given problem.

The fuzzy set theory uses the membership function to encode a preference among the possible interpretations of the corresponding label. A fuzzy set can be defined by examplification, ranking elements according to their typicality with respect to the concept underlying the fuzzy set [7].

In this paper, we propose and evaluate a fuzzy-based system for decision of sightseeing spots considering hot spot access as a new parameter. In our system, we considered four input parameters: Ambient Temperature (AT), Air Quality (AQ), Noise Levle (NL) and Hot Spot Access (HSA) to decide the output parameter Visit or Not Visit (VNV).

The structure of this paper is as follows. In Sect. 2, we introduce FL used for control. In Sect. 3, we present the proposed fuzzy-based system. In Sect. 4, we discuss the simulation results. Finally, conclusions and future work are given in Sect. 5.

2 Application of Fuzzy Logic for Control

The ability of fuzzy sets and possibility theory to model gradual properties or soft constraints whose satisfaction is matter of degree, as well as information pervaded with imprecision and uncertainty, makes them useful in a great variety of applications [8,9,10,11,12,13,14,15,16].

The most popular area of application is Fuzzy Control (FC), since the appearance, especially in Japan, of industrial applications in domestic appliances, process control, and automotive systems, among many other fields.

In the FC systems, expert knowledge is encoded in the form of fuzzy rules, which describe recommended actions for different classes of situations represented by fuzzy sets.

In fact, any kind of control law can be modeled by the FC methodology, provided that this law is expressible in terms of “if ... then ...” rules, just like in the case of expert systems. However, FL diverges from the standard expert system approach by providing an interpolation mechanism from several rules. In the contents of complex processes, it may turn out to be more practical to get knowledge from an expert operator than to calculate an optimal control, due to modeling costs or because a model is out of reach.

A concept that plays a central role in the application of FL is that of a linguistic variable. The linguistic variables may be viewed as a form of data compression. One linguistic variable may represent many numerical variables. It is suggestive to refer to this form of data compression as granulation.

The same effect can be achieved by conventional quantization, but in the case of quantization, the values are intervals, whereas in the case of granulation the values are overlapping fuzzy sets. The advantages of granulation over quantization are as follows:

  • it is more general;

  • it mimics the way in which humans interpret linguistic values;

  • the transition from one linguistic value to a contiguous linguistic value is gradual rather than abrupt, resulting in continuity and robustness.

FC describes the algorithm for process control as a fuzzy relation between information about the conditions of the process to be controlled, x and y, and the output for the process z. The control algorithm is given in “if ... then ...” expression, such as:

$$\begin{aligned} \begin{array}{c} \hbox {If x is small and y is big, then z is medium}; \\ \hbox {If x is big and y is medium, then z is big}. \end{array} \end{aligned}$$

These rules are called FC rules. The “if” clause of the rules is called the antecedent and the “then” clause is called consequent. In general, variables x and y are called the input and z the output. The “small” and “big” are fuzzy values for x and y, and they are expressed by fuzzy sets.

Fuzzy controllers are constructed of groups of these FC rules, and when an actual input is given, the output is calculated by means of fuzzy inference.

Fig. 2.
figure 2

FVS structure.

Full size image

3 Proposed Fuzzy-Based System

The proposed system stucture is show in Fig. 2. We call this system: Fuzzy-based Visiting Spots (FVS) system. In this work, we consider four parameters: Ambient Temperature (AT), Air Quality (AQ), Noise Level (NL) and Hot Spot Access (HSA) to decide the sightseeing spots Visit or Not Visit (VNV). The AT is the temperature at the sightseeing spots. We use the air pollution data around sightseeing spots to decide the AQ. The NL is the amplitude level of the noise. For HSA, we consider the access by walk, train, bus, car and airplane. These four parameters are not correlated with each other, for this reason we use fuzzy system. The membership functions for our system are shown in Fig. 3. In Table 1, we show the fuzzy rule base of our proposed system, which consists of 135 rules.

Fig. 3.
figure 3

Membership functions.

Full size image
Table 1. FRB.
Full size table

The input parameters for FVS are: AT, AQ, NL and HSA. The output linguistic parameter is VNV. The term sets of AT, AQ, NL and HSA are defined respectively as:

$$\begin{aligned} AT&=\{{ Very}~{ Cold},~{ Cold},~{ Normal},~Hot,~{ Very}~Hot\} \nonumber \\&=\{VC,~Co,~No,~Ho,~VH\}; \nonumber \\ AQ&=\{{ Good},~{ Normal},~Bad\}\nonumber \\&=\{{ Good},~Nor,~Bad\}; \nonumber \\ NL&=\{Low,~{ Middle},~{ High}\} \nonumber \\&=\{Lo,~Mi,~Hi\}; \nonumber \\ HSA&=\{Bad,~{ Normal},~{ Good}\} \nonumber \\&=\{Bd,~N,~Gd\}. \end{aligned}$$
(1)

and the term set for the output VNV is defined as:

$$\begin{aligned} VNV=\left( \begin{array}{c} { VisitLevel}1 \\ { VisitLevel}2 \\ { VisitLevel}3 \\ { VisitLevel}4 \\ { VisitLevel}5 \\ { VisitLevel}6 \\ { VisitLevel}7 \\ \end{array}\right) =\left( \begin{array}{c} VL1 \\ VL2 \\ VL3 \\ VL4 \\ VL5 \\ VL6 \\ VL7 \\ \end{array}\right) . \end{aligned}$$
Fig. 4.
figure 4

Relation of VNV with AT and AQ for different HSA when \(\hbox {NL}=10\).

Full size image
Fig. 5.
figure 5

Relation of VNV with AT and AQ for different HSA when \(\hbox {NL}=50\).

Full size image
Fig. 6.
figure 6

Relation of VNV with AT and AQ for different HSA when \(\hbox {NL}=90\).

Full size image

4 Simulation Results

In this section, we present the simulation results for our proposed fuzzy-based system. In our system, we decided the number of term sets by carrying out many simulations.

From Fig. 4, 5 and 6, we show the relation of VNV with AT, AQ, NL and HSA. In these simulations, we consider the NL and HSA as constant parameters. In Fig. 4, we consider NL value 10 units. We change the HSA value from 20 to 80 units. When the HSA increases, the VNV is increased. By increaseing AQ, the VNV is decreased. And when AT is normal, the VNV is the best. In Fig. 5 and Fig. 6, we change NL value to 50 and 90 units, respectively. We see that, when the NL increases, the VNV is decreased.

5 Conclusions and Future Work

In this paper, we proposed a fuzzy-based system to decide the sightseeing spots. We took into consideration four parameters: AT, AQ, NL and HSA. We evaluated the performance of proposed system by computer simulations. From the simulations results, we conclude that when AQ and NL are increased, the VNV is decreased. When the AT is normal, the VNV is the best. But by increasing HSA, the VNV is increased.

In the future, we would like to make extensive simulations to evaluate the proposed system and compare the performance of our proposed system with other systems.