Aimeé A. Gutiérrez-Vázquez
| Florencio A. Roldan-Castellanos | Vianey Torres-Argüelles*
OPEN ACCESS
The hotel industry has a negative effect on the environment, since its activities generate large consumption of resources and greenhouse gas emissions, which is why the World Tourism Organization makes a strong call to all its sectors to move towards a sustainable development model. In the hotel industry, indicators have been used to improve sustainable performance, however, these sustainable indicators are scattered in the literature, which makes it difficult to select them. Therefore, Harmony Search (HS) is proposed to determine which are the best indicators to evaluate the environmental impact generated by the hotel industry. As a result of the HS search, a list of 20 indicators was obtained, which best met the selection criteria: frequency of use, level of application and year of publication.
harmony search, hospitality industry, Metaheuristics, selection methods, sustainable indicators
The hotel industry is one of the most influential sectors within tourism and both share a very close relationship. On the one hand, tourism makes use of lodging establishments when travelers seek to stay overnight at a destination, and a hotel can even be recognized as a tourist attraction, as is the case of Xcaret in Mexico; on the other hand, the hotel industry benefits from the tourists who arrive at various destinations in search of its services. Furthermore, adding links in the tourism-hotel industry relationship, Zhang et al. [1] point out that the specialization and tourist competition of the destination influences the efficiency and quality of the hotel industry. And Torres and Anchundia [2] affirm that lodging and accommodation services constitute a strategic and fundamental element for the development of tourism, since they represent part of the tourism infrastructure.
Tourism has grown significantly in recent years, to such an extent that it has become a key element for the development and socioeconomic growth of nations. Consequently, the hotel industry has benefited from this boom and has positioned itself as an important economic sector, since it represents, together with tourism, a considerable source of income, in addition to creating jobs for the benefit of the economic sector and society [3].
While it is true that tourism and hospitality complement each other, that they bring benefits to nations and that they are crucial agents for the development of countries, to such an extent that this sector currently has a turnover equal to or even higher than that of businesses such as oil exports, automobiles and the food products industry, it is also true that tourism and hospitality are crucial for the development of countries [4], the negative impact they have on the environment is also a major concern.
Tourism, due to the nature of its activities and processes, contributes to global warming with 5% of the total emissions produced by humans and it is estimated that by 2030 this figure will increase to 5.3% [5], it also leads to increased consumption of resources such as soil, water and energy, increased generation of solid waste and wastewater, destruction of landscapes due to infrastructure and buildings, alteration of ecosystems, introduction of exotic species of animals and plants, as well as inducing population flows to more depopulated areas [3].
On the other hand, the hotel industry is considered a major consumer of energy and other resources such as water, gas and materials. It also produces large amounts of waste and greenhouse gases (GHG), and 21% of the total ecological footprint caused by tourism belongs to the hotel industry; all these factors contribute to global warming and generate negative impacts on the environment [6-10].
Besides, the hotel industry impacts on local communities through the occupation of space, the use of infrastructure, relations with local businesses and governments, even hotels have the ability to influence the behavior of the population and promote social exclusion, non-compliance with regulations and the introduction of foreign ideologies that could distort the local culture, as well as tangible and intangible heritage [6, 7].
Faced with this problem, the World Tourism Organization (UNWTO) adopts the model of sustainable development, hence, the concept of sustainable tourism arises in order to meet the current and future needs of visitors, both the industry, environment and host communities [11]. As a result, sustainability has gained popularity in studies of the hospitality industry, and in recent years research has focused on green practices, sustainable construction of lodging establishments and employee and customer perspectives and interest in environmental stewardship [12-14]. At the same time, sustainable criteria have been identified [15]. Of the latter, indicators can be identified.
Indicators in this case are parameters that help to analyze, measure and evaluate green practices within the hotel industry. In the literature there is a wide variety of indicators that have been applied in various case studies, such as those mentioned by the authors identified 66 criteria distributed in five dimensions: environmental, social, cultural, economic and political [15]. Also Duric and Potočnik Topler [16] present 6 factors as the main indicators for the performance of environmental management practices in hotels according to the importance of their impacts; whereas, Asadi et al. [8] developed 8 constructs for which they assigned 32 measurement items, as well, [17] they defined 8 criteria containing 33 sub-criteria, i.e. indicators. Or [18] that take specific indicators such as nZEBs for energy performance.
Table 1. Selection of sustainable indicators applied
|
Author |
Research |
Method |
|
[15] |
Criteria for assessing a sustainable hotel business Rodrigo |
Extensive literature review, semi-structured questionnaire (applied to 177 professionals linked to the hotel market and academia). In-depth interview (in a workshop with 18 participants) and confirmatory factor analysis (R software). |
|
[16] |
The role of performance and environmental sustainability indicators in hotel competitiveness |
Questionnaire based on a literature review, with Likert Scale, Cronbach's Alpha coefficient and a one-factor analysis of variance (ANOVA), applied to hotels in Serbia. |
|
[8] |
Investigating influence of green innovation on sustainability performance: A case on Malaysian hotel industry |
Purposive sampling for the survey of 183 hotels in Malaysia, use of online questionnaire and literature review for items. For measurement, different scales such as Likert scale and partial least squares structural equation modeling (PLS-SEM) were used for data analysis. |
|
[17] |
Sustainable management practices in UAE hotels |
Literature review to identify service management practices. Survey and expert opinion to categorize and prioritize the most important practices and used an analytical hierarchical process (AHP) to prioritize the main criteria and sub-criteria. |
|
[18] |
Comparison of nZEB indicators for hotel renovations under different European climatic conditions |
Extension of the study on the application of nZEB (Near Zero Energy Efficiency Building) energy performance indicators. |
These studies are contained in Table 1, where it is highlighted that the common method for the selection of indicators is based on literature review for the design of questionnaires, surveys or in-depth interviews and an expert evaluation (application in the industry) accompanied by statistical analysis to determine the correlation of indicators, or a group of specific indicators is taken for a given evaluation, as in the case of the study [18] indicators are taken for energy consumption. However, the latter method neglects the selection of indicators that integrate all dimensions of sustainable development. In addition, the studies do not include a selection method that helps to optimally identify indicators that measure the sustainable performance of hotels across large numbers of variables.
Based on the above, it can be inferred that the process for this selection is composed of three main stages or steps:
From the process described above, it is explained that once the parameters have been identified, the next step is to select the indicators that are useful for the study to be carried out. At this point, the studies show that the indicators are taken and added to a questionnaire, and then subjected to an expert evaluation and with the help of various statistical methods, those that are most significant are selected. For methods such as confirmatory factor analysis, Cronbach's Alpha coefficient, one-factor analysis of variance and partial least squares, the number of indicators to be analyzed is limited, and the time it takes to apply them is greater compared to the use of a metaheuristic algorithm, since in a matter of minutes they obtain the result on optimal indicators, the algorithm indicates which are the best within an analysis of more than 100,000 variables.
Thus, the use of metaheuristic algorithms is proposed as a method for the selection of indicators, as well as the inclusion of the dimensions of sustainable development in the hotel industry as a distinctive element. Figure 1 shows the indicator selection process explained previously, as well as the point where the metaheuristic algorithm is incorporated.
Figure 1. Aggregation of Metaheuristics in the indicator selection process
The proposed algorithm is Harmony Search (HS) which is highlighted in yellow at the bottom with the larger circle, while at the top are the methods that are widely used.
1.1 Metaheuristics
Metaheuristics are part of the field of heuristics, which are regaining value in scientific methodology, being applied mainly by cognitive psychology and artificial intelligence [19]. Within the latter is the use of Metaheuristics essentially for solving optimization problems through algorithms, which offers a broad framework of generic algorithms that can be applied to almost any optimization problem [20], Therefore, its use is proposed for the indicator selection problem in order to optimize the process.
Metaheuristics are originally a solution method that directs an interaction between local improvement procedures and higher level strategies, in order to obtain a process capable of scaling from the local optimum, through a robust search within a solution space. Over time, these methods have also come to include all procedures that employ strategies to overcome the limitation of local optimality and search in complex solution spaces, especially procedures that use one or more neighborhood structures as a means to define admissible moves from one solution to another, or to construct or destroy solutions in constructive and destructive processes [21]. In other words, its robust search mechanism focuses on the harmonization between two search elements, exploration or diversification and exploitation or intensification, where the former consists of a search in the areas surrounded by the best (local) solution, while the latter usually seeks to reach new search areas (scalar) [20].
Optimization algorithms within the metaheuristic framework are able to exhibit a higher mass implementation capability with few critical code changes [22], this capability makes a metaheuristic algorithm a viable tool for general and specific industrial applications, differing from a traditional iterative methodology as the application of surveys [23].
The metaheuristic optimization algorithms have the following characteristics pointed out by the studies [20, 23]:
1.2 Taxonomy
In the taxonomy of metaheuristic algorithms, there are several classifications, either according to the trajectory and population, if they are based on metaphors, inspirations in nature, or bioinspiration’s. Figure 2 shows the classification proposed by Abdel-Basset, Abdel-Fatah, and Kumar in 2018, which divides metaheuristics into metaphor-based and non-metaphor-based; where non-metaphor-based ones focus on mathematical models, while metaphor-based ones include the mathematical basis as well as inspiration from nature.
Figure 2. Taxonomy of Metaheuristics
Source: own elaboration with information from the study [20]
The first group contains algorithms such as Iterated Local Search (ILS), Pop Music, Grasp and Variable Neighborhood Search (VNS); whereas Cuckoo Search (CS), Firefly Algorithm (FA), Ant Colony Optimization (ACO), Flower Pollination Algorithm (FPA), Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Simulated Annealing (SA), Sine Cosine Algorithm (SCA) and Harmony Search (HS) belong to the second group.
In turn, it can be seen that the use of those with natural inspiration is broader, since their procedure focuses on the search for optimal solutions based on biological behavior, that is, imitating an organic system such as mass movement patterns or the intelligence of colonies [20]. On the other hand, due to the complexity and variety of the biological spectrum, algorithms have been taken to the analysis and application of more complex techniques such as the imitation of the human nervous system or the harmony that jazz musicians look for when improvising a song.
1.3 Applications of metaheuristics in tourism
As mentioned above, metaheuristic algorithms are used to solve optimization problems, so that their application can be carried out in different fields of study; in the case of tourism, they have been used mainly to solve problems such as the Traveling Salesman Problem (TSP) and the Tourist Travel Design Problem, both problems focus on the creation of tourist circuits to optimize time, costs and tourist preferences.
Table 2. Metaheuristics applied in tourism
|
Author |
Algorithm |
Problem |
|
[24] |
HS |
Traveling salesman problem (TSP) for travelers who need to plan a trip with 21 places located in Lampang, Thailand. |
|
[25] |
SA |
Traveling salesman problem (TSP) to generate the optimal travel route taking into account various user preference criteria. |
|
[26] |
KSA ( K-means and SA combination ) |
Tourist Trip Design Problem, consists of selecting points of interest that match user preferences to suggest personalized daily sightseeing tours. |
|
[27] |
K-means y GA |
Tourist Travel Design Problem, consists of the optimization of itineraries for tourists in order to facilitate the organization of their visits. |
|
[28] |
GA |
Forest road planning to reduce calculation time, road construction costs and environmental impact. |
Table 2 shows that the most used algorithms belong to those based on metaphors such as GA, SA and HS. In addition, no metaheuristic was found used for the selection of sustainable indicators for the hotel industry, nor the application of HS in the field of hospitality. Therefore, this algorithm is proposed for the indicator selection process.
1.4 Harmony Search (HS)
Harmony Search is an algorithm developed in 2000, based on the analogy between improvisations performed by musicians in Jazz, searching for the best harmony determined by the aesthetic estimation and the search in the process for the optimal solution, which is determined by the evaluation of the objective function [29]. A musician produces sounds within a range to form melodies (chords), that is, he plays simultaneous superimpositions of two or more notes that have a harmonic relationship always complying with certain established aesthetic patterns. If the melodies and harmonies played form good combinations, the musician stores them in his memory, which allows him to increase his chances of creating another good combination in his next improvisation [30].
Figure 3 shows the analogy on improvisation, it describes the behavior and process of improvisation of jazz musicians, first, there are three instruments (saxophone, cello and guitar), each one plays a set of notes, in this case the saxophone plays C, D, E, F and G, the cello with G, E, D, A and C, while the guitar plays D, C, G, E and B. After that, the musician pays attention to each tone and begins to recognize those that sound good, where the perceived aesthetic notes for the saxophone is the note E, the cello with D and the guitar with G, which when combined form a new melody (E, D, G); Once the musician forms a chord, the moment of decision arrives, where, if the melody formed by these notes meets the aesthetic criteria and is heard well, the musician memorizes it and keeps it in his repertoire of melodies, otherwise, if it is heard badly, he discards it because it does not meet the aesthetic criteria. In such a way that this process of improvisation is followed until the desired number of chords is obtained.
Figure 3. Harmony Search Analogyq
Source: own elaboration based on the study [31]
Similarly, the lower part shows the relationship with the process of optimizing a function, where each decision variable takes random values within a certain range, forming a solution vector $f(3,2,5)$ or $f(E, D, G)$ that will be stored in a harmonic memory of each variable, which increases the chances of obtaining better solutions in the subsequent iteration [31].
In this context, the objective of this work is to apply a Harmony Search algorithm in the field of hospitality, to select sustainable indicators reported in the literature; in order to find the best harmony composed of the most optimal tones (indicators) when selecting indicators to evaluate the environmental impact. The following sections discuss the methodology used, followed by the results and conclusions.
The indicator selection process presented above in Figure 1 of Section I is considered, so that for the last step, which corresponds to the selection of the optimal indicators for the evaluation of the environmental impact of the hotel industry, we propose the application of the HS algorithm to a sample of 149 indicators extracted from the literature, which are distributed in six dimensions of sustainable development: Environmental, Social, Economic, Technological, Cultural and Political.
Figure 4. Flowchart: Harmony Search
Source: Own elaboration base on the study [29]
For the application of the HS algorithm, a four-step process was executed that recommends [32], the flow diagram used can be seen in Figure 4, where each element is explained, as well as the start and end points, which are represented with blue diamonds, the feedback points with pink diamonds and the steps with white rectangles.
Step 1. Initialize the HS memory (HM): define the number of randomly generated solutions to the optimization problems considered. That is, the population (HMS) which in this case corresponds to the indicators reported in literature.
Step 2. Improvisation of a new solution: a new candidate harmony is produced using the following parameters:
To then make a comparison of indicators with the best harmony.
Step 3. Update HM: the new solution from step 2 is evaluated. If the harmony is better than the worst harmony stored in HM, it replaces it. Otherwise, it is discarded. New optimal solution is added to the harmonic memory (list of indicators).
Step 4. Repeat steps 2 and 3 until the pre-set termination criterion is met, to obtain the optimal harmony, i.e., the final list of optimal indicators.
The following objective function is proposed to determine the best indicator:
$Z \max =\frac{x_1}{\max x_{1 j}}+\frac{x_2}{\max x_{2 j}}+\frac{x_3}{\max x_{3 j}}$ (1)
which seeks to maximize the decision variables $x_n$:
$x_1= Frequency\,\, of\,\, use$. From the list, evaluate the indicators that are most frequently repeated, i.e., those that have been used in the greatest number of studies.
$x_2= Level \,\,of \,\,application$. This can be international, national or regional.
$x_3= Year$. Priority is given to indicators used in recent years.
While the restrictions for each of the variables consist of:
$x_1<0$: since the indicator must have been used at least once.
$x_2>0, x_2<6$: since the indicator must have been used at least once.
$x_3 \geq 2016, x_3 \leq 2022$: those between 2016 and 2022 are considered to be the best.
Finally, with respect to the programming of the algorithm, Python language is used for the code, the pseudocode is discussed in the following section.
2.1 Pseudocode HS
The pseudocode is the guide for programming the code, it describes step by step what the program will do, this should be written as close as possible to a programming language, in this case the pseudocode was based on the study [33] with Python for programming the HS algorithm.
1: Initialize and determine the parameters of the HSA problem. Input data. HMS, HSCR, PAR.
2: Initialize the harmonic memory HM.
Construct harmonic memory vectors.
Recognize the worst harmonic in the HM.
3: Improvise a new harmony.
$x^1=\phi$ // new harmony
for $i=1, \ldots, N$ do // N variables of decision.
if (input of registed data $\leq H M C R)$ then
start
$x_i^{\prime} \,\, E\,\,\left\{x_i\,\,^1,\,\, x_i\,\,^2, \,\,\ldots,\,\, x_i\,\,^{H M S}\right\}$ // Indicator acceptance rate.
if $($ indicators input $\leq P A R)$ then
$x_i^{\prime}\,\,=\,\,v_{i,\,\, k}$ // Pitch adjustment
end if
end if
end for
4: Update harmonic memory (HM)
if $\left(f\left(x^{\prime}\right)<f\left(x^P\right)\right)$ then
Included in $x^{\prime}$ en HM
Exclude in $x^P$ en HM
5: Check the stop/fitness criterion
while (that the termination criterion is not specified)
Repeat (steps 3 y 4)
end
According to the indicator selection process seen above, after the literature review, the indicators currently in use by the hotel industry were identified. At this point, a study was carried out where 847 factors were identified, grouped in 149 indicators contained in 6 dimensions, Table 3 shows the list of them with the values assigned to $x_1, x_2, x_3$.
For the selection of indicators, the values of $x_1, x_2, x_3$ (see Table 3) were taken to be conditioned and added to the HS code; once the algorithm is ready with all the parameters declared and well defined, it is processed and this yields the result with the best harmony, which for this problem turns out to be:
$x_1=2, \quad x_2=4, \quad x_3=2021$
Regarding the search area of the algorithm, Figure 5 shows a heat plot, where all the possible improvisation tones are found, i.e., the 149 indicators that will be evaluated and the best ones that will be stored in the jazz musician's memory, in this case the red dot shows where the musician identifies the best harmony.
Figure 5. HS search space
Table 3. Sustainable indicators and values for $x_1, x_2, x_3$
|
# |
$x_1$ |
$x_2$ |
$x_3$ |
# |
$x_1$ |
$x_2$ |
$x_3$ |
|
1En |
2 |
4 |
2021 |
76Ec |
3 |
3 |
2021 |
|
2En |
8 |
4 |
2021 |
77Ec |
9 |
4 |
2021 |
|
3En |
32 |
4 |
2021 |
78Ec |
1 |
4 |
2020 |
|
4En |
23 |
4 |
2021 |
79Ec |
6 |
4 |
2020 |
|
5En |
4 |
4 |
2016 |
80Ec |
4 |
4 |
2018 |
|
6En |
29 |
4 |
2021 |
81Ec |
6 |
4 |
2020 |
|
7En |
12 |
4 |
2021 |
82Ec |
1 |
4 |
2018 |
|
8En |
6 |
4 |
2021 |
83Ec |
8 |
4 |
2018 |
|
9En |
10 |
4 |
2021 |
84Ec |
1 |
4 |
2016 |
|
10En |
102 |
4 |
2021 |
85Ec |
2 |
4 |
2016 |
|
11En |
2 |
4 |
2020 |
86Ec |
3 |
4 |
2021 |
|
12En |
13 |
4 |
2020 |
87Ec |
2 |
4 |
2019 |
|
13En |
16 |
4 |
2021 |
88Ec |
2 |
4 |
2019 |
|
14En |
3 |
2 |
2020 |
89Ec |
1 |
4 |
2019 |
|
15En |
1 |
5 |
2020 |
90Ec |
4 |
5 |
2020 |
|
16En |
1 |
5 |
2020 |
91Ec |
1 |
4 |
2019 |
|
17En |
3 |
5 |
2020 |
92T |
6 |
1 |
2020 |
|
18En |
6 |
4 |
2021 |
93T |
2 |
1 |
2020 |
|
19En |
2 |
3 |
2020 |
94T |
3 |
1 |
2020 |
|
20En |
3 |
4 |
2020 |
95T |
1 |
5 |
2020 |
|
21En |
1 |
4 |
2018 |
96T |
3 |
1 |
2020 |
|
22En |
1 |
4 |
2017 |
97T |
1 |
5 |
2020 |
|
23En |
1 |
4 |
2017 |
98T |
6 |
4 |
2020 |
|
24En |
1 |
4 |
2016 |
99T |
12 |
5 |
2020 |
|
25En |
6 |
4 |
2021 |
100T |
1 |
4 |
2017 |
|
26S |
8 |
4 |
2020 |
101T |
2 |
2 |
2021 |
|
27S |
7 |
4 |
2021 |
102T |
1 |
4 |
2018 |
|
28S |
13 |
4 |
2021 |
103T |
2 |
2 |
2021 |
|
29S |
7 |
4 |
2020 |
104T |
2 |
2 |
2021 |
|
30S |
12 |
4 |
2021 |
105T |
1 |
3 |
2021 |
|
31S |
21 |
4 |
2021 |
106T |
4 |
4 |
2021 |
|
32S |
5 |
4 |
2020 |
107T |
1 |
4 |
2016 |
|
33S |
3 |
3 |
2021 |
108C |
5 |
4 |
2020 |
|
34S |
1 |
5 |
2020 |
109C |
6 |
4 |
2021 |
|
35S |
20 |
4 |
2021 |
110C |
3 |
4 |
2021 |
|
36S |
6 |
1 |
2021 |
111C |
7 |
4 |
2021 |
|
37S |
10 |
4 |
2021 |
112C |
1 |
5 |
2020 |
|
38S |
2 |
4 |
2018 |
113C |
2 |
5 |
2020 |
|
39S |
1 |
4 |
2018 |
114C |
4 |
4 |
2021 |
|
40S |
7 |
4 |
2021 |
115C |
2 |
4 |
2021 |
|
41S |
6 |
4 |
2020 |
116C |
1 |
4 |
2016 |
|
42S |
1 |
5 |
2020 |
117C |
3 |
4 |
2017 |
|
43S |
3 |
5 |
2020 |
118C |
1 |
4 |
2016 |
|
44S |
8 |
4 |
2021 |
119C |
2 |
4 |
2018 |
|
45S |
1 |
4 |
2021 |
120P |
19 |
4 |
2021 |
|
46S |
2 |
2 |
2020 |
121P |
4 |
4 |
2020 |
|
47S |
2 |
4 |
2019 |
122P |
5 |
5 |
2021 |
|
48S |
3 |
4 |
2019 |
123P |
15 |
4 |
2021 |
|
49S |
1 |
4 |
2018 |
124P |
2 |
5 |
2020 |
|
50S |
2 |
1 |
2020 |
125P |
3 |
4 |
2020 |
|
51S |
2 |
4 |
2018 |
126P |
11 |
4 |
2021 |
|
52S |
1 |
4 |
2018 |
127P |
3 |
4 |
2020 |
|
53S |
2 |
4 |
2018 |
128P |
10 |
4 |
2021 |
|
54S |
5 |
1 |
2020 |
129P |
1 |
4 |
2018 |
|
55S |
1 |
4 |
2019 |
130P |
2 |
4 |
2020 |
|
56S |
2 |
4 |
2021 |
131P |
6 |
4 |
2020 |
|
57S |
3 |
4 |
2020 |
132P |
4 |
4 |
2018 |
|
58S |
1 |
4 |
2019 |
133P |
5 |
4 |
2021 |
|
59Ec |
5 |
4 |
2019 |
134P |
3 |
1 |
2020 |
|
60Ec |
15 |
4 |
2021 |
135P |
3 |
1 |
2021 |
|
61Ec |
19 |
4 |
2021 |
136P |
11 |
4 |
2021 |
|
62Ec |
2 |
4 |
2021 |
137P |
2 |
1 |
2021 |
|
63Ec |
15 |
4 |
2021 |
138P |
4 |
1 |
2020 |
|
64Ec |
8 |
4 |
2021 |
139P |
3 |
5 |
2020 |
|
65Ec |
3 |
4 |
2019 |
140P |
2 |
1 |
2020 |
|
66Ec |
4 |
2 |
2020 |
141P |
2 |
5 |
2020 |
|
67Ec |
12 |
4 |
2019 |
142P |
2 |
5 |
2020 |
|
68Ec |
1 |
4 |
2018 |
143P |
1 |
4 |
2020 |
|
69Ec |
7 |
4 |
2020 |
144P |
1 |
4 |
2016 |
|
70Ec |
5 |
4 |
2020 |
145P |
3 |
4 |
2020 |
|
71Ec |
5 |
4 |
2020 |
146P |
2 |
1 |
2020 |
|
72Ec |
2 |
1 |
2021 |
147P |
1 |
4 |
2016 |
|
73Ec |
6 |
4 |
2020 |
148P |
2 |
4 |
2018 |
|
74Ec |
3 |
5 |
2020 |
149P |
1 |
4 |
2018 |
|
75Ec |
6 |
1 |
2021 |
|
|||
The indicators corresponding to the best harmony $\left(x_ 1=2, x_ 2=4, x_ 3=2021)\right.$ are 1 En, 56 S and 115 C, these being the best since they have a regional application and are the most updated according to their date of application. However, in order to obtain a list instead of a small group of optimal indicators, it was decided to select the ten best harmonies given by HS.
Thus, the indicators that are positioned as the second best in harmony are the chord $x_1=8, x_2=4, x_3=2021$ where indicators 2 En, 44 S and 64 Ec are selected, followed by the chord $x_1=32, x_2=4, x_3=2021$ which corresponds to indicator 3 En, on the other hand the $x_1=23, x_2=4, x_3=2021$ contains the indicator 4 En, followed by the $x_1=102, x_2=4, x_3=2021$ with the indicator 10 En, up to this point we have 5 chords as best harmonies with a total of 9 indicators.
Table 4. Best harmony
|
Best Harmony |
Indicator |
Indicator Description |
|
2, 4, 2021 |
1A |
Efficient use of transport |
|
56S |
Employee commitment to the organization |
|
|
115C |
Cultural interactions |
|
|
8, 4, 2021 |
2A |
Reducing the use of toxic substances and chemicals, which are harmful to the environment |
|
44S |
Internal environmental program initiatives |
|
|
64E |
Green-marketing |
|
|
32, 4, 2021 |
3A |
Waste management: adoption of a system for measuring and reducing the quantity of solid waste |
|
23, 4, 2021 |
4A |
Recycling and reuse of resources |
|
102, 4, 2021 |
10A |
Sustainable management and efficient use of resources: water, energy and raw materials |
|
20, 4, 2021 |
35S |
Implementation of an environmental education program by hotel companies |
|
19, 4, 2021 |
61E |
Customer purchase decision factors for a sustainable hotel |
|
120P |
Commitment of top management to govern in accordance with sustainable management policies |
|
|
12, 4, 2021 |
7A |
Adoption of a system to counteract environmental threats, evaluate, control and minimize the effects of greenhouse gas emissions |
|
30S |
Sustainable education for staff, customers and local community |
|
|
7, 4, 2021 |
27S |
Participate in internal promotion and sustainable conservation activities |
|
40S |
Equal employment opportunity |
|
|
111C |
Preservation by hotel companies of archaeological, cultural, religious and sacred sites in the area where they are located |
|
|
10, 4, 2021 |
9A |
Hotel companies minimize pollution from noise, light, runoff and other environmental hazards, as well as health and welfare risks to the community |
|
37S |
Employee occupational health and safety |
|
|
128P |
The hotel integrates environmental measures into its policies, strategies and planning |
The search continues with another 5 chords and $x_1=20, x_2=4, x_3=2021$ is obtained as the sixth best harmony which contains the indicator number 35 S, followed by the chord $x_1=19, x_2=4, x_3=2021$ with the indicators 61 Ec and 120 P, the chord $x_1=12, x_2=4, x_3=2021$ with 7 En and 30 S, then, the chord $x_1=7, x_2=4, x_3=2021$ to which correspond 27 S, 40 S and 111 C, finally with the tenth best harmony the chord $x_1=10, x_2=4, x_3=2021$ where we have the indicators 9 En, 37 S and 128 P. It should be noted that the 9 selected harmonies share the same values of level of application and year of publication as the first best harmony.
Table 4 shows the best harmonies, as well as the indicators that compose each chord, together with the description of each of the selected indicators, these are ordered according to their position obtained with HS. A total of 20 indicators were selected, which are integrated into the dimensions of sustainable development, Environmental (En), Social (S) and Economic (Ec), as well as two other dimensions, which were identified in the Cultural (C) and Political (P) literature, as these are important in tourism and the hotel industry. However, the algorithm did not select any indicator of the Technological (T) dimension within these top 10 harmonies.
The final list of sustainable indicators is shown in Table 5, where it can be seen that most indicators correspond to the Environmental and Social dimensions, both with 7 indicators, followed by Economic, Cultural and Political with 2 indicators respectively. However, the position of each indicator does not indicate its level of importance, i.e., in this list, it is no longer considered which corresponds to the most optimal harmony, but simply proposes a list resulting from the HS algorithm.
On the other hand, Genetic Algorithm (GA) was used to compare the performance of HS with respect to the optimal result, i.e., with the best harmony ($x_1=2, x_2=4, x_3=2021$), so that the parameters and objective function of GA are the same as those used in HS.
Once the code was ready, it was processed and yielded as its best fitness, that is, best harmony or optimum result $x_1=102, x_2=4, x_3=2021$ which corresponds to indicator number 10, this in turn, is in the Environmental dimension and is described as: Sustainable management and efficient use of resources: water, energy and raw materials.
Table 5. List of proposed sustainable indicators
|
# |
Dimension |
Indicator |
|
1 |
Environment |
Efficient use of transport |
|
2 |
Reducing the use of toxic substances and chemicals, which are harmful to the environment |
|
|
3 |
Waste management: adoption of a system for measuring and reducing the quantity of solid waste |
|
|
4 |
Sustainable management and efficient use of resources: water, energy and raw materials |
|
|
5 |
Recycling and reuse of resources |
|
|
6 |
Hotel companies minimize pollution from noise, light, runoff and other environmental hazards, as well as health and welfare risks to the community |
|
|
7 |
Adoption of a system to counteract environmental threats, evaluate, control and minimize the effects of greenhouse gas emissions |
|
|
8 |
Social |
Employee commitment to the organization |
|
9 |
Internal environmental program initiatives |
|
|
10 |
Implementation of an environmental education program by hotel companies |
|
|
11 |
Sustainable education for staff, customers and local community |
|
|
12 |
Participate in internal promotion and sustainable conservation activities |
|
|
13 |
Employee occupational health and safety |
|
|
14 |
Equal employment opportunity |
|
|
15 |
Economy |
Green-marketing |
|
16 |
Customer purchase decision factors for a sustainable hotel |
|
|
17 |
Cultural |
Cultural interactions |
|
18 |
Preservation by hotel companies of the archaeological, cultural, religious heritage and of the sacred places in the environment where they are located |
|
|
19 |
Politics |
Commitment of senior management to govern in accordance with sustainable management policies |
|
20 |
The hotel integrates environmental measures in its policies, strategies and planning |
The use of Metaheuristics for problem solving in the field of tourism and the hotel industry is not widely in use, since it is mainly focused on route resolution, specifically in Traveling Salesman Problem (TSP) with GA algorithms. While the application of HS does not present use for this type of problems.
For its part, the process of selecting sustainable indicators for the hotel industry presents the use of tools such as questionnaires, for expert judgment and in-depth interviews, this being the most common method for this type of problems, in turn, it can be seen that the search and application of more complex methodologies is in full development, since, prior technical knowledge is required for its application, such is the case of multicriteria decision-making methods such as AHP or the method proposed in this work (HS) which is the programming for Metaheuristic algorithms.
The advantages of using this list lie in the fact that the indicators are up to date because recent literature was considered. Furthermore, since they are selected based on maximization criteria, they are not biased by the subjectivity that could arise at the time of selection based on the criteria of individuals, but rather, based on the restrictions and values given to the algorithm.
On the other hand, when comparing the optimal result given by HS and GA, despite the fact that both were programmed under the same criteria and data, there are two different results, being Efficient use of transportation with two publications, national level and from the year 2021 the best indicator for HS, while Sustainable management and efficient use of resources: water, energy and raw materials with 102 publications, national level and from the year 2021, the best option for GA.
From the above, it is concluded that GA achieved a better performance since the result it yielded has the indicator with the highest number of publications, in addition to the most recent year and its most frequent application level, i.e., the objective function is better fulfilled by maximizing the X variables, so that if the 10 best fitness are searched for, a list of indicators different from that provided by HS would be obtained, since the space and search analogy of both is different. However, the use of this list is viable due to the advantages it offers in comparison to the common methods, in addition, with this HS a precedent is set for the use of more complex methodologies in the selection of sustainable indicators, in turn, it is intended to promote the use of Metaheuristic algorithms within the hotel industry.
Thus, for future work, it is recommended to implement another type of Metaheuristics, perhaps returning to basic algorithms such as GA and PSO, which are highly consolidated and developed, allowing to go to libraries with codes and pseudocodes that serve as a basis for their conditioning and subsequent application.
This work is supported by the CONACYT (Consejo Nacional de Ciencia y Tecnología de México).
|
$x_n$ |
Relevant indicator |
|
Z |
Value of the addition of relevant indicators |
|
HSA |
Harmony search algorithm |
|
HM |
Harmony memory vectors |
|
HMS |
Harmony memory size |
|
HMCR |
Harmony search memory change rate |
|
PAR |
Pitch adjustment rate |
|
$x_i$ |
Memory vector define in a search space |
|
$x_i^{\prime}$ |
New accepted memory vector candidate |
|
$x^p$ |
New worst harmony within the vectors |
|
E |
Condition declaring that if the result is beyond the certain acceptance range of HM |
|
$v_{i, k}$ |
Pitch adjustment based on best vector |
|
$f\left(x^{\prime}\right)$ |
Function for evaluating acceptation in memory vector |
|
$f\left(x^p\right)$ |
Function for evaluating non acceptation in memory vector |
|
En |
Environment |
|
S |
Social |
|
C |
Cultural |
|
T |
Technological |
|
P |
Political |
|
Ec |
Economical |
|
# |
Number |
|
Greek symbols |
|
|
$\phi$ |
New harmony which fulfill fitness value |
[1] Zhang, D., Tu, J., Zhou, L., Yu, Z. (2020). Higher tourism specialization, better hotel industry efficiency? International Journal of Hospitality Management, 87: 102509. https://doi.org/10.1016/j.ijhm.2020.102509
[2] Torres, J.I., Anchundia, M.D.S. (2017). El alojamiento turístico en hogares: una alternativa de negocio para la dinamización de la economía en la parroquia de Canoa (destino de sol y playa) después del terremoto del 16 de abril. International journal of scientific management and tourism, 3(3): 259-271.
[3] London, S., Rojas, M.L., Candias, K.N. (2021). Turismo sostenible: un modelo de crecimiento con recursos naturales. Ensayos de Economía, 31(58): 158-177. https://doi.org/10.15446/ede.v31n58.88712
[4] ¿Por qué el Turismo? OMT. (2021). https://www.unwto.org/es/turismo.
[5] Transformar el turismo para la acción por el clima. (2020). Organización Mundial del Turismo. https://www.unwto.org/es/desarrollo-sostenible/accion-por-el-clima.
[6] Al-Aomar, R., Hussain, M. (2018). An assessment of adopting lean techniques in the construct of hotel supply chain. Tourism Management, 69: 553-565. https://doi.org/10.1016/j.tourman.2018.06.030
[7] Leyva, E.S., Parra, D.P. (2021). Environmental approach in the hotel industry: Riding the wave of change. Sustainable Futures, 3: 100050. https://doi.org/10.1016/j.sftr.2021.100050 R
[8] Asadi, S., Pourhashemi, S.O., Nilashi, M., Abdullah, R., Samad, S., Yadegaridehkordi, E., Aljojo, N., Razali, N.S. (2020). Investigating influence of green innovation on sustainability performance: A case on Malaysian hotel industry. Journal of cleaner production, 258: 120860. https://doi.org/10.1016/j.jclepro.2020.120860
[9] Sangeetha, R. (2020). Environmental sustainability practices for hotel in Chennai. Malaya Journal of Matematik, 8(2): 1740-1745. https://doi.org/10.26637/MJM0S20/0463
[10] Sin, K.Y. (2021). A mixed-method study on the perceptions of quality management and sustainability in Malaysian hotel industry. Studies of Applied Economics, 39(1). https://doi.org/10.25115/eea.v39i1.4282
[11] Desarrollo sostenible | OMT. (2021). https://www.unwto.org/es/desarrollo-sostenible.
[12] Oriade, A., Osinaike, A., Aduhene, K., Wang, Y. (2021). Sustainability awareness, management practices and organisational culture in hotels: Evidence from developing countries. International Journal of Hospitality Management, 92: 102699. https://doi.org/10.1016/j.ijhm.2020.102699
[13] Nam, H.V., Lo, A., Yeung, P., Hatter, R. (2020). Hotel ICON: Towards a role-model hotel pioneering sustainable solutions. Asia Pacific Journal of Tourism Research, 25(5): 572-582. https://doi.org/10.1080/10941665.2020.1746367
[14] Olya, H., Altinay, L., Farmaki, A., Kenebayeva, A., Gursoy, D. (2021). Hotels’ sustainability practices and guests’ familiarity, attitudes and behaviours. Journal of Sustainable Tourism, 29(7): 1063-1081. https://doi.org/10.1080/09669582.2020.1775622
[15] dos Santos, R.A., Méxas, M.P., Meirino, M.J., Sampaio, M.C., Costa, H.G. (2020). Criteria for assessing a sustainable hotel business. Journal of Cleaner Production, 262: 121347. https://doi.org/10.1016/j.jclepro.2020.121347
[16] Duric, Z., Potočnik Topler, J. (2021). The role of performance and environmental sustainability indicators in hotel competitiveness. Sustainability, 13(12): 6574. https://doi.org/10.3390/su13126574
[17] Alameeri, A., Ajmal, M.M., Hussain, M., Helo, P. (2018). Sustainable management practices in UAE hotels. International Journal of Culture, Tourism and Hospitality Research, 12(4): 440-466. https://doi.org/10.1108/IJCTHR-10-2017-0100
[18] Cunha, F.O., Oliveira, A.C. (2021). Comparison of nZEB indicators for hotel renovations under different European climatic conditions. International Journal of Low-Carbon Technologies, 16(1), 246-257. https://doi.org/10.1093/ijlct/ctaa059
[19] Arizmendi, L. (2014). Mundo Siglo XXI. 29: 100.
[20] Abdel-Basset, M., Abdel-Fatah, L., Sangaiah, A. K. (2018). Metaheuristic algorithms: A comprehensive review. Computational intelligence for multimedia big data on the cloud with engineering applications, 185-231. https://doi.org/10.1016/B978-0-12-813314-9.00010-4
[21] Resende, M.G., Ribeiro, C.C., Glover, F., Martí, R. (2010). Scatter search and path-relinking: Fundamentals, advances, and applications. Handbook of metaheuristics, 87-107. https://doi.org/10.1007/978-1-4419-1665-5_4
[22] Rajakumar, R., Dhavachelvan, P., Vengattaraman, T. (2016). A survey on nature inspired meta-heuristic algorithms with its domain specifications. In 2016 international conference on communication and electronics systems (ICCES), IEEE. pp. 1-6.
[23] Fortemps, P., Ost, C., Pirlot, M., Teghem, J., Tuyttens, D. (1996). Using metaheuristics for solving a production scheduling problem in a chemical firm. A case study. International Journal of Production Economics, 46: 13-26. https://doi.org/10.1016/0925-5273(95)00168-9
[24] Ruttanateerawichien, K., Pichpibul, T. Harmony Search Algorithm for Traveling Salesman Problem in Culture and Ego Tourism in Lampang Province, Thailand. 550.
[25] Baizal, Z.K.A., Lhaksmana, K.M., Rahmawati, A.A., Kirom, M., Mubarok, Z. (2019). Travel route scheduling based on user’s preferences using simulated annealing. International Journal of Electrical and Computer Engineering, 9(2): 1275. https://doi.org/10.11591/ijpeds.v9i2.pp1275-1287
[26] Tlili, T., Krichen, S. (2021). A simulated annealing-based recommender system for solving the tourist trip design problem. Expert Systems with Applications, 186: 115723. https://doi.org/10.1016/j.eswa.2021.115723
[27] Tenemaza, M., Lujan-Mora, S., De Antonio, A., Ramirez, J. (2020). Improving itinerary recommendations for tourists through metaheuristic algorithms: an optimization proposal. IEEE Access, 8: 79003-79023. https://doi.org/10.1109/ACCESS.2020.2990348
[28] Talebi, M., Nickabadi, A., Majnounian, B., Abdi, E., Safabakhsh, R., Izadyar, N., Laschi, A. (2022). Forest road planning to improve tourism accessibility: a comparison of different methods applied in a real case study. Geocarto International, 1-20. https://doi.org/10.1080/10106049.2022.2032389
[29] Ayachi, I., Kammarti, R., Ksouri, M., Borne, P., de Lille, L.E.C. (2013). Harmony search algorithm for the container storage problem. arXiv preprint arXiv:1306.0090. https://doi.org/10.48550/arXiv.1306.0090
[30] Yang, X.S. (2009). Harmony search as a metaheuristic algorithm. Music-inspired harmony search algorithm: theory and applications, 1-14. https://doi.org/10.1007/978-3-642-00185-7_1
[31] Molina García, J.A. (2019). Algoritmo de Búsqueda Armónica: Fundamentos y resolución de problemas de optimización con restricciones.
[32] Gao, X.Z., Govindasamy, V., Xu, H., Wang, X., Zenger, K. (2015). Harmony search method: theory and applications. Computational intelligence and neuroscience, 2015, 39-39. https://doi.org/10.1155/2015/258491
[33] Al-Betar, M.A., Khader, A.T. (2012). A harmony search algorithm for university course timetabling. Annals of Operations Research, 194: 3-31. https://doi.org/10.1007/s10479-010-0769-z
