Razamin Ramli

Shrimp Feed Formulation via Evolutionary Algorithm with Power Heuristics for Handling Constraints

Formulating feed for shrimps represents a challenge to farmers and industry partners. Most previous studies selected from only a small number of ingredients due to cost pressures, even though hundreds of potential ingredients could be used in the shrimp feed mix. Even with a limited number of ingredients, the best combination of the most appropriate ingredients is still difficult to obtain due to various constraint requirements, such as nutrition value and cost. This paper proposes a new operator which we call Power Heuristics, as part of an Evolutionary Algorithm (EA), which acts as a constraint handling technique for the shrimp feed or diet formulation. The operator is able to choose and discard certain ingredients by utilising a specialized search mechanism. The aim is to achieve the most appropriate combination of ingredients. Power Heuristics are embedded in the EA at the early stage of a semirandom initialization procedure. The resulting combination of ingredients, after fulfilling all the necessary constraints, shows that this operator is useful in discarding inappropriate ingredients when a crucial constraint is violated.

Developing a two-stage approach of super efficiency slack-based measure in the presence of non-discretionary factors and mixed integer-valued data envelopment analysis

Abstract An alternatve approach of super efficiency slack-based measure data envelopment analysis has been proposed to make the projection of an efficient decision making unit strongly-Pareto efficient. The approach however did not examine the simultaneous effect of non-discretionary factors and integer requirements on efficiency measures. To obtain more accurate efficiency measures, this paper proposes a two-stage approach of super efficiency slack-based measure in non-discretionary factors and mixed integer requirements. Both new factors and requirements were first integrated into the existing approach. The optimal solution of the proposed approach was then obtained by transforming its fractional form to a linear form. Thus, the scalar measures of the proposed approach can now deal directly with discretionary mixed integer input saving-output surplus and discretionary mixed integer input excess-output shortfall. The practicability of the proposed approach was tested using empirical data of Malaysian community colleges.

A hybrid integer data envelopment analysis based on an alternative approach of super slack based measure for measuring super efficiency and inefficiency of decision making units

Conventional data envelopment analysis (DEA) models assume that all values of input and output variables are non-integers. However, in many situations of real life DEA application, some of the input and/or output variables are to be integers.The rounding process of the non-integer values to their nearest integers can cause inaccurate efficiency and performance measurement. Thus, it is important to develop a non-radial hybrid integer DEA model. Moreover, the projection of decision making units (DMUs) in the existing super efficiency slack based measure hybrid integer model may not be strongly Pareto-efficient.Thus, our hybrid integer DEA model is developed based on an alternative super efficiency slack based measure DEA model for ranking efficient and inefficient DMUs.The developed model can project efficient DMUs resulted from super efficiency strongly Pareto-efficient by identifying input excesses and output shortfalls of non-integer and integer slack variables. It then discriminates inefficient DMUs whose efficiency scores resulted from super efficiency slack based measure model equal to one.An application to measure the efficiency of 41 academic departments at National Cheng Kung University in Taiwan (NCKU) is used to test the applicability of developed models. The results showed that 51.20% of the departments (DMUs) were super efficiency. Moreover, the result also showed that most of the inefficient departments were caused by their input excesses of expenses and teaching space, and output shortfalls associating with publications and grants.

Development of multi-item EOQ when the constraints of investment and storage capacity are active

The liability in inventory models decide of “how much or how many” of inventory items to order. The economic order quantity (EOQ) varies from one model to another, depending on assumptions and variables. This paper has developed the EOQ in deterministic inventory model of multi-item when the objective function is subjected to investment and capacity of shortage space constraints. The constraints are assumed to be active if the left hand side does not satisfy the right hand side condition. Thus, Lagrange method is used to find the new multi-item EOQ in each four models with each constraint to achieve the new formula of EOQ.

Investigating data envelopment analysis model with potential improvement for integer output values

The decrement of input proportions in DEA model is associated with its input reduction. This reduction is apparently good for economy since it could reduce unnecessary cost resources. However, in some situations the reduction of relevant inputs such as labour could create social problems. Such inputs should thus be maintained or increased. This paper develops an advanced radial DEA model dealing with mixed integer linear programming to improve integer output values through the combination of inputs. The model can deal with real input values and integer output values. This model is valuable for situations dealing with input combination to improve integer output values as faced by most organizations.

Measuring efficiency of rice growing farmers using data envelopment analysis

Self-sufficiency in rice production has been the main issue in Malaysia agriculture. It is significantly low and does not comply with the current average rice yield of 3.7 tons per ha per season. One of the best options and the most effective way to improve rice productivity is through more efficient utilization of paddy farmers. Getting farmers to grow rice is indeed a challenge when they could very well be making better money doing something else. This paper attempts to study the efficiency of rice growing farmers in Kubang Pasu using Data Envelopment Analysis model. For comparative analysis, three scenarios are considered in this study in measuring efficiency of rice growing farmers. The first scenario considers only fertilizer factor as an input while for the second, the land size is added as another factor. The third scenario considers more details about the inputs such as the type of fertilizer, NPK and mixed and also land tenureship and size. In all scenarios, the outputs are rice yield (tons) and ...

The use of arithmetic average method in identifying critical success criteria for Homestay Programmes

Malaysian Homestay is very unique. It is classified as Community Based Tourism (CBT). Homestay Programme which is a community events where a tourist stays together with a host family for a period of time and enjoying cultural exchange besides having new experiences. Homestay programme has booming the tourism industry since there is over 100 Homestay Programme currently being registered with the Ministry of Culture and Tourism Malaysia. However, only few Homestay Programme enjoying the benefits of success Homestay Programme. Hence, this article seeks to identify the critical success factors for a Homestay Programme in Malaysia. An Arithmetic Average method is utilized to further evaluate the identified success factors in a more meaningful way. The findings will help Homestay Programme function as a community development tool that manages tourism resources. Thus, help the community in improving local economy and creating job opportunities.

Power heuristics for handling constraint in evolutionary algorithms

The focus of our study is to propose a new constraint handling technique for real value encoding problem, specifically on the animal diet problem. This new proposed technique is a modification of mutation operator known as Power Mutation. This technique named as Power Heuristics is able to choose a better combination of feed ingredients based on certain performance. As the intention is to cater for strictness of nutrient and ingredients restriction, the Power Heuristics is introduced at the initial stage of the main methodology. The result shows that this technique is useful to remove inappropriate ingredients when an important constraint is violated.

Simulated annealing with probabilistic analysis for solving traveling salesman problems

Simulated Annealing (SA) is a widely used meta-heuristic that was inspired from the annealing process of recrystallization of metals. Therefore, the efficiency of SA is highly affected by the annealing schedule. As a result, in this paper, we presented an empirical work to provide a comparable annealing schedule to solve symmetric traveling salesman problems (TSP). Randomized complete block design is also used in this study. The results show that different parameters do affect the efficiency of SA and thus, we propose the best found annealing schedule based on the Post Hoc test. SA was tested on seven selected benchmarked problems of symmetric TSP with the proposed annealing schedule. The performance of SA was evaluated empirically alongside with benchmark solutions and simple analysis to validate the quality of solutions. Computational results show that the proposed annealing schedule provides a good quality of solution.

Modified reactive tabu search for the symmetric traveling salesman problems

Reactive tabu search (RTS) is an improved method of tabu search (TS) and it dynamically adjusts tabu list size based on how the search is performed. RTS can avoid disadvantage of TS which is in the parameter tuning in tabu list size. In this paper, we proposed a modified RTS approach for solving symmetric traveling salesman problems (TSP). The tabu list size of the proposed algorithm depends on the number of iterations when the solutions do not override the aspiration level to achieve a good balance between diversification and intensification. The proposed algorithm was tested on seven chosen benchmarked problems of symmetric TSP. The performance of the proposed algorithm is compared with that of the TS by using empirical testing, benchmark solution and simple probabilistic analysis in order to validate the quality of solution. The computational results and comparisons show that the proposed algorithm provides a better quality solution than that of the TS.