Wayan Firdaus Mahmudy

Real Coded Genetic Algorithms for Solving Flexible Job-Shop Scheduling Problem - Part II: Optimization

This paper addresses optimization of the flexible job-shop problem (FJSP) by using real-coded genetic algorithms (RCGA) that use an array of real numbers as chromosome representation. The first part of the papers has detailed the modelling of the problems and showed how the novel chromosome representation can be decoded into solution. This second part discusses the effectiveness of each genetic operator and how to determine proper values of the RCGAs parameters. These parameters are used by the RCGA to solve several test bed problems. The experimental results show that by using only simple genetic operators and random initial population, the proposed RCGA can produce promising results comparable to those achieved by other best-known approaches in the literatures. These results demonstrate the robustness of the RCGA.

Optimization of part type selection and loading problem with alternative production plans in flexible manufacturing system using hybrid genetic algorithms - part 1: Modelling and representation

Two NP-hard and strongly related problems in flexible manufacturing system (FMS), part type selection problem and loading problem, are addressed in this paper. Various flexibilities including alternative production plans are considered. This effort will further exploit the flexibility of the FMS and improve system productivity. Real coded genetic algorithms (RCGA) which uses an array of real numbers as chromosome representation is proposed to solve these problems. Hybridizing the RCGA with variable neighborhood search (VNS) is performed to obtain better results. A strategy to maintain population diversity and avoid a premature convergence is also implemented. This first part of the paper addresses a modeling of the problems and discusses how the chromosome representation of the RCGA can handle various flexibilities of operations in the FMS. The second part of the paper will discuss the effectiveness of this hybrid approach to solve several test bed problems.

Optimization of part type selection and loading problem with alternative production plans in flexible manufacturing system using hybrid genetic algorithms - part 2: Genetic operators and results

This paper as the continuation of the first part addresses two NP-hard and strongly related problems in flexible manufacturing system (FMS), part type selection problem and loading problem. This first part of the paper detailed a modeling of the problems and discussed how the chromosome representation of the real coded genetic algorithms (RCGA) can handle various flexibilities of operations in the FMS. Hybridizing the RCGA with variable neighborhood search (VNS) and a strategy to maintain population diversity were implemented. This second part of the paper discusses the effectiveness of this hybrid approach to solve several test bed problems. This approach improves the FMS performance by considering two objectives, maximizing system throughput and maintaining the balance of the system (minimizing system unbalance). The resulted objective values are compared to the optimum values produced by branch-and-bound method. The experiments show that the proposed RCGA could produces promising results and the hybridization can improve the performance of the RCGA.

Rainfall prediction in Tengger region Indonesia using Tsukamoto fuzzy inference system

Rainfall Prediction in Indonesia is very important for agricultural sector. However, obtaining an accurate prediction is difficult as there are too many input parameters including the world climate change that affect the accuracy. An accurate prediction is required to arrange a good schedule for planting agricultural commodities. A good approach is required to obtain a good model as well as the accurate prediction. This paper proposes Tsukamoto fuzzy inference system (FIS) to solve the problem. An intensive effort is put in building fuzzy membership function based on rainfall data in Tengger region from ten years ago. A series of numerical experiments prove that the proposed approach produces better results comparable to those achieved by other approach. In Tutur region Tsukamoto fuzzy inference system obtain Root Mean Square Error (RMSE) of 8.64, it is better than GSTAR-SUR method that obtain RMSE of 10.89.

Indonesian-to-Javanese Machine Translation

Javanese is a multi-level language; it comprises four speech levels used to convey local politeness. However, the negative tendency is detected regarding the use of Javanese speech levels among teenagers. They prefer to use the Indonesian national language (bahasa Indonesia, BI) because of the Javanese speech level complexity. A combination of statistical and memory-based machine translation is designed by the authors to help Javanese youths in translating between both languages. The evaluation shows that translating speech levels of Javanese to Indonesian is more accurate than translating in the opposite direction, as revealed by the average accuracy (A) of 0.83 for Javanese-Indonesian translation and 0.68 for the other direction. Index Terms—Indonesian, Javanese speech levels, machine translation.

Real Coded Genetic Algorithms for Solving Flexible Job-Shop Scheduling Problem - Part I: Modelling

This paper and its companion (Part 2) deal with modelling and optimization of the flexible job-shop problem (FJSP). The FJSP is a generalised form of the classical job-shop problem (JSP) which allows an operation to be processed on several alternatives machines. To solve this NP-hard combinatorial problem, this paper proposes a customised Genetic Algorithm (GA) which uses an array of real numbers as chromosome representation so the proposed GA is called a real-coded GA (RCGA). The novel chromosome representation is designed to produces only feasible solutions which can be used to effectively explore the feasible search space. This first part of the papers focuses on the modelling of the problems and discusses how the novel chromosome representation can be decoded into a feasible solution. The second part will discuss genetic operators and the effectiveness of the RCGA to solve various test bed problems from literature.

Optimization of analytic hierarchy process using genetic algorithm for selecting tutoring agencies in Kampung Inggris Pare

The growing number of tutoring agencies in Kampung Inggris Pare results in the growing number of the students, whereas the applicants still review the agencies they are interested in manually. This prolongs the process of choosing the right agency. Unfortunately, it is possible that the agency they have chosen later turns out not suitable for them. Therefore, a support system for selecting the right tutoring agency is needed in Kampung Inggris Pare. With the developing system, the process of reviewing and choosing an agency will be easier due to the help of Analytical Hierarchy Process (AHP). One of the problems contained in AHP is the weight criteria that affect accuracy results obtained. GA can help overcome this problem by finding the optimal weight criteria in AHP to obtain better accuracy results. One of challenging task in GA implementation is designed a suitable chromosome representation. In this study, a new chromosome is formed based on pairwise comparisons in AHP. With AHP weighting optimization using genetic algorithms, correlations amounted 0.951. The value is greater than the previous level of correlation amounted 0.78. The use of GA to optimize the weight criteria in AHP has proven to provide a better accuracy result compared with the use of traditional AHP only.

Sugeno-Type Fuzzy Inference Optimization With Firefly and K-Means Clustering Algorithms For Rainfall Forecasting

Rainfall is very influential in our daily lives, ranging from agriculture, aviation, to flood-prone areas. The intensity of rainfall is used as an early detection for preventing harmful effects of rainfall. This research used Sugeno-Method Fuzzy Logic, in which the prediction is accomplished by mapping rules from the data obtained using the K-Means Clustering Algorithm as the classification to form the membership function and mapping rules and Firefly Alghorithm for optimization output. The test result from the 30 examined data found is 2.93 RMSE. This shows that the data support from K-Means Clustering and Firefly Algorithms of the fuzzy logic can predict precipitation accurately.

Performance Analysis of Data Mining Methods for Sexually Transmitted Disease Classification

Zigbee technology has been developed for short range wireless sensor networks and it follows IEEE 802.15.4 standard. For such sensors, several considerations should be taken including; low data rate and less design complexity in order to achieve efficient performance considering to the transceiver systems. This research focuses on implementing a digital transceiver system for Zigbee sensor based on IEEE 802.15.4 . The system is implemented using offset quadrature phase shift keying (OQPSK) modulation technique with half sine pulse-shaping method. Direct conversion scheme has been used in the design of Zigbee receiver in order to fulfill the requirements mentioned above. System performance is analyzed considering to BER when it encountered adaptive white Gaussian noise (AWGN), besides showing the effect of using direct sequence spread spectrum (DSSS) technique.The inverted pendulum is an under-actuated and nonlinear system, which is also unstable. It is a single-input double-output system, where only one output is directly actuated. This paper investigates a single intelligent control system using an adaptive neuro-fuzzy inference system (ANFIS) to stabilize the inverted pendulum system while tracking the desired position. The non-linear inverted pendulum system was modelled and built using MATLAB Simulink. An adaptive neuro-fuzzy logic controller was implemented and its performance was compared with a Sugeno-fuzzy inference system in both simulation and real experiment. The ANFIS controller could reach its desired new destination in 1.5 s and could stabilize the entire system in 2.2 s in the simulation, while in the experiment it took 1.7 s to reach stability. Results from the simulation and experiment showed that ANFIS had better performance compared to the Sugeno-fuzzy controller as it provided faster and smoother response and much less steady-state error.Association Rule mining plays an important role in the discovery of knowledge and information. Association Rule mining discovers huge number of rules for any dataset for different support and confidence values, among this many of them are redundant, especially in the case of multi-level datasets. Mining non-redundant Association Rules in multi-level dataset is a big concern in field of Data mining. In this paper, we present a definition for redundancy and a concise representation called Reliable Exact basis for representing non-redundant Association Rules from multi-level datasets. The given non-redundant Association Rules are loss less representation for any datasets.This paper presents a novel technique for numeral reading in Indian language speech synthesis systems using the rule-based Concatenative speech synthesis technique. The model uses a set of rules to determine the context of the numeral pronunciation and is being integrated with the waveform concatenation technique to produce speech out of the input text in Indian languages. To analyze the performance of the proposed technique, a set of numerals are considered in different context and a comparison of the proposed technique with an existing numeral reading method is also presented to show the effectiveness of the proposed technique in producing intelligible speech out of the entered text.This paper presents a data processing system based on an architecture comprised of multiple stacked layers of computational processes that transforms Raw Binary Pollution Data com- ing directly from Two EUMETSAT Metop satellites to our servers, into ready to interpret and visualise continuous data stream in near real time using techniques varying from task automation, data preprocessing and data analysis to machine learning using feed forward ar- tificial neural networks. The proposed system handles the acquisition, cleaning, processing, normalizing, and predicting of Pollution Data in our area of interest of Morocco.Advanced Communication Systems are wideband systems to support multiple applications such as audio, video and data so and so forth. These systems require high spectral efficiency and data rates. In addition, they should provide multipath fading and inter-symbol interference (ISI) free transmission. Multiple input multiple output orthogonal frequency division multiplexing (MIMO OFDM) meets these requirements Hence, MIMO-OFDM is the most preferable technique for long term evaluation advanced (LTE-A). The primary objective of this paper is to control bit error rate (BER) by proper channel coding, pilot carriers, adaptive filter channel estimation schemes and space time coding (STC). A combination of any of these schemes results in better BER performance over individual schemes. System performance is analyzed for various digital modulation schemes. In this paper,adaptive filter channel estimated MIMO OFDM system is proposed by integrating channel coding, adaptivefilter channel estimation, digital modulation and space time coding. From the simulation results, channel estimated 2×2 MIMO OFDM system shows superior performance over individual schemes.Electricity markets are different from other markets as electricity generation cannot be easily stored in large amounts and in order to avoid blackouts, the generation of electricity must be balanced with customer demand for it on a second-by-second basis. Customers tend to rely on electricity for day-to-day living and cannot replace it easily so when electricity prices increase, customer demand generally does not reduce significantly in the short-term. As electricity generation and customer demand must be matched perfectly second-by-second, and because generation cannot be stored to a large extent, cost bids from generators must be balanced with demand estimates in advance of real-time. This paper outlines a a forecasting algorithm built on artificial neural networks in order to predict short-term (72 hours ahead) wholesale prices on the Irish Single Electricity Market so that market participants can make more informed trading decisions. Research studies have demonstrated that an adaptive or self-adaptive approach to forecasting would appear more suited to the task of predicting energy demands in territory such as Ireland. Implementing an in-house self-adaptive model should yield good results in the dynamic uncertain Irish energy market. We have identified the features that such a model demands and outline it here.Received May 2, 2018 Revised Jul 9, 2018 Accepted Aug 2, 2018 Zigbee technology has been developed for short range wireless sensor networks and it follows IEEE 802.15.4 standard. For such sensors, several considerations should be taken including; low data rate and less design complexity in order to achieve efficient performance considering to the transceiver systems. This research focuses on implementing a digital transceiver system for Zigbee sensor based on IEEE 802.15.4. The system is implemented using offset quadrature phase shift keying (OQPSK) modulation technique with half sine pulse-shaping method. Direct conversion scheme has been used in the design of Zigbee receiver in order to fulfill the requirements mentioned above. System performance is analyzed considering to BER when it encountered adaptive white Gaussian noise (AWGN), besides showing the effect of using direct sequence spread spectrum (DSSS) technique. Keyword:This paper presents the use of Simelectronics Program for modeling and control of a two degrees-of freedom coupled mass-spring-damper mechanical system.The aims of this paper are to establish a mathematical model that represents the dynamic behaviour of a coupled mass-spring damper system and effectively control the mass position using both Simulink and Simelectronics.The mathematical model is derived based on the augmented Lagrange equation and to simulate the dynamic accurately a PD controller is implemented to compensate for the oscillation sustained by the system as a result of the complex conjugate pair poles near to the imaginary axis.The input force has been subjected to an obstacle to mimic actual challenges and to validate the mathematical model a Simulink and Simelectronics models were developed, consequently, the results of the models were compared. According to the result analysis, the controller tracked the position errors and stabilized the positions to zero within a settling time of 6.5sec and significantly reduced the overshoot by 99.5% and 99. 7% in Simulink and Simelectronics respectively. Furthermore, it is found that Simelectronics model proved to be capable having advantages of simplicity, less time-intense and requires no mathematical model over the Simulink approach.

Determining Growing Season of Potatoes Based on Rainfall Prediction Results Using System Dynamics

Potato has been and is a basic food for many countries. However, because of the uncertainty in rainfall patterns that have occurred since the existence of climate change make a significant impact on the outcome of potatoes production from year to year. Therefore, it needs the determination of new growing season period according to climate change. The determination of growing season is based on the result of rainfall prediction data using system dynamics ever done in previous studies to predictions of rainfall during the next five years starting in 2017-2021. Based on the modeling that has been done shows that early dry season ranges in mid-April to mid-May by the length of days in the growing season ranges from 162-192 days. The growing season prediction model has small error only about two dasarian. By the middle of the dry season, rainfall is expected to be very low which will make the potatoes into water deficit and will affect the harvest of potatoes plants which can be overcome with the irrigation system.