S. Quispe, July Diana Banda Tapia, Monika N. Lopez Paredes, D. Barrios-Aranibar, R. E. Patiño-Escarcina
{"title":"Automation of the brazil-nuts classification process using dynamic level set","authors":"S. Quispe, July Diana Banda Tapia, Monika N. Lopez Paredes, D. Barrios-Aranibar, R. E. Patiño-Escarcina","doi":"10.1109/HIS.2011.6122162","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122162","url":null,"abstract":"The usual method for classification processes of brazil-nut is manual and present some drawbacks like slowness, subjectivity, and inconsistency. In this paper, the main objective is to automate the classification process by analysing digital images with multiple brazil-nuts. These images have been segmented using the Level Set method without reinitialization with a new stopping criteria based on the area of objects, which have been proposed in order to reach better results. The goal is to optimize the manual classification process that has been done until now by generating higher productivity. The efficiency achieved by the proposal is 97.63% for whole brazil-nuts and 84.09% for broken brazil-nuts for image taken at a distance of 40 cm and 99.55% and 98.44% for whole and broken brazil-nuts respectively for image taken at a distance of 30 cm, properly classified.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121351684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Starting configuration of Cuckoo Search algorithm using Centroidal Voronoi Tessellations","authors":"Moaath Shatnawi, M. F. Nasrudin","doi":"10.1109/HIS.2011.6122077","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122077","url":null,"abstract":"Cuckoo Search (CS) is a meta-heuristic optimization algorithm that is inspired by breeding strategy of some cuckoo species that involves laying of eggs in the nests of other host birds. Like other population based optimization algorithms, the initial positions of the population, in the case of CS are host nests, will influence the performance of the searching. Based on this fact, we believe that the CS algorithm can further be improved by strategically selecting the starting positions of the nests instead of the standard random selection. This work suggests the use of positions generated from the Centroidal Voronoi Tessellations (CVT) as the starting points for the nests. A CVT is a Voronoi tessellation of a set such that the generators of the Voronoi sets are simultaneously their centers of mass. The CVT will initially present the problem space in equally distributed manner. The performance of CS algorithm initialized using CVT is compared with those generated from the standard CS algorithm on several benchmark test functions. The results show that the initialization of CS algorithm using the CVT improves its performance especially for benchmark functions with high-dimensional input spaces.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115363596","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
B. AjithaShenoyK., Somenath Biswas, Piyush P. Kurur
{"title":"Metropolis algorithm for solving shortest lattice vector problem (SVP)","authors":"B. AjithaShenoyK., Somenath Biswas, Piyush P. Kurur","doi":"10.1109/HIS.2011.6122146","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122146","url":null,"abstract":"In this paper we study the suitability of the Metropolis Algorithm and its generalization for solving the shortest lattice vector problem (SVP). SVP has numerous applications spanning from robotics to computational number theory, viz., polynomial factorization. At the same time, SVP is a notoriously hard problem. Not only it is NP-hard, there is not even any polynomial approximation known for the problem that runs in polynomial time. What one normally uses is the LLL algorithm which, although a polynomial time algorithm, may give solutions which are an exponential factor away from the optimum. In this paper, we have defined an appropriate search space for the problem which we use for implementation of the Metropolis algorithm. We have defined a suitable neighbourhood structure which makes the diameter of the space polynomially bounded, and we ensure that each search point has only polynomially many neighbours. We can use this search space formulation for some other classes of evolutionary algorithms, e.g., for genetic and go-with-the-winner algorithms. We have implemented the Metropolis algorithm and Hasting's generalization of Metropolis algorithm for the SVP. Our results are quite encouraging in all instances when compared with LLL algorithm.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131643043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A fast and efficient method for inferring structure and parameters of S-system models","authors":"Bin Yang, M. Jiang, Yuehui Chen","doi":"10.1109/HIS.2011.6122111","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122111","url":null,"abstract":"Most previous methods of inferring the S-system models have a significant limitation. That is, the structure of S-system models is fixed, and the only goal is to optimize its parameters and coefficients. Because the number of S-system parameters is proportional to the square of the number of variable, a large number of S-system parameters need to be simultaneously estimated, when the number of variable is very large. This limit may lead to the overwhelming computational complexities. To overcome this limitation we propose the restricted additive tree model for inferring the S-system models. In this approach, the evolution algorithm based on tree-structure and the particle swarm optimization (PSO) are employed to evolve the structure and the parameters of the S-system models, respectively. And the partitioning strategy is used to reduce the search space. We make three experiments and Simulation results using both synthetic data and real microarray measurements show that the structures and parameters of the S-system models can be identified correctly, which demonstrate the effectiveness of the proposed methods. The experiment results show that the structures and parameters of the S-system models can be identified correctly. And compared with other methods, the spent time is sharply reduced.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130652102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Training neural networks using Clonal Selection Algorithm and Particle Swarm Optimization: A comparisons for 3D object recognition","authors":"H. Akbar, N. Suryana, S. Sahib","doi":"10.1109/HIS.2011.6122190","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122190","url":null,"abstract":"Clonal Selection Algorithm (CLONALG) and Particle Swarm Optimization (PSO) have been applied for wide spectrum of computer vision problems. However, their applications to 3D object recognition receive only little attention. In this paper, CLONALG and PSO algorithms for recognition of 3D object are discussed. Instead of using any predefined model to extract the geometrical information, the 3D object is modeled based on its 2D image appearance. Firstly, the 2D image is segmented using Otsu thresholding method. Secondly, a set of moment features that are invariant under translation, changes in scale, and rotation is extracted. Thirdly, the CLONALG and PSO are used to initialize the neural network weights. Then, the neural network training is continued by Levenberg-Marquardt algorithm. The experimental results showed that the CLONALG-LM is better than PSO-LM and the other traditional training algorithms: Levenberg-Marquardt (LM), Scaled Conjugate Gradient (SCG), Gradient Descent (GD), Gradient Descent with Momentum (GDM), Gradient Descent with Adaptive Learning Rate (GDA), and Gradient descent with momentum and adaptive learning rate (GDMA).","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121599816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohammed Rokibul Alam Kotwal, M. A. Razzaque, Arif Hossen, M. N. Huda
{"title":"Hybridization of two stage Multilayer Neural Networks based Bangla ASR incorporating dynamic parameters","authors":"Mohammed Rokibul Alam Kotwal, M. A. Razzaque, Arif Hossen, M. N. Huda","doi":"10.1109/HIS.2011.6122099","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122099","url":null,"abstract":"This paper presents a hybridization of Multilayer Neural Network-based Bangla phoneme recognition method for Automatic Speech Recognition (ASR) incorporating dynamic parameters. The method consists of four stages: at first stage, a multilayer neural network (MLN) converts acoustic features, mel frequency cepstral coefficients (MFCCs), into phoneme probabilities. Phoneme probabilities from the first stage are inserted into second stage MLN for obtaining more accurate phoneme probabilities with reduced context where the third stage computes dynamic (velocity (A) and acceleration (AA)) parameters from the phoneme probabilities by using three point linear regressions (LRs). Finally, the phoneme probabilities, dynamic parameters, A and AA, and the input MFCCs, combined as hybrid features, are fed into a hidden Markov model (HMM) based classifier to obtain more accurate phoneme strings. From the experiments on Bangla speech corpus prepared by us, it is observed that the proposed method provides higher phoneme recognition performance than the existing method. Moreover, it requires a fewer mixture components in the HMMs.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114983257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Artificial immune algorithm based gravimetric fluid dispensing machine","authors":"D. Yap, J. Koh, S. Tiong, E. S. Sim, M. Yaw","doi":"10.1109/HIS.2011.6122140","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122140","url":null,"abstract":"One of the most prominent methods used in handling the end process for materials-mixing is by having a dispensing system. An effective dispensing method using Pulse Width Modulation (PWM) at the end of the dispensing sequence with Artificial Immune System (AIS) automatic dispensing parameter fine tuning capability is proposed by optimizing the components of Dispensing Time and Stopping Time Delay to obtain constant and accurate reading from the precision balance scale. Based on the new dispensing sequence, experimental tests had been carried out using different materials with varying viscosities. The results denote that the combination of both PWM and AIS techniques would minimize the error rate for overshooting while exhibiting better accuracy. These are important in order to overcome the limitations of the conventional volumetric dispensing and manual parameter tuning presently applied in the dispensing system used in the coatings industry.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129071803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimal skin detection for face localization using genetic algorithms","authors":"T. Babu, K. Mahalakshmi, S. Subrahmanya","doi":"10.1109/HIS.2011.6122186","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122186","url":null,"abstract":"Face Recognition remains a challenging task over two decades in spite of many advances. Face Localization and Detection forms an important step in Face Recognition systems, face tracking in video surveillance, gesture analytics, etc. Many algorithms are in use for face detection each having their relative advantages and disadvantages. The challenges of the task emanate from with image specific variations in color components, light saturation, background clutter etc. In the current work, we focus on application of Genetic Algorithms for finding optimal limits for color components as well as de-saturation that leads to highly accurate skin color detection.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128357264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Manifold synthesis: Predicting a manifold from one sample","authors":"L. Lo, Ju-Chin Chen","doi":"10.1109/HIS.2011.6122156","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122156","url":null,"abstract":"This study proposes a manifold synthesis approach based on the regression model to predict a manifold from one sample in order to cope with the single sample per person problem for face recognition. To reduce the dimensionality and preserve the data relation in the input image space, local preserving projection (LPP) is applied. Thus for each subject the facial images with pose angles can be represented by a manifold in the LPP space but the pose and the subject's appearance information are depicted in the same manifold. Hence, the manifold alignment approach is applied to extract the identity-invariant manifold that only the pose information is included in the joint latent space. Based on the regression model, two approaches are developed in the LPP and joint latent space to estimate the manifold when one frontal image is given. In the experimental results, FacePix database is conducted to evaluate the system performance.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117096675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chao-Chun Chen, Rain Chen, Ding-Chau Wang, Ting Dai
{"title":"GA-based dissimilarity visualization engine for design patent map systems","authors":"Chao-Chun Chen, Rain Chen, Ding-Chau Wang, Ting Dai","doi":"10.1109/HIS.2011.6122172","DOIUrl":"https://doi.org/10.1109/HIS.2011.6122172","url":null,"abstract":"Patent deployment has become a competition strength for companies. The intelligence property can keep the competition advantage of a company from opponents through the patent deployment which can be visualized by the patent map technique. The patent map is an important strategic tool for establishing design strategies. Our past efforts studied the display techniques in design patent map, and the comparisons of design patents in United States and Taiwan. Of types of patents, design patents occupy a unique patent field, since design patents are not as definitive as other patent fields. Therefore, the construction of design patent map is extremely difficult. Current commercial patent map systems visualize the patents according to non-populace attributes. However, such patent map systems are insufficient for providing more objective results from populace to support more powerful evidences in law courts. A key component to support the patent map system adopting the populace opinions is a fast dissimilarity visualization engine which can traslate the dissimilarity of patents from the populace opinions to a patent map. This paper presents a GA-based dissimilarity visualization engine for the above mentioned purpose. We design a set of crossover and multion operations based on the observations could generate patent maps with better quality. Our primary results reveal that the GA-based dissimilarity visualization engine indeed speeds up around 50% than the traditional method. Hence, such the engine is quite suitable for impatient users on the internet platform.","PeriodicalId":418397,"journal":{"name":"2011 11th International Conference on Hybrid Intelligent Systems (HIS)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116324719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}