Pub Date : 2019-01-07DOI: 10.14569/IJARAI.2014.030703
C. Utomo, Aan Kardiana, R. Yuliwulandari
Breast cancer is the second cause of dead among women. Early detection followed by appropriate cancer treatment can reduce the deadly risk. Medical professionals can make mistakes while identifying a disease. The help of technology such as data mining and machine learning can substantially improve the diagnosis accuracy. Artificial Neural Networks (ANN) has been widely used in intelligent breast cancer diagnosis. However, the standard Gradient-Based Back Propagation Artificial Neural Networks (BP ANN) has some limitations. There are parameters to be set in the beginning, long time for training process, and possibility to be trapped in local minima. In this research, we implemented ANN with extreme learning techniques for diagnosing breast cancer based on Breast Cancer Wisconsin Dataset. Results showed that Extreme Learning Machine Neural Networks (ELM ANN) has better generalization classifier model than BP ANN. The development of this technique is promising as intelligent component in medical decision support systems.
{"title":"Breast Cancer Diagnosis using Artificial Neural Networks with Extreme Learning Techniques","authors":"C. Utomo, Aan Kardiana, R. Yuliwulandari","doi":"10.14569/IJARAI.2014.030703","DOIUrl":"https://doi.org/10.14569/IJARAI.2014.030703","url":null,"abstract":"Breast cancer is the second cause of dead among women. Early detection followed by appropriate cancer treatment can reduce the deadly risk. Medical professionals can make mistakes while identifying a disease. The help of technology such as data mining and machine learning can substantially improve the diagnosis accuracy. Artificial Neural Networks (ANN) has been widely used in intelligent breast cancer diagnosis. However, the standard Gradient-Based Back Propagation Artificial Neural Networks (BP ANN) has some limitations. There are parameters to be set in the beginning, long time for training process, and possibility to be trapped in local minima. In this research, we implemented ANN with extreme learning techniques for diagnosing breast cancer based on Breast Cancer Wisconsin Dataset. Results showed that Extreme Learning Machine Neural Networks (ELM ANN) has better generalization classifier model than BP ANN. The development of this technique is promising as intelligent component in medical decision support systems.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116647327","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}
Pub Date : 2016-10-01DOI: 10.14569/IJARAI.2016.050902
K. Arai
Pursuit Reinforcement guided Competitive Learning: PRCL based on relatively fast online clustering that allows grouping the data in concern into several clusters when the number of data and distribution of data are varied of reinforcement guided competitive learning is proposed. One of applications of the proposed method is image portion retrievals from the relatively large scale of the images such as Earth observation satellite images. It is found that the proposed method shows relatively fast on the retrievals in comparison to the other existing conventional online clustering such as Vector Quatization: VQ. Moreover, the proposed method shows much faster than the others for the multi-stage retrievals of image portion as well as scale estimation. A new approach for online clustering based on reinforcement learning, called Pursuit Reinforcement Guided Competitive Learning. PRCL which is derived from pursuit method in reinforcement learning that maintain both action- value and action preferences, with the preferences continually pursuing the action that is greedy according to the current action-value estimates together with learning automata is proposed. PRCL can be used as online clustering method. One of the applications is, then introduced for evacuation simulation. The following section describes the proposed PRCL with learning automata together with the existing conventional online clustering methods of RGCL, SRGCL and VQ. Then preliminary experiments are described followed by its application of image retrievals. After all, conclusion is described with some discussions.
{"title":"Pursuit Reinforcement Competitive Learning: PRCL based Online Clustering with Tracking Algorithm and its Application to Image Retrieval","authors":"K. Arai","doi":"10.14569/IJARAI.2016.050902","DOIUrl":"https://doi.org/10.14569/IJARAI.2016.050902","url":null,"abstract":"Pursuit Reinforcement guided Competitive Learning: PRCL based on relatively fast online clustering that allows grouping the data in concern into several clusters when the number of data and distribution of data are varied of reinforcement guided competitive learning is proposed. One of applications of the proposed method is image portion retrievals from the relatively large scale of the images such as Earth observation satellite images. It is found that the proposed method shows relatively fast on the retrievals in comparison to the other existing conventional online clustering such as Vector Quatization: VQ. Moreover, the proposed method shows much faster than the others for the multi-stage retrievals of image portion as well as scale estimation. A new approach for online clustering based on reinforcement learning, called Pursuit Reinforcement Guided Competitive Learning. PRCL which is derived from pursuit method in reinforcement learning that maintain both action- value and action preferences, with the preferences continually pursuing the action that is greedy according to the current action-value estimates together with learning automata is proposed. PRCL can be used as online clustering method. One of the applications is, then introduced for evacuation simulation. The following section describes the proposed PRCL with learning automata together with the existing conventional online clustering methods of RGCL, SRGCL and VQ. Then preliminary experiments are described followed by its application of image retrievals. After all, conclusion is described with some discussions.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129734213","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}
Pub Date : 2016-03-01DOI: 10.14569/IJARAI.2016.050301
K. Arai, M. Nakashima
Remote sensing portal site for practical uses which is dedicated to local governments is created. Key components of the site are (1) links to data providers, (2) links to the data analysis software tools, (3) examples of actual uses of the satellite remote sensing data in particular for local governments. Users’ demands for remote sensing satellite data are investigated for the local governments situated in Kyushu, Japan. According to the users’ demands, the remote sensing portal site is created with the aforementioned key components. For the examples of remote sensing data applications, creation of land use maps, disaster mitigations, forest maps, vegetation index map for evaluation of vitality of agricultural fields and forests, etc. are taken into account. In particular for forest map creation, it is created with free open source software: FOSS of classifiers together with open data API derived training samples applied to Landsat-8 OLI data. On the other hand, volcanic eruption is featured for disaster relief with 3D representation by using open data derived DEM data. In accordance with the users’ evaluation reports, it is found that the proposed portal site is useful.
{"title":"Creation of a Remote Sensing Portal for Practical Use Dedicated to Local Goverments in Kyushu, Japan","authors":"K. Arai, M. Nakashima","doi":"10.14569/IJARAI.2016.050301","DOIUrl":"https://doi.org/10.14569/IJARAI.2016.050301","url":null,"abstract":"Remote sensing portal site for practical uses which is dedicated to local governments is created. Key components of the site are (1) links to data providers, (2) links to the data analysis software tools, (3) examples of actual uses of the satellite remote sensing data in particular for local governments. Users’ demands for remote sensing satellite data are investigated for the local governments situated in Kyushu, Japan. According to the users’ demands, the remote sensing portal site is created with the aforementioned key components. For the examples of remote sensing data applications, creation of land use maps, disaster mitigations, forest maps, vegetation index map for evaluation of vitality of agricultural fields and forests, etc. are taken into account. In particular for forest map creation, it is created with free open source software: FOSS of classifiers together with open data API derived training samples applied to Landsat-8 OLI data. On the other hand, volcanic eruption is featured for disaster relief with 3D representation by using open data derived DEM data. In accordance with the users’ evaluation reports, it is found that the proposed portal site is useful.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115030553","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}
Pub Date : 2015-09-10DOI: 10.14569/IJARAI.2015.040906
Beaudelaire Saha Tchinda, D. Tchiotsop, R. Tchinda, D. Wolf, M. Noubom
Parasites live in a host and get its food from or at the expensive of that host. Cysts represent a form of resistance and spread of parasites. The manual diagnosis of microscopic stools images is time-consuming and depends on the human expert. In this paper, we propose an automatic recognition system that can be used to identify various intestinal parasite cysts from their microscopic digital images. We employ image pixel feature to train the probabilistic neural networks (PNN). Probabilistic neural networks are suitable for classification problems. The main novelty is the use of features vectors extracted directly from the image pixel. For this goal, microscopic images are previously segmented to separate the parasite image from the background. The extracted parasite is then resized to 12x12 image features vector. For dimensionality reduction, the principal component analysis basis projection has been used. 12x12 extracted features were orthogonalized into two principal components variables that consist the input vector of the PNN. The PNN is trained using 540 microscopic images of the parasite. The proposed approach was tested successfully on 540 samples of protozoan cysts obtained from 9 kinds of intestinal parasites. - See more at: http://thesai.org/Publications/ViewPaper?Volume=4&Issue=9&Code=ijarai&SerialNo=6#sthash.S5fRMF9g.dpuf
{"title":"Automatic Recognition of Human Parasite Cysts on Microscopic Stools Images using Principal Component Analysis and Probabilistic Neural Network","authors":"Beaudelaire Saha Tchinda, D. Tchiotsop, R. Tchinda, D. Wolf, M. Noubom","doi":"10.14569/IJARAI.2015.040906","DOIUrl":"https://doi.org/10.14569/IJARAI.2015.040906","url":null,"abstract":"Parasites live in a host and get its food from or at the expensive of that host. Cysts represent a form of resistance and spread of parasites. The manual diagnosis of microscopic stools images is time-consuming and depends on the human expert. In this paper, we propose an automatic recognition system that can be used to identify various intestinal parasite cysts from their microscopic digital images. We employ image pixel feature to train the probabilistic neural networks (PNN). Probabilistic neural networks are suitable for classification problems. The main novelty is the use of features vectors extracted directly from the image pixel. For this goal, microscopic images are previously segmented to separate the parasite image from the background. The extracted parasite is then resized to 12x12 image features vector. For dimensionality reduction, the principal component analysis basis projection has been used. 12x12 extracted features were orthogonalized into two principal components variables that consist the input vector of the PNN. The PNN is trained using 540 microscopic images of the parasite. The proposed approach was tested successfully on 540 samples of protozoan cysts obtained from 9 kinds of intestinal parasites. - See more at: http://thesai.org/Publications/ViewPaper?Volume=4&Issue=9&Code=ijarai&SerialNo=6#sthash.S5fRMF9g.dpuf","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":" 22","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132012006","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}
Pub Date : 2014-12-01DOI: 10.14569/IJARAI.2014.031206
S. Placzek
An Artificial Neural Network with cross-connection is one of the most popular network structures. The structure contains: an input layer, at least one hidden layer and an output layer. Analysing and describing an ANN structure, one usually finds that the first parameter is the number of ANN’s layers. A hierarchical structure is a default and accepted way of describing the network. Using this assumption, the network structure can be described from a different point of view. A set of concepts and models can be used to describe the complexity of ANN’s structure in addition to using a two-level learning algorithm. Implementing the hierarchical structure to the learning algorithm, an ANN structure is divided into sub-networks. Every sub-network is responsible for finding the optimal value of its weight coefficients using a local target function to minimise the learning error. The second coordination level of the learning algorithm is responsible for coordinating the local solutions and finding the minimum of the global target function. In the article a special emphasis is placed on the coordinator’s role in the learning algorithm and its target function. In each iteration the coordinator has to send coordination parameters into the first level of sub-networks. Using the input X and the teaching ?? vectors, the local procedures are working and finding their weight coefficients. At the same step the feedback information is calculated and sent to the coordinator. The process is being repeated until the minimum of local target functions is achieved. As an example, a two-level learning algorithm is used to implement an ANN in the underwriting process for classifying the category of health in a life insurance company.
{"title":"A two-level on-line learning algorithm of Artificial Neural Network with forward connections","authors":"S. Placzek","doi":"10.14569/IJARAI.2014.031206","DOIUrl":"https://doi.org/10.14569/IJARAI.2014.031206","url":null,"abstract":"An Artificial Neural Network with cross-connection is one of the most popular network structures. The structure contains: an input layer, at least one hidden layer and an output layer. Analysing and describing an ANN structure, one usually finds that the first parameter is the number of ANN’s layers. A hierarchical structure is a default and accepted way of describing the network. Using this assumption, the network structure can be described from a different point of view. A set of concepts and models can be used to describe the complexity of ANN’s structure in addition to using a two-level learning algorithm. Implementing the hierarchical structure to the learning algorithm, an ANN structure is divided into sub-networks. Every sub-network is responsible for finding the optimal value of its weight coefficients using a local target function to minimise the learning error. The second coordination level of the learning algorithm is responsible for coordinating the local solutions and finding the minimum of the global target function. In the article a special emphasis is placed on the coordinator’s role in the learning algorithm and its target function. In each iteration the coordinator has to send coordination parameters into the first level of sub-networks. Using the input X and the teaching ?? vectors, the local procedures are working and finding their weight coefficients. At the same step the feedback information is calculated and sent to the coordinator. The process is being repeated until the minimum of local target functions is achieved. As an example, a two-level learning algorithm is used to implement an ANN in the underwriting process for classifying the category of health in a life insurance company.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130162094","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}
Pub Date : 2014-10-01DOI: 10.14569/IJARAI.2014.031003
P. Barraclough, G. Sexton, M. A. Hossain, N. Aslam
Phishing attacks has been growing rapidly in the past few years. As a result, a number of approaches have been proposed to address the problem. Despite various approaches proposed such as feature-based and blacklist-based via machine learning techniques, there is still a lack of accuracy and real-time solution. Most approaches applying machine learning techniques requires that parameters are tuned to solve a problem, but parameters are difficult to tune to a desirable output. This study presents a parameter tuning framework, using adaptive Neuron-fuzzy inference system with comprehensive data to maximize systems performance. Extensive experiment was conducted. During ten-fold cross-validation, the data is split into training and testing pairs and parameters are set according to desirable output and have achieved 98.74% accuracy. Our results demonstrated higher performance compared to other results in the field. This paper contributes new comprehensive data, novel parameter tuning method and applied a new algorithm in a new field. The implication is that adaptive neuron-fuzzy system with effective data and proper parameter tuning can enhance system performance. The outcome will provide a new knowledge in the field.
{"title":"Parameter optimization for intelligent phishing detection using Adaptive Neuro-Fuzzy","authors":"P. Barraclough, G. Sexton, M. A. Hossain, N. Aslam","doi":"10.14569/IJARAI.2014.031003","DOIUrl":"https://doi.org/10.14569/IJARAI.2014.031003","url":null,"abstract":"Phishing attacks has been growing rapidly in the past few years. As a result, a number of approaches have been proposed to address the problem. Despite various approaches proposed such as feature-based and blacklist-based via machine learning techniques, there is still a lack of accuracy and real-time solution. Most approaches applying machine learning techniques requires that parameters are tuned to solve a problem, but parameters are difficult to tune to a desirable output. This study presents a parameter tuning framework, using adaptive Neuron-fuzzy inference system with comprehensive data to maximize systems performance. Extensive experiment was conducted. During ten-fold cross-validation, the data is split into training and testing pairs and parameters are set according to desirable output and have achieved 98.74% accuracy. Our results demonstrated higher performance compared to other results in the field. This paper contributes new comprehensive data, novel parameter tuning method and applied a new algorithm in a new field. The implication is that adaptive neuron-fuzzy system with effective data and proper parameter tuning can enhance system performance. The outcome will provide a new knowledge in the field.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122244061","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}
Pub Date : 2013-02-01DOI: 10.14569/IJARAI.2013.020206
R. Sathya, Jyoti Nivas, Annamma Abraham.
This paper presents a comparative account of unsupervised and supervised learning models and their pattern classification evaluations as applied to the higher education scenario. Classification plays a vital role in machine based learning algorithms and in the present study, we found that, though the error back-propagation learning algorithm as provided by supervised learning model is very efficient for a number of non-linear real-time problems, KSOM of unsupervised learning model, offers efficient solution and classification in the present study.
{"title":"Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification","authors":"R. Sathya, Jyoti Nivas, Annamma Abraham.","doi":"10.14569/IJARAI.2013.020206","DOIUrl":"https://doi.org/10.14569/IJARAI.2013.020206","url":null,"abstract":"This paper presents a comparative account of unsupervised and supervised learning models and their pattern classification evaluations as applied to the higher education scenario. Classification plays a vital role in machine based learning algorithms and in the present study, we found that, though the error back-propagation learning algorithm as provided by supervised learning model is very efficient for a number of non-linear real-time problems, KSOM of unsupervised learning model, offers efficient solution and classification in the present study.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127462521","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}
Pub Date : 2013-01-18DOI: 10.14569/IJARAI.2013.020309
K. Arai, I. N. Abdullah, H. Okumura
Human has a duty to preserve the nature. One of the examples is preserving the ornamental plant. Huge economic value of plant trading, escalating esthetical value of one space and medicine efficacy that contained in a plant are some positive values from this plant. However, only few people know about its medicine efficacy. Considering the easiness to obtain and the medicine efficacy, this plant should be an initial treatment of a simple disease or option towards chemical based medicines. In order to let people get acquaint, we need a system that can proper identify this plant. Therefore, we propose to build a system based on Redundant Discrete Wavelet Transformation (RDWT) through its leaf. Since its character is translation invariant that able to produce some robust features to identify ornamental plant. This system was successfully resulting 95.83% of correct classification rate.
{"title":"Identification of Ornamental Plant Functioned as Medicinal Plant based on Redundant Discrete Wavelet Transformation","authors":"K. Arai, I. N. Abdullah, H. Okumura","doi":"10.14569/IJARAI.2013.020309","DOIUrl":"https://doi.org/10.14569/IJARAI.2013.020309","url":null,"abstract":"Human has a duty to preserve the nature. One of the examples is preserving the ornamental plant. Huge economic value of plant trading, escalating esthetical value of one space and medicine efficacy that contained in a plant are some positive values from this plant. However, only few people know about its medicine efficacy. Considering the easiness to obtain and the medicine efficacy, this plant should be an initial treatment of a simple disease or option towards chemical based medicines. In order to let people get acquaint, we need a system that can proper identify this plant. Therefore, we propose to build a system based on Redundant Discrete Wavelet Transformation (RDWT) through its leaf. Since its character is translation invariant that able to produce some robust features to identify ornamental plant. This system was successfully resulting 95.83% of correct classification rate.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128166324","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}
The Brain Computer Interface is a major breakthrough for the technical industry, medical world, military and the society on a whole. It is concerned with the control of devices around us such as computing gears & even automobiles in the near future without really the physical intervention of the user. It helps bridge the communication gap between the society and the disabled. This mainly lays its focus on people suffering from brainstem stroke, going through a spinal cord injury or even blindness. BCI helps such patients to retain or restore communication with the outside world through intelligent signals from the brain due to the high risk of paralysis under such circumstances. This is achieved by a signal acquisition technique and converting these signals available from the sensors placed on the scalp into real-time computer commands that can be visually operated and understood. It has nothing to do with the natural neural transmission of brain signals but extracts them with the help of sensors to be processed and direct the outputs to an external device. This may also prove to be a major military gadget where troops may communicate their thoughts in highly stressed situations without breaking the hush. But, as every technology have some merits and demerits, so does BCI.
{"title":"Brain Computer Interface Boulevard of Smarter Thoughts","authors":"Sumit Ghulyani, Yash Pratap, Sumit Bisht, Ravideep Singh","doi":"10.14569/IJARAI.2012.010705","DOIUrl":"https://doi.org/10.14569/IJARAI.2012.010705","url":null,"abstract":"The Brain Computer Interface is a major breakthrough for the technical industry, medical world, military and the society on a whole. It is concerned with the control of devices around us such as computing gears & even automobiles in the near future without really the physical intervention of the user. It helps bridge the communication gap between the society and the disabled. This mainly lays its focus on people suffering from brainstem stroke, going through a spinal cord injury or even blindness. BCI helps such patients to retain or restore communication with the outside world through intelligent signals from the brain due to the high risk of paralysis under such circumstances. This is achieved by a signal acquisition technique and converting these signals available from the sensors placed on the scalp into real-time computer commands that can be visually operated and understood. It has nothing to do with the natural neural transmission of brain signals but extracts them with the help of sensors to be processed and direct the outputs to an external device. \u0000This may also prove to be a major military gadget where troops may communicate their thoughts in highly stressed situations without breaking the hush. But, as every technology have some merits and demerits, so does BCI.","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121218214","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}
Pub Date : 2012-04-01DOI: 10.14569/IJARAI.2012.010108
Zhi-Jie Chen, Chiuh-Cheng Chyu
In practice, a project usually involves cash in- and out- flows associated with each activity. This paper aims to minimize the payment failure risk during the project execution for the resource-constrained project scheduling problem (RCPSP). In such models, the money-time value, which is the product of the net cash in-flow and the time length from the completion time of each activity to the project deadline, provides a financial evaluation of project cash availability. The cash availability of a project schedule is defined as the sum of these money-time values associated with all activities, which is mathematically equivalent to the minimization objective of total weighted completion time. This paper presents four memetic algorithms (MAs) which differ in the construction of initial population and restart strategy, and a double variable neighborhood search algorithm for solving the RCPSP problem. An experiment is conducted to evaluate the performance of these algorithms based on the same number of solutions calculated using ProGen generated benchmark instances. The results indicate that the MAs with regret biased sampling rule to generate initial and restart populations outperforms the other algorithms in terms of solution quality. payment failure risk during the project execution. To achieve this goal, the money-time value, which is the product of the cash in-flow and the length from the time the cash received to the project makespan, can provide a financial evaluation of project cash availability. The cash availability of a project schedule is defined as the total money-time values associated with all activities. This financial metric does not consider discount rate, and it will provide a conservative estimate of cash in-flows during the project execution, since cash on hand will grow in value over time. In the proposed model, the cash in-flows are assumed to occur at the completion time of each activity, and the cash amounts can be used during the rest of project execution time. Hereafter, we shall refer to this model as the project cash availability maximization problem (PCAMP) for the resource constrained project scheduling problem (RCPSP). The PCAMP is mathematically equivalent to the RCPSP with the objective of minimizing total weighted completion time (also known as total weighted flow time). This problem is strongly NP-hard since its sub-problem, single machine scheduling with total flow time minimization objective subject
{"title":"Solving the Resource Constrained Project Scheduling Problem to Minimize the Financial Failure Risk","authors":"Zhi-Jie Chen, Chiuh-Cheng Chyu","doi":"10.14569/IJARAI.2012.010108","DOIUrl":"https://doi.org/10.14569/IJARAI.2012.010108","url":null,"abstract":"In practice, a project usually involves cash in- and out- flows associated with each activity. This paper aims to minimize the payment failure risk during the project execution for the resource-constrained project scheduling problem (RCPSP). In such models, the money-time value, which is the product of the net cash in-flow and the time length from the completion time of each activity to the project deadline, provides a financial evaluation of project cash availability. The cash availability of a project schedule is defined as the sum of these money-time values associated with all activities, which is mathematically equivalent to the minimization objective of total weighted completion time. This paper presents four memetic algorithms (MAs) which differ in the construction of initial population and restart strategy, and a double variable neighborhood search algorithm for solving the RCPSP problem. An experiment is conducted to evaluate the performance of these algorithms based on the same number of solutions calculated using ProGen generated benchmark instances. The results indicate that the MAs with regret biased sampling rule to generate initial and restart populations outperforms the other algorithms in terms of solution quality. payment failure risk during the project execution. To achieve this goal, the money-time value, which is the product of the cash in-flow and the length from the time the cash received to the project makespan, can provide a financial evaluation of project cash availability. The cash availability of a project schedule is defined as the total money-time values associated with all activities. This financial metric does not consider discount rate, and it will provide a conservative estimate of cash in-flows during the project execution, since cash on hand will grow in value over time. In the proposed model, the cash in-flows are assumed to occur at the completion time of each activity, and the cash amounts can be used during the rest of project execution time. Hereafter, we shall refer to this model as the project cash availability maximization problem (PCAMP) for the resource constrained project scheduling problem (RCPSP). The PCAMP is mathematically equivalent to the RCPSP with the objective of minimizing total weighted completion time (also known as total weighted flow time). This problem is strongly NP-hard since its sub-problem, single machine scheduling with total flow time minimization objective subject","PeriodicalId":323606,"journal":{"name":"International Journal of Advanced Research in Artificial Intelligence","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127507412","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：