IJARAI Volume 4 Issue 10

Paper 1: Diagrammatic Representation as a Tool for Clarifying Logical Arguments

Abstract: Knowledge representation of reasoning processes is a central notion in the field of artificial intelligence, especially for knowledge-based agents, because such representation facilitates knowledge of action outcomes necessary for optimum performance by problem-solving agents in complex situations. Logic is the primary vehicle by which knowledge is represented in knowledge-based agents. It involves logical inference that produces answers from what is known based on this inference mechanism. Modus Ponens is the best-known rule of inference that is sound. Recently, a dispute has arisen regarding attempts to show that modus ponens is not a valid form of inference. Part of the cause of the controversy is miscommunication of the involved problem. This paper proposes a diagrammatic representation of modus ponens with the hope that such a representation will serve to clarify the issue. The advantage of this diagrammatic representation is a better understanding of the reasoning process behind this inference rule.

Author 1: Sabah Al-Fedaghi

Keywords: artificial intelligence; diagrammatic representation; conditionals; argument forms; logical argumentation; modus ponens

PDF

Paper 2: Relation Between Chlorophyll-A Concentration and Red Tide in the Intensive Study Area of the Ariake Sea, Japan in Winter Seasons by using MODIS Data

Abstract: Relation between chlorophyll-a concentration and red tide in the intensive study area of the back of Ariake Sea, Japan in the recent winter seasons is investigated by using MODIS data. Mechanism of red tide appearance is not so clarified. On the other hand, chlorophyll-a concentration can be estimated with satellite remote sensing data. An attempt is made for estimation of the location and size of red tide appearance. In particular, severe damage due to red tide is suspected in the winter seasons now a day. Therefore, 6 years (winter 2010 to winter 2015) data of MODIS data derived chlorophyll-a concentration and truth data of red tide appearance (the location and the volume) which are provided by Saga Prefectural Fishery Promotion Center: SPFPC (once/10 days of shipment data) have been investigated. As the results of the investigation, it is found that a strong correlation between the chlorophyll-a concentration and red tide appearance together with the possible sources of the red tide.

Author 1: Kohei Arai

Keywords: chlorophyl-a concentration; red tide; diatom; MODIS; satellite remote sensing

PDF

Paper 3: Estimation of Rice Crop Quality and Harvest Amount from Helicopter Mounted NIR Camera Data and Remote Sensing Satellite Data

Abstract: Estimation of rice crop quality and harvest amount in paddy fields with the different rice stump density derived from helicopter mounted NIR camera and remote sensing satellite data is made. Using the intensive study site of rice paddy fields with managing, estimation of protein content in rice crop and nitrogen content in rice leaves through regression analysis with Normalized Difference Vegetation Index: NDVI derived from camera mounted on a radio-control helicopter is made together with harvest amount of rice crops. Through experiments at rice paddy fields which is situated at Saga Prefectural Agriculture Research Institute SPRIA in Saga city, Japan, it is found that protein content in rice crops is highly correlated with NDVI which is acquired with visible and Near Infrared: NIR camera mounted on radio-control helicopter. It also is found that nitrogen content in rice leaves is correlated to NDVI as well. Protein content in rice crop is negatively proportional to rice taste. Therefore rice crop quality can be evaluated through NDVI observation of rice paddy field.

Author 1: Kohei Arai

Author 2: Masanoori Sakashita

Author 3: Osamu Shigetomi

Author 4: Yuko Miura

Keywords: Rice Crop; Rice Leaf; Nitrogen content; Protein content; NDVI

PDF

Paper 4: A Design of a Multi-Agent Smart E-Examiner

Abstract: this paper proposes a design of an application of multi agent technology on a semantic net knowledge base, to build a smart e-examiner system. This e-examiner could be used in building and grading a personalized special on-line e-assessment. The produced e-assessment should cover the majority of examined topics and material. It should cover various levels of difficulties and learners profile(s). The e-examiner will use a semantic net question bank, to emphasize on the structuring categories of all course domains. This task is done through four different intelligent agents: control agent, personal agent, examiner agent, and grading agent. The system might select questions from a bank of questions for several courses. It could be used in different education levels and natures. Also, it will produce a key for the produced exam, to be used latter in grading, and giving final marks of e-assessments.

Author 1: Khaled Nasser ElSayed

Keywords: m-Learning; e-Assessments; Multi-agent; Semantic net; Examiner

PDF

Paper 5: Improved Text Reading System for Digital Open Universities

Abstract: The New Generation of Digital Open Universities (DOUNG) is a recently proposed model using m-learning and cloud computing option and based on an integrated architecture built with open networks as GSM and Internet. The goal of achieving the ubiquitous ability of the m-learning is having the large number of languages as a serious issue. It needs to use many teachers in order to repeat the same course in various languages. In this paper, an extended system is proposed under the consideration of the low capacities of the cell-phone device in terms of computing and visualization. The model uses the possibility to build a voice warehouse which can be used to generate the audio format of every course provide in a text format and in a particular language. The Advanced Text Reading System (ATRS) is proposed to use that voice warehouse and to produce the audio format of a course, giving facility to teachers to easily overcome the constraints of language barrier. The new proposed model is described and its contributions are discussed.

Author 1: Mahamadou ISSOUFOU TIADO

Author 2: Abdou IDRISSA

Author 3: Karimou DJIBO

Keywords: m-learning; distance learning; digital open universities; cloud-computing; audio warehouse

PDF

Paper 6: Recognition of Similar Wooden Surfaces with a Hierarchical Neural Network Structure

Abstract: The surface quality assurance check is an important task in industrial production of wooden parts. There are many automated systems applying different methods for preprocessing and recognition/classification of surface textures, but in the most cases these methods cannot produce very high recognition accuracy. This paper aims to propose a method for effective recognition of similar wooden surfaces applying simple preprocessing, recognition and classification stage. The method is based on simultaneously training two different neural networks with surface image histograms and their second derivatives. The combined outputs of these networks give an input training set for a third neural network to make the final decision. The proposed method is tested with image samples of seven similar wooden texture images and shows high recognition accuracy. The results are analyzed, discussed and further research tasks are proposed.

Author 1: Irina Topalova

Keywords: recognition; preprocessing; neural network; wooden surface

PDF

Paper 7: Application of K-Means Algorithm for Efficient Customer Segmentation: A Strategy for Targeted Customer Services

Abstract: The emergence of many business competitors has engendered severe rivalries among competing businesses in gaining new customers and retaining old ones. Due to the preceding, the need for exceptional customer services becomes pertinent, notwithstanding the size of the business. Furthermore, the ability of any business to understand each of its customers’ needs will earn it greater leverage in providing targeted customer services and developing customised marketing programs for the customers. This understanding can be possible through systematic customer segmentation. Each segment comprises customers who share similar market characteristics. The ideas of Big data and machine learning have fuelled a terrific adoption of an automated approach to customer segmentation in preference to traditional market analyses that are often inefficient especially when the number of customers is too large. In this paper, the k-Means clustering algorithm is applied for this purpose. A MATLAB program of the k-Means algorithm was developed (available in the appendix) and the program is trained using a z-score normalised two-feature dataset of 100 training patterns acquired from a retail business. The features are the average amount of goods purchased by customer per month and the average number of customer visits per month. From the dataset, four customer clusters or segments were identified with 95% accuracy, and they were labeled: High-Buyers-Regular-Visitors (HBRV), High-Buyers-Irregular-Visitors (HBIV), Low-Buyers-Regular-Visitors (LBRV) and Low-Buyers-Irregular-Visitors (LBIV).

Author 1: Chinedu Pascal Ezenkwu

Author 2: Simeon Ozuomba

Author 3: Constance kalu

Keywords: machine learning; data mining; big data; customer segmentation; MATLAB; k-Means algorithm; customer service; clustering; extrapolation

PDF