KJC Korea
Journal Central

There are different types of diseases occur in plants and fruits due to the changes of not only the climate, weather, and seasons, but also the environmental factors like temperature, humidity, and rainfall etc. Diseases can change the structure of plants, fruits and also crops. The influence of plants and fruits disease affects our agriculture industry and agriculture sector. Diseases can interrupt our plant’s growth, fruits growth, production growth, and also makes an effect on economic growth all over the world. Farmers have a lot of experience in detecting problems and also they can identify the diseases in various plants. They can easily take care or actions for environmental factorial diseases but sometimes it’s not working. Technologies can support farmers to make their methods more reliable to improve farmer’s crops and fruits quality for a good production. Therefore in this study, we analyse different types of plum plant diseases and then use the linear regression model to know the condition of plum fruit size using plum growth, plum length and plum width. In result and discussion, we identify the environment factorial diseases in plum and also make a decision by verifying the plum fruits size after diseases occurred in Plum Plants.

Plant diseases are one of the most significance issues in agriculture fields. The diseases destroy fruits and are decreased the production rate. They also decrease the economic growth in worldwide and increase the demand about preventing plant diseases. The major cause of plant diseases is climate changes, weather conditions and environmental factors. To prevent the diseases, we need to identify the plant diseases about corresponding environmental factors. In this study, we analysis the plum data and identify the plant diseases with corresponding environmental factors by using Logistic Regression model. The first process is to identify the number of diseases and its type, and then implement Logistic Regression to predict the diseases by using environmental factors as inputs. Finally, we compare the actual value of diseases with predicted value of diseases, and need to check the accuracy of diseases by using correlation method. We also find the environmental factors for the reasons to forms more diseases. In result and discussion, it would be clearly explained about the plum diseases and their environmental factors.

The use of biomedical technology has been applied to all smart devices such as smart phones and tablet PCs, mainly shopping malls, medical systems, and financial institutions. The core of biomedical technology is the authentication function. Authentication verifies the validity of the identity at the remote server by the registered user. It is also a basic security service that allows access to remote servers. Passwords, smart cards, and biometrics are three commonly used elements in authentication. Remote user authentication schemes for various multi-server environments have been proposed by many researchers. Lin et al.'s suggested that the scheme of Baruah et al.'s is vulnerable to impersonation attacks, smart card theft attacks, etc. in a multi-server environment and proposed an improved scheme. However, there is a weakness of some parameter calculations as a result of Lin et al.'s analysis of the authentication scheme. It was revealed that users and servers were colluding, or when users' smart cards were stolen, they were vulnerable to impersonation attacks, smart card stolen attacks, replay attacks, and denial of service attacks. Thus, this paper logically reanalyzes and compares the vulnerabilities of the Lin et al 's scheme.

There are various types of fuzzy sets used to evaluate the reliability of the systems. In the fuzzy sets, the membership value is represented as a real number and the reliabilities are expressed by using it. In the interval valued fuzzy sets, the degree of membership is represented as an interval [, ] which is used to describe the reliabilities. In the vague sets, the degree of membership is represented as [, ] and it is used to express the reliabilities. In the interval valued vague sets, the membership degree is represented as a [, , , ] and it is used to express the reliabilities. In the level (λ, 1) interval valued fuzzy sets, the membership degree is represented as a interval [λ, 1] which is used to describe the reliabilities. In order to represent the degree of membership in the interval valued neutrosophic sets, (, , ) is used and the reliabilities are expressed by using it. In this paper we propose a level (λ, 1) interval valued neutrosophic sets that can express the merits of the level (λ, 1) interval valued fuzzy sets and the interval valued neutrosophic sets. In the level (λ, 1) interval valued neutrosophic sets its provide flexibility to adjust the size of the minimum membership value using λ and also enable to express the indeterminacy by using the indeterminacy membership value of the neutrosophic sets. Therefore the level (λ, 1) interval valued neutrosophic sets become more flexible and rigorous to describe the reliabilities than the other methods.

Fog is a natural phenomenon in which light is scattered by an atmospheric aerosol. Fog effects rendering is used for games or image synthesis, as well as for special effects in movies or many digital contents. For realistic fog effects generation, depth-altitude information is essential; However, two-dimensional (2D) images generally do not have depth information, and thus fog effects are expressed simply with white color and blending, and it cause artifacts such as the shower door effect. In addition, although we can consider depth information for the effects, it has a limitation in that the SW only takes a specific type of input image that has depth information. In this paper, we propose a novel technique for generating fog effects on a two-dimensional (2D) inputted image based on the atmosphere scattering model. For this, we extract approximated depth information from the 2D input image, then, we apply the Beer-Lambert law based on approximated depth and altitude information. Based on our method, we can express fog effect onto 2D images easly and quickly and it can efficiently express various fog effects and generate natural fog effect animations.

Word2Vec is a most popular method in text mining area, recently. It converts words to vectors using association among words in sentences. Similar words are nearly located in the vector space. As deep learning technology has developed rapidly, deep neural network that adopts deep learning is being applied in many areas. Improving predictive accuracy of recommender algorithms is a major work in the area of recommender systems. This study proposed an integrated method for movie recommender systems using Word2Vec and deep neural networks. First, it constructs Corpus of users and movies. It generates sentences for constructing Corpus. It finds users that give same rating to a movie, generates a sentence with those users, and constructs the Corpus of users using the sentences. It finds movies that are given same rating from an user, generates a sentence with those movies, and constructs the Corpus of movies using the sentences along the same lines. Secondly, it calculates user vectors and movie vectors using Word2Vec. Thirdly, it learns a model of deep neural networks with inputs composed of the user vectors and the movie vectors. Lastly, it recommends movies to the target user through the learned deep neural networks. To validate, the proposed method was applied to filmtrust dataset. The experimental results of 10-fold cross validation showed that the proposed method improved accuracy greatly than conventional collaborative filtering method(uCF). Also, it showed that the proposed method could solve problems with comparatively high accuracy, recommendation problems to new customers and new products, but the conventional collaborative filtering methods had difficulties recommendation to those problems.

As the error tolerance of low-cost components in servo systems such as optical disc drives become wider, the effects of the errors on model uncertainty increase in comparison with a nominal model. In the case of the optical disk, the size of the data pattern is reduced to increase the storage capacity, so that fast, precise and stable control is required to place the laser spot on the disk. In this paper, we introduce a new technique of a loop gain adjustment (LGA) based on an embedded dynamic signal analyzer (EDSA) that is used for estimating the gains and phases at a cross-over frequency of the system. Conventional algorithms repeat LGA operations until the system finds a target value; however, the proposed LGA directly calibrates the target value to coincide with the frequency response of the nominal model. A measuring algorithm for calculation of the frequency characteristics is proposed for the removal of the effects of additive white Gaussian noise. Moreover, because the proposed algorithms are implemented on a system-on-chip, they can be applied to diverse applications, such as robots, vehicles, and aircraft. The experimental and simulation results show that the proposed LGA based on error-free EDSA exhibits notable and reliable performance.

The integration of IoT and livestock management, particularly the use of the Internet and networking technology in existing automation devices, to observe and quantify environmental and animal conditions without limits in time or space, is called smart livestock farming. In particular, the observation of estrus and timing of fertilization account for the greatest proportion of livestock breeding management. This paper proposes IoT-based system that provides service of estrus detection to the user based on the activity of korean native cattle. The proposed estrus detection system provides an alarm service to user by diagnosing and analysing the estrus state of korean native cattle through the characteristic of increasing activity compared to the korean native cattle of weak estrus. In this study, acceleration sensors were attached to livestock in a farms with poor prediction to measure livestock activity and to analyze the collected to data to enable rapid response in case of atypical symptoms, such as various diseases and estrus, in order to suggest a better system. Upon estrus, livestock movement increases above normal, while movement decreases in diseased livestock. Based on these characteristics, a livestock movement monitoring system was designed using an acceleration sensor. Also, we can calculate the expected delivery time and the next estrus through the implementation of database for estrus detection of livestock. The economic benefits and competitive advantages can be improved in livestock farmhouse by implementing the developed technology of livestock IoT convergence.

Deep learning technology among artificial intelligence technologies has shown good results in image recognition field. In this paper, we use a learning model that is based on a Tensorflow based model that utilizes this deep learning technique and that has been repaired by Inception-v3 model. Based on the characteristics of the fruit, we construct a fruit classification system that classifies into four categories : Healthy apple, Damaged apple, Diseased apple and Discolored apple. To do this, we designed a learning model in which the number of learning iterations was 500 times based on 1,280 apple image data of four kinds and conducted a model evaluation experiment based on the fruit image data taken by the user. Experiments were based on images taken in three directions for accurate model evaluation. Experimental results show that the accuracy of the learning model is more than 90%. However, since fruit showed different classification results according to direction, it suggested the necessity of classification algorithm according to image direction in the future. If such a deep learning based fruit classification system is applied to farmers, fruit quality classifiers due to farm labor shortage are essential, and it will be possible to construct a fruit quality screening system with high accuracy and low cost.

One of the advantages in virtual reality (VR) is that it can provide indirect experience to users without the space and the time limitations. Furthermore, the VR allows users to avoid every dangerous situations in a various environment, so the VR is a best method to practice manufacturing devices, which can be occurred in dangerous conditions. Therefore, this paper proposes a VR based education system for a general lathe. The proposed system is composed of an head mounted display, controllers, a foot tracker, and a PC. The virtual environment was designed using Unity 3D. A user can study the general lathe with two modes, a study mode and a practice mode. A user can get the information of the general lathe’s each part and a basic to use the general lathe. In the practice mode, a user can select a material and a blueprint, and can control a spindle speed, a handle, and a break paddle by gestures. Furthermore, we recorded real sounds according to the materials and spindle speeds to enhance the experience of users. Finally, user tests are conducted with working-level workers and non-working-level workers, and compared the proposed system and a previously developed VR based general lathe education system. The results show that the proposed system is suitable for teaching educatee.

Oryeong-san is a prescription widely used for diseases where water is stagnant because it has the effect of circulating the water in the body and releasing it into the urine. In order to investigate the mechanisms of oryeong-san, we in this paper construct and analysis the compound-target network of medicinal materials constituting oryeong-san based on a systems pharmacology approach. First, the targets related to the 475 chemical compounds of oryeong-san were searched in the STITCH database, and the search results for the interactions between compounds and targets were downloaded as XML files. The compound-target network of oryeong-san is visualized and explored using Gephi 0.8.2, which is an open-source software for graphs and networks. In the network, nodes are compounds and targets, and edges are interactions between the nodes. The edge is weighted according to the reliability of the interaction. In order to analysis the compound-target network, it is clustered using MCL algorithm, which is able to cluster the weighted network. A total of 130 clusters were created, and the number of nodes in the cluster with the largest number of nodes was 32. In the clustered network, it was revealed that the active compounds of medicinal materials were associated with the targets for regulating the blood pressure in the kidney. In the future, we will clarify the mechanisms of oryeong-san by linking the information on disease databases and the network of this research.

The healthcare and physical strength are critical factors to be considered in a highly competitive environment in human life. Many people prefer sport is designed to obtain the key of human life because it is a good characteristic both health and physical strength. One of the Golf Swing Model (GSM) in sport is defined as a designed, computer treated of complexity of motions automatically. Especially, GSM is apparently concerned with speed generation its adaptability such as golfer segment angular kinematics, kinetic energy and angular momentum. For this reason, the design of GSM is need to expertise on knowledge of motion patterns, improve by altering the sequence of rotations in the conventional golf swing. In our research paper, it is to study and evaluate the GSM by simulating modeling for experiment and analysis. The methodology used in our research is simulated by Self-Organizing Maps (SOM). SOM provide the design system as well as offer environment to which experiment of the system can be performing. Eventually, our GSM by using SOM is presented some researchable scenario. In addition, we extend the algorithm to handle attribute datasets containing both numeric and categorical attributes in Big Data Environment.

The Aviation industry has undergone tremendous development through intensive investment and constant research of capital compared to other means of transportation. As the number of airline, aircraft and the size of the aircraft increased, accidents and risks had increased. However, due to the development of aircraft technology and the efforts of aviation workers, the accident rate related to aircraft decreased. Even when a single aircraft accident occurs, it causes many casualties and tremendous property damage. In order to prevent human and material loss due to aircraft accidents, the international community classifies runaway escape accidents into high risk categories together with Loss of Control in Flight (LOC-I) and Controlled Flight into Terrain (CFIT) In order to improve their awareness and improvement. However, the incident of runway deviations has remained at a certain level. Especially, in the case of Veer Off and Overrun at landing, it is the most common type of landing approach. More than half of these aircraft accidents are linked to fatalities. Therefore, To contribute the safety improvement of the aviation industry, this study aims to derive a plan for solving safety hazards of runway deviations accidents by utilizing actual flight data and RSARA algorithm for domestic airports.

Reliability analysis is the important discipline of reliability engineering. In conventional reliability analysis, the reliability of the components of a system is represented as exact values. Obtaining these data under changing environment conditions is often difficult. Hence fuzzy set theory is used to analyze the fuzzy system reliability, where the reliabilities of the components of a system are represented by fuzzy sets. There are various types of fuzzy sets used to evaluate the reliability of the systems such as the fuzzy sets, interval valued fuzzy sets, intutionistic fuzzy sets, picture fuzzy sets. In the fuzzy sets, the degree of membership is represented as a real number. In the interval valued fuzzy sets, the degree of membership is represented as an interval [, ], where is the minimum degree of membership and is the maximum degree of membership. [, ] ⊆ . In the intuitionistic fuzzy sets, the degree of membership consist of and , where is the degree of membership and is the degree of non-membership. , ∈ . In the picture fuzzy sets, the degree of membership consist of , , and , where is called the degree of positive membership, is called the degree of neutral membership, and is called the degree of negative membership. , , ∈ . In this paper we propose the way to analyze the fuzzy system reliability based on the picture fuzzy sets. The picture fuzzy sets have the capability of representing the positive, negative, neutral, and refusal situation. Therefore the picture fuzzy sets become more flexible to describe the reliabilities than the other methods.

Many phenomenons and systems in real world can be adapted their behavior in reaction to a given usage situation, and using the possibilities of sensors. We are surrounded with a hugh number of communicating and interacting things. Such a system is characterized by being distributed with a smart device or component from a large class. In addition, many cellular phone applications are able to provide a context-aware behavior, in which expose more flexible service and conventional software APP. However, by changing conditions on the dynamic environment act in an undesire behavior on their system. And also, by the undesirable behavior, web services such as power cells and embedded systems can be rely on their resources. Moreover, It can also be caused by the failure of certain resources or nodes in their system that provide to the quality of service and accuracy. After all, Adaptive systems typically use information about their system environment to adapt themselves to certain usage situations. Accordingly, this paper is required newly design methodology for Self-Adaptive with enable to a various systems. For this reason, we design formal description exploration model-based architecture. Especially, we present to optimization with synthesizing and optimizing system level for self-adaptive system, as well as propose Formal specification method for designing self-adaptive system. Futhermore, we show a classification of big data with methodological approach, and provide useful implications with their formation and evolution method.