Vijay Kumar Jha

Adaptive Ontology Construction Method for Crop Pest Management

Knowledge represented as ontologies can be accessed easily by automated systems in Semantic Web. If ontologies are used to represent agricultural knowledge, e.g., crop pest information, it can be shared by many existing expert systems in agricultural field. Different languages are used by farmers all over India. As knowledge in the form of ontologies can be converted easily into different languages, farmers in various states in India can benefit from expert’s knowledge. Developing crop pest ontology from scratch will be a difficult task for agricultural experts and it will consume lot of time. We provide user-friendly interface in which agricultural expert can upload text descriptions of crop pests. The system will extract keywords from text files by applying keyphrase extraction steps and comparing it with AGROVOC thesaurus. For this purpose, we propose a Pest Keywords Extraction Algorithm described in detail in the paper. Agricultural expert can add new pest types, pest examples, and details of each pest such as reason, symptom, and remedy for pest. All the details will be automatically saved as pest ontology in OWL format. The system is adaptive as the expert can see pest type hierarchy, add or remove a pest type and pest details at any point in crop pest ontology. Once complete, ontology for crop pests is ready to be used by expert systems as part of inference engine.

Using IoT for integrated pest management

Management of pests is an important task in agriculture. Integrated Pest Management (IPM) is a way to prevent pest risks for long term using effective methods. Use of IoT for integrated pest management is unavoidable as it involves various tools from biological, chemical, mechanical and cultural field. Information about pests and all these tools needs to be maintained. Storing this information as ontology is the best option, as it then can be used by number of automated systems in agricultural field. Information in terms of ontology can be used by web services and can be made available online. It will help not only researchers in agriculture field but also farmers to manage pests and improve yield percentage. We describe automated method for construction of IPM ontology as web ontology language document and explain how it can be made available to farmers as an IoT application.

A Novel Fuzzy Min-Max Neural Network and Genetic Algorithm-Based Intrusion Detection System

Today in the era of ICT, security of data and services on the WWW has become the most important issue for web service providers. Loopholes in the security systems of WWW may break the integrity, reliability, and availability of data and services. Today, intrusion detection systems based on data mining is the best security framework for the Internet. In this paper a novel intrusion detection system is proposed which is based on the fuzzy min-max neural network and the genetic algorithm. The proposed model is trained using fuzzy min-max neural network and the learning system is optimized by application of genetic algorithm. The developed system is tested on the KDD Cup dataset. The parameters classification accuracy and classification error were used as a final performance evaluator of the learning process. The experimental results show that the proposed model gives superior performance over other existing frameworks.

Enhancing Multibiometric System Security Using ECC Based on Score Level Fusion

Unimodal biometric system has several inherent problems such as large intra-class variation, non-universality, and spoofing attack. And the performance of unimodal is also affected by the condition of user health, weather condition, and type of sensor used. To overcome this limitation, multibiometric is a good option where we can use two or more individual modalities. In this paper, we propose a multibiometric-based system to enhance the security using ECC based on score level fusion. This work extract feature from three different modalities, namely, fingerprint, face, and iris. The first level of authentication will be considered as successful if the score generated after the score level fusion of three modalities is above system threshold value. And then the user considers as a genuine user otherwise acts as an imposter. In the second level of authentication, an OTP is generated by the bank server which is sent to the user mobile for making transaction. The generated OTP is not secure in a network as it can be easily guessed or stolen by attackers. So to enhance the security, we use the concept of biometric signature based on elliptic curve cryptography. And finally, users entered OTP in a bank transaction screen for the execution of transaction.

Decision Tree and Genetic Algorithm Based Intrusion Detection System

Today’s computer network security systems like IDS, firewall, access control, etc., are not yet 100% trusted, Still they are suffering from the high classification error. Therefore, there is challenge for the researchers to minimize the classification error of the IDS. In this paper, an IDS has been proposed which is based on the decision tree and genetic algorithm. The base of the system is decision tree C4.5 and in the second phase of the intrusion detection system, genetic algorithm is used to overcome the problem of small disjunct in the C4.5. The competence of the system is tested with KDD CUP data set and outcomes of the proposed system are compared with existing systems. It is worth to mention that the experimental assessment of the proposed system is better in comparison to the IDS reported in the literatures.

Crop Suitability and Fertilizers Recommendation Using Data Mining Techniques

Economy of India highly depends on agriculture. Still traditional ways of recommendations are used for agriculture. Currently, agriculture is done based on various approximations of fertilizers quantity and the type of crop to be grown or planted. Agriculture highly depends on the nature of soil and climate. Therefore, it becomes important to make advancement in this field. The paper proposes development of an ontology-based recommendation system for crop suitability and fertilizers recommendation. It bridges the gap between farmers and technology. The system predicts suitable crop for the field under consideration based on region in Maharashtra state of India and type of soil. It provides proper recommendation of fertilizers to the farmers. Fertilizer recommendation is done based on nitrogen, phosphorus, and potassium (NPK) contents of soil and using past years research data that is stored in ontology. Along with fertilizer recommendation system also provides suggestions about crop suitability in particular region. Recommendation system uses random forest algorithm and k-means clustering algorithm.

IPMOntoShare: Merging of Integrated Pest Management Ontologies

Integrated pest management (IPM) is a combination of different techniques to increase crop production in eco-friendly manner. Minimizing use of pesticides with IPM will reduce risk of human diseases and will also reduce environmental risks. Various computerized systems are used for IPM, where agricultural experts provide their pest management knowledge as input for decision-making. Integrated pest management knowledge if represented as ontology, it can be shared by heterogeneous agricultural computerized systems. This paper presents a tool to develop IPM ontology using upper IPM ontology and domain specific crop IPM ontology. Tool is named IPMOntoDeveloper. IPM ontologies developed by distinct agricultural experts can be integrated into one to enrich knowledge base of IPM practices for specific crop. This paper presents a system named IPMOntoShare to merge IPM ontologies developed by various agricultural experts. It combines several approaches of ontology matching, including name matching and structure matching.

Secure key-distribution in IoT cloud networks

Internet of Things (IoT) cloud networks is itself a pervasive idea where all the physical objects are connected over the internet and are allocated with special self-identifying ability to discover other potential objects to transmit data over the internet. The most important shortcoming of IoT cloud networks which needs immediate addressing is the issue of IoT nodes when used within a virtual network of a cloud system. The IoT nodes often communicate over a virtual network and this communication needs to be monitored and managed by the cloud service provider (CSP). This CSP needs to make sure that no IoT node with malicious intent can thrive in such a network. In this paper we propose a framework for the security over virtual network for IoT nodes in a cloud system. Firstly, we propose a secure key management protocol between the CSP and the user group having the IoT nodes using a balanced incomplete block design (BIBD) model. Secondly, we device a lightweight cryptographic technique involving a key exchange protocol to establish a secure end-to-end communication between the IoT nodes. Finally we measure the efficiency and resiliency of the distribution using different metrics.

Ontology Based System for Pests and Disease Management of Grapes in India

About 35% of Indias Gross National Product comes through agricultural sector. Any losses in gross agricultural product also affect Indian economy. Percentage of crop yield loss due to pests and dieses is considerable. As grapes are grown in most of states in India, it plays important role in gross crop yield. Having a computerized system for managing pests and disease occurring in grapes will help in increasing total yield of grapes. The paper proposes expert system for pest and disease management of grapes where we provide forecasting of probable pests and diseases. This work considers current weather conditions at grape farm location for forecasting. Knowledge base for pests and disease is generated by extracting information from internet and storing it as OWL document. Inference engine for grape expert system is based on fuzzy logic as weather conditions can logically be represented as fuzzy variables. It uses rule base developed by experts.

AgroKanti: Location-Aware Decision Support System for Forecasting of Pests and Diseases in Grapes

Grape is an important crop in Indian agriculture. There are many pests occurring on Grapes which cause huge yield loss to farmers. The grapes development is driven mainly by temperature and many pests have direct relation with temperature. We propose a decision support system named AgroKanti for managing pests on table grapes like powdery mildew and anthracnose. The decision support system is location based i.e. farmer is provided with details of pests considering current weather conditions at farmer’s location. We support farmers with pest details like symptoms and management techniques for pests. We provide our system as an application on mobile phones. The knowledge base of pests is stored as ontology in OWL format. We have also developed a black box for agricultural experts where agricultural experts can generate pest ontology form text descriptions. We have used NLP techniques and AGROVOC library to extract pest details from text descriptions and generate ontology.