No abstract

Coupling measurement in object-oriented software is becoming an important area day by day from the software quality evaluation point of view. Coupling is an interdependence relationship between classes (modules) of object-oriented software. The coupling measurement helps to maintain dependency degree between modules of object-oriented software. The moderate coupling values result in quality software. Ultimately quality software retains moderate range of values of software quality attributes such as complexity, efficiency, reusability, maintainability, understandability, flexibility, portability, interoperability, etc. This paper proposes a web based tool for measuring coupling in object-oriented Java software. The idea of a web based tool is to deploy a software coupling tool on intranet or cloud to give access to the prescribed users. The tool can be used online to compute coupling and the resulting data of the tool can be sent/received via the public network. The detailed architecture and components of the tool are described in the paper. The tool is most secured for input processing. The Java and Android projects are evaluated using the tool, the coupling values of Java and Android projects are compared in the results and discussion section of the paper. The Advantages of using the web based tool are also described in the paper. Seven coupling metrics are used from the literature to compute their values using web based tool proposed in this paper. Percentage coupling values of seven coupling metrics are computed for Java and Android projects. The percentage range of coupling values computed in the paper using web based tool is compared with standard range of coupling values described in the literature. The results obtained using web based tool gives us coupling values of Java and Android projects. The coupling values obtained using web based tool proposed in the paper are compared with standard coupling values described in the literature. It is found that the values obtained using the web based tool, are within the standard range of coupling values described in the literature. It means the web based tool proposed in this paper calculates correct coupling values of any object-oriented Java code.

In agricultural regions, the procedure of weed removal is crucial. Weed removal in the classic way, takes longer and requires greater physical effort. The idea is to eliminate weeds from agricultural fields automatically. The proposed study uses a deep learning algorithm to detect weeds growing between crops. Deep learning method also known as deep learning is used to analyse the main properties of agricultural photographs. Weeds and crops have been identified using the dataset. Convolutional neural network (CNN) uses a completely attached surface with rectified linear units (RELU) to differentiate weed and crop. It extracts features of crop using deep learning. The CNN uses features of proceeded image to extract region of interest (ROI). A deep learning network features are used to identify crop. In total of 1280 images are used for testing the system, and 10 images are used to find the confidence score.

The majority of people are medically unqualified to research or comprehend the severity of their ailments or symptoms. Natural language processing plays a critical role in healthcare in this area. These chatbots collect patient health data and, based on that data, provide more relevant information to patients about their physical ailments, as well as advise next steps. Artificial intelligence (AI)-powered healthcare chatbots are useful in the medical industry for supporting patients and directing them to the most appropriate resources. Chatbots are more useful for online searches that users or patients conduct when they are searching for answers to their health-related questions. With this application, a user can make health requests via text message and might also get relevant health suggestions/recommendations through it. This Chatbot is developed to be both educational and conversational. Chatbot delivers medical information, such as symptoms and remedies for diseases. Patients’ personal and medical information is stored in a database for further study, and patients receive real-time advice from experts. AI-powered apps in healthcare have experienced a significant increase in recent days. As a result, office wait times are reduced, saving money and energy. Patients may be learning medical information and assisting at their own pace and location.

All over the world, there are a significant number of patients suffering every year from blood cancer. Most of the people are unaware of the risk involved in such a disease. A majority of these diseases are dangerous and may cause death. The patient who have been diagnosed with such a disease, feels very afraid. The patient may feel that the disease is very uncontrolled. Such diseases are very uncommon, and the patient may get very less assistance and information available about this disease. This symptom is called as acute lymphocytic leukemia (ALL) in medical science. In such a kind of cancer, white blood cells are mostly affected. In case of children, this disease is mainly detected i.e. children are more prone to this disease. If the disease is diagnosed in the early stage, the chances of recovery are maximum. Hence, there should be an accurate and guaranteed mechanism available to detect such type of blood cancers in the patients. This work proposes a system to distinguish the three different types of ALL using a convolutional neural network (CNN) by means of microscopic pictures of peripheral blood smears (PBS) and obtain accuracy levels that surpass those of practicing physicians.