Design and Evaluation of Parallel Processing Techniques for 3D Liver Segmentation and Volume Rendering
Ensuring Software Quality in Engineering Environments
New 3D Face Matching Technique for an Automatic 3D Model Based Face Recognition System
Algorithmic Cost Modeling: Statistical Software Engineering Approach
Prevention of DDoS and SQL Injection Attack By Prepared Statement and IP Blocking
A personalized health care system model is proposed that provides e-health services in term of prediction, disease diagnosis and prevention strategy. Medical Internet of Things (MIoT) is utilized for generating various smart devices, sensors and mobile application. The collected data from hospitals, clinics, and laboratories will be stored on the cloud with the help of cloud and fog computing. Big data analytics and data mining algorithms can provide real time data analysis, testing and decision making. The required percussions will suggest an emergency service to user, if needed.
COVID-19 is a very deadly disease, which has killed thousands and infected millions of people worldwide. More recently in the year 2021, one of its mutants known as "The Delta Variant" has ravaged our country. It is also currently the chief cause of increasing cases in some North-Eastern states like Manipur and Arunachal Pradesh. Different measures have been adopted by the Government in collaboration with local social bodies to identify the infected individuals, detect the level of infection and also vaccinating individuals to shield them from this deadly disease. The current paper is also focused on one such stage, which is quite critical at this juncture, and will use the power of Artificial Intelligence to appropriately identify COVID-19 affected individuals using chest X-Ray images. When implemented, it will make it easier to identify the infection of the lungs by COVID-19. More specifically, the proposed methodology seeks to establish a chain of processes that can help in detecting the infection in the lungs using an advanced and novel image pre-processing with a prediction fusion-based deep learning-based identification system. The image pre-processing technique will initially improve the raw images by selectively optimizing the chromatic intensity and brightness of needy pixels using a deep learning-based Conditional Random Field (CRF) that uses the sigmoidal function. The enhanced image samples are made to undergo training with GoogLeNet and MobileNet deep learning models so that during the testing phase a prediction-fusion approach can be implemented to generate more robust prediction results. An exhaustive implementation with a standard dataset has revealed that the proposed approach can provide a mean accuracy of 98.63%, with the Covid and Normal classes showing 97.17% and 99.22% accuracies respectively. Another deadly disease that has infected thousands of people worldwide is skin cancer. Using the similar technical approach described above, a technique for identifying the type of skin cancer has been developed and experimented by using a standard dataset. Good accuracy of 85.42% has been achieved despite some classes having a comparatively lesser number of image samples. Finally, a Graphical User Interface (GUI) has also been developed by using the trained deep learning files of GoogLeNet and MobileNet so that a user can simply enter the desired image and check the type of prediction/class.
An increasing number of future labour force will not just comprise highly skilled human resources, but would also seek to hire personnel with sound technical, analytical, and soft skills to get engaged in cross-cultural and multi-lingual organizational setup. The major challenge of higher education is the lack of knowledge of the talents of students, so their chances of success decreases. Choosing a wrong course leads to incompletion and getting a job becomes tougher. Predicting student skills early can help mentors to advice students in a timely manner and improve student success. In this paper, a model has been created using Naïve Bayes, J48, Random Forest, and Support Vector Machine (SVM) classification algorithm, with 100 attributes. Among the models built, Naïve Bayes and Random Forest algorithm yielded better accuracy rating. In this research work, we attempt to explore dynamic dataset by applying data mining methods to explore student's insights based on characteristics related to academic, technical, environment and interpersonal factors. The model has been tested and found to be performing well in constraint based learning environment.
Present day's e-commerce business has tremendously increased as everyone got Internet on their hands through their mobile devices. E-commerce big giants like Amazon, Alibaba, Flipkart, etc. have come up with surprise sales with huge discounts on the products called Flash Events (FE) or Flash Sales (FS). It attracts the customers to purchase the product on such specified dates. Huge client requests were coming into the servers on these days. Based on this scenario, attackers target these networks to degrade the performance of e-commerce portals by generating huge fake server requests called Distributed Denial of Service (DDoS) attacks. Network attacks caused during Flash Events (FE), Flash Sales (FS) are considered as Flash Crowd attacks (FC). With FC attacks, the performance of the server is reduced as well as it affects the clients by not sending proper responses. In this paper, the two datasets to CAIDA and WC 1998 datasets have been considered. WC 1998 dataset deals with flash crowd and CAIDA dataset have DDoS attack information. Similar features from both datasets have been taken and the flash crowd and DDoS attacks have been classified using the Deep Neural Network (DNN) approach. The accuracy of discriminating the DDoS and FC/FE with an accuracy of 70.49 % at 100 epochs and 72.1 % at 1000 epochs has been achieved.
Parkinson's disease is a disorder which is identified with loss of neurons and neurologic function. It is a condition that arises when fifty to seventy five percent of the neuronal cells are affected. The symptoms include muscle rigidity, tremors and change in the speech and gait. The genetic factor also increases the risk of Parkinson's disease in a person. Some researchers also suggest that Parkinson's disease is also caused by environmental factors and excessive medications. With the advancement of deep learning and machine learning technologies, disease prediction has received additional attention from big data researchers, and numerous studies have been conducted with a choice of different mechanisms. Studies have shown that about 90% of patients with this disease suffer from certain degree of speech impairment. Therefore, we have chosen voice data as an input for our model. The proposed methodology presents how algorithm works best for identification of disease with high accuracy by splitting the dataset. XGBoost algorithm has been applied on the dataset in order to get accuracy expected out of the model.
