Text categorization is the task in which documents are classified into one or more of predefined categories based on their contents. This paper shows that the proposed system consists of three main steps: document representation, classifier construction and performance evaluation. In the first step, a set of pre-classified documents is provided. Input documents are initially pre-processed in order to be split into features and eliminate non-informative features. The remaining features are next weighted based on the frequency of each feature in that document and standardized by reducing a feature to its root using the stemming process. Due to the large number of features even after the non-informative features removal and the stemming process, the proposed system applies specific thresholds to extract distinct features which represent the input document. In the second step, the text categorization model (classifier) is built by learning the distinct features which represent all the pre-classified documents; this process can be achieved by using one of the supervised classification techniques that is called the rough set theory. The model uses a pair of precise concepts from the above theory that are called lower and upper approximations to classify any test document into one or more of main categories and sub-categories. In the final step, the performance of the proposed system is evaluated. It has achieved good results up to 96%, when applied to a number of test documents for each sub-category of main categories.
Parkinson's disease (PD) is one of the chronic neurological diseases whose progression is slow and symptoms have similarities with other diseases. Early detection and diagnosis of PD is crucial to prescribe proper treatment for patient's productive and healthy lives. The disease's symptoms are characterized by tremors, muscle rigidity, slowness in movements, balancing along with other psychiatric symptoms. The dynamics of handwritten records served as one of the dominant mechanisms which support PD detection and assessment. Several machine learning methods have been investigated for the early detection of this disease. But, most of these handcrafted feature extraction techniques predominantly suffer from low performance accuracy issues. This cannot be tolerable for dealing with detection of such a chronic ailment. To this end, an efficient deep learning model is proposed which can assist to have early detection of Parkinson's disease. The significant contribution of the proposed model is to select the most optimum features which have the effect of getting the high performance accuracies. The feature optimization is done through genetic algorithm wherein K-Nearest Neighbour technique. The proposed novel model results into detection accuracy higher than 95%, precision of 98%, area under curve of 0.90 with a loss of 0.12 only. The performance of proposed model is compared with some state of the art machine learning and deep learning based PD detection approaches to demonstrate the better detection ability of our model.
Recently, different techniques have been applied to detect, predict, and reduce traffic congestion to improve the quality of transportation system services. Deep learning (DL) is becoming increasingly valuable for solving critiques. DL applications in transportation have been collected in several recently published surveys over the last few years. The existing research has discussed the cloud environment, which does not provide timely traffic forecasts, which is the cause of frequent traffic accidents. Thus, a solid understanding of the difficulties in predicting congestion is required because the transportation system varies widely between non-congested and congested states. This research develops a bi-directional recurrent neural network (BRNN) using Gated Recurrent Units (GRUs) to extract and classify traffic into congested and non-congested. This research uses a bidirectional recurrent neural network to simulate and forecast traffic congestion in smart cities (BRNN). Urban regions worldwide struggle with traffic congestion, and conventional traffic control techniques have failed miserably. This research suggests a data-driven approach employing BRNN for traffic management in smart cities, which uses real-time data from sensors and linked devices to control traffic more efficiently. The primary measures include predicting traffic metrics such as speed, weather, current, and accident probability. Congestion prediction performance has also been improved by extracting more features such as traffic, road, and weather conditions. The proposed model achieved better measures than the existing state-of-the-art methods. This research also explores an overview and analysis of several early initiatives that have shown promising results; moreover, it explores two potential future research approaches to increase the accuracy and efficiency of large-scale motion prediction.
Scheduling Timetables for courses in the big departments in the universities is a very hard problem and is often be solved by many previous works although results are partially optimal. This work implements the principle of an evolutionary algorithm by using genetic theories to solve the timetabling problem to get a random and full optimal timetable with the ability to generate a multi-solution timetable for each stage in the collage. The major idea is to generate course timetables automatically while discovering the area of constraints to get an optimal and flexible schedule with no redundancy through the change of a viable course timetable. The main contribution in this work is indicated by increasing the flexibility of generating optimal timetable schedules with different copies by increasing the probability of giving the best schedule for each stage in the campus with the ability to replace the timetable when needed. The Evolutionary Algorithm (EA) utilized in this paper is the Genetic Algorithm (GA) which is a common multi-solution metaheuristic search based on the evolutionary population that can be applied to solve complex combinatorial problems like timetabling problems. In this work, all inputs: courses, teachers, and time acted by one array to achieve local search and combined this acting of the timetable by using the heuristic crossover to ensure that the essential conditions are not broken. The result of this work is a flexible scheduling system, which shows the diversity of all possible timetables that can be created depending on user conditions and needs.
The security nowadays considered as significant topic specifically in design smart home. This paper is dedicated on an authentication problem in design smart door lock authentication using string matching technique based on password string. This work contains two main parts, Android application (remote control) and control circuit using Arduino UNO, plus the communication medium based on Bluetooth technology which is used to send and receive information and commands in this work. The main purpose of design smart door lock, using Jaro Winkler algorithm is to compare the registered password security with each entered password which may contain some wrong or swapped characters. The results show more strength authentication for access in real-time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.