Papers by Keyword: Pattern Recognition

Abstract: Writing matching has evolved dramatically from simple string comparison algorithms to sophisticated natural language processing techniques. This comprehensive literature review examines matching methods over the last 20 years, with special emphasis on transitioning from traditional frameworks to modern NLP methods to identify opportunities for practical theoretical integration and development exploring both models' fundamental principles, strengths and limitations. Our systematic review covers three main areas: (1) classical text matching algorithms, including Levenstein distance, Boyer-Moore, and Knuth-Morris-Pratt; (2) modern NLP techniques, such as transformer-based models and contextual ontologies; and (3) emerging hybrid approaches that seek to integrate these approaches. Intensive analysis of more than 40 papers from leading areas in information retrieval, natural language processing, and algorithmic evolution reveals key patterns in adopting text-matching strategies and highlights promising directions for future research. The study highlights a significant difference between the computational efficiency of traditional methods and the logical comprehension capabilities of modern NLP methods. Our study examines various attempts to bridge this gap and discusses the challenges and opportunities in integrating classical and modern approaches. We examine how different approaches manage the trade-off between computational complexity, logical clarity, and application-specific requirements.

Abstract: In digital image processing, artificial intelligence is increasingly applied to image analysis, enhancement, pattern recognition, object recognition, and classification. Unlike traditional image processing, which often relies on rules and predefined algorithms, AI-based approaches use learning, adaptation, and automatic decision-making to identify and manage image features. Key technologies include deep learning, neural networks, and machine learning-based algorithms. AI-driven technology is now present across an expanding range of fields and industries, significantly augmenting classical image processing methods or even replacing certain steps or sub-processes with the power of machine intelligence. The paper aims to highlight the opportunities and trends offered by artificial intelligence in the field of digital image processing.

Abstract: The challenging for buyers around the globe to identify good quality of Durian. For several kinds of Durian, it may be difficult for buyers to determine the Durian quality by appearance. The ability to select only good quality Durian without cutting or cleaving is useful because buyers will not waste money ordering undesirable Durian.This paper proposes a nondestructive technique to determine the stages of maturity of durian fruits. The presented methodology utilizes the concept of pattern matching. We used the local knocking equipment to knock the durian for knocked-sound. After that the knocked-sound was analyzed and generated to Mel-frequency cepstral coefficients (MFCCs) that is used to train data for the classifier. Feed-Forward Neural Network was used for the classifier and can effectively classification the stages of maturity of durian fruits with accuracy rate more than 82%.

Abstract: Nowadays application and development of cognitive graphic tools for the usage in intelligent system of data and knowledge analysis, decision-making and its justification for different problem areas including material research are urgency. Most significantly developed cognitive graphics tools based on n-simplex which are invariant to problem areas are presented. Specificity of program realization of cognitive graphics tools which is invariant to problem areas is described. Most significant results are given and discussed. Future investigations are connected with the usage of new approach to rendering, cross-platform realization, improving cognitive features and expanding n-simplex family

Abstract: Applications of electronic noses to classify the freshness of food and beverages by mimicking the olfactory perception are becoming widely recognized in food industries. For pasteurized orange juice, packaging and shelf-life are key factors for the quality control, which are generally inspected by the sensory stability and quality (odor, color, texture and taste) of the orange juice. An electronic nose based on five different commercial metal oxide gas sensors, a temperature sensor and a humidity sensor has been designed and constructed to examine the quality of orange juice as subjected to the fermentation process. The duration for a single measurement from an orange juice sample was approximately two minutes. The data acquisition of the voltage responses of the gas sensors were achieved via a microcontroller unit. The data classification was statistically analyzed by the “Principal Component Analysis (PCA)”. The Euclidean distance between two PCA groups was used as an indicator of ethanol concentration. The orange juice was laced with various concentrations of ethanol from 0.1 to 1.0% ethanol to simulate fermented orange juice at different stages. The objective was to characterize the freshness of orange juice by means of the ethanol level from the fermentation process. The results show a distinctive classification of the orange juice for an alcohol concentration lower than 0.1%. Thus the electronic nose offers a rapid, highly sensitive alternative for the quality control process.

Abstract: Keystroke dynamics is known to be able to recognise a person associated with their way of typing on a computer keyboard. It is a fea-sible and useful method as an additional component to safety measures for identity verification. Previous studies show how keystroke dynamics can help to improve the recognition systems. Users behaviour when typ-ing, illustrates individual characteristics behind the computer screen. In this paper, we propose to use this application or technology along with a keypad to determine the construction workers’ attitude during work-ing hours, whether they have been working within a reasonable time or otherwise. This could possibly be a way to monitor their validity period while working. Keywords: Biometrics, keystroke dynamics, pattern recognition, construction.

Abstract: — Continuous casting of steel is a process in which liquid steel is continuously solidified into semi-finished or finished product (slabs, blooms or billets). There are many problems associated with continuous casting shop which affect the casting process. A major problem is associated in continuous casting shop is breakout of molten steel. Breakout leads to temporary shutdown of caster, damage of machinery due to splash of molten steel, capital loss, safety hazards etc. In Bokaro steel plant a logical based breakout prediction system is used to predict the breakout. This system sometimes generates false alarm and sometimes even fail to generate an alarm before breakout. Also the logical model has lot of dependence on specific equipment, process and calibration. Neural network can be implemented for a better breakout prediction system. So, in this paper a back-propagation neural network model is developed for predicting the existence of primary cracks that might lead to a breakout. The network gets its input temperatures from thermocouples which are attached to the wide and narrow sides of the mould. The output of the neural network is either logic 1 (for presence of crack) or logic 0 (for no crack). Testing the network shows excellent result as evident from the confusion matrix and performance plot. The neural network model is validated by simulating in MatLab/Simulink. The developed network may be used effectively in predicting breakouts during continuous casting. Such effective prediction can go a long way in reducing production losses in steel manufacturing.

Abstract: Due to the introduction of an energy management system, a lot of existing manufacturing plants were equipped with energy measurement systems. With sufficient sample rates those retrofitted energy measuring systems could provide additional information beside active power and energy consumption. Each production plant is characterized by a process and product specific power consumption with an associated power signal. In this paper a method to determine the information content in power signals of milling operations is discussed. By using the cross correlation function and hidden markov models (HMM) for operation recognition and automatic derivation of energy key performance indicators (EnPI) can be realized. In addition, further production related key performance indicators (KPI) can be derived with pattern recognition in load and current profiles.

Abstract: In this paper, the optimal projection recognition (OPR) developed in our lab has been used to find the regularities of forming core-shell Co-Al Hydroxides superstructures.The criteria for predicting core-shell Co-Al Hydroxides superstructures can be obtained by using OPR method among different kinds of pattern recognition diagrams. The new samples predicted to be core-shell Co-Al Hydroxides superstructures were designed by using the inverse projection based on the OPR method. The predicted results agreed well with our experiments. Therefore, the work presented is very useful in the shape-controlled synthesis of core-shell Co-Al Hydroxides superstructures.

Abstract: This paper is concerned with an algorithm of determining a position of an object and its borders in an X-Ray image. The algorithm is based on a preliminary estimation of a histogram of given image. The information retrieved from estimation provides complementary parameters for further edge detection. As a result, this approach allows reducing the processing time. The future research and development of the algorithm will be aimed at object tracking in real-time systems.