Search

Data clustering are applied in various fields such as document classification, dental X-ray image segmentation, medical image segmentation, etc. Especially, clustering algorithms are used in satellite image processing in many important application areas, including classification of vehicles participating in traffic, logistics, classification of satellite images to forecast droughts, floods, forest fire, etc. In the process of collecting satellite image data, there are a number of factors such as clouds, weather, ... that can affect to image quality. Images with low quality will make the performance of clustering algorithms decrease. Apart from that, the parameter of fuzzification in clustering algorithms also affects to clustering results. In the past, clustering methods often used the same fuzzification parameter, m = 2. But in practice, each element should have its own parameter m. Therefore, determining the parameters m is necessary to increase fuzzy clustering performance. In this research, an improvement algorithm for the data partition with confidence problem and multi fuzzifier named as TS3MFCM is introduced. The proposed method consists of three steps namely as “FCM for labeled data”, “Data transformation”, and “Semi-supervised fuzzy clustering with multiple point fuzzifiers”. The proposed TS3MFCM method is implemented and experimentally compared against with the Confidence-weighted Safe Semi-Supervised Clustering (CS3FCM). The performance of proposed method is better than selected methods in both computational time and clustering accuracy on the same datasets

While the number of universities in Vietnam has increased dramatically over the past decade, the country's poor quality of higher education has received much attention in recent times. The increasing number of university graduates without jobs and the number of university lecturers switching to other jobs is attracting many studies to find the causes, including public service motivation, job satisfaction, and teaching performance of university lecturers. This study aims to enrich the research literature and examine the role of service motivation as a moderator variable in the relationship between job satisfaction and teaching effectiveness of Vietnamese university lecturers. This study was conducted through a cross-sectional survey using a purposive sampling technique (n=200). Multivariable linear regression analysis and moderator regression were applied to test the proposed research hypotheses. Research results show a positive and significant relationship between satisfaction at work, motivation to serve the public, and teaching effectiveness of Vietnamese university teaching. In particular, public service motivation moderates the relationship between job satisfaction and the teaching performance of university lecturers in this country.

Most of the current attribute reduction methods use the measure to define the reduct, such as positive region of rough set theory (RST), granular information entropy, and granular distance measures. However, the reducts defined based on the measures are still limited in sizes because of the information conservation property of the reduct compared to the original dataset. Dealing with this matter, this paper proposes a new approach using the intuitionistic fuzzy topology (IFT) to develop an attribute reduction method to find the reduct with the optimal size through topology. Specifically, the IFT base and IFT sub-base structures are proposed based on the pre-order relation. Secondly, we propose a new measure to evaluate the significance of the attribute based on the IFT sub-base. Lastly, we propose a new definition of the reduct based on the IFT base and design two new algorithms based on Heuristic approaches. The theoretical and experimental results show that the proposed method is efficient in size and accuracy of the reduct

The tolerance rough set model is an effective tool to solve attribute reduction problem directly on incomplete decision systems without pre-processing missing values. In practical applications, incomplete decision systems are often changed and updated, especially in the case of adding or removing attributes. To solve the problem of finding reduct on dynamic incomplete decision systems, researchers have proposed many incremental algorithms to decrease execution time. However, the proposed incremental algorithms are mainly based on filter approach in which classification accuracy was calculated after the reduct has been obtained. As the results, these filter algorithms do not get the best result in term of the number of attributes in reduct and classification accuracy. This paper proposes two distance based filter-wrapper incremental algorithms: the algorithm IFWA_AA in case of adding attributes and the algorithm IFWA_DA in case of deleting attributes. Experimental results show that proposed filter-wrapper incremental algorithm IFWA_AA decreases significantly the number of attributes in reduct and improves classification accuracy compared to filter incremental algorithms such as UARA, IDRA.

Attribute reduction from decision tables has been much focused in recent years in which the incremental methods of the tradition rough set and extended models are mostly used for adding, removing, or updating the object or attribute set. However, when dealing with the dynamic decision tables, the existing incremental methods do not recalculate information which has been added into the decision table. In this article, we propose some new incremental methods using the hybrid filter–wrapper with fuzzy partition distance on fuzzy rough set. Experimental results indicate that the proposed algorithms decrease significantly the cardinality of reduct as well as achieve higher accuracy than the other filter incremental methods such as IV-FS-FRS-2, IARM, ASS-IAR, IFSA, and IFSD.

Many effective tools in fuzzy soft set theory have been proposed to handle various complicated problems in different fields of our real life, especially in decision making. Molodtsov’s soft set theory has been regarded as a newly emerging mathematical tool to deal with uncertainty and vagueness. Lattice ordered multi-fuzzy soft set (LMFSS) has been applied in forecasting process. However, similarity measure is not used in this application. In our research, similarity measure of LMFSS is proposed to calculate the similarity between two LMFSSs. Moreover, some of its properties are introduced and proved. Finally, an application of LMFSS in decision making using similarity measure is analysed.

In dental diagnosis, recognizing tooth complications quickly from radiology (e.g., X-rays) takes highly experienced medical professionals. By using object detection models and algorithms, this work is much easier and needs less experienced medical practitioners to clear their doubts while diagnosing a medical case. In this paper, we propose a dental defect recognition model by the integration of Adaptive Convolution Neural Network and Bag of Visual Word (BoVW). In this model, BoVW is used to save the features extracted from images. After that, a designed Convolutional Neural Network (CNN) model is used to make quality prediction. To evaluate the proposed model, we collected a dataset of radiography images of 447 patients in Hanoi Medical Hospital, Vietnam, with third molar complications. The results of the model suggest accuracy of 84% ± 4%. This accuracy is comparable to that of experienced dentists and radiologists.

This research problematizes the conception of time and space in online distance education. It argues that online distance education is constructed from different times and spaces, namely those as organized by the institutions and those as experienced by the distance learners. In essence, it seeks to unfold how these organizational time and space and the experienced time and space are connected or separated, from the learners’ perspective. It employs a narrative inquiry to recount the experience of a 32-year-old British man pursuing a distance learning course. In doing this, the research aims to identify how online learners are engaged with the course that they are taking with respect to time and space, as well as pinpointing the gaps that separate them from the course. With consideration of those aspects in mind, online distance courses could be more effectively organized in such a way that enhances student motivation, commitment and resilience, thus contributing to their overall experience of digital learning.

In the modern world, people care more about dental health care, and dentistry has an important role in our health. Using dental X-ray images, dentists can diagnose possible dental diseases and create an effective treatment for patients. In this chapter, we introduce several machine learning methods to segment the dental images to support dentists in dental disease diagnoses. The proposed methods have been implemented on the real dataset of radiography patients from Hanoi Medical University Hospital. The empirical results show that these methods have a higher performance than the related ones through various validity indices. The content of this chapter presents the results of our research that has been performed since 2015.

Artificial intelligence has been applied in various fields including medicine. Cancer is one of the most common and dangerous diseases that need to be diagnosed for the best treatment. Herein, we introduce a new model using complex fuzzy inference system (CFIS) for colorectal cancer diagnosis. The time series characteristic of colorectal disease is signification in examination, diagnosis, and treatment. The model is implemented on a colonography dataset to evaluate the performance. The obtained results show that it gets high quality in comparison with some other compared methods.

In the current trend, people pay attention to healthcare services more and more. Liver-related diseases, same as other common diseases, have many effects on human health. Herein, we introduce a novel model to liver disease diagnosis problem based on the hybrid of fuzzy min–max neural network, semi-supervised clustering, and Genetic Algorithm. Our model is evaluated on four popular datasets from the University of California Irvine and one real dataset. Our proposed model has a better performance and much smaller number of hyper boxes compared with other available methods.

This study assesses the risk of exposure to hazardous chemical residues in pork meat, liver, and kidney collected at wet markets in Nghe An and Hung Yen provinces and discusses health impact implication. 514 pig feed, kidney, liver, and pork samples were pooled and qualitatively and quantitatively analyzed for tetracyclines, fluoroquinolones, sulphonamide, chloramphenicol, β-agonists, and heavy metals. We compare the results with current regulations on chemical residues and discuss health implications. Legal antibiotics were found in feed. Tetracycline and fluoroquinolones were not present in pork, but 11% samples were positive with sulfamethazine above maximum residue limits (MRL); 11% of packaged feed and 4% of pork pooled samples were positive for chloramphenicol, a banned substance; two feed, two liver, and one pork samples were positive for β-agonists but did not exceed current MRL; 28% of pooled samples had lead, but all were below MRL; and all samples were negative for cadmium and arsenic. Thus, the health risks due to chemical hazards in pork in Hung Yen and Nghe An seemed not as serious as what were recently communicated to the public on the mass media. There is potential exposure to sulphonamide, chloramphenicol, and β-agonists from pork. Risk communication needs to focus on banned chemicals, while informing the public about the minimal risks associated with heavy metals.

There are many factors affecting the quality of faculty that numerous researchers mentioned, analyzed and pointed out the different degrees of influence. The paper studies external factors affecting the quality of faculty such as Political regime, Management mechanism and Salary regime. These three factors have been existing in each country and make a different impact on the quality of faculty creating the unique characteristics of each country. The author builds a theoretical framework for research on the above-mentioned three ones and conduct a direct survey of 400 lecturers from 10 universities in Hanoi - the capital city of Vietnam. The survey is selectively done, in which its surveyed subjects are lecturers with doctorate or higher and their working time from 5 years or more. Through secondary data collected from published documents combined with those gained from direct investigations and surveys, the author contributes to clarifying the impact of the above-mentioned factors on the quality of Vietnamese faculty. From that result, he proposes a number of workable solutions on the policies with the hope of providing leaders and managers with scientific arguments so that they have more sound bases to appropriately adjust their policies to satisfy the essential needs of lecturers, which helps them have more opportunities to create and maximize their capacity. That also contributes to completing the policies on developing a team of high-quality Vietnamese faculty meeting the requirements of higher education in the modern and integrated social context.

The study evaluated the translation quality of the Vietnamese version of the film “Rio”, which was translated and dubbed in the project of MegaStar Media Ltd. Company, Vietnam in April 2011. To reach its aim, the study used four methods including analysis and comparison, which were based on Newmark’s model. In addition, statistical and observational methods were also applied to examine the synchronisation of each utterance and its translated version. The research instrument was “Aegisub”, a free open-source cross-platform subtitle editing program designed for timing and styling of subtitles. The researcher’s purpose was to see how well utterances in both versions of the flm are synchronised with each other. The research findings showed that in general, the film was well-translated in terms of structures, proper nouns, hierarchical pronouns, borrowed words and puns. Weaknesses of the translation were found in the title and several mistranslations. The study also revealed that the translated utterances were synchronised with the original ones quite well, especially in terms of duration.

This study comprises greenhouse gas (GHG) emission measurements on rice fields in the Vu Gia/Thu Bon Basin in Central Vietnam , as part of an interdisciplinary research project. The experiments were conducted in the delta lowland (DL) and hilly midland (HM), over three seasons (summer–autumn in 2011 and 2012; winter–spring season in 2012) with two water management treatments namely continuous flooding (CF) and alternate wetting and drying (AWD) . GHG emissions were dominated by methane (CH4) emissions showing large difference among seasons, whereas nitrous oxide (N2O) emissions were negligible and irrelevant in the overall carbon footprint . However, temporal patterns were not conclusive over the entire observation period. The observed seasonal CH4 emission rates ranging from 83 to 696 kg CH4 per ha were relatively higher compared to other field studies and can, at least in part, be attributed to organic amendments applied in accordance to farmers’ practice. The practice of AWD reduced CH4 emissions significantly (P < 0.0001) in all seasons, corresponding in average to 71 % of the emissions from CF. On the other hand, AWD had no significant effect on N2O emissions. The average seasonal CH4 emission in the DL (420 kg ha−1) was also significantly higher than in the HM (206 kg ha−1). Compared with IPCC default values, this data set from Vietnamese rice fields indicates a higher emission level and Scaling factor for AWD. The average grain yield across all sites and seasons increased by 4 % (P < 0.0002) relative to CF with the practice of AWD.

Medical diagnosis is considered as an important step in dentistry treatment which assists clinicians to give their decision about diseases of a patient. It has been affirmed that the accuracy of medical diagnosis, which is much influenced by the clinicians' experience and knowledge, plays an important role to effective treatment therapies. In this paper, we propose a novel decision making method based on fuzzy aggregation operators for medical diagnosis from dental X-Ray images. It firstly divides a dental X-Ray image into some segments and identified equivalent diseases by a classification method called Affinity Propagation Clustering (APC+). Lastly, the most potential disease is found using fuzzy aggregation operators. The experimental validation on real dental datasets of Hanoi Medical University Hospital, Vietnam showed the superiority of the proposed method against the relevant ones in terms of accuracy.