IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Detection of chronic kidney disease using binary whale optimization algorithm
Get PDFChronic kidney disease (CKD), a medical illness, is characterized by a steady deterioration in kidney function. A disease's ability to be prevented and effectively significantly treated depends on early diagnosis. The addition of filter feature selection to the machine learning algorithm has been done to detect CKD. However, the quality of its feature subset is not optimal. Wrapper feature selection can improve the quality of these feature subsets. Therefore, we proposed wrapper feature selection and binary whale optimization algorithm (BWOA) to enhance the accuracy of early CKD detection. We also make data improvements to improve accuracy, namely the preprocessing process with the median and modus techniques. We used a public dataset of 250 medical records of kidney sufferers and 150 completely healthy people. There are 24 features in this dataset. The test results showed that adding BWOA feature selection can increase accuracy. The proposed method produced an accuracy of 100%. Further research on these methods can be used to develop expert systems for early detection of CKD
Applying Bayesian networks in making intelligent applications for static and dynamic unbalance diagnosis
Get PDFOne of the problems often encountered in vibration analysis is unbalanced or imbalanced, namely the occurrence of a shift in the center of mass from the center of rotation to cause high vibrations. Unbalance itself is divided into two, namely static and dynamic unbalance. Identification of the right type of unbalance must be done because each type of unbalance requires different handling. Therefore, this study aims to design a system to identify the type of unbalance based on the required parameters. The system design determines the input and then builds an algorithm by combining vibration analysis methods and Bayesian networks (BN). Systems and applications are built using MATLAB. After the application is finished, testing is carried out using vibration measurement data obtained from a demo machine that has previously been conditioned for damage. The BN method has been successfully applied to the unbalance diagnosis system. When there is evidence of large amplitude in 1X the frequency spectrum and the value of the static phase range, the percentage of static unbalance from 26.8% increases to 75%. The system can predict all testing data quickly and precisely for the six experiments
Image classification in cultural heritage
Get PDFIn this paper, an automated supervised image classification technique, specifi- cally for classifying images in the cultural heritage domain, is developed. The developed technique classifies images according to a particular date, culture, people and historical age. The proposed technique consists of two stages, fea- ture extraction using the unsupervised segmentation technique, and the classi- fication stage using supervised classification techniques. Common features are extracted, and their histograms are applied to three classifiers: k-nearest neigh- bor (KNN), logistic regression (LR), and decision tree (DT). When our tech- nique was applied to a repository of images from cultural heritage, it showed reduced complexity and improved classification accuracy. DT has achieved a higher weighted average recall. This is also represented by the weighted av- erage f-measure where DT has obtained 0.81. DT has outperformed the other classifiers in terms of classifying heritage images
A multilingual semantic search chatbot framework
Get PDFChatbots are conversational agents which interact with users and simulate a human interaction. Companies use chatbots on their customer-facing sites to enhance user experience by answering questions about their products and directing users to relevant pages on the site. Existing chatbots which are used for this purpose give responses based on pre-defined frequently asked questions (FAQs) only. This paper proposes a framework for a chatbot which combines two approaches-retrieval from a knowledge base consisting of question answer pairs, combined with a natural language search mechanism which can scan through the paragraphs of text information. A feedback-based knowledge base update is implemented which provides continuous improvement in user experience. The framework achieves a result of 81.73 percent answer matching on stanford question answering dataset (SQuAD) 1.1 and 69.21 percent answer matching on SQuAD 2.0. The framework also performs well on languages such as Spanish (67.32 percent answer match), Russian (61.43 percent answer match), and Arabic (51.63 percent answer match). By means of zero shot learning
Balanced clustering for student admission school zoning by parameter tuning of constrained k-means
Get PDFThe Indonesian government issued a regulation through the Ministry of Education and Culture, number 51 of 2018, which contains zoning rules to improve the quality of education in school educational institutions. This research aims to compare the performance of the k-means algorithm with the constrained k-means algorithm to model the zoning of each school area based on the shortest distance parameter between the school location and the domicile of prospective students. The study used data from 2,248 prospective students and 22 public school locations. The results of testing the k-means algorithm in grouping showed the formation of non-circular patterns in the cluster membership with different numbers of centroid cluster members. In contrast, testing the constrained k-means algorithm showed balanced outcomes in cluster membership with a membership value of 103 for each school as the cluster center. The research findings state that the developed constrained k-means algorithm solves the problem of unbalanced data clustering and overlapping issues in the process of new student admissions. In other words, the constrained k-means algorithm can be a reference for the government in making decisions on new student admissions
Cost-effective internet of things privacy-aware data storage and real-time analysis
Get PDFIt has been estimated that about 20 billion internet of things (IoT) devices are currently connected to the Internet. This has led to voluminous data generation which makes storaging, managing, and decision making on data to be challenging. Hence, exposes users’ privacy to be vulnerable to unauthorized people. To address these issues, this research proposed cost-effective storage for keeping and processing the IoT data in real-time. The proposed Fframework utilized a reliable hybridised data privacy model to protect the personal information of users. An empirically evaluation was done to identify the best models using data k-anonymity (KA), l-diversity (LD), t-closeness (TC), and differential privacy (DP). The performance evaluation of cloud computing and fog computing was done through simulations. The results obtained show that the combination of two data privacy models: differential privacy and k-anonymity models performed better than any individual model and any other combined models in the protection of users’ personal information. Lastly, fog computing was found to perform better than the cloud in terms of latency, energy consumption, network usage and execution time. In conclusion, the current study strongly recommends the use of hybridised privacy model of differential privacy (DP) and k-anonymity (KA) for the protection of IoT generated data privacy
Intelligent classification and performance prediction of multi-text assessment with recurrent neural networks-long short-term memory
Get PDFThe assessment document at the time of study program accreditation shows performance achievements that will have an impact on the development of the study program in the future. The description in the assessment document contains unstructured data, making it difficult to identify target indicators. Apart from that, the number of Indonesian-based assessment documents is quite large, and there has been no research on these assessment documents. Therefore, this research aims to classify and predict target indicator categories into 4 categories: deficient, enough, good, and very. Learning testing of the Indonesian language assessment sentence classification model using recurrent neural networks-long short-term memory (RNN-LSTM) using 5 layers and 3 parameters produces performance with an accuracy value of 94.24% and a loss of 10%. In the evaluation with the Adamax optimizer, it had a high level of accuracy, namely 79%, followed by stochastic gradient descent (SGD) of 78%. For the Adam optimizer, Adadelta, and root mean squared propagation (RMSProp) have an accuracy rate of 77%
Detection and identification of un-uniformed shape text from blurred video frames
Get PDFThe identification and recognition of text from video frames have received a lot of attention recently, that makes many computer vision-based applications conceivable. In this study, we modify the picture mask and the original identification of the mask region convolution neural network and permit detection in three levels, including holistic, sequence, and at the level of pixels. To identify the texts and determine the text forms, semantics at the pixel and holistic levels can be used. With masking and detection, existences of the character and the word are separated and recognised. In addition, text detection using the results of 2-D feature space instance segmentation is done. Moreover, we explore text recognition using an attention-based optical character recognition (OCR) method with mask region convolution neural networks (R-CNN) to address and detect the problem of smaller and blurrier texts at the sequential level. Using attribute maps of the word occurrences in sequence to seq, the OCR method calculates the character sequence. At last, a fine-grained learning strategy is proposed to constructs models at word level using the annotated datasets, resulting in the training of a more precise and reliable model. The well-known benchmark datasets ICDAR 2013 and ICDAR 2015 are used to test our suggested methodology
Enhancing intrusion detection system using rectified linear unit function in pigeon inspired optimization algorithm
Get PDFThe increasing rate of cybercrime in the digital world highlights the importance of having a reliable intrusion detection system (IDS) to detect unauthorized attacks and notify administrators. IDS can leverage machine learning techniques to identify patterns of attacks and provide real-time notifications. In building a successful IDS, selecting the right features is crucial as it determines the accuracy of the predictions made by the model. This paper presents a new IDS algorithm that combines the rectified linear unit (ReLU) activation function with a pigeon-inspired optimizer in feature selection. The proposed algorithm was evaluated on network security layer - knowledge discovery in databases (NSL-KDD) datasets and demonstrated improved performance in terms of training speed and accuracy compared to previous IDS models. Thus, the use of the ReLU activation function and a pigeon-inspired optimizer in feature selection can significantly enhance the effectiveness of an IDS in detecting unauthorized attacks
The rise of artificial intelligence: a concise review
Get PDFArtificial intelligence (AI) has emerged as a transformative force with farreaching implications across various domains. This research review provides a concise analysis of the rise of AI, examining its evolution, applications, ethical considerations, and future prospects. The study traces the historical development of AI, highlighting key milestones and technological advancements that have propelled its growth. It explores the wide-ranging applications of AI in sectors such as healthcare, finance, transportation, manufacturing, human resource management and entertainment, showcasing its impact on efficiency, decisionmaking, and user experiences. Ethical considerations surrounding AI, including bias, privacy, and societal implications, are thoroughly discussed. The transformative potential of AI in shaping society is expolred, with insights into its effects on employment, education, governance, and societal challenges. Looking ahead, the review identifies emerging technologies and discusses challenges related to data privacy, security, and transparency. The research review concludes by emphasizing the importance of responsible and ethical development of AI, while underscoring the need for continued research and collaboration to fully harness its potential. This review serves as a valuable resource for researchers, and practitioners seeking a holistic understanding of the rise of AI and its implications