K- nearest neighbour (KNN)

Classification is one of the most predominant tasks for wide range of applications such as Sentiment analysis in text, voice recognition, image recognition, genetic engineering, data classification etc. Though many efficient classification algorithms have been introduced in the past few decades, due to the drastic increase in the amount of data generated across industry and academia there is a demand for classification algorithms with very high accuracy and robustness. This paper presents a new approach to enhance the accuracy of the classifier by combining Support Vector Machine (Classification algorithm) with K-Means Clustering algorithm and, finally using K Nearest Neighbours to make optimal choice on the classification problem .Experiments have shown that this new methodology has increased the accuracy of the classification problem and thus serves the intended purpose.

Parkinson's disease is a central nervous-system disorder. 90% of people with parkinson disease are reported to have speech and voice disorders. Vocal folds are normally weakened by this disorder and the patient talks improperly. Various elements of the speech patterns of healthy people and those with parkinson disease were studied for prediction of parkinson's disease. Optimized features affecting the data classification process were then identified using genetic algorithms and the KNN classification method was used to eventually classify the data based on different numbers of optimized features.

'El Diario de Juárez' is a local newspaper in a city of 1.5 million Spanish-speaking inhabitants that publishes texts of which citizens read them on both a website and an RSS (Really Simple Syndication) service. This research applies natural-language-processing and machine-learning algorithms to the news provided by the RSS service in order to classify them based on whether they are about a traffic incident or not, with the final intention of notifying citizens where such accidents occur. The classification process explores the bag-of-words technique with five learners (Classification and Regression Tree (CART), Naïve Bayes, kNN, Random Forest, and Support Vector Machine (SVM)) on a class-imbalanced benchmark; this challenging issue is dealt with via five sampling algorithms: synthetic minority oversampling technique (SMOTE), borderline SMOTE, adaptive synthetic sampling, random oversampling, and random undersampling. Consequently, our final classifier reaches a sensitivity of 0.86 and an area under the precision-recall curve of 0.86, which is an acceptable performance when considering the complexity of analyzing unstructured texts in Spanish.

In todays present day world, Globalization, demographic transition, lifestyles fashion modifications and nutritional meal patterns impacts people's nutrition. This painting tries to illustrate the evaluation of malnutrition primarily based totally on meals intakes, wealthy index, age group, schooling level, occupation, etc. There is no decrease in number of patients with undernourishment or over nutrition illness. This form of sickness reasons extra of 5,00,000 instances in India each 12 months and is the principal basis for dying in India. The approach of this work is to use agent Technology and Data mining technology. Uncovering the relationships in data mining has a prospect which leads to malnutrition when provided large data sets. In the primary stage the variables from non-clustered facts have become correlated with malnutrition indices. Further on, the statistics became parts into clusters. This became completed with the aid of using the k-nearest set of rules and logistic regression. Subsequently every cluster became analyzed the usage of the software program and the correlation outcomes became compared. The end result of supervised information mining strategies in nutrition database affords the nutrition repute of kids age below five. Choosing a extra appropriate set of rules that quality represents malnutrition in India could as a consequence be very useful. This work is beneficial to enhance nutrition stage of public fitness with the assist of presidency fitness offerings to the people.

Industrial safety stays basic worry in many nations. Industrial accidents cause human suffering as well as result in immense money related misfortune and ecological effects. To counteract these accidents in the future, the examination of the risk control plan is basic. In every industry, casualty and accident reports could be accessible for past accidents. This ―design research paper‖ proposes the Accident reports mining using NLP.

The fundamental cause of death among women in developed nations of the world is breast cancer. Breast cancer has been identified as one of the most deadly type of cancer prevalent among women globally. There have been a dramatic increase of breast cancer cases among women of recent. Machine learning algorithms are effective tools that have found application in the field of medical imaging for early detection and diagnosis of cancer. This paper investigate the performance of eight (8) machine learning algorithms that have been applied for timely detection of breast cancer. Diagnosing breast cancer involves making a distinction between benign and malignant breast lumps. Our experimental results indicated that Support Vector Machine (SVM) have the best performance in term of classification accuracy (97.07%) and lowest error rate compared to Radial Based Function (96.49 %), Simple Linear Logistic Regression Model (96.78%), Naïve Bayes (96.48%), k-Nearest Neighbour (96.34%), AdaBoost (96...

We suggest a method for defining the hand movements or Mudras of Bharatanatyam. This requires a pre-processing stage in which a skin-based segmentation is performed to obtain the boundary of the hand. The extraction process of the function involves obtaining the chaincode of the entire contour of the hand followed by normalization. It also involves extracting the Euclidean distance from the centroid over 360 degrees to the outermost limits of the side. Extracted features from the training images are used to create four Naïve Bayes, KNN, Logistic Regression, Multiclass SVM recognition models. The method displays an accuracy of 88.47%, 87.06%, 89.83%, 92.3% using Naïve Bayes, KNN, Multiclass SVM, Logistic Regression, respectively. We proposed here the framework for identifying other mudras and to incorporate facial expression recognition and posture recognition, and to integrate the modules. Using enhanced noise reduction technique can also increase device efficiency.

There is a long lineage in neighbourhood research that has underpinned sustained academic and policy interest in the UK centred on understanding how spatial ‘clusters’ of neighbourhood-based deprivation might be destabilised. This has seen the privileging of composite indices in the analysis of deprivation which have been criticised for fostering a common perception that deprived neighbourhoods are homogeneous in terms of their compositions and underlying structures. Such indices have also been criticised for being ineffective at capturing temporal change, providing only static snapshots of deprivation at particular points in time. This paper focuses on patterns of deprived neighbourhood change in the Greater Manchester city-region between 2001 and 2007. It develops a typology of neighbourhood change that is triangulated with three complementary typologies capturing the socioeconomic and demographic compositions of deprived neighbourhoods; the functional roles played by deprived neighbourhoods in redistributing population through migration; and the spatial contexts in which deprived neighbourhoods are located. The analysis reveals that an over reliance on static indices to measure deprivation has long-served to conceal complexities in the way that deprived neighbourhoods change, owing to their variable structures and contexts. It illustrates the danger that lies in treating all deprived neighbourhoods in the same way.

During the past few years, time series models and neural network models are widely used to predict traffic flow and traffic congestion based on historical data. Historical data traffic from sensors is often applied to time series prediction or various neural network predictions. Recent research shows that traffic flow pattern will be different on weekdays and weekends. We conducted a time series prediction of traffic flow on Monday, using data on weekdays and whole days data. Prediction of short time traffic flows on Monday based on weekdays data using k-NN methods shows a better result, compared to prediction based on all day’s data. We compared the results of the experiment using k-NN and Neural Network methods. From this study, we observed that generally, using similar traffic data for time series prediction show a better result than using the whole data.

Three algorithms for the forecasting of energy consumption at individual EV charging outlets have been applied to real world data from the UCLA campus. Out of these three algorithms, namely k-Nearest Neighbor (kNN), ARIMA, and Pattern Sequence Forecasting (PSF), kNN with k=1, was the best and PSF was the worst performing algorithm with respect to the SMAPE measure. The advantage of PSF is its increased robustness to noise by substituting the real valued time series with an integer valued one, and the advantage of NN is having the least SMAPE for our data. We propose a Modified PSF algorithm (MPSF) which is a combination of PSF and NN; it could be interpreted as NN on integer valued data or as PSF with considering only the most recent neighbor to produce the output. Some other shortcomings of PSF are also addressed in the MPSF. Results show that MPSF has improved the forecast performance.

The fundamental cause of death among women in developed nations of the world is breast cancer. Breast cancer has been identified as one of the most deadly type of cancer prevalent among women globally. There have been a dramatic increase of breast cancer cases among women of recent. Machine learning algorithms are effective tools that have found application in the field of medical imaging for early detection and diagnosis of cancer. This paper investigate the performance of eight (8) machine learning algorithms that have been applied for timely detection of breast cancer. Diagnosing breast cancer involves making a distinction between benign and malignant breast lumps. Our experimental results indicated that Support Vector Machine (SVM) have the best performance in term of classification accuracy (97.07%) and lowest error rate compared to Radial Based Function (96.49 %), Simple Linear Logistic Regression Model (96.78%), Naïve Bayes (96.48%), k-Nearest Neighbour (96.34%), AdaBoost (96...

Praca opisuje w sposób przeglądowy (zgodny z profilem czasopisma Informatyka) zagadnienia związane z rozpoznawaniem obrazów. Przedstawione jest zadanie rozpoznawania (wraz z jego charakterystyką), omówione jest pojęcie przestrzeni cech, pokazane są zalety stosowanej niekiedy transformacji cech i omówione są najpopularniejsze algorytmy rozpoznawania.

In this paper we describe a semi-supervised approach to person re-identification that combines discriminative models of person identity with a Conditional Random Field (CRF) to exploit the local manifold approximation induced by the nearest neighbor graph in feature space. The linear discriminative models learned on few gallery images provides coarse separation of probe images into identities, while a graph topology defined by distances between all person images in feature space leverages local support for label propagation in the CRF. We evaluate our approach using multiple scenarios on several publicly available datasets, where the number of identities varies from 28 to 191 and the number of images ranges between 1003 and 36 171. We demonstrate that the discriminative model and the CRF are complementary and that the combination of both leads to significant improvement over state-of-the-art approaches. We further demonstrate how the performance of our approach improves with increas...

Skin cancer is the most common among all cancers and its early diagnosis increases the patient's chances of healing. One of the ways to make this diagnosis is through dermatoscopy. Dermatoscopy is a technique that consists of recognizing structures present in the skin, not visible to the naked eye. Therefore, for assisting the use of dermatoscopy by health professionals, this work presents a device to support skin cancer recognition using the histogram of oriented gradients and machine learning, based on the ABCDE rule.

This report intends to classify three types of wine by thirteen of their physical and chemical properties.
The classification was done using K Nearest neighbour (KNN) and decision tree classifiers from sklearn in python. It was found that the wines could be classified with a
classification error rate of 0.057.
We found that the three wines were well classified by their physical and chemical properties, and decision tree classifier performed best with the data.

This research demonstrates that transmission line faults can be classified automatically according to their underlying cause, and lays a foundation for operational classification of transmission line faults in system control centres. The transmission line fault waveforms are characterised by instantaneous symmetrical component analysis to describe the transient and steady state fault conditions. Using a large fault record and waveform database, classification features based on the waveform and external environmental characteristics have been identified to develop single-nearest-neighbour classifiers that identify the underlying cause of transmission line faults, and good classification accuracy has been achieved.

With the advancement of internet technology, the numbers of threats are also rising exponentially. To reduce the impact of these threats, researchers have proposed many solutions for intrusion detection. In the literature, various machine learning classifiers are trained on older datasets for intrusion detection which limits their detection accuracy. So, there is a need to train the machine learning classifiers on latest dataset. In this paper, UNSW-NB15, the latest dataset is used to train machine learning classifiers. On the basis of theoretical analysis, taxonomy is proposed in terms of lazy and eager learners. From this proposed taxonomy (FPR) on UNSW-NB15 dataset and comparative analysis of these machine learning classifiers is carried out. The experimental results show that RF classifier outperforms other classifiers.

Clinical predictions using clinical data by computational methods are common in bioinformatics. However, clinical predictions using information from genomics datasets as well is not a frequently observed phenomenon in research. Precision medicine research requires information from all available datasets to provide intelligent clinical solutions. In this paper, we have attempted to create a prediction model which uses information from both clinical and genomics datasets. We have demonstrated multiclass disease predictions based on combined clinical and genomics datasets using machine learning methods. We have created an integrated dataset, using a clinical (ClinVar) and a genomics (gene expression) dataset, and trained it using instance-based learner to predict clinical diseases. We have used an innovative but simple way for multiclass classification, where the number of output classes is as high as 75. We have used Principal Component Analysis for feature selection. The classifier predicted diseases with 73% accuracy on the integrated dataset. The results were consistent and competent when compared with other classification models. The results show that genomics information can be reliably included in datasets for clinical predictions and it can prove to be valuable in clinical diagnostics and precision medicine.

There are more than thousands of insurance companies in the world which handles large amount of data. Insurance fraud has become the most common among the organizations across the industries. Insurance industry is one among the most growing industries hence fraud detection becomes very important in this current world. Fraud detection can be implemented in various fields like banking, insurance, financial sectors and information security systems. There are many approaches by which fraud can be detected. In this paper, we use various techniques of machine learning for the detection of vehicle insurance fraud. We make use of Random forest and KNN algorithm for the accuracy detection the insurance fraud. The performance calculation is done by calculation of confusion matrix.

—Early detection of cancer is the most promising way to enhance a patient's chance for survival. This paper presents a computer-aided classification method using computed tomography (CT) images of the lung based on ensemble of three classifiers including MLP, KNN and SVM. In this study, the entire lung is first segmented from the CT images and specific features like Roundness, Circularity, Compactness, Ellipticity, and Eccentricity are calculated from the segmented images. These morphological features are used for classification process in a way that each classifier makes its own decision. Finally, majority voting method is used to combine decisions of this ensemble system. The performance of this system is evaluated using 60 CT scans collected by Lung Image Database Consortium (LIDC) and the results show good improvement in diagnosing of pulmonary nodules.

Developing and nurturing talented employees costs enormous amounts of work time, money, and
company performance. In addition, training and adaptation of employees consume time and money.
Therefore, estimating the employee turnover rate is vital for talent management. To estimate employee
turnover, the approaches applied within the company and the employees and work environments must
be profiled. Today, many companies ignore these approaches in determining the source of the problem.
Thanks to the latest developments in technology, artificial intelligence is now included in all business
lines. An important branch of artificial intelligence is algorithms called machine learning. Machine
learning is an advanced computational algorithm designed to mimic human intelligence by learning
from the surrounding environment. In this article, the estimation of employee turnover probability was
calculated with the K-nearest neighbor algorithm, one of the machine learning algorithms, on the
employee data set created through IBM Watson analysis software. Through a robust and comprehensive
evaluation process, the performance of this machine learning method for predicting the probability of
employee turnover was analyzed and determined using statistical methods. However, this method is a
reliable guide for examining large and complex human resources datasets.

In recent years, the vision-based innovation of hand motion acknowledgment is a significant piece of human computer interaction (HCI).In the last decades; keyboard and mouse play a significant role in human-computer interaction. However, owing to the rapid development of hardware and software, new types of HCI methods have been required. In particular technologies, such as speech recognition and gesture recognition receive great attention in the field of HCI. Hand gesture recognition is very significant for human-computer interaction. On survey many models were used to recognize hand gestures with different custom images from various datasets captured by camera. One of the approaches that highly used in image feature extraction is Convolution neural network (CNN). In this work, we present a novel real-time method for hand gesture recognition. In our framework, the hand gesture is detected from the trained dataset of images. Then, the palm and fingers are segmented so as to detect and recognize the fingers. Finally, a rule classifier is applied to predict the labels of hand gestures. The experiments on the data set of 2569 images show that our method performs well and is highly efficient. Finally we have shown the comparison among the CNN with Softmax and KNN classifier on the images which leads accurate result.

The construction industry has suffered for many years from productivity losses such as delays. The continual growth in complexity of construction projects such as highrise buildings in the 21st century further aggravates the issue. Thus, the construction industry continually seeks for smarter and intelligent ways to solve existing productivity issues. This study presents a comparison of an early model (Bromilow’s Time-Cost Model) to a more contemporary approach (k-Nearest Neighbors) in predicting the construction duration of high-rise buildings. The performance of both methods have been compared by means of the correlation coefficient, root mean squared error (RMSE) and mean absolute percentage error (MAPE). Interestingly, the results showed that the predictive capability of the BTC model was comparable to that of KNN. Though, KNN performed better with correlation coefficient (0.83), RMSE (3.45) and MAPE (22.04%) compared to the BTC model with correlation coefficient (0.81), RMSE (5.05) and MAPE (22.73%) respectively. Despite the predictive capabilities of the two techniques investigated in this study, future research may seek to explore the capabilities of more powerful machine learning techniques, as well as a variety of case studies.

The aim of this project is to implement the heart disease prediction application. Many people all over the world like nearly 60% of the world's population are now-a-days suffering from heart disease. Heart Disease Prediction system is an android application which helps the users for the easy prediction, prevention and curing of the disease. An android application gets the disease name as the output based on the data provided by the user or patient. Android application is also used to get the preventive measures like nearby doctor details, hospitals details and location for hospitals. Proposed system consists of an intelligent system which works on the machine learning algorithms like KNN. The data entered by the user is compared with some existing standard datasets to get probability. KNN used to find the probability.

A Phonocardiogram or PCG is a plot of high fidelity recording of the sounds and murmurs made by the heart with the help of the machine called phonocardiograph. It has developed continuously to perform an important role in the proper and accurate diagnosis of the defects of the heart. As usually with the stethoscope, it requires highly and experienced physicians to read the phonocardiogram. A diagnostic system based on Artificial Neural Networks (ANN) is implemented as a detector and classifier of heart diseases. The output of the system is the classification of the sound as either normal or abnormal, if it is abnormal what type of abnormality is present. In this paper, Based on the extracted time domain and frequency domain features such as energy, mean, variance and Mel Frequency Cepstral Coefficients (MFCC) various heart sound samples are classified using Support Vector Machine (SVM), K Nearest Neighbour (KNN), Bayesian and Gaussian Mixture Model (GMM) Classifiers. The data used in this paper was obtained from Michigan university website.

This article presents an innovative research methodology that enables the efficient classification of cardiac disorders (17 classes) based on ECG signal analysis and an evolutionary-neural system.

From a social point of view, it is extremely important to prevent heart diseases, which are the most common cause of death worldwide. According to statistical data, 50 million people are at risk for cardiac diseases worldwide. The subject of ECG signal analysis is very popular. However, due to the great difficulty of the task undertaken, and high computational complexity of existing methods, there remains substantial work to perform.

This research collected 1000 fragments of ECG signals from the MIH-BIH Arrhythmia database for one lead, MLII, from 45 patients. An original methodology that consisted of the analysis of longer (10-s) fragments of the ECG signal was used (an average of 13 times less classifications). To enhance the characteristic features of the ECG signal, the spectral power density was estimated (using Welch’s method and a discrete Fourier transform). Genetic optimization of parameters and genetic selection of features were tested. Pre-processing, normalization, feature extraction and selection, cross-validation and machine learning algorithms (SVM, kNN, PNN, and RBFNN) were used.

The best evolutionary-neural system, based on the SVM classifier, obtained a recognition sensitivity of 17 myocardium dysfunctions at a level of 90.20% (98 errors per 1000 classifications, accuracy = 98.85%, specificity = 99.39%, time for classification of one sample = 0.0023 [s]). Against the background of the current scientific literature, these results are some of the best results to date.

High-rise buildings, which have become a significant part of the urban habitat, is particularly notorious for their delayed completion times. Though, there exists a plethora of studies on construction delays, the problem however is insufficient research on prescriptive methods to mitigate delays. Thus, this study sought to employ Machine Learning (ML) techniques to learn from historical data on high-rise construction to forecast potential delay times. An input data containing 9 features, and 12 cases was used. Initially five feature sets were built based on the recursive feature elimination process. Further to that was the classification process that employs the following ML techniques: Multi-Linear Regression Analysis (MLRA), k-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), and Support Vector Machines (SVM) to determine delay times. The predictive performance of these techniques was measured using their correlation co-efficient (R2) and their Root Mean Squared Errors (RMSE). The best three models according to the ML techniques used was SVM with 2 features (R2 0.56, RMSE 1.6), ANN with 2 features (R2 0.49, RMSE 1.83), and KNN with all features (R2 0.46, RMSE 1.71). To seek improvement of the predictive performance of the models developed, the three best performing models were combined using fixed and trained rules. The results showed an improvement for a fixed rule based on the minimum values with (R2 0.59, RMSE 1.65). The study has significant implications in the risk management process of high-rise projects to avoid delays. The originality is evident in that this is the first study that employs ML in predicting construction delay times.

Generalized Information (GI) is a measurement of the degree to which a program can be said to generalize a dataset. It is calculated by creating a program to model the data set, measuring the Active Information in the model, and subtracting out the size of the model. Active Information allows GI to be usable with both exact and inexact models.

Agriculture is a major source of income for a very large population in India and a lot of people depend upon it both for livelihood and consumption of the produce obtained. Therefore, it is a very important sector. Diseases are a major threat to the crops. Diseases destroy the crop and thus reduce the yield and also the quality of the crops thereby decreasing the profits. The use of technology in the area of agriculture will reduce manual labor and increase the accuracy by decreasing the amount of error. The systems developed earlier have just been able to detect diseases of leaves, this system will use image processing and classifiers which include SVM, KNN and Random Forest to detect the diseases achieving an accuracies of up to 97% and then additionally a corresponding pesticide spray system based on Arduino UNO board, relay switches and pumps will spray pesticides according to the disease detected.

Context awareness was introduced in several fields in routine human activities. Healthcare systems are the most important ones among context-aware applications. The existence and awareness of the context made mobile device users conscious of physical environments or situations. Smart devices, armed with multiple sensors, can sense and react based on their environment, and become context-aware agents. Smart devices are ideal assistants that provide accurate solutions for the critical aspects of healthcare, and medical staff works as well as the closer up to date state
of the patient. In addition, hospital's staff members can communicate with the patients reliably and suitably by using smart devices offers. But the applications of healthcare have lack of standardization in handling the context and the perceived sensors data. To perceive the context, we can rely on sensors, which may be physical or virtual. More generally, our research will concern on contextual applications of healthcare that aroused increasingly important interest. To improve the user experience, the advantage of contextual data is aimed to take by context-aware
applications. A useful tool to reason about context is proved by using case-based reasoning (CBR) and fuzzy techniques to deal with lack of standardization in handling the context and uncertainty of data. On the other side, it could be interesting to analyse how context reasoning relates to CBR. To assess how CBR can be integrated with contextual information is the primary concern of our research study. So, in this paper, we concrete on the mobile application of healthcare that deals with contextual data by using CBR techniques to analyse the context data. It gives a perfect situation in a right way or prediction for providing accurate solutions for the critical aspect of healthcare and medical staff work. It can overcome the problem of the standardization for dealing with context data.

K-Nearest Neighbor (KNN) adalah suatu metode yang menggunakan algoritma supervised dimana hasil dari query instance yang baru diklasifikan berdasarkan mayoritas dari kategori pada KNN. Tujuan dari algoritma ini adalah mengklasifikasikan obyek baru bedasarkan atribut dan training sample. Classifiertidak menggunakan model apapun untuk dicocokkan dan hanya berdasarkan pada memori. Diberikan titik query, akan ditemukan sejumlah k obyek atau (titik training) yang paling dekat dengan titik query. Klasifikasi menggunakan voting terbanyak diantara klasifikasi dari k obyek.. algoritma KNN menggunakan klasifikasi ketetanggaan sebagai nilai prediksi dariquery instance yang baru.

The absence of prediction system that can provide prediction analysis on the graduation rate of students becomes the reason for the research on the prediction of the level of graduation rate of students. The number of students who graduate on time becomes indicator of success of universities. Many studies on predicting students on time graduation have been conducted. The Fuzzy K-Nearest Neighbor, a method to classify objects based on training data located closest to the object, and using data from teknokrat universities student graduates in 2009 until 2013 faculties of engineering and computer science was used in this study. Selection of the value of k in KNN algorithm became important because it would affect the performance of the algorithm KNN. Based on the results of measuring the performance of the algorithm by using cross validation, confusion matrix, it was found the value of k = 10 and the fuzzy K-Nearest Neighbor had an accuracy value of 77,35%. 1. PENDAHULUAN Data Mining didefinisikan sebagai proses penemuan pola dalam data. Berdasarkan tugasnya, data mining dikelompokkan menjadi deskripsi, estimasi, prediksi, klasifikasi, clustering dan asosiasi.[6] Selain itu data mining merupakan salah satu teknik yang dapat melakukan prediksi dengan teknik penggalian data. Penggalian data berdasarkan data pendidikan di universitas dapat meningkatkan kualitas pembelajaran Mahasiswa di universitas. Melakukan Prediksi Tentang prediksi tingkat kelulusan Mahasiswa sangatlah penting dimana informasi yang dihasilkan oleh hasil prediksi ini dapat dijadikan sebagai bahan pertimbangan bagi pihak manajemen program studi untuk melakukan langkah secara persuasif dalam rangka meningkatkan persentasi kelulusan Mahasiswa yang memenuhi standar mutu yang telah ditetapkan kampus. Prediksi dalam bentuk komputasi merupakan satu kegiatan matematis. Prediksi ini telah dilakukan bertahun-tahun sebelum penguasaan komputer, yaitu menggunakan kalkulator. Prediksi tingkat kelulusan Mahasiswa dapat membantu pihak manajemen dalam mengambil keputusan. Bagaimana menganalisa kelulusan Mahasiswa dan mendapatkan parameter terbaik dari metode yang digunakan untuk dapat memprediksi kelulusan Mahasiswa. Sebuah penelitian membahas tentang Analisis Prediksi Tingkat Pengunduran Diri Mahasiswa dengan Metode K-Nearest Neighbor. Dimana dalam penelitian yang dilakukan oleh penulis mengangkat masalah mengenai pentingnya analisis prediksi tentang pengunduran diri Mahasiswa di STIKOM UYELINDO Kupang karena menentukan prediksi tingkat pengunduran diri Mahasiswa dalam jumlah besar tidak mungkin dilakukan secara manual karena membutuhkan waktu yang cukup lama. Untuk itu dibutuhkan sebuah algoritma yang dapat mengkategorisasikan prediksi tingkat pengunduran diri Mahasiswa secara otomatis menggunakan komputer. Hasil yang didapat dari penelitian ini yaitu bertujuan untuk menghasilkan sebuah data yang dapat diuji untuk mendapat prediksi dan keakuratan klasifikasi [8].

The present article discusses various preprocessing techniques suitable for dealing with time series data for environmental science-related studies. The errors or noises due to electronic sensor fault, fault in the communication channel, etc., are considered here. Such errors or glitches that occur during the data acquisition or transmission phases need to be eliminated before it fed to the forecasting or classification systems. Computationally simple and efficient techniques are discussed here so that they can even be adopted for a hard real-time system environment. While adopting these techniques, we may also end up with some of the real genuine values, which may consider as an outlier. A special indicator function, the moving Inter Quartile Range (MIQR) algorithm, is proposed to overcome such special cases.

Sign language is a tool used by deaf for communication. They use different gestures to express their thoughts and communicate to people. Each gestures or movement of the hand has a special assigned meaning. Previous studies were conducted on hand gestures using Kinect camera, detection gloves, and leap motion controller to improve the accuracy in detection of the implied meanings. This study aims to develop a model that would increase the accuracy rate of detection, using a customized camera that addresses the background and lighting conditions. Moreover, the study will provide learning to those people who are not familiar in sign languages. The model were tested to 28 gestures together with the forming of words, it acquired an accuracy rate of 94.49%.

Nowadays, recommendation systems are used successfully to provide items (example: movies, music, books, news, images) tailored to user preferences. Amongst the approaches existing to recommend adequate content, we use the collaborative filtering approach of finding the information that satisfies the user by using the reviews of other users. These reviews are stored in matrices that their sizes increase exponentially to predict whether an item is relevant or not. The evaluation shows that these systems provide unsatisfactory recommendations because of what we call the cold start factor. Our objective is to apply a hybrid approach to improve the quality of our recommendation system. The benefit of this approach is the fact that it does not require a new algorithm for calculating the predictions. We are going to apply two algorithms: k-nearest neighbours (KNN) and the matrix factorization algorithm of collaborative filtering which are based on the method of (singular-value-decomposition). Our combined model has a very high precision and the experiments show that our method can achieve better results.

Million Song Data Set is the largest Dataset on Music till date and is developed in Columbia University. The main acoustic features are defined by the Echo Nest Analyze API. The API provides these for every “segment”, which are generally delimited by note onsets, or other discontinuities in the signal. The API estimates the tatums, beats, bars (usually groups of 3 or 4 beats) and sections. The MSD does not distribute raw acoustic signals, but does distribute a range of extracted audio features, many of which can be used for classification. Some audio features, like average loudness or estimated tempo, exist at the track-level and are straightforward to incorporate as classification features. We note one interesting segment-level feature that touches on fundamental aspects of music. Timbre refers to the musical “texture” or type of sound—the “quality that distinguishes different types of musical instruments or voices.” This is represented as 12-dimensional vectors that are the principal components of Mel-frequency cepstral coefficients (MFCCs); they represent the power spectrum of sound, and are derived from Fourier analysis and further processing. MFCCs are very commonly used in speech recognition and music information retrieval. Every track as a different number of N segments depending on its length—therefore the timbre data is a matrix in 12*1, where N varies extremely widely for every song, ranging from 400 to more than 1600 (average around 900). Also track level audio features such as loudness and tempo which captures the high level information of the audio. Tempo is defined as number of beats per minute, or BPM and loudness is a real value number describes the general loudness of the song.
We Implemented Naive Bayes, k-NN, Neural Networks and SVM on the Data Set to predict the Year of the Song.

( Alternatif Link download Buku Analisis Big Data: http://bit.ly/2x8ta9S )

Alhamdulillahhi robbil alamin, puji syukur kehadirat Allah SWT atas segala rahmat dan karunia-Nya dengan terselesaikannya penulisan buku ini dengan judul “Analisis Big Data”. Buku ini merupakan uraian untuk memudahkan pemahaman konsep, tingkat dasar sampai lanjut dalam sistem cerdas dan penerapannya melalui pemanfaatan teknologi Big Data, dengan mengedepankan keterampilan dalam pembuatan dan hasil implementasi dengan berbagai kombinasi algoritma berbasis sistem cerdas maupun dengan perpaduan berbagai macam tools untuk membangun ekosistem analisis Big Data yang powerfull. Konsep sederhana Analisis Big Data mencakup Volume, Velocity, dan Variety (3V), dan pengembangannya ada yang menyebut (7V) termasuk Volume, Velocity, Variety, Variability, Veracity, Value dan Visualization, atau 10V bahkan lebih dari itu, tetapi sebaiknya tidak membatasi pemahaman Big Data ini hanya dengan sedikit banyaknya istilah dari huruf V yang digunakan :). Kemudian dengan adanya ekosistem tersebut, jika dibutuhkan analisis sederhana maupun yang lebih kompleks, maka harapannya tidak akan ada kendala dari besarnya data yang diolah. Adanya kemajuan teknologi dalam hal penyimpanan, pengolahan, dan analisis Big Data meliputi (a) penurunan secara cepat terhadap biaya penyimpanan data dalam beberapa tahun terakhir; (b) fleksibilitas dan efektivitas biaya pada pusat data dan komputasi awan untuk perhitungan dengan konsep elastisitas dan penyimpanannya; serta (c) pengembangan kerangka kerja baru seperti Hadoop ecosystem (salah satu peluang bisnis yang besar untuk developer untuk saat ini dan ke depannya dalam rangka membangun ekosistem analisis Big Data yang sangat powerfull sekelas Cloudera, Hortonworks, etc), yang memungkinkan pengguna untuk mengambil manfaat dari sistem komputasi terdistribusi, misal untuk menyimpan sejumlah data yang besar melalui pemrosesan parallel, dukungan database NoSQL, dan komputasi berbasis streaming. Sehingga kemajuan teknologi ini telah menciptakan beberapa perbedaan yang sangat signifikan, misal dalam hal kecepatan maupun ketepatan dari hasil yang didapatkan antara analisis tradisional dengan tools yang bukan dengan konsep Big Data versus analisis modern untuk saat ini dan masa depan dengan membangun ekosistem Big Data yang sangat powerfull.
Penulis mengucapkan terimakasih yang sebesar-besarnya kepada kedua orang tua penulis, spesial kepada Istriku tercinta “Alfun Lailatul Musabbikha”, bapak ibu mertua, dik Wiwik, dik Ganda, kak Mat, kak Deri, Bude Gi, Pakde Dul, Bude Gani, Pak Abu, mbak Nik, dik Andre, Mbak As, Mbak Lia, Mas Mualif, Mbak Lis, Pakde Naji, Bulik Yul, Pakde Tasrun, Pakde Zen, Pakde Zud, Paklik Fiq, mas Bowo dan semua sanak saudaraku yang tak bisa kusebutkan seluruhnya, serta beberapa pihak yang telah membantu penyelesaian buku ini:
1. Para penulis artikel Analisis Big Data di forum, web, blog dan buku yang menjadi referensi buku ini untuk memberikan masukan yang sangat berharga sekali untuk perbaikan dan penyelesaian buku ini.
2. Mbak Efi Riyandani, yang telah banyak membantu penulisan buku, dan mahasiswa-mahasiswa terbaik saya semester Ganjil 2016/2017, yaitu: Maryamah, Moh. Fadel Asikin, Daisy Kurniawaty, Selly Kurnia Sari, Nanda Agung Putra, Ardisa Tamara Putri, Dhimas Anjar Prabowo, Listiya Surtiningsih, Raissa Arniantya, Brillian Aristyo Rahadian, Diva Kurnianingtyas, Dyan Putri Mahardika, Tusty Nadia Maghfira.
3. Mahasiswa-mahasiswa terbaik saya semester Ganjil 2017/2018, yaitu: Yessica Inggir F., Kholifaul K., Ni Made Gita D. P., Ema Agasta, Retiana Fadma P. Sinaga, Fachrul Rozy Saputra Rangkuti, Yunita Dwi Alfiyanti, Dyah Ayu Wahyuning Dewi, Annisaa Amalia Safitri, Sarah Aditya Darmawan, Danastri Ramya Mehaninda, Eka Novita Shandra, Fakharuddin Farid Irfani, Rio Cahyo Anggono, Robih Dini, Yulia Kurniawati, Novirra Dwi Asri, Muhammad Vidi Mycharoka, Vania Nuraini Latifah, Olivia Bonita, Eka Miyahil Uyun, Cusen Mosabeth, Evilia Nur Harsanti, Ivarianti Sihaloho.

Semoga kontribusi kalian menjadi ilmu yang barokah dan bermanfaat. Aamiin. :). Tidak ada gading yang tak retak. Maka penulis memohon kritik dan saran untuk perbaikan dan penyempurnaan buku ini. In Syaa Allah pada edisi berikutnya, kami akan memberikan manualisasi Map Reduce, Spark, etc. dari setiap algoritma pada setiap contoh kasusnya. Selamat membaca buku ini dan semoga bermanfaat.

Malang, 19 Juli 2016-24 Mei 2018

Penulis