Unsupervised Feature Learning for Speech Emotion Recognition Based on Autoencoder

Speech signals contain abundant information on personal emotions, which plays an important part in the representation of human potential characteristics and expressions. However, the deficiency of emotion speech data affects the development of speech emotion recognition (SER), which also limits the promotion of recognition accuracy. Currently, the most effective approach is to make use of unsupervised feature learning techniques to extract speech features from available speech data and generate emotion classifiers with these features. In this paper, we proposed to implement autoencoders such as a denoising autoencoder (DAE) and an adversarial autoencoder (AAE) to extract the features from LibriSpeech for model pre-training, and then conducted experiments on the Interactive Emotional Dyadic Motion Capture (IEMOCAP) datasets for classification. Considering the imbalance of data distribution in IEMOCAP, we developed a novel data augmentation approach to optimize the overlap shift between consecutive segments and redesigned the data division. The best classification accuracy reached 78.67% (weighted accuracy, WA) and 76.89% (unweighted accuracy, UA) with AAE. Compared with state-of-the-art results to our knowledge (76.18% of WA and 76.36% of UA with the supervised learning method), we achieved a slight advantage. This suggests that using unsupervised learning benefits the development of SER and provides a new approach to eliminate the problem of data scarcity.

Accelerating RepeatClassifier Based on Spark and Greedy Algorithm with Dynamic Upper Boundary

Transposable elements (TEs) represent quantitatively important components of genome sequences (e.g. 90% of the wheat genome), and play important roles in genome organization and evolution. The promotion of unsupervised annotation of transposable elements is of great significance. Classification is an important step in TE annotation, which summarize the information about the type or mechanism for the raw repetitive sequences. RepeatClassifier is a basic homology-based classification tool which compares the TE families to both the Repeat Protein Database (DB) and libraries of RepeatMasker. Unfortunately, RepeatClassifier is inefficient and takes a few days to classify the repetitive sequences of large genomes. Hence, we proposed Spark-based RepeatClassifier (SRC) which uses Greedy Algorithm with Dynamic Upper Boundary (GDUB) for data division and load balancing, and Spark to improve the parallelism of RepeatClassifier. Experimental results show that SRC can not only ensure the same level of accuracy as that of RepeatClassifier, but also achieve 42-88 times of acceleration compared to RepeatClassifier. At the same time, SRC shows excellent parallel performance when dealing with input datasets with unbalanced length distribution.

Segmentation of Brain Tumors from MRI Images Using Convolutional Autoencoder

The use of machine learning algorithms and modern technologies for automatic segmentation of brain tissue increases in everyday clinical diagnostics. One of the most commonly used machine learning algorithms for image processing is convolutional neural networks. We present a new convolutional neural autoencoder for brain tumor segmentation based on semantic segmentation. The developed architecture is small, and it is tested on the largest online image database. The dataset consists of 3064 T1-weighted contrast-enhanced magnetic resonance images. The proposed architecture’s performance is tested using a combination of two different data division methods, and two different evaluation methods, and by training the network with the original and augmented dataset. Using one of these data division methods, the network’s generalization ability in medical diagnostics was also tested. The best results were obtained for record-wise data division, training the network with the augmented dataset. The average accuracy classification of pixels is 99.23% and 99.28% for 5-fold cross-validation and one test, respectively, and the average dice coefficient is 71.68% and 72.87%. Considering the achieved performance results, execution speed, and subject generalization ability, the developed network has great potential for being a decision support system in everyday clinical practice.

An Analysis on Wind Speed Forecasting Result with the Elman Recurrent Neural Network Method

Weather factors in the archipelago have an important role in sea transportation. Weather factors, especially wind speed and wave height, become the determinants of sailing permits besides transportation’s availability, routes, and fuel. Wind speed is also a potential source of renewable energy in the archipelago. Accurate wind speed forecasting is very useful for marine transportation and development of wind power technology. One of the methods in the artificial neural network field, Elman Recurrent Neural Network (ERNN), is used in this study to forecast wind speed. Wind speed data in 2019 from measurements at the Badan Meteorolog Klimatologi dan Geofisika (BMKG) at Hang Nadim Batam station were used in the training and testing process. The forecasting results showed an accuracy rate of 88.28% on training data and 71.38% on test data. The wide data range with the randomness and uncertainty of wind speed is the cause of low accuracy. The data set is divided into the training set and the testing set in several ratio schemas. The division of this data set considered to have contributed to the MAPE value. The observation data and data division carried out in different seasons, with varying types of wind cycles. Therefore, the forecasting results obtained in the training process are 17% better than the testing data.

Prediction of Potential Evapotranspiration Using Temperature-Based Heuristic Approaches

The potential or reference evapotranspiration (ET0) is considered as one of the fundamental variables for irrigation management, agricultural planning, and modeling different hydrological pr°Cesses, and therefore, its accurate prediction is highly essential. The study validates the feasibility of new temperature based heuristic models (i.e., group method of data handling neural network (GMDHNN), multivariate adaptive regression spline (MARS), and M5 model tree (M5Tree)) for estimating monthly ET0. The outcomes of the newly developed models are compared with empirical formulations including Hargreaves-Samani (HS), calibrated HS, and Stephens-Stewart (SS) models based on mean absolute error (MAE), root mean square error (RMSE), and Nash-Sutcliffe efficiency. Monthly maximum and minimum temperatures (Tmax and Tmin) observed at two stations in Turkey are utilized as inputs for model development. In the applications, three data division scenarios are utilized and the effect of periodicity component (PC) on models’ accuracies are also examined. By importing PC into the model inputs, the RMSE accuracy of GMDHNN, MARS, and M5Tree models increased by 1.4%, 8%, and 6% in one station, respectively. The GMDHNN model with periodic input provides a superior performance to the other alternatives in both stations. The recommended model reduced the average error of MARS, M5Tree, HS, CHS, and SS models with respect to RMSE by 3.7–6.4%, 10.7–3.9%, 76–75%, 10–35%, and 0.8–17% in estimating monthly ET0, respectively. The HS model provides the worst accuracy while the calibrated version significantly improves its accuracy. The GMDHNN, MARS, M5Tree, SS, and CHS models are also compared in estimating monthly mean ET0. The GMDHNN generally gave the best accuracy while the CHS provides considerably over/under-estimations. The study indicated that the only one data splitting scenario may mislead the modeler and for better validation of the heuristic methods, more data splitting scenarios should be applied.

Training and Testing Data Division Influence on Hybrid Machine Learning Model Process: Application of River Flow Forecasting

The hydrological process has a dynamic nature characterised by randomness and complex phenomena. The application of machine learning (ML) models in forecasting river flow has grown rapidly. This is owing to their capacity to simulate the complex phenomena associated with hydrological and environmental processes. Four different ML models were developed for river flow forecasting located in semiarid region, Iraq. The effectiveness of data division influence on the ML models process was investigated. Three data division modeling scenarios were inspected including 70%–30%, 80%–20, and 90%–10%. Several statistical indicators are computed to verify the performance of the models. The results revealed the potential of the hybridized support vector regression model with a genetic algorithm (SVR-GA) over the other ML forecasting models for monthly river flow forecasting using 90%–10% data division. In addition, it was found to improve the accuracy in forecasting high flow events. The unique architecture of developed SVR-GA due to the ability of the GA optimizer to tune the internal parameters of the SVR model provides a robust learning process. This has made it more efficient in forecasting stochastic river flow behaviour compared to the other developed hybrid models.

Performance Evaluation of Spectrogram Based Epilepsy Detection Techniques Using Gray Scale Features

Electroencephalogram (EEG) is most common instrument for treatment and diagnosis of brain related diseases. Analysis of EEG signals for treatment of patient is time consuming and not easy task for neurologist. There is always a chance of human error. The purpose of this paper is to present an automatic detection model for epileptic seizure from EEG signals. To fulfill this objective, EEG signals are preprocessed and converted into spectrogram images using Short Time Fourier Transform (STFT). From this spectrogram images gray scale features are extracted. Support Vector Machine (SVM) with six different kernel functions and three data division protocols are utilized for performance evaluation of proposed model. Results show that quadratic SVM classifier has achieved highest classification accuracy.

PList-based Divide and Conquer Parallel Programming

This paper details an extension of a Java parallel programming framework – JPLF. The JPLF framework is a programming framework that helps programmers build parallel programs using existing building blocks. The framework is based on {\em PowerLists} and PList Theories and it naturally supports multi-way Divide and Conquer. By using this framework, the programmer is exempted from dealing with all the complexities of writing parallel programs from scratch. This extension to the JPLF framework adds PLists support to the framework and so, it enlarges the applicability of the framework to a larger set of parallel solvable problems. Using this extension, we may apply more flexible data division strategies. In addition, the length of the input lists no longer has to be a power of two – as required by the PowerLists theory. In this paper we unveil new applications that emphasize the new class of computations that can be executed within the JPLF framework. We also give a detailed description of the data structures and functions involved in the PLists extension of the JPLF, and extended performance experiments are described and analyzed.

Pengukuran Tingkat Kapabilitas Sistem Tata Kelola TI Menggunakan Cobit 5 dengan ISO 38500

<p align="center"><strong>Abstrak</strong><strong></strong></p><p><strong> </strong>Penggunaan sistem informasi dan teknologi informasi pada suatu organisasi sangat dibutuhkan karena sistem informasi sangat berpengaruh dalam menunjang kinerja suatu organisasi. Tata kelola sistem informasi sangat dibutuhkan untuk mencapai penyelenggaraan institusi yang lebih efisien dan efektif. Unit Pelaksanaan Teknis Teknologi Informasi dan Komunikasi (UPT TIK) Universitas Negeri Semarang (Unnes) memiliki beberapa bagian divisi yaitu divisi data, sistem informasi dan layanan, dan infrastruktur. Penelitian ini menggunakan COBIT 5 dengan ISO 38500 untuk audit sistem informasi tata kelola TI pada UPT TIK. Tujuan penelitian ini untuk mengukur tingkat kapabilitas tata kelola TI sehingga dapat dijadikan acuan dalam memperbaiki sistem tata kelola TI. Data penelitian diperoleh dari UPT TIK berupa visi misi institusi dengan dokumen pendukung antara lain dokumen rencana kerja dan kuisioner. Dari hasil penelitian audit menggunakan COBIT 5 dengan ISO 38500 diperoleh 17 Domain COBIT 5 dengan tingkat kapabilitas 2. Hal ini berarti pada tingkat managed proses, institusi telah melakukan perencanaan, pengontrolan dan penyesuaian terhadap proses TI yang sedang berlangsung. Penelitian ini menghasilkan nilai GAP sebesar 1 yang diperoleh dari selisih antara target yaitu 3 dengan tingkat kapabilitas sebesar 2. Dengan ini dapat dikatakan bahwa kombinasi COBIT 5 dan ISO 38500 dapat dijadikan acuan dalam memperbaiki sistem tata kelola TI.</p><p> </p><p align="center"><strong><em>Abstract</em></strong><strong><em></em></strong></p><p><strong><em> </em></strong><em>The usage of information systems and information technology in an organization is essential since information system is very important in supporting the performance of an organization. Information system governance is required to attain more efficient and effective performance of institutions. The technical implementation unit of information technology and communication (UPT TIK) State University of Semarang (Unnes) having several divisions that is the data division, information systems and services, and the infrastructure. This study applied COBIT 5 with ISO 38500 to audit information system of IT governance of UPT TIK. The purpose of this research is to measure the capabilities of IT governance so it can be used as reference in improving the information system management. The research data is obtained from UPT TIK in form of the vision and mission of institution with the supporting documents such as the document of work plan and questionnaires. The audit research using COBIT 5 with ISO 38500 obtained 17domains COBIT 5 with a capability level of 2. This means on the managed process level, institution have done planning, control and adjustments to the Information Technology on-going process. This research gained a GAP value of 1 from the margin between the targets of 3 with a capability level of 2. Therefore, it can be described that the combination of COBIT 5 and ISO 38500 can be used as a reference in improving IT governance systems.</em></p>