It is well known that human voice at the perceptual level consists of multimodality information. Therefore, a modality can be shared via neural emotion network through the independent stimuli processes. The expression and identification of emotions are significant steps for the human communication process. This process is biologically adaptive in a continuous manner, and for this reason, human voice identification becomes useful for classifying and identifying an effective specific characteristic between them. In this paper, we propose to identify the difference between the six essentials of human voice emotion. They will be generated using prosodic and spectral features extraction by utilizing Deep Neural Networks (DNNs). The result of our experiment has obtained accuracy as much as 78.83%. It presupposed that the higher intensity of emotions found in the sound sample would automatically trigger the level of accuracy as same as a higher one. Moreover, gender identification was also carried out along with the approximate accuracy at 90%. Nevertheless, from the learning process with the composition of 80:20, the training-testing data has obtained an exact accurate result by 100%.
The development of the dairy cows cattle industry has management standards ranging from feed management, breeding, and milk production. Inbreeding of dairy cows, Artificial Insemination (AI) is carried out from selected stud semen so that dairy cows have more opportunity to calve female cows. Dairy cows have indication of lust regularly called as estrous cycle. Good handling of AI during the estrous period, will increase the percentage pregnancy of the cow. A balanced plan between stud semen stock with AI needs in the farm will help the management of dairy cows. This research uses a dataset of 1,790 dairy cows with the collection of training and testing data. The stored data will be processed using the Multiple Logistic Regression method to be calculated as a result of the prediction ahead of the estrous cycle. Data on dairy cows that meet the processing requirements will be categorized by themselves. Variables in the dataset used in prediction calculations are time-series data. The results showed that the two features of the independent variables χ1 and χ2 have constant-coefficient values (βO) = 0.7927, (β1) = 0.0156, (β2) = 0.0000926 with model accuracy> 80%. Independent variable multinomial calculations produce an accuracy of 83.2%.
1 June 2022 in IAES International Journal of Artificial Intelligence (IJ-AI)
This study describes the methods for eliminating irrelevant features in speech data to enhance toxic speech classification accuracy and reduce the complexity of the learning process. Therefore, the wrapper method is introduced to estimate the forward selection technique based on support vector machine (SVM) and random forest (RF) classifier algorithms. Eight main speech features were then extracted with derivatives consisting of 9 statistical sub-features from 72 features in the extraction process. Furthermore, Python is used to implement the classifier algorithm of 2,000 toxic data collected through the world's largest video sharing media, known as YouTube. Conclusively, this experiment shows that after the feature selection process, the classification performance using SVM and RF algorithms increases to an excellent extent. We were able to select 10 speech features out of 72 original feature sets using the forward feature selection method, with 99.5% classification accuracy using RF and 99.2% using SVM.
29 May 2020 in Jurnal Nasional Teknik Elektro dan Teknologi Informasi
Dalam interaksi perilaku sosial, suara manusia menjadi salah satu saluran utama pembawa atribut ekspresi emosi kondisi mentalnya. Suara manusia merupakan hasil olah vokal yang tersusun dengan disertai urutan kata demi kata, hingga menghasilkan kalimat dalam rupa pola wicara yang memiliki makna ekspresi kondisi psikologisnya. Pola tersebut memberikan karakteristik khusus untuk proses identifikasi biometrik yang menggunakan pola wicara. Teknik visualisasi berupa citra spektrum telah terbukti mampu memberikan representasi hasil olah sinyal wicara. Makalah ini mengidentifikasi jenis emosi pada wicara menggunakan kombinasi fitur multi spektrum Hilbert dan cochleagram. Spektrum Hilbert merepresentasikan hasil transformasi Hilbert-Huang (HHT) untuk memproses sinyal emosi wicara yang nonlinear dan nonstasioner secara instan dengan fungsi mode intrinsik. Dengan meniru cara kerja komponen telinga luar dan tengah, sinyal emosi wicara dipecah menjadi frekuensi yang berbeda secara alami dengan hasil representasinya berupa cochleagram. Kedua masukan berupa spektrum wicara diproses menggunakan metode Convolutional Neural Networks (CNN) yang dikenal terbaik dalam mengenali data citra karena merepresentasikan mekanisme kerja retina manusia, serta metode Long Short-Term Memory (LSTM). Berdasarkan hasil uji coba dengan tiga himpunan data (dataset) publik emosi wicara yang terbagi ke dalam delapan kelas emosi, diperoleh akurasi sebesar 90,97% dengan CNN dan 80,62% dengan LSTM.
Computer games have become a special attraction for some people. Every computer game has the same important structure including the use of images and sounds, objects that interact visually on the screen, and repeatedly update the display per second according to the simulated situation. One component in computer games is having objects that interact visually so that players can understand the game's storyline. One important structure in modern games is the presence of sound to enhance emotional feelings that can trigger feelings so that it can be used as an alternative for media rehabilitation for disabled people. However, for people with disabilities they have problems playing games that they like because of the limitations of the game control system so that in the development of game control systems biological and physiological sensors are added, one of which is voice control technology. Voice recognition is a system that has the ability to understand human speech in this study. We make computer games with the FPS genre using a sound control system created using the Unity Windows Speech Library engine from Unity3D 5.5 as a game engine to create games with voice recognition system facilities in it.
22 September 2020 in International Journal of Interactive Mobile Technologies (iJIM)
Nowadays, the fingerprint scanner widely used to records attendance. However, this technology has a weakness. Much research has done to improve the attendance system by utilizing mobile technology, like usage a fingerprint smartphone and location by GPS sensor to validate user location manually. In this research, we developed an application to enhance the records attendance system with a smartphone by crossing numbers to verify user position automatically, which implemented in a mobile app. This application using the PNPOLY method for detecting the location of the user inside of the polygon area predetermined. This method is part of the crossing number algorithm for increasing x and fixed y from point P, which x is latitude, and y is a longitude. The result of the experiment demonstrated that the percentage of successful validate user coordinate inside edges of the polygon boundary is 87%, depending on the GPS sensor embedded into a mobile device.