MOS Test Research Articles

Adaptive Classroom Berbasis IoT (Internet of Things), Manajemen Penggunaan Air Conditioner (AC) secara otomatis

Temperature and humidity are one of the comfort factors. According to the SNI standard, the comfortable temperature range is at 20.5°C-27.1°C. If the temperature is above 27.1°C, an Air Conditioner (AC) is needed to get the effective thermal comfort. AC installed in each PSTI FT UNRAM classroom is operated manually. This research implements Internet of Things (IoT) for automatic AC usage management. This IoT device is made using PIR sensor and DHT22 sensor, the MQTT protocol for data communication between the IoT device and the web system. Based on the testing scenario for the classroom containing students and the empty classroom that has been done, the IoT device is able to manage the AC usage automatically, so that the classroom can be called adaptive classroom. From the MOS testing that has been done, a value of 4.57 from a scale of 5, the system is feasible to use.

Adaptive Speech Coding Method Based on Singular Value Decomposition and Grey Wolf Optimization for Arabic Language

Speech coding plays a crucial role in maintaining speech quality while optimizing network resources and expediting transmission, as well as facilitating the storage of speech data. In this paper, an adaptive method for speech coding using singular value decomposition (SVD), grey wolf optimization (GWO), and run-length encoding (RLE) was proposed. The proposed method streamlines the speech matrix through preprocessing, converting it into short intervals. Subsequently, each interval undergoes decomposition using SVD, followed by optimization of compression quality using GWO. Finally, RLE is employed as the last step to increase space-saving. The developed method was conducted on two datasets: Quran and LibriSpeech using PSNR, PSEQ, and MOS tests. The results demonstrate promising outcomes, achieving space-saving up to 89.80, 84.04, 74.76, 67.24, and 59.52, respectively, for different values of quality (10, 20, 30, 40, and 50). GWO was used to optimize the quality factor which varies in each block, further increasing the space-saving up to 85.77. The average value of PSNR was equal to 21.3, MOS = 4.71, and PSEQ was equal to 3.95. Lastly, the RLE method effectively reduced the size of speech matrices, yielding a highly satisfactory space saving of up to 90.77, while maintaining excellent speech quality.

Оценка назальных симптомов в комплексе с нейрокогнитивным тестированием у пациентов с хроническим полипозным риносинуситом

The sinonasal symptoms inherent in chronic polypositis rhinosinusitis have a complex effect on the central structures of the patient's nervous system. The study of impaired cognitive and mnestic functions in this category of patients allows us to form a comprehensive understanding of the symptom complex of clinical manifestations and affect therapeutic tactics. Objective: to conduct a comprehensive comparative analysis of clinical and functional indicators characterizing nasal symptoms in patients with chronic polypous rhinosinusitis and cognitive tests in the pre- and postoperative period. Materials and methods: testing was performed in 45 patients with polypous rhinosinusitis (PRS) with a long history of the disease (M= 117 months). The age of the study group was from 22 to 65 years (M=48.964 years), without concomitant chronic pathology. The scope of clinical testing included the SNOT-22 sinonasal symptoms scale, Lund-Mackey tests and active anterior rhinomanometry (ml/sec). Changes in X-ray examinations (CT ONP) were evaluated on the Lund-Kennedy scale. Cognitive abilities were tested on the basis of the MoCA test in points with subsequent interpretation by a psychiatrist. The evaluation of the indicators was carried out before the surgical treatment of PRS, after 1 and 6 months. Results: The results were obtained to reduce the indicators of sinonasal symptoms on the SNOT-22 scale from M=31.42 before surgery and up to 4.04 points after 6 months; the Lund-Kennedy scale from M=7.87 to M=0.38 points; the Lund-Mackey scale from M=15.49 to M =0.47 points at the final stage. The indicators of active anterior rhinomanometry tended to increase from M=399.04 ml/sec before surgery and M=856.60 ml/sec after six months. Testing of neurocognitive disorders according to MoHS in patients preoperatively demonstrated average values of 21.49 points, which indicated the presence of mild variants of disorders. Further testing made it possible to obtain indicators of 25.38 points after 1 month, which were fixed during the study after 6 months. Conclusion. An interdisciplinary approach to the assessment of clinical manifestations in patients with polypous rhinosinusitis, based on the inclusion of testing of neurocognitive disorders in the study, allows for a more complete assessment of the impact of the pathological process on the patient's body. The inclusion of the MOS test in the complex of pre- and postoperative studies allows us to form an individualized approach to the implementation of therapeutic and rehabilitation measures in this category of patients.

Comparison of the effect of combined general and regional anesthesia on the cognitive functions of women of reproductive age: retrospective observational study

BACKGROUND: Depression and cognitive dysfunction in the postoperative period may be associated with pregnancy, surgery, and type of anesthetic support.
 OBJECTIVE: To perform a comparative assessment of the effect of combined general and regional anesthesia on memory and attention in pregnant and nonpregnant women.
 MATERIALS AND METHODS: The study involved 120 women of reproductive age who were admitted for surgery. According to the indications, they received various anesthesia types depending on their somatic status. The cognitive potential of the patients and indicators of memory and attention, anxiety, and depression were evaluated using specially selected tests before surgery and three days after surgery. The effect of anesthesia on pregnant women during planned operative delivery was studied, and planned interventions in gynecology were used for comparison.
 RESULTS: The MOS test scores in all groups were reduced, and they indicated a reduced cognitive potential in nonpregnant women [26.2 (26.9; 25.5) and 24 (24.59; 23.44)] under general anesthesia (p 0.003) and pregnant women [25.2 (25.7; 24.7) and 24.6 (25.36; 23.84)] under general anesthesia (p 0.004). After the operation under OA, the results worsened, and statistical differences were revealed. The level of attention in pregnant women decreased according to the results of the Wexler test after surgery in the general anesthesia group [4.5 (5.1; 3.9) and 3 (3.46; 2.54), p 0.006], and in the regional anesthesia group, the results decreased but to a lesser extent degree [5 (5.8; 4.2) and 3.5 (4.2; 2.8, p 0.005], showing statistical difference. According to the results of the Benton test after surgery in the general anesthesia group, visual short-term memory decreased in pregnant women [6.15 (6.75; 5.55) and 4 (4.86; 3.14), p 0.002], and in the regional anesthesia group, the results decreased, but to a lesser extent [6.2 (6.9; 5.5) and 4.5 (5.2; 3.8, p 0.012], and statistical differences were noted.
 CONCLUSION: The effect of combined general and regional anesthesia led to the development of cognitive dysfunction, increased depression, and changes in memory and attention.

The effect of obesity on cognitive function, anxiety and depression in pregnant patient during regional anesthesia

Background. A number of studies have associated aggravation of cognitive impairment, anxiety and depression in pregnant women with anesthesia. In addition, obesity during pregnancy itself is associated with an increased risk of developing these complications.The objective was to study the effect of obesity on cognitive function, anxiety and depression in pregnant women during regional anesthesia.Materials and methods. The study included 70 pregnant women who were admitted for planned delivery. Patients were divided into two groups: obese pregnant women (BMI≥ 30) (n = 35) and pregnant women with normal weight (BMI < 30) (n = 35). All patients underwent surgery under spinal anesthesia. The indicators of cognitive function, anxiety, and depression were evaluated using specially selected tests before surgery and on the third day of the postoperative period.Results. The development of obesity during pregnancy was accompanied by an impairment of cognitive functions. After surgery, in the BMI≥ 30 group, cognitive function according to the MOS test decreased from 25.1 (25.9; 24.2) to 24.3 (25.2; 23.4) points (p = 0.004), and in the BMI < 30 group, there were no statistical differences – 26.3 (27.1; 25,5) and 25.6 (26.5; 24.7) points (p = 0.071). In addition, the baseline indicators of anxiety and depression in obese pregnant women were higher in comparison with pregnant women with normal weight (p < 0.001). Performing a cesarean section under spinal anesthesia in all patients led to a decrease in anxiety and an increase in depression in the BMI≥ 30 group from 7.2 (8.1; 6.7) to 6.9 (7.5; 6.3) points (p = 0.004), and in the BMI < 30 group – from 6.5 (6.8; 6.2) to 6.1 (6.5; 5.7) points (p = 0.038).Conclusion. The presence of obesity during pregnancy was revealed in combination with impairment of cognitive functions even before surgery, after delivery under spinal anesthesia, cognitive dysfunction increased.

Perbandingan Certainty Factor dan Dempster Shafer dalam Sistem Pakar Diagnosis Penyakit Tanaman Padi Kerjasama dengan Petani

Rice is the staple food of the people in West Lombok. However, rice plants are susceptible to disease from pests, fungi and unfavorable environments. This study was constructed to compare the performance of the Dempster Shafer and Certainty Factor methods in an expert system for diagnosing rice plant diseases based on the knowledge of 3 experts. From the accuracy test performed, it was found that the accuracy value of the system using the Dempster Shafer method was 81.11% while using the Certainty Factor method an accuracy value was 69%, so it can be concluded that the expert system for diagnosing rice plant diseases using the Dempster Shafer method is more accurate than using Certainty Factor method. From the MOS test carried out, using the Dempster Shafer method and obtained an average result of 4.2 while using the Certainty Factor method obtained an average result of 4.63, so it can be concluded that the system with the Certainty Factor method is easier and more interesting to use even though the accuracy value is lower.

Analysis of the survey of voice synthesis technology

The original purpose of speech synthesis was to complete the task of converting from text to speech (TTS). With the application of deep learning models in this field of speech synthesis, the results of speech synthesis have gradually reached the level of human voice, which makes it widely used for voice assistant, navigation, reading, intelligent customer service, and many other aspects. In order to help readers expand more research ideas and understand the development process of speech synthesis technology and the ethical choices faced, this article introduces as much as possible in the development process of speech synthesis technology, several frameworks for optimization, as well as interpreting their respective advantages and disadvantages, summarize their approximate results obtained in the MOS test method and analyze the ethical issues that may be brought about by voice cloning technology.

VLSP 2021 - TTS Challenge: Vietnamese Spontaneous Speech Synthesis

Text-To-Speech (TTS) was one of nine shared tasks in the eighth annual international VLSP 2021 workshop. All three previous TTS shared tasks were conducted on reading datasets. However, the synthetic voices were not natural enough for spoken dialog systems where the computer must talk to the human in a conversation. Speech datasets recorded in a spontaneous environment help a TTS system to produce more natural voices in speaking style, speaking rate, intonation... Therefore, in this shared task, participants were asked to build a TTS system from a spontaneous speech dataset. This 7.5-hour dataset was collected from a channel of a famous youtuber "Giang ơi..."and then pre-processed to build utterances and their corresponding texts. Main challenges at this task this year were: (i) inconsistency in speaking rate, intensity, stress and prosody across the dataset, (ii) background noises or mixed with other voices, and (iii) inaccurate transcripts. A total of 43 teams registered to participate in this shared task, and finally, 8 submissions were evaluated online with perceptual tests. Two types of perceptual tests were conducted: (i) MOS test for naturalness and (ii) SUS (Semantically Unpredictable Sentences) test for intelligibility. The best SUS intelligibility TTS system had a syllable error rate of 15%, while the best MOS score on dialog utterances was 3.98 over 4.54 points on a 5-point MOS scale. The prosody and speaking rate of synthetic voices were similar to the natural one. However, there were still some distorted segments and background noises in most of TTS systems, a half of which had a syllable error rate of at least 30%.

Research on the Sound Quality Evaluation Method Based on Artificial Neural Network

For the improvement of the traditional evaluation effect of the automobile sound quality, an evaluation model of automobile sound quality is constructed based on BP neural network. The first is to introduce the basic principle of the BP neural network in detail. The second is to use the MGC parameters to establish the vehicle interior sound conversion model. The converted sound characteristic parameters are taken into the WORLD model to synthesize the new sound signals. Furthermore, the wavelet decomposition method is used to remove noise from the synthesized sound signals. Finally, a sound evaluation model based on BP neural network is established. The sound quality of automobiles can be better evaluated by carrying out the ABX test and MOS test in the field of sound conversion. For the newly synthesized sound signal and the target sound signal, it can be seen that the newly synthesized sound signal is more inclined to the target sound signal, and the sound quality is better. In addition, the sound quality is tested through loudness, roughness, sharpness, and level A in the field of sound quality evaluation. The final results show that the quality of newly synthesized sound is better, and the average errors of sound signals meet the sound standard. Therefore, the constructed sound conversion model and the sound evaluation model are feasible and effective.

Isolated Word-Based Spoken Dialogue System Using Odia Phones

Aims: To develop Spoken Dialogue System in Indian language with Voice response and voice based biometric feature. Backgrounds: Most of research works in spoken dialogue system are carried out in U.S. and Europe and currently, few government funding projects on spoken dialogue system (SDS) are carried out in Indian academic institutes. Objective: We have tried to use our developed spoken language system to eliminate the desktop clutter. It is very normal tendency of computer users to place the most frequently used files, folders, applications shortcuts on their computer’s desktop. Cluttering of desktop not only slows down the productivity of computer but also looks very messy and very difficult to find files as well. Therefore, we tried to use the spoken dialogue system to eliminate the desktop clutters in painless manner and the services are provided to the computer users by opening the files, folders and frequently used application of users in spoken command mode with voice response. Methods: In this research article, we have attempted to utilize an Indian spoken language for communication with spoken dialogue system. We have adopted a statistical machine learning algorithm called Hidden Markov Model for development of speech recognition engine. The speaker verification module is developed using fuzzy c-means algorithm. Speech synthesis is carried out using diphone corpus. Results: The speaker verification module has yielded satisfactory results with average accuracy of 66.2% using FCM algorithm. It is also seen that fundamental frequency and formant frequency carry the distinctive characteristics of speaker verification over Indian spoken language. The vital module of SDS i.e. speech recognition engine is developed by using HMM, a statistical algorithm. It is observed that word accuracy of ASR engine is 78.22 % and 62.31 % for seen and unseen users respectively. The voice response is given to the user in terms of synthesized speech. The audio quality of synthesized speech is measured using the MOS test. The MOS test value is found as 3.8 and 3.6 over two distinct groups of listeners. Conclusion: In this research paper, we have developed a spoken dialogue system based on Odia language phone set. We have integrated speaker verification module in order to provide additional biometric based security.

Voice and Position Simultaneous Communication System Based on Beidou Navigation Constellation

Considering China Beidou has unique two-way communication capability for short messages that are not available in other navigation systems such as GPS, a 600bps vocoder adapted to the short message channel of Beidou is developed. The sinusoidal excitation linear prediction algorithm is adopted by the vocoder to achieve voice communication with clear communication quality. Furthermore, a coordinate compression algorithm for processing positioning information is designed to provide more transmission space for speech encoded data. Based on the above-mentioned results, a communication system that only the Beidou navigation system is used to complete two-way secure voice and positioning simultaneous interpretation is realized. The system firstly uses a voice conversion program to convert the voice coded data obtained by the vocoder codec module into the Beidou short message data format; and then the voice code analysis program and the latitude and longitude analysis program is used to parse the voice code and location information; Finally, the experimental results of voice communication and positioning transmission are verified on the Beidou short message transceiver, and the subjective MOS test score indicates that the way is paved for the practical use of Beidou short message voice communication.

Rancang Bangun Aplikasi Hybrid Kondisi Jalan dan Fasilitas Kelengkapan Jalan di Kota Mataram

Hybrid Application of Roads and Road Fittings Facilities Conditions in the City of Mataram is an application consisting of web applications and mobile applications. The web application is used by Dinas Pekerjaan Umum dan Penataan Ruang of mataram city and Dinas Perhubungan of mataram city to manage condition data from city roads and also road fittings facilities in the city of Mataram and to receive complaints of damage from the public. While the mobile application is used by the people of the city of Mataram to see the condition of the road and road fittings facilities based on data from the department and the public can also make complaints about damage from roads and road facilities. System testing using the Black Box method and MOS testing. MOS test results indicate that the average rating of respondents from Dinas Pekerjaan Umum dan Penataan Ruang of Mataram City stated strongly agree and agree were 66.67% and 33.33%. The average rating of respondents from Dinas Perhubungan of Mataram City stated strongly agree and agree were 58,33% and 41,67%. The average rating of respondents from the community stated strongly agree and agree were 52,50% and 44,17%. Therefore, this research concluded that this system is eligible to use.

Adaptive Classroom Berbasis IoT (Internet Of Things), Saklar Lampu Berdasarkan Keberadaan Seseorang Dan Intensitas Cahaya

A switch is a device for disconnecting or connecting electricity, usually used on lights. The Informatics Engineering Study Program (PSTI) of the Faculty of Engineering of the University of Mataram (UNRAM) has several classrooms with light switches controlled by manual switches. Problems occur when classroom users do not turn off class lights after use or when the room has sufficient lighting from outside. The solution is by implementing an automatic control system based on Internet of Things (IoT) that uses several sensors as a trigger switch. The monitoring system created can display light intensity data, motion status, and lamp status in real time obtained from the electronic circuit of the system via the MQTT protocol. Based on the test scheme carried out, the system created can perform lamp management based on the conditions received. MOS testing produces value 4.58 from scale 5 shows that the system is feasible to use.

Sistem Pakar untuk Mendiagnosis Gangguan Mental pada Anak Menggunakan Metode Forward Chaining dan Certainty Factor

Mental health problems in children, such as stress, anxiety, or depression are real and these problems are as important as physical health problems, but many children do not get the care they need so an artificial intelligence technology such as an expert system can help diagnose the disorder mentally in children early. This research developed an expert system to diagnose mental disorders in children using the mobile-based Forward Chaining and Certainty Factor method that diagnoses 7 types of mental disorders in children from 46 symptoms obtained based on the knowledge of 3 experts. Based on the results of the black box testing states that the expert system that was built has had compatibility in terms of functionality. The results of the theoretical calculation test states that the calculation system of an expert diagnosis of a child's mental disorder is in accordance with the results of calculations done manually. In testing the accuracy of the system from 30 cases tested on 3 experts, the expert system that was built succeeded in producing system accuracy values ​​based on the final belief value of the three experts, based on the belief values ​​of experts 1, 2, and 3, respectively 91.11%, 96.67%, 96.67% and 80%. Furthermore, the results of MOS testing conducted on 35 respondents produce MOS of 4.12 from a scale of 5 where based on that value the expert system built is categorized into a good system.

A study on the ASMR effect of reed wind sound

The ASMR (Autonomous Sensory Meridian Response) method using sound is an acoustic healing method that stimulates the human hearing by using the sound during the five senses, thereby making the mind comfortable. The acoustic characteristics of the ASMR are being used in various ways as a very quiet and calm sound. In this paper, ASMR effect of reed wind sound is studied. Experimental results show that the sound of reeds in the reed forests that run across each other by the wind shows white noise components evenly distributed over the entire bandwidth of the human audible frequency band. To check the effect of reed wind on people, we tested physical information such as blood pressure and pulse, and conducted interviews and surveys. The results of the physical examination performed while listening to the reed winds showed that healing of the mind and body was comfortable. The result of the MOS test and the interview showed that the sound of the reed winds drove the thought out and the body and mind seemed to relax. Through this study, it was numerically proved that the reed winds produced by the reed forest winds have the effect of comforting and healing people.

Rancang Bangun Aplikasi Pencarian Bengkel Dan Cuci Motor Terdekat Berbasis Mobile

As the number of motorcycles users are increasing in Indonesia, so is the problems of the motorcycles that they face. On the other hand, the user of the smartphone is increasing as well. Based on that matters, we can develop an application in order to help the user to cope with their problem easier. The application can help the user to find the nearest garage and motorcycles wash, in order to solve the problems, such as dirty motorcycle, flat tire, the tire burst, oil change, etc. This application was designed to provide some information about the nearest garage, the route to the garage, reveal the comments and send a message to the owner of the garage. Meanwhile, the owner of the garage can see the comments about their garage, receive an order and see the customer location. The testing technique which was used in this research were blackbox and MOS testing. The result of blackbox testing showed that all features can be run as planned, meanwhile, the MOS testing showed the customer respondents value was 84,83% and the owner respondents value was 84,77%.
 Keywords: Garage location, Motorcycles, Problems of the Motorcycles, Order Service, MOS Testing.

Sistem Presensi Siswa berbasis Internet of Things menggunakan Sensor Sidik Jari pada SMK Perhotelan 45 Mataram

Fingerprint is one of the unique part of human body that can be used as a personal identity with the help of fingerprint biometric technology to help identify it. The use of fingerprint biometric technology can be a solution for student attendance that helps minimize errors or fraud such as manipulation or falsification in the process of recording attendance. The application of computerized attendance recording can be done by utilizing the concept of the Internet of Things (IoT) which assumes that electronic devices can be connected to each other to communicate or exchange data independently through internet networks that using protocols to communicate, including the MQTT (Message Queue Telemetry Transport protocol), which is lightweight message and designed for devices with limited resources. Therefore, an Internet of Things based attendance system was created by utilizing fingerprint sensor technology on the MQTT protocol to assist schools in improving attendance recording performance, as well simplifying the process of recording student attendance at SMK Perhotelan 45 Mataram which still applies conventional attendance recording procedure. The fingerprint enroll process is carried out with a system interface in the form of a web application using the MQTT protocol. Fingerprint feature data is stored on the fingerprint sensor memory module. The total time used to record attendance for 10 respondents is 11,241 seconds with the average time obtained is 1.1241 seconds. It was found that 50% of users agreed to the application of the internet-based fingerprint presence system based on MOS testing.

Application of Different Statistical Tests for Validation of Synthesized Speech Parameterized by Cepstral Coefficients and LSP

The following document tries out different statistical norms to validate the quality of synthesized voices applied to an HTS-based spanish synthesizer, which uses LSP and Cepstral Coefficients parameterizations. The standard MOS tests were carried out. Other types of quality tests were performed as well to reinforce the MOS results. Such as: MUSHRA, ABX and CCR. The subjective test PESQ was also applied. To validate intelligibility a SUS test was used.

Rancang Bangun Aplikasi Pendukung Pembelajaran Ilmu Pengetahuan Sosial (IPS) Sekolah Dasar Berbasis Android

IPS is a lesson at the elementary school level. Based on the curriculum at SDN 22 Ampenan which uses the 2006 KTS curriculum, each student learns to use the media of LKS and books as the supporting media. The availability of the media has less influence on students. The purpose of this research is to develop an Android-based application which can support the school. This application aims to help the learning process of students with multimedia available in the application. This application displays materials, images, videos, and evaluations which are contained in the exercises and games of each chapter in grades 5 and 6.This application is built using android studio version 2.2.1 with the Java programming language. Besides this application is also developed using the waterfall model. The testing method used is a black box and MOS testing. Testing using the MOS method on application quality shows that 62.5% of the respondents stated strongly agree, teacher respondents stated strongly agree with the percentage of 62.75%.

HMM-based generation of laughter facial expression

This paper proposes a model for visual laughter generation by the means of speaker-dependent training of Hidden Markov Models (HMMs). It is composed of the following parts: 1) facial and 2) and head motions are modeled with separate HMMs while 3) eye-blink are added as a post-processing step on the generated eyelid trajectories.The models are trained on a database of facial expressions recorded on one male subject watching humorous videos. A commercially available marker-based motion capture system was used to record the visual data. A preliminary study has shown that modeling head motion with the same transcriptions as for facial deformation is not the best choice due to the rigidness of the resulting head motion.Finally, the generated facial laughter trajectories are used to animate a 3D face model and the corresponding animation is rendered in a video. An online perception MOS test is conducted to assess the improvement compared to the previous method and to compare with the perception of ground truth trajectories. Results show that the new approach significantly outperforms the previous one.