Explore the vast range of titles available.

Affective computing is an emerging area of research that aims to enable intelligent systems to recognize, feel, infer and interpret human emotions. The widely spread online and off-line music videos are one of the rich sources of human emotion analysis because it integrates the composer’s internal feeling through song lyrics, musical instruments performance and visual expression. In general, the metadata which music video customers to choose a product includes high-level semantics like emotion so that automatic emotion analysis might be necessary. In this research area, however, the lack of a labeled dataset is a major problem. Therefore, we first construct a balanced music video emotion dataset including diversity of territory, language, culture and musical instruments. We test this dataset over four unimodal and four multimodal convolutional neural networks (CNN) of music and video. First, we separately fine-tuned each pre-trained unimodal CNN and test the performance on unseen data. In addition, we train a 1-dimensional CNN-based music emotion classifier with raw waveform input. The comparative analysis of each unimodal classifier over various optimizers is made to find the best model that can be integrate into a multimodal structure. The best unimodal modality is integrated with corresponding music and video network features for multimodal classifier. The multimodal structure integrates whole music video features and makes final classification with the SoftMax classifier by a late feature fusion strategy. All possible multimodal structures are also combined into one predictive model to get the overall prediction. All the proposed multimodal structure uses cross-validation to overcome the data scarcity problem (overfitting) at the decision level. The evaluation results using various metrics show a boost in the performance of the multimodal architectures compared to each unimodal emotion classifier. The predictive model by integration of all multimodal structure achieves 88.56% in accuracy, 0.88 in f1-score, and 0.987 in area under the curve (AUC) score. The result suggests human high-level emotions are automatically well classified in the proposed CNN-based multimodal networks, even though a small amount of labeled data samples is available for training.

The violin is produced in Europe and is recognized by the world as one of the most important Western musical instruments. It enjoys the reputation of \"Queen of Musical Instruments\". Since it was introduced to China, it has deeply influenced the music and cultural life of our people and accelerated the development of the violin. At present, many colleges and universities offer violin teaching courses, and the number of students majoring in violin is increasing. Based on this, this paper conducts an in-depth analysis of the current reform trend and current situation of violin-playing teaching in colleges and universities in China through the analysis of big data, and proposes a new reform idea.

Physics is the science that studies an object, and interactions between objects, also studies natural phenomena that include matter, space, and interactions between humans. Human interaction is related to culture and customs that are inherent in people's lives. Every region in Indonesia has different customs and customs in the community. Aceh is one area that has diverse customs in the way of making food, playing games and using its musical instruments. The culture of people's original knowledge relating to scientific physics knowledge is called ethnoscience. The study examines, analyzes the application of the concepts of temperature and heat and impulse momentum in Aceh culture. The method used is a literature study with study materials including (1) the cultural art game of Aceh kekuriken, (2) The typical food of Aceh tribe Pisang sale.

Gamelan is one of Indonesia’s traditional music which has become a cultural identity and has survived for a long time. Bonang is a gamelan musical instrument that is played by being hit on the protruding upper part. The importance of preserving traditional music culture makes us realize that traditional music is not lost in today’s technological era. This research is to design a virtual bonang musical instrument using the Arduino Mega2560 microcontroller and the HC-SR04 sensor as tone identification. The result of this research is a virtual bonang musical instrument prototype that can be operated via an Android-based smartphone. This prototype is also useful for introducing art as part of STEAM to students.

Several abstract topics in mathematics are considered unrelated to contextual problems. This condition occurs because students cannot use some abstract mathematics topics which obtained at school in their daily activities. Hence, students are less interested in mathematics learning. Therefore, a bridge connecting formal school mathematics and the local culture is needed; one of them is ethnomathematics research method design. Ethnomathematics is a qualitative method design which examines the practice and elements of mathematics in a cultural group. One of the cultures which grows, develops, and is popular in Banda Aceh City is the Rapa’i Geleng dance. Rapa’i Geleng is a traditional Acehnese dance performed by shaking the head to the left and right regularly in a specific pattern following the rhythmic strains of the Acehnese traditional musical instrument called Rapa’i. The data were collected through document review, including videos, photos, notes, and interviews with experts. The results of the exploration show that there is a mathematical concept in the Rapa’i Geleng dance, namely number pattern. The sequence topic was observed from dancers’ regular movement based on their position. Consequently, this dance is supposed to be used as a learning medium to explain abstract mathematical concepts to the students.

Gambo as a traditional stringed musical instrument from Mbojo tribe (NTB) is increasingly missing its existence among the younger generation. This instrument has never been used as a media for learning physics, even though it can show the phenomena of vibration, waves and sound. This paper aims to explain the learning design of contruction the concept of natural resonance using a gambo system and involving advanced spectrum applications of smartphone and evidence the effectiveness of its implementation based on student understanding about the concept and its responses. The learning activity is guided inquiry which involves 28 senior high school students of Kota Bima grade XI. Data was collected through document studies and concept understanding tests. The results of test were analyzed using descriptive statistics and using the normalized gain test, while the analysis of student responses to learning activities used a likert scale. Based on studies and research results, it was concluded that the learning of the natural resonance concept of the string system using Gambo has been well designed and can be implemented easily and effectively. Understanding of students’ concepts increases significantly, and gets a good response from students.

Whenever we move, speak, or play musical instruments, our actions generate auditory sensory input. The sensory consequences of our actions are thought to be predicted via sensorimotor integration, which involves anatomical and functional links between auditory and motor brain regions. The physiological connections are relatively well established, but less is known about how sensorimotor integration affects auditory perception. The sensory attenuation hypothesis suggests that the perceived loudness of self-generated sounds is attenuated to help distinguish self-generated sounds from ambient sounds. Sensory attenuation would work for louder ambient sounds, but could lead to less accurate perception if the ambient sounds were quieter. We hypothesize that a key function of sensorimotor integration is the facilitated processing of self-generated sounds, leading to more accurate perception under most conditions. The sensory attenuation hypothesis predicts better performance for higher but not lower intensity comparisons, whereas sensory facilitation predicts improved perception regardless of comparison sound intensity. A series of experiments tested these hypotheses, with results supporting the enhancement hypothesis. Overall, people were more accurate at comparing the loudness of two sounds when making one of the sounds themselves. We propose that the brain selectively modulates the perception of self-generated sounds to enhance representations of action consequences.