Yazar "Kasif, Ahmet" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Classical Turkish Music Composition with LSTM Self-Attention
    (2024) Kasif, Ahmet; Sevgen, Selcuk
    Synthetic symbolic music generation, the process of creating new musical pieces using symbolic representations, has gained significant traction in the field of music informatics and computational creativity. It holds immense potential for various applications, ranging from music education and composition assistance to music therapy and personalized music recommendation systems. Classical Turkish music (CTM) exhibit distinct characteristics regarding Western Tonal Classical Music (WCM) such as melodic organization, formation of rhythmic structure or melodic expressions. This study tackles the challenge of symbolic music composition, focusing on CTM. Unlike WCM, CTM incorporates microtonal intervals. These intervals are smaller than the semitones in Western music, allowing for a more nuanced expression of pitch. This leads to a more diverse set of pitch ranges. The proposed method employs a combination of self-attention and long-short term memory (LSTM) networks to capture long-term relational information and generate realistic CTM compositions. LSTMs effectively model sequential dependencies and improve local relations within musical structures and self-attention improves the context vector, allowing the model to attend to different aspects of the musical context simultaneously. This combination enables the proposed method to generate compositions that are both musically coherent and stylistically consistent with distinct features of CTM. The proposed method was evaluated on two datasets, the CTM dataset and Classical Music Piano (CPM) dataset. The assessment of musical contents is evaluated through melodic similarity and stylistic consistency metrics. The results demonstrate that the proposed method is able to generate musical content that is coherent and produce music that is pleasing-to-hear. Overall, the article presents a novel and effective approach to symbolic music composition, focusing on CTM.
  • Küçük Resim Yok
    Öğe
    Deep learning-based modelling of pyrolysis
    (Springer, 2024) Özcan, Alper; Kasif, Ahmet; Sezgin, İsmail Veli; Catal, Cagatay; Sanwal, Muhammad; Merdun, Hasan
    Pyrolysis is one of the thermochemical methods used to produce value-added products from biomass. Thermogravimetric analysis (TGA) is frequently used to examine the energy potential and thermal behavior of biomass, coal, and their blends. The investigation of the TGA data using Artificial Neural Networks (ANN) is one of the most important research areas in recent years. While there are different research papers on the use of Machine Learning (ML) in this field, there is a lack of systematic application of deep learning (DL) algorithms. As such, we applied DL algorithms together with ML algorithms to evaluate the predictive performance of thermal behaviors of proposed bioenergy sources. Thermal behavior of tomato, pepper, eggplant, squash, and cucumber harvest wastes, the equal mass (20%) mixture of them, and the blends of the mixture with coal in the ratios of 20, 33, and 50% under nitrogen atmosphere were investigated by the TGA and ML models. Based on the pyrolysis thermal behavior of the harvest wastes, the eggplant, pepper, tomato, and 5-biomass mixture had the highest conversion potential. According to the thermal behavior of co-pyrolysis of coal and harvest waste mixtures, it had positive effects on pyrolysis conversion degrees and temperature range compared to the coal, and therefore, they can be used as alternative sources for energy production. The MSE and R2 scores of Bi-directional LSTM demonstrate that an improved performance can be obtained with DL based solutions. Promising results were obtained when the Bi-directional LSTM is applied for modeling the pyrolysis. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2023.
  • Küçük Resim Yok
    Öğe
    Federated Learning for Smart and Sustainable Aquaponics: A Decentralized AI Approach for Urban Resilience
    (Springer-Verlag Singapore Pte Ltd, 2025) Kasif, Ahmet; Catal, Cagatay
    The majority of machine learning models rely on centralized methods, which require large data transfers to central repositories. Federated learning, a decentralized machine learning approach, offers a solution by enabling local computations and aggregating local models to build a global model. While federated learning has been applied in some agricultural domains, its use in aquaponics remains unexplored. Aquaponics, a sustainable agricultural method combining fish farming and soil-less plant production, presents unique opportunities for federated learning applications, particularly in urban farming environments. By using edge-based federated learning, we improve scalability, data privacy, and sustainability and also, reduce data transmission needs in smart urban agriculture. This research, a collaboration between research teams from three countries, highlights how federated learning and deep learning can enhance environmental monitoring and sustainability in urban resilience strategies, particularly in smart agriculture. The Flower framework was used to implement federated learning, and ResNet-18 was employed for fish disease detection. This paper introduces novel contributions in federated learning and deep learning techniques for the management of aquaponics systems, highlighting the potential of these technologies to optimize aquaponics systems' efficiency.
  • Küçük Resim Yok
    Öğe
    Hierarchical multi-head attention LSTM for polyphonic symbolic melody generation
    (Springer, 2024) Kasif, Ahmet; Sevgen, Selcuk; Ozcan, Alper; Catal, Cagatay
    Creating symbolic melodies with machine learning is challenging because it requires an understanding of musical structure and the handling of inter-dependencies and long-term dependencies. Learning the relationship between events that occur far apart in time in music poses a considerable challenge for machine learning models. Another notable feature of music is that notes must account for several inter-dependencies, including melodic, harmonic, and rhythmic aspects. Baseline methods, such as RNNs, LSTMs, and GRUs, often struggle to capture these dependencies, resulting in the generation of musically incoherent or repetitive melodies. As such, in this study, a hierarchical multi-head attention LSTM model is proposed for creating polyphonic symbolic melodies. This enables our model to generate more complex and expressive melodies than previous methods, while still being musically coherent. The model allows learning of long-term dependencies at different levels of abstraction, while retaining the ability to form inter-dependencies. The study has been conducted on two major symbolic music datasets, MAESTRO and Classical-Music MIDI, which feature musical content encoded on MIDI. The artistic nature of music poses a challenge to evaluating the generated content and qualitative analysis are often not enough. Thus, human listening tests are conducted to strengthen the evaluation. Qualitative analysis conducted on the generated melodies shows significantly improved loss scores on MSE over baseline methods, and is able to generate melodies that were both musically coherent and expressive. The listening tests conducted using Likert-scale support the qualitative results and provide better statistical scores over baseline methods.