Music genre classification is one part of the music recommendation process, which is a challenging job. This research proposes the classification of music genres using Bidirectional Long Short-Term Memory (BiLSTM) and Mel-Frequency Cepstral Coefficients (MFCC) extraction features. This method was tested on the GTZAN and ISMIR2004 datasets, specifically on the IS-MIR2004 dataset, a duration cutting operation was carried out, which was only taken from seconds 31 to 60 so that it had the same duration as GTZAN, namely 30 seconds. Preprocessing operations by removing silent parts and stretching are also performed at the preprocessing stage to obtain normalized input. Based on the test results, the performance of the proposed method is able to produce accuracy on testing data of 93.10% for GTZAN and 93.69% for the ISMIR2004 dataset.

The aim of the research is to describe the role of Indonesian mobile sisters in social and religious activities at the Khadijati Foundation. The research method is descriptive qualitative. Data collection techniques using interviews, observation, and documentation. Data processing techniques using reduction, data presentation, and conclusions. Data validity technique using triangulation. Research results: (1) role: compensation for orphans and poor people, Friday rounds, humanitarian activities, assistance for orphans and poor people in Palestine, and providing Qurbani for memorizing the Qur'an. (2) Supporting factors: synergy and partnership between sister communities, and use of social media platforms for social movements. Inhibiting factors: time flexibility, limitations on movement, donation cases. Conclusion: the role of the sisters in the foundation is running very well and has great benefits for society.
 

The purpose of this research is to analyze the implementation of democracy and village autonomy in the process of village head elections. The election of a village head is one form of genuine and pure village autonomy and democracy. However, with the emergence of modern states, the independence and ability of rural communities to manage their affairs have diminished. This is closely related to the decentralization that occurs in unitary states such as Indonesia. In a unitary state, one of the central matters is legal affairs. Legal matters include regulating the election of village heads, as stipulated in Minister of Home Affairs Regulation No. 112 of 2014 concerning the Election of Village Heads. This research uses a normative juridical method. The research results explain that village head elections, based on rules from the central government cascaded down to the village level, become procedural in the implementation of village head elections. In fact, these rules lead to the phenomenon of husband and wife pairs running as village head candidates in the same village to avoid having a single candidate, thereby enabling the village head election to take place. Furthermore, violations of rules regarding village head elections are common, such as instances of money politics and the lack of neutrality among village officials, but there is no legal follow-up related to these violations. Tujuan penelitian ini untuk menganalisis pelaksanaan demokrasi dan otonomi desa dalam proses pemilihan kepala desa. Pemilihan kepala desa merupakan salah satu bentuk dari otonomi dan demokrasi desa yang asli dan murni. Namun dengan munculnya negara modern, kemandirian dan kemampuan masyarakat desa untuk mengatur urusan desanya mulai berkurang. Hal tersebut tidak lepas dengan adanya desentralisasi yang terjadi di negara kesatuan seperti Indonesia. Dalam negara kesatuan salah satu urusan yang menjadi urusan pusat adalah soal hukum. Urusan hukum tersebut tidak lepas dari urusan untuk mengatur pemilihan kepala desa sebagaimana terdapat pada Permendagri No 112 Tahun 2014 tentang Pemilihan Kepala Desa. Metode penelitian ini menggunakan yuridis normatif. Hasil penelitian menjelaskan bahwa pemilihan kepala desa yang berdasarkan aturan-aturan dari pemerintah pusat yang diturunkan hingga tingkat desa menjadi prosedural dalam pelaksaan pemilihan kepala desa. Bahkan aturan tersebut menimbulkan adanya fenomena pasangan suami istri yang maju sebagai calon kepala desa di desa yang sama untuk menghindari calon tunggal sehingga pemilihan kepala desa dapat dilaksanakan. Selain itu ternyata aturan mengenai pemilihan kepala desa juga banyak terjadi pelanggaran namun tidak ada tindak lanjut hukum terkait pelanggaran tersebut. Pelanggaran tersebut antara lain adalah adanya money politics dan ketidaknetralan perangkat desa.      

The rapid The main problem in the misuse of data used in crime is the result of a lack of file security. This study proposes a data security method to protect document files using the Advanced Encryption Standard (AES) algorithm combined with the Vigenere Cipher. This research carried out 2 processes, namely the encryption process and the decryption process. The encryption process will be carried out by the AES algorithm and then encrypted again with the Vigenere Cipher algorithm. The experiments show that the proposed method can encrypt files properly, where there are changes in the value of the document file and the encrypted file cannot be opened and the description results do not cause changes to the original file. The results of this study are that the system is able to work properly so as to produce file encryption and decryption using the AES method combined with the Vigenere Cipher. In document files, the largest difference in encryption and decryption time is 8 seconds, while in image files the difference in encryption and decryption time is 17 seconds. This longest time difference is generated by large files.

WSN menggunakan jaringan nirkabel untuk menghubungkan node sensor dan sink node. Node sensor bertugas mengumpulkan informasi dengan melakukan sensing terhadap target seperti panas, cahaya, dan suhu. Namun, node sensor memiliki keterbatasan dalam hal memori, sumber daya pengolahan, energi, dan masa pakai, yang dapat mempengaruhi kinerja jaringan, termasuk network lifetime dan packet delivery ratio. Oleh karena itu, diperlukan protokol yang efektif untuk meningkatkan kinerja jaringan WSN. Salah satu penelitian untuk meningkatkan kinerja jaringan adalah menggunakan Shortest Geopath Routing (SGP) berbasis tetangga terdekat dan lokasi. Namun, SGP memiliki permasalahan seperti seringnya terjadi kongesti yang menyebabkan packet drop dan kegagalan pengiriman data saat terjadi Routing hole. Untuk mengatasi permasalahan tersebut, penelitian ini melakukan protokol SGP dengan mekanisme Swing routing untuk meningkatkan kinerja jaringan WSN. Dalam mengatasi Routing hole, Swing routing Protocol juga melakukan pencarian jalur alternatif dengan memilih node berdasarkan lokasi koordinat terdekat dengan sink node. Hasil simulasi menggunakan simulator SIDnet-SWAN menunjukkan bahwa penggunaan Swing routing Protocol dapat mengurangi warning congestion dalam jaringan sebesar rata-rata 10 node, meningkatkan network lifetime sebesar 5.27% (14 menit), dan meningkatkan packet delivery ratio sebesar 8.27% dibandingkan dengan protokol SGP. Dalam penanganan Routing hole, Swing routing Protocol mendapatkan rata-rata packet delivery ratio sebesar 21.77% dibandingkan dengan protokol SGP.

Penelitian ini bertujuan untuk melakukan analisis mengenai dampak Beban Kerja dan Stres Kerja terhadap Kinerja Pegawai yang dihubungkan oleh variabel Mediasi Kepuasan Kerja. Studi empiris ini dilakukan pada Pegawai Satuan Polisi Pamong Praja Provinsi Kalimantan Timur, suatu topik yang memiliki relevansi yang signifikan dalam ranah manajemen sumber daya manusia. Metodologi yang diterapkan dalam penelitian ini adalah kuantitatif deskriptif, dengan pengumpulan data dilakukan melalui kuesioner menggunakan metode sampling jenuh pada 69 responden. Data yang terhimpun kemudian dianalisis dengan menerapkan metode Persamaan Struktural Partial Least Squares (SEM PLS). Hasil analisis data menunjukkan bahwa Beban Kerja dan Stres Kerja memberikan dampak negatif terhadap Kepuasan Kerja dan Kinerja Pegawai. Selain itu, Kepuasan Kerja teridentifikasi sebagai mediator yang mampu menghubungkan antara Beban Kerja dan Stres Kerja dengan Kinerja Pegawai.

Diabetes Mellitus is a hazardous disease, and according to the World Health Organization (WHO), diabetes will be one of the main causes of death by 2030. One of the most popular diabetes datasets is PIMA Indians, and this dataset has been widely tested on various machine learning (ML) methods, even deep learning (DL). But on average, ML methods are not able to produce good accuracy. The quality of the dataset and features is the most influential thing in this case, so deeper investment is needed to examine this dataset. This research will analyze and compare the PIMA Indians and Abelvikas datasets using the Random Forest (RF) method. The two datasets are imbalanced, in fact, the Abelvikas dataset is more imbalanced and has a larger number of classes so it is be more complex. The RF was chosen because it is one of the ML methods that has the best results on various diabetes datasets. Based on the test results, very contrasting results were obtained on the two datasets. Abelvikas had accuracy, precision, and recall, reaching 100%, and PIMA Indians only achieved 75% for accuracy, 87% for precision, and 80% for the best recall. Testing was done with 3, 5, 7, 10, and 15 tree number parameters. Apart from that, it was also tested with k-fold validation to get valid results. This determines that the features in the Abelvikas dataset are much better because more complete glucose features support them.

The purpose of this research is to (1) determine the percentage of loading and unloading productivity at the Port of Cappa Ujung Parepare (2) to find out the criteria that have good performance in loading and unloading services at the Port of Cappa Ujung Parepare (3) to find out the criteria that are considered according to the interests of users Loading and unloading services at Cappa Ujung Parepare Port. The population in this study was 120 people, which is the number of respondents in this study related to loading and unloading service assessment performance and the interests of loading and unloading service users. The data collection techniques used were interviews and questionnaires. The data analysis technique in this research was carried out using the Customer Satisfaction Index (CSI) Method and the IPA Analysis Method. The results of this study indicate that (1) The productivity of loading and unloading at the Cappa Ujung Parepare Port in 2021 will reach 5,137,823 Tons/M3 with the biggest achievement in December reaching 1,873% greater than the monthly target. The productivity of loading and unloading at Cappa Ujung Parepare Port in 2022 reached 6,944,242 tons/M3 with the biggest achievement in December reaching 2,510% greater than the monthly target (2) CSI calculation results of 77.64%. Thus, the level of customer satisfaction with loading and unloading services is in the satisfactory category. The highest WF value is shown at 10.42% on attribute 8 (safety in the port environment) which means that this attribute is considered the most important by customers in unloading services. The lowest WF value is shown at 9.69% on attribute 7 (clarity of information about loading and unloading) which means that this attribute is considered not too important by customers in loading and unloading services.

Plant disease is one of the problems in the world of agriculture. Early identification of plant diseases can reduce the risk of loss, so automation is needed to speed up identification. This study proposes a custom-designed convolutional neural network (CNN) model for plant disease recognition. The proposed CNN model is not complex and lightweight, so it can be implemented in model applications. The proposed CNN model consists of 12 CNN layers, which consist of eight layers for feature extraction and four layers as classifiers. Based on the experimental results of a plant disease dataset consisting of 38 classes with a total of 87,867 image records. The proposed model can get high performance and not overfitting, with 97%, 98%, 97% and 97%, respectively, for accuracy, precision, recall and f1-score. The performance of the proposed model is also better than some popular pre-trained models, such as InceptionV3 and MobileNetV2. The proposed model can also work well when implemented in mobile applications.