Hasil Pencarian  ::  Simpan CSV :: Kembali

Abstrak :
Kegiatan berbelanja secara daring di e-commerce meningkat seiring dengan peningkatan pengguna internet di Indonesia. Kondisi ini mengakibatkan melonjaknya kegiatan pengiriman barang. Dalam proses pengiriman barang terdapat tahap last-mile delivery. Adapun tantangan yang dihadapi pada tahap ini adalah jumlah pengiriman yang banyak dan waktu pengiriman yang panjang. Hal ini bisa mengakibatkan penambahan jumlah alat transportasi yang digunakan. Salah satu alat transportasi untuk last-mile delivery adalah truk. Penggunaan truk dalam last-mile delivery dapat menyebabkan polusi udara serta tidak dapat mengirimkan paket tepat waktu karena kemacetan lalu lintas (dalam kasus daerah perkotaan). Karena hal itu, harus dicari jalan keluar yang dapat menurunkan polusi udara serta menurunkan kasus pengiriman paket tidak tepat waktu dalam last-mile delivery. Penelitian ini menggabungkan pemakaian truk dan drone yang bermaksud untuk menurunkan kasus pengiriman paket tidak tepat waktu serta menurunkan polusi udara dengan keunggulan drone. Metode yang dipakai melibatkan implementasi Fuzzy C-Means (FCM) clustering untuk mengelompokkan data pelanggan dengan mempertimbangkan kendala jumlah drone yang tersedia serta radius terbang drone dan implementasi Algoritma Genetika untuk merancang rute pengiriman yang optimal dengan mempertimbangkan kendala Time Windows pada depot dan semua cluster. Penerapan kedua metode itu dipakai pada data 90 pelanggan. FCM bisa menurunkan 63,15% jumlah cluster, menurunkan 36,03% keseluruhan jarak tempuh rute, menurunkan 28,77% keseluruhan waktu tempuh rute, serta pengurangan 4,06% nilai fungsi objektif bila ketimbang dengan yang didapat dari clustering secara intuitif. ......Online shopping activities in e-commerce are increasing along with the rise in internet users in Indonesia. This trend has led to a surge in goods delivery activities. In the delivery process, there is a crucial last-mile delivery stage. The challenges faced during this stage include a high volume of deliveries and extended delivery times, leading to the necessity of deploying additional transportation means. One commonly used transportation method for last-mile delivery is trucks. However, the utilization of trucks in last-mile delivery poses challenges such as air pollution and the inability to ensure timely package deliveries due to traffic congestion, particularly in urban areas. To address these issues, a solution must be found that not only reduces air pollution but also mitigates instances of delayed package deliveries in last-mile delivery. This research proposes a novel approach by integrating the use of trucks and drones to capitalize on the advantages offered by drones. The methodology employed incorporates the implementation of Fuzzy C-Means (FCM) clustering to categorize customer data, considering constraints related to the number of available drones and the flying radius of the drones. Additionally, a Genetic Algorithm is applied to optimize delivery routes, considering time window constraints at the depot and within all clusters. The application of these two methods was tested on a dataset comprising 90 customers. FCM demonstrated the ability to reduce the number of clusters by 63.15%, decrease the overall route travel distance by 36.03%, and minimize the overall route travel time by 28.77%. Furthermore, it led to a 4.06% reduction in the objective function values compared to intuitive clustering.

Abstrak :
Demam Berdarah termasuk penyakit yang paling umum terjadi di negara tropis seperti Indonesia dan sering berakibat fatal dalam kesehatan. Prediksi dini terhadap jumlah kasus Demam Berdarah merupakan salah satu kunci untuk menanggulangi risiko penyebarannya dalam masyarakat dan dapat membantu pihak-pihak yang terkait seperti Dinas Kesehatan Daerah dalam membuat kebijakan dan rencana pencegahan. Pada tugas akhir ini, untuk angka insiden DBD diprediksi menggunakan metode Artificial Neural Network dengan dua algoritma berbeda untuk proses training ANN, yaitu Backpropagation (ANN-BP) dan Genetic Algorithm (ANN-GA). Penggunaan GA dalam training ANN bertujuan untuk membandingkan dengan BP yang cenderung tidak menemukan minimum global dari fungsi errornya. Variabel prediktor yang digunakan adalah jumlah insiden dan variabel cuaca sebelumnya yang terdiri dari temperatur, kelembapan, dan curah hujan. Variabel prediktor ditentukan dengan mencari time lag dari masing-masing variabel prediktor terhadap jumlah insiden menggunakan korelasi silang. Model yang dibentuk dievaluasi dengan Mean Squared Error, dan hasil prediksi dievaluasi menggunakan Mean Squared Error, Root Mean Squarred Error, dan Mean Absolut Error. Pada tugas akhir ini metode ANN-BP menghasilkan hasil prediksi jumlah insiden DBD kumulatif lebih baik dibandingkan metode ANN-GA pada kota madya Jakarta Pusat, Jakarta Selatan, dan Jakarta Utara, dengan selisih MSE berturut-turut 3,966; 50,162; 23,933; selisih RMSE masing-masing 0,232; 1,742; 1,304; dan selisih MAE masing-masing 0,496; 0,901; 0,734. Sedangkan pada Jakarta Barat dan Jakarta Timur metode ANN-GA menghasilkan hasil prediksi jumlah insiden DBD kumulatif lebih baik dibandingkan metode ANN-BP, dengan selisih MSE berturut-turut 16,915; 37,621; selisih RMSE masing-masing 0,484; 1,44; dan selisih MAE masing-masing 0,319; 0,739. ......Dengue Fever is one of the most common diseases in tropical countries like Indonesia and is often fatal in health. Early prediction of the number of Dengue Fever cases is one of the keys to overcoming the risk of its spread in the community and can assist related parties such as the District Health Office in making policies and prevention plans. In this final project, the DHF incidence rate is predicted using the Artificial Neural Network method with two different algorithms for the ANN training process, namely Backpropagation (ANN-BP) and Genetic Algorithm (ANN-GA). The use of GA in ANN training aims to compare with BP which tends not to find a global minimum of its error function. The predictor variables used are the number of incidents and previous weather variables consisting of temperature, humidity, and rainfall. Predictor variables are determined by finding the time lag of each predictor variable to the number of incidents using cross correlation. The model formed was evaluated with Mean Squared Error, and the predicted results were evaluated using Mean Squared Error, Root Mean Squared Error, and Mean Absolute Error. In this final project, the ANN-BP method produces a prediction of cumulative DHF incidents that is better than the ANN-GA method in the cities of Central Jakarta, South Jakarta, and North Jakarta, with a MSE difference 3.966, 50.162, 23.933, respectively, the difference in RMSE each city is 0.232, 1.742, 1.304, respectively and the MAE difference 0.496, 0.901, 0.734, respectively. Whereas in West Jakarta and East Jakarta the ANN-GA method produces a better prediction of cumulative DHF incidents compared to the ANN-BP method, with a MSE difference 16.915, 37.621, respectively, the difference in RMSE each city is 0.484, 1.44, respectively, and the MAE difference of each city is 0.319, 0.739, respectively.

Abstrak :
Analysis of Genetic Association Studies, textbook in statistical genetics and genetic epidemiology, and a reference book for the analysis of genetic association studies. The book is applicable to the study of statistics, biostatistics, genetics and genetic epidemiology. In addition to providing derivations, the book uses real examples and simulations to illustrate step-by-step applications. Introductory chapters on probability and genetic epidemiology terminology provide the reader with necessary background knowledge.

Abstrak :
This book constitutes the thoroughly refereed conference proceedings of the 10th International Conference on Computational Methods in Systems Biology, CMSB 2012, held in London, UK, during October 3-5, 2012. The 17 revised full papers and 8 flash posters presented together with the summaries of 3 invited papers were carefully reviewed and selected from 62 submissions. The papers cover the analysis of biological systems, networks, and data ranging from intercellular to multiscale. Topics included high-performance computing, and for the first time papers on synthetic biology.