Hasil Pencarian  ::  Simpan CSV :: Kembali

"ABSTRACTRequired Safe Egress Time (RSET) consists of 4 elements, namely, fire detection time, alarm time, pre-evacuation time, and travel or movement time. Pre-evacuation time is currently regarded as the key critical evacuation process. If pre-evacuation time is not explicit, RSET timeline will not be reliable and effect on life of evacuees in the building. The purpose of this cross-sectional study was to develop the model for predicting pre-evacuation time in 10 plastic industries. Regression analysis was performed in order to find the factors significantly associated with pre-evacuation time. Only 4 influenced variables were tested by using regression analysis. Regression analysis and back propagation artificial neural networks model (BP-ANNs) were run to predict pre-evacuation time from 4 influential variables. BP-ANNs model was constructed as 4-10-1 by comprising of 4 input variables, 10 hidden nodes, 1 output variable, momentum was 0.05, learning rate was 0.08, and learning time was 100,000 epochs. The findings revealed BP-ANNs model showed the least error with the value of Mean Absolute Deviation (MAD), Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE) and Root Mean Square Error (RMSE) were 2.04, 1.64, 1743.90 and 41.76 respectively when comparing with regression analysis model. BP-ANNs model can correctly predict pre-evacuation time with 75.15% accuracy. Therefore, BP-ANNs was an appropriate model for predicting pre-evacuation. This finding showed the advantage of BP-ANNs model which was more suitable to predict RSET and eliminated factors that could delay evacuation time in 10 plastic industries."

"Keberadaan COVID-19 di Indonesia saat ini bukanlah satu-satunya wabah penyakit yang harus diwaspadai. Menteri Kesehatan mengatakan ada penyakit yang tidak kalah  berbahaya dan juga tidak kalah mematikan dibandingkan dengan wabah penyakit COVID-19, yaitu Demam Berdarah Dengue. Penyakit ini sudah sepatutnya untuk diwaspadai mengingat jumlah kasusnya yang semakin meningkat dan melebihi jumlah kasus penyakit COVID-19. Faktor cuaca seperti curah hujan, temperatur, dan kelembapan merupakan faktor yang sangat berpengaruh dalam penyebaran parasit dan vektor penular DBD. Untuk mengoptimalkan upaya pencegahan dan penanganan DBD, perlu dilakukannya prediksi terkait jumlah insiden DBD. Dalam tugas akhir ini dilakukan proses prediksi jumlah insiden DBD di DKI Jakarta dengan memperhitungkan faktor iklim (curah hujan, kelembapan, dan temperatur) menggunakan metode Extreme Learning Machine dan metode Artificial Neural Network-Back Propagation serta membandingkan kinerja dari kedua metode tersebut.  Berbeda dari Artificial Neural Network-Back Propagation, Extreme Learning Machine tidak membutuhkan proses iterasi untuk update parameter. Dengan menggunakan data variabel cuaca dan data jumlah insiden DBD kumulatif, Extreme Learning Machine dapat memberikan hasil prediksi yang lebih akurat dibandingkan dengan  Artificial Neural Network - Back Propagation. Extreme Learning Machine dengan persentase data training sebesar 90% menunjukkan hasil prediksi yang lebih baik dibandingkan dengan persentase data training lainnya yang digunakan dalam tugas akhir ini yaitu sebesar 80% dan 70%.

---

The existence of COVID-19 currently in Indonesia is not the only disease which must be watched out. The Health Ministry has said that there was a disease that is as dangerous as COVID-19. That disease is Dengue Fever. Dengue Fever also must be given an extra caution because it is noted that until now the number of dengue cases continues to increase and exceeds COVID-19 cases. The weather factors, such as rainfall, temperature, and humidity, are a very influential factor in the spread of parasites and infectious vectors of dengue fever.  To optimize the dengue handling and prevention effort, it is important to make the dengue cases prediction.

In this final paper, the number of dengue incidences will be predicted by involving weather factors (rainfall, temperature, and humidity) using Extreme Learning Machine and Artificial Neural Network-Back Propagation and also comparing the both of their performance. Unlike the Artificial Neural Network-Back Propagation, Extreme Learning Machine does not need the iteration process to update the parameter.

The result shows that Extreme Learning Machine can give the dengue incidences prediction  which is more accurate than the dengue incidences prediction that is given by using Artificial Neural Network-Back Propagation. Extreme Learning Machine by using 90% training data can show the better prediction result than other training data percentage which is used in this final paper, 80% and 70%."

"abstrakKonsumsi energi listrik nasional mengalami pertumbuhan rata-rata sekitar 4,8per tahun selama 5 tahun terakhir, salah satunya adalah sektor rumah tangga. Salahsatu solusi untuk mengurangi konsumsi energi listrik pada sektor ini adalah denganmemonitor konsumsi beban listrik peralatan rumah tangga dan memberikaninformasi ini kembali kepada pelanggan. Salah satu teknik memonitor konsumsibeban peralatan listrik paling efisien dan murah adalah teknik Non-Intrusive LoadMonitoring (NILM). Berbeda dengan teknik konvensional, NILM menjanjikanpengurangan penggunaan sensor secara signifikan. NILM umumnya menggunakankondisi daya listrik saat transien atau tunak. Pada penelitian ini, metode Back-Propagation Artificial Neural Network (BP-ANN) akan dikembangkan untuk dapatmengidentifikasi penggunaan peralatan rumah tangga pada sinyal daya listrik dalamkondisi tunak dengan fitur ekstraksi perubahan daya. Fitur ekstraksi tersebutmemiliki keunggulan yaitu pada akusisi data menggunakan tingkat sampling yangrendah. Dalam penelitian ini telah dikembangkan arsitektur jaringan syaraf tiruandengan tipe dual input. Tipe dual input pada jaringan syaraf tiruan tersebut terdiridari daya aggregate dan daya maksimum peralatan rumah tangga. Penggunaanarsitektur jaringan syaraf tiruan dengan tipe dual input ini unggul dalammengidentifikasi penggunaan peralatan rumah tangga yang memiliki karakteristiknilai daya hampir mirip atau sama dan karakteristik daya dengan kondisi multi daya.Untuk memverifikasi efektivitas metode yang dikembangkan, maka data bebanperalatan rumah tangga yang digunakan adalah tracebase dataset dan penyusunandatanya menggunakan model synthetic aggregate. Dari hasil pengujian tipe dualinput pada arsitektur jaringan syaraf tiruan ini dapat mengidentifikasi penggunaanperalatan rumah tangga yang memiliki nilai daya hampir mirip atau sama dankarakteristik daya dengan kondisi multi daya, sehingga dapat meningkatkan nilaiRecognition Rate (RR) sampai 94.2.

---

abstractNational electric energy consumption experienced average growth about 4.8per annum over the past 5 years, one of them is household sector. One of thesolutions to reduce electrical energy consumption in this sector is to monitor electricpower consumption of household appliances and to give this information back toconsumers. One of the most efficient and the cheapest techniques to monitor theelectric power consumption appliances is Non-Intrusive Load Monitoring (NILM).This is different with conventional techniques where NILM promises the reductionof sensor deployment significantly. NILM commonly uses either transient or steadystate signal. In this research, the method of Back-Propagation Artificial NeuralNetwork (BP-ANN) will be developed to identify the utilization of householdappliances using power change features extraction in the steady state signals. Thefeature extraction has an advantage on data acquisition by applying a low samplingrate. This research has developed neural network architecture with dual input type.Dual input types of the neural network consist of aggregate power and maximumpower of the household appliances. Applying of neural network architecture withdual input types outperforms in identifying of the household appliances load wherethe power is almost similar and it has a multi states power characteristics. To verifythe effectiveness of the method, the data of the load is provided by tracebase datasetand the forming of the data uses a synthetic aggregate model. From the experimentresult of the dual input type in the neural network architecture, it can identify theload which has power almost similar and it has a multi states power characteristics.Finally, it can increase the value of Recognition Rate (RR) to 94.2"

"As an extension of artificial intelligence research, artificial neural networks (ANN) aim to simulate intelligent behavior by mimicking the way that biological neural networks function. In Artificial Neural Networks, an international panel of experts report the history of the application of ANN to chemical and biological problems, provide a guide to network architectures, training and the extraction of rules from trained networks, and cover many cutting-edge examples of the application of ANN to chemistry and biology. In the tradition of the highly successful Methods in Molecular Biology series, this volume exhibits clear, easy-to-use information with many step-by-step laboratory protocols."

"Integrasi antara data log dengan data seismik merupakan salah satu metode untuk melakukan prediksi terhadap suatu parameter log dalam area survei seismik. Analisa data dalam metode ini terdiri atas serangkaian data target log, yang dalam hal ini adalah log porositas dari beberapa sumur yang dikorelasikan dengan beberapa atribut seismik dari volume seismik 3D untuk menurunkan transformasi multi atribut dalam bentuk linear maupun non linear yang menghasilkan pemodelan terhadap parameter target log. Dalam transformasi linear, dihasilkan serangkaian konstanta bobot melalui metode least-square. Sedangkan pada transformasi non-linear diperlukan aplikasi Artificial Neural Network yang salah satunya adalah Probabilistic Neural Network (PNN). Untuk mengkalkulasi keberhasilan dari penurunan transformasi multi atribut, digunakan metode validasi silang. Nilai error yang dihasilkan melalui proses validasi ini menggambarkan nilai prediksi error ketika hasil transformasi multi atribut tersebut diaplikasikan kedalam volume seismik. Setelah didapatkan nilai korelasi yang optimum antara pemodelan log dengan log sebenarnya, selanjutnya dapat dibuat peta sayatan data (data slicing) yang menunjukkan penyebaran pororitas secara lateral yang dapat membantu menentukan zona persebaran porsitas tinggi yang merupakan indikasi prospek area reservoir hidrokarbon.

---

Integration between log data and seismic data is one of the method to predict log properties in seismic survey area. Data analysis in this method consists of series of target log data, which in this case is porosity log from some wells which correlate with seismic attributes from 3D seismic volume to derive linear or non linear multi attribute transform to product a predicted target log properties. In linear mode, the transformation consists of series of wheights derived by Least Square minimization. In non linear mode, application of Artificial Neural Network (ANN) is needed. One of the ANN which used in this research is Probabilistic Neural Network (PNN). To estimate the reliability of the derived multi attribute transform, crossvalidation method is used. Error that product from this validation method illustrate like prediction error when the transform is applied to seismic volume. After correlation value between predicted log and actual log obtained optimumly, a data slicing map showing the spreading of porosity lateraly can be made. This data slicing map abble to assist to determine high porosity spreading zone which is indicates the prospect area of hydrocarbon reservoir."

"Perkembangan teknologi otomotif di dunia yang sangat pesat menuntut para pelaku industri otomotif untuk terus-menerus mengembangkan teknologi dan inovasi terbaru. Namun, inovasi yang dilakukan di industri otomotif tidak lagi terbatas pada inovasi produk namun juga pada proses pengembangan produk. Salah satunya adalah dengan menerapkan strategi product platform. Penelitian ini dilakukan untuk memprediksi waktu pergantian platform pada salah satu jenis produk multi-generasi, yaitu produk otomotif, dengan menggunakan metode peramalan artificial neural network. Hasil prediksi pada penelitian menunjukkan bahwa prediksi waktu pergantian platform berkisar dalam kurun waktu 32-33 quarter yang merupakan hasil yang sesuai dengan rentang waktu inovasi platform yang ideal yaitu 8-10 tahun. Selain itu, penelitian juga memperlihatkan bahwa pergantian platform pada produk otomotif kerap dilakukan ketika produk sedang berada di tahap maturity dalam siklus hidupnya serta berhasil mengidentifikasi faktor-faktor yang mempengaruhi keputusan perusahaan untuk melakukan pergantian platform.

---

The rapid growth of technology in the automotive industry has forced the manufacturers to continuously develop new technology and make innovations. Nowadays, innovation in the automotive industry does not only refer to product innovation, but it refers to process innovation as well, for example by implementing the product platform strategy. This research aims to predict the development time of new platform for one of the multiple-generation product line, automotive product, using artificial neural network. The prediction from this research shows that new platform should be introduced in 32-33 quarters. This result is suitable to the ideal condition of platform innovation which is in 8-10 years. Moreover, the result shows that most of the time company decides to introduce the next-generation platform while the older generation is still in the maturity stage of its life cycle and the research also successfully identifies the factors influencing company to introduce the next-generation platform."

"Skripsi ini dibuat untuk merancang perangkat lunak yang mampu mengenali nilai nominal uang kertas rupiah beserta keasliannya melalui proses pengolahan citra berbasiskan metode jaringan syaraf tiruan dengan algoritma backpropagation. Sistem pengenalan citra (image recognition) ini memperoleh kemampuan deteksi dengan cara belajar dari contoh (learning by examples).Pola dari tiap uang kertas rupiah memiliki ciri yang unik yang membedakannya satu dengan yang lainnya, baik bentuk angka, jumlah angka nol, serta gambar latar belakangnya. Pola khas dari tiap jenis uang kertas inilah yang dikenali oleh perangkat lunak ini, sehingga mampu membedakan tidak hanya uang kertas rupiah (valid data) tapi juga uang kertas pecahan lain (unknown data).Pencitraan uang kertas berasal dari dua sumber yakni citra tampak (visible image), yang berasal dari scanner 300 dpi, dan tak tampak (invisible image), yang menggunakan sinar ultraviolet (UV). Beberapa area tertentu diambil dari citra sebagai masukan identifikasi yang akan diolah melalui proses dijitalisasi sehingga dihasilkan reduksi citra hitam-putih (gray-scale) sebesar 8x7 pixel. Hal ini bertujuan selain mengurangi besar data pelatihan jaringan syaraf tiruan (JST) juga meningkatkan kemampuan identifikasi.Metode backpropagation dipilih didasarkan atas masukan data relatif kecil dengan harapan waktu pendeteksian dapat dipersingkat. Hasil identifikasi mungkin tidak akan mendekati klasifikasi, tetapi akan didekati dengan persentase kesalahan sekecil mungkin. Jumlah total data sebanyak 76 set, dimana 25 diantaranya digunakan untuk melatih JST, dan sisanya sebanyak 51 set digunakan untuk menguji JST. Hasil simulasi menunjukkan sistem mampu mengenali dengan tingkat akurasi hingga sebesar 92% bervariasi tergantung dari jumlah set data pelatihan yang dilakukan. Metode yang diterapkan dapat digunakan untuk mengenali uang kertas pecahan rupiah.

---

This paper is written to design a software that capable to recognize the nominal value of rupiah banknote with its authenticity by means of image-processing technic based on artificial neural network with backpropagation algorithm. This image-processing technic has its recognition ability from learning-by-examples process.

Each rupiah banknote has its unique characteristic which distinguish the banknote with one another, such as numeral shape, amount of zeroes, and its background image. The software then uses this banknote’s unique pattern to recognize not only for valid currency, but also for unknown currency.

The banknote imaging process itself came from two sources, visible image—taken from a 300dpis scanner, and unvisible image—taken from a UV. Some certain areas are taken from the image as identification source that will be processed by some digitalization until these areas become an 8x7 pixels gray-scale image. This is intented to reduce the data size for the artificial neural network training process, thus increase the identification ability.

Backpropagation method is chosen based on its input data which is relatively small, hoping that the detection time can be decreased. The identification result might not get closer with the classification result, but will get approached with as small error as possible. The total amount of data are 76 sets, where 25 of them are used to train the artificial neural network, and the rest of them are used to test the neural network. Simulation result shows that the sistem is capable to identify up to 92% of accuracy, depends on amount of train-sets data. This method can be used to identify the rupiahs banknote authenticity."