Hasil Pencarian  ::  Simpan CSV :: Kembali

"Tujuan dari tesis ini adalah untuk berkontribusi dalam pengembangan sistem kecerdasan buatan (artificial intelligence) untuk memodelkan pergerakan saham yang bersifat tidak liner dan penuh ketidakpastian. Pendekatan yang digunakan adalah model Artificial Neural Network (ANN) metode Backpropagation. Sebagai pembanding, digunakan model multivariate ARIMA. Penelitian akan membuktikan bahwa model ANN dapat lebih tepat memprediksi pergerakan harga saham di Indonesia, khususnya saham-saham anggota indeks LQ45, dibandingkakan model multivariate ARIMA. Penelitian ini adalah penelitian observasi model. Penelitian menghasilkan kesimpulan bahwa model ANN signifikan secara statistik lebih akurat daripada model multivariate ARIMA.

---

The objective of this thesis is to contribute the development of artificial intelligence system in modeling stock price movement which highly non-linier and uncertain in nature. Our approach is using Artificial Neural Network (ANN) with Backpropagation method. In comparing the accuracy of the model, we use multivariate ARIMA method. This research intend to show that ANN model is more accurate in predicting Indonesian stock price movement, especially LQ45 index, compared to multivariate ARIMA model. This research is using observational method in selecting the best model. The result of the research is that ANN is statistically significant and more accurate compared to multivariate ARIMA model."

"Saham sektor properti dan real estate merupakan jalan bagi investor untuk berinvestasi di pasar properti dan real estate. Harga saham properti dan real esatate memiliki kecenderungan untuk mengalami pergerakkan yang fluktuatif. Untuk meningkatkan potensi perolehan capital gain serta untuk mengukur risiko investasi, harga saham dapat diprediksi menggunakan metode artificial neural network apabila faktor-faktor yang dapat mempengaruhinya diketahui. Variabel yang mempengaruhi harga saham properti dan real estate di Indonesia antara lain, Gross Domestic Product, inflasi, nilai Rupiah terhadap Dollar Amerika, uang beredar, harga minyak mentah, suku bunga jangka panjang, serta volume perdagangan saham.Hasil prediksi dan performa harga saham properti dan real estate Indonesia menggunakan artificial neural network kemudian dibandingkan dengan metode time series konvensional ARIMA dan regresi linier yang menunjukkan hasil berupa metode artificial neural network lebih unggul dibanding ARIMA dan regresi linier.

---

Property and real estate stocks facilitates investors to invest their fund in property and real estate market. Property and real estate stock price has a tendency to move fluctuatively. The price can be predicted using artificial neural network, if the variables which affect the price of property and real estate stock could be identified. The variables which affecting the Indonesian poperty and real estate stock price are Gross Domestc Product, inflation, exchange rate of Rupiah to US Dollar, money aggregates, crude oil price, long-term interest rate, and stock trading volume.

Predicticon results and the methods' performance then compared with the more conventional methods which are time series analysis ARIMA and linear regression. The result shows that performance of artificial neural network is better than ARIMA and linear regression."

"Emisi kendaraan terutama yang menggunakan mesin diesel merupakan masalah yang sudah tidak asing lagi. Nox, HC, O2, CO, CO2 dan asap yang merupakan zat- zat hasil pembakaran mesin diesel dapat di ukur melalui percobaan eksperimental. Tetapi tentunya percobaan eksperimental ini mempunyai beberapa kekurangan seperti pengoperasiannya yang mahal serta prosesnya yang memakan waktu cukup panjang. Untuk mengatasi masalah itu semua, maka dibuatlah suatu metode pemodelan matematika menggunakan Artificial Neural Network (ANN). Metode ANN yang digunakan dalam skripsi ini adalah Backpropagation. Dengan dilakukannya penelitian ini diharapkan karakter emisi kendaraan mesin diesel dapat diprediksi secara akurat. Hasil dari penelitian ini membuktikan bahwa ANN cukup handal dalam memprediksi emisi bahan bakar mesin diesel.

---

Vehicle emissions, especially using diesel engine is not a strange problem anymore. NOx, HC, O2, CO, CO2 and smoke emissions comes from the combustion of substances in diesel engines can be measured through experimental test. Certainly this experimental test has several shortcomings such as the operation is expensive and time consuming process which is long enough.

To cope with this problem, then a mathematical modeling method using Artificial Neural Network (ANN) was made. ANN method used in this thesis is Backpropagation. This research expect to predict characters of diesel engine emissions accurately. The results of this study proves that ANN quite good to predict diesel engine emission."

"Estimation of porosity (and other petrophysical parameters) from well logs are important yet difficult task encountered in geophysical formation evaluation and reservoir engineering. Motivated by recent result of artificial neural network (ANN) modelling offshore eastern Canada and North sea, we have developed neural nets for converting well logs in the Field-X, West Java, to porosity. We use back propagation artificial neural network (BPANN) to model porosity of the area. The porosity ANN is a simple three layer network using sonic, density and resistivity logs for input.Optimum network's parameters, like type of activation function, number of facts, and number of neurons also have been investigated through series of trials and errors of network. The network, initially developed for basin-scale problems, perform sufficiently accurate to meet normal requirements. There is strong similarity (R=0.964) between the predicted porosity from BPANN with density-derived porosity (which has been used as a substitute for core plug porosity due to not enought core data available). A major adventage is that no a priori knowledge of the rock material and pore fluids is required. Real-time conversion based on measurements while drilling (MWD) is thus an obvious application."

"Biomassa merupakan salah satu potensi energi alternatif untuk mengurangi ketergantungan penggunaan energi fosil. Indonesia memiliki potensi energi biomassa sebesar 49.810 MW yang berasal dari limbah dan tanaman. Pemanfaatan energi tersebut dapat dilakukan melalui proses gasifikasi yang mengubah biomassa menjadi gas sintetik. Salah satu metode untuk memodelkan proses tersebut adalah dengan menggunakan kecerdasan buatan atau artificial intelligence (AI). Studi literatur yang dilakukan menunjukkan bahwa metode artificial neural network (ANN) adalah pendekatan AI yang sering dipakai untuk melakukan pemodelan proses gasifikasi. Namun, ANN memiliki beberapa kekurangan dalam pemodelan dinamis yang kemudian disempurnakan melalui salah satu pengembangannya yang dinamakan recurrent neural network (RNN) yang mampu memodelkan variabel dependen terhadap waktu. Kesimpulan dari penelitian ini menyarankan agar pengembangan RNN dapat dijadikan acuan untuk membuat sistem kontrol pintar pada prototipe gasifier yang akan datang.

---

Biomass is one of the alternative energy sources to reduce the usage of fossil energy. The potential of biomass energy in Indonesia reaches 49,810 MW, which comes from organic wastes and plants. Gasification is a process to convert biomass to synthetic gas, which is one of the utilizations of biomass energy. Artificial Intelligence (AI) implemented to model the complex process of gasification. Artificial Neural Network (ANN) is a common approach in AI to model the process in the gasifier. Yet, ANN is still inferior in modeling dynamic process that leads to an improvement of ANN called recurrent neural network (RNN). The result of this study suggests that RNN could be the foundation for the development of smart control for the next prototypes."

"The problem of telecomunication service facility is the availability of server/operator and buffer that can sustain every customer calling for service...."

"Tujuan: Tujuan dari penelitian ini adalah mendapatkan model jaringan saraf tiruan dengan algoritma pembelajaran backpropagation berdasarkan data masukan dari pola sidik jari penderita obesitas. Diharapkan model JST yang diperoleh dapat menjadi alat bantu diagnosis bagi para klinisi dalam mengidentifikasi kasus obesitas berdasarkan keturunan. Metode: Data dari pola sidik jari penderita obesitas dan data penunjang lainnya diuraikan menjadi variabel masakan Variabel keluaran ditentuknn berdasarkan kasus obesitas yang diderita oleh pasien. Kemudian data sampel dibagi dua yaitu data untuk training dan data untuk testing. Dengan menggunakan data training maka Metode Jaringan syaraf tiruan mempelajari pola sidik jari pendarita obesitas yang kemudian digunakan untuk memprediksi data testing. Akurasi identifikssi atau pengenalan pola sidik jari penderita obesitas akan sangat ditentukan oleh hasil prediksi algoritma jaringan syaraf tiruan terhadap data testing. Hasil: Dalam proses pemhelajaran dengan metode jaringan berbasil melakukan pengenal terhadap data training dengan error sebesar O,QI berhasil dicapai. Untuk prediksi polo sidik jari melalui data testing rata-rata keberhasilan adalah 71,82%. Angka prosentasi keberbasilan ini cukup baik dan depat dijadikan alat bantu bagi para praktisi medis di bidang obesitas dalam menentukan faktor keturunan dari penyakit obesitas. Kesimpulan: Percobaan ini menghasilkan model JST yang dapat diaplikasikan pada pengelan pola sidik jari pendarita obesitas. Rata-rata keberhasilan prediksi sebesar 71,82% dapat ditingkat dengan menambah data training bagi Metode Jaringan Saraf Tiruan.

---

Objective: The objective of this research is to obtain an artificial neural network model with backpropagation learning algorithm based on input data from the fingerprint pattern of the obese patients. It is expected that ANN models can be obtained as diagnostic tool for clinicians in identifying cases of obesity based on descent.

Methods: Data from the fingerprint pattern of obesity and other supporting data is decomposed into input variables. Output variable is determined on a case-obesity suffered by the patient Then the sampled data is divided into two data. One for training and other for testing. By using training data. the method of artificial neural networks learn the patterns of the obese fingerprint which is then used to predict the testing data. Accuracy of fingerprint pattern recognition of obesity will be detemined by the results of neural network algorithm prediction against testing data.

Results: In the learning process stage, Artificial Neural Network succceded in identifying a network of training with error 0.01 was achieved. For the prediction of fingerprint patterns through data testing success rate was 80%. The rate for the percentage of success is quite good and can be used as a tool for medical practitioners in the field of obesity in determining obesity cases base of genetic factor.

Conclusion: This experiment resulted ANN model that can be applied to the fingerprint pattern recognition of obese patients. The average prediction success of 71,82% would be increase if we can add more data for 1raining process for Neural Network Method."