Claim Missing Document
Check
Articles

Found 37 Documents
Search

Analisis Fast Fourier Tansform untuk Pengenalan Voice Register Wanita dalam Teknik Bernyanyi Muhathir, Muhathir; Susilawati, Susilawati; Muliono, Rizki
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 2, No 2 (2019): EDISI JANUARI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (408.71 KB) | DOI: 10.31289/jite.v2i2.2166

Abstract

Automatic speech recognition merupakan kemampuan untuk menerima dan mengidentifikasi kata-kata yang diucapkan dengan mengubah sinyal analog ke digital, dan mengekstraksi karakteristik vokal unik seperti pitch, frekuensi, nada dan irama untuk membentuk model speaker atau sampel suara. Sampel suara yang digunakan yaitu voice register, voice register adalah pembagian wilayah suara manusia berdasarkan sumber suara, sensasi ruang resonansi, bentuk, warna, timbre suara, dan tinggi rendahnya nada yang dihasilkan. Fast Fourier Transform digunakan sebagai transformasi untuk mengolah sample suara yang akan diklasifikasi. FFT dalam mentransormasikan sinyal voice register hanya mampu mengklasifikasikan dengan rata-rata true positive rate 65.4%. 
Perhitungan Metode Fuzzy Sugeno Dan Antropometri Dalam Memprediksi Status Gizi Indeks Massa Tubuh Syahputra, Dinur; Muhathir, Muhathir
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 2, No 1 (2018): EDISI JULI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (287.694 KB) | DOI: 10.31289/jite.v2i1.1676

Abstract

Antropometri merupakan ilmu yang mempelajari berbagai ukuran tubuh manusia. Dalam bidang ilmu gizi digunakan untuk menilai status gizi. Metode yang digunakan adalah fuzzy sugeno, yaitu aturan yang direpresentasikan dalam bentuk IF-THEN dengan output berupa konstanta untuk melakukan perhitungan terhadap status gizi indeks massa tubuh. Dalam hal memprediksi status gizi indeks massa tubuh dilakukanlah perhitungan dengan menggunakan metode fuzzy sugeno dan antropometri.
KLASIFIKASI EKSPRESI WAJAH MENGGUNAKAN BAG OF VISUAL WORDS Muhathir, Muhathir
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 1, No 2 (2018): Edisi Januari
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (435.293 KB) | DOI: 10.31289/jite.v1i2.1426

Abstract

Pada hakikatnya, manusia dapat membedakan pola terhadap suatu objek berdasarkan bentuk visual yang mengandung keadaan emosional. Seperti membedakan ekspresi wajah seseorang pada suatu citra. Manusia dapat membedakan ekspresi pada citra tersebut secara kasat mata. Namun komputer yang tidak dapat mengenali ekspresi wajah tersebut. Bag of visual words merupakan suatu skema untuk mengklasifikasikan citra berdasarkan nilai-nilai pixel pada citra. Dengan menggunakan deteksi interest point dan ekstraksi interest point, bag of visual words mengambil ciri unik pada citra sehingga dapat membedakan pola-pola yang terdapat pada suatu citra. Bag of visual word dengan nilai K 500 mampu mengklasifikasi pola ekspresi wajah dengan tingkat akurasi 69%,Kata kunci: Wajah, Klasifikasi, Speed-up Robust Feature, Bag of visual words, Ekspresi
Analisis Pengaruh Fungsi Aktivasi, Learning Rate Dan Momentum Dalam Menentukan Mean Square Error (MSE) Pada Jaringan Saraf Restricted Boltzmann Machines (RBM) Susilawati, Susilawati; Muhathir, Muhathir
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 2, No 2 (2019): EDISI JANUARI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1243.5 KB) | DOI: 10.31289/jite.v2i2.2162

Abstract

Restricted boltzmann machines (RBM) merupakan algoritma pembelajaran jaringan syaraf tanpa pengawaas (unsupervised learning) yang hanya terdiri dari dua lapisan yang visible layer dan hidden layer. Kinerja RBM sangat dipengaruhi oleh parameter-parameternya seperti fungsi aktivasi yang digunakan untuk mengaktifkan neuron pada jaringan dan learning rate serta momentum untuk mempercepat proses pembelajaran. Pemilihan fungsi aktivasi yang tepat sangat mempengaruhi kinerja dalam menentukan Mean Square Error (MSE) pada jaringan saraf RBM. Fungsi aktivasi yang digunakan pada jaringan RBM adalah fungsi aktivasi sigmoid. Beberapa varian dari fungsi aktivasi sigmoid seperti fungsi sigmoid biner dan sigmoid tangen hiperbolik (tanh). Dengan menggunakan dataset MNIST untuk pembelajaran dan pengujian, terlihat bahwa tingkat keberhasilan untuk klasifikasi pada fungsi aktivasi sigmoid biner, ditentukan oleh nilai MSE yang kecil. Berbeda dengan fungsi aktivasi tangen nilai MSE menaik seiring bertambahnya jumlah epoch. Fungsi aktivasi sigmoid biner dengan learning rate 0.05 dan momentum 0.7 memiliki tingkat pengenalan tulisan tangan yang tinggi sebesar 93.42%, diikuti dengan learning rate 0.01 momentum 0.9 yakni 91.92%, learning rate 0.05 momentum 0.5 yakni 91.31%, learning rate 0.01 momentum 0.7 sebesar 90.56% dan terakhir learning rate 0.01 momentum 0.5 sebesar 87.49%.
Perbandingan Algoritma Blowfish Dan Twofish Untuk Kriptografi File Gambar Muhathir, Muhathir
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 2, No 1 (2018): EDISI JULI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (246.817 KB) | DOI: 10.31289/jite.v2i1.1673

Abstract

Masalah keamanan dan kerahasiaan data dan informasi merupakan suatu hal yang sangat penting. Salah satu cara untuk menjaga data tersebut yaitu dengan teknik enkripsi dan dekripsi atau juga sering disebut dengan kriptografi. Kriptografi adalah ilmu dan seni  untuk menjaga keamanan data dengan cara mengubahnya menjadi suatu bentuk yang tidak dapat dikenali lagi. Kriptografi dapat diterapkan pada berbagai jenis file salah satunya adalah gambar. Algoritma blowfish dan twofish yang digunakan untuk membahas tingkat kecapatan masing-masing algoritma. Hasil penelitian menunjukkan bahwa rata-rata perbandingan kecepatan dari algoritma blowfish dan algoritma twofish  dalam satuan milidetik adalah  4355:4267.
Design of Parking Control Using Ultrasonic Sensor Based On Fuzzy Logic Fawwaz, Insidini; Azmi, Fadhillah; Muhathir, Muhathir; Dharshinni, N P
JITE (JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING) Vol 3, No 1 (2019): EDISI JULI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (496.812 KB) | DOI: 10.31289/jite.v3i1.2675

Abstract

The number of vehicles in Indonesia is currently increasing, which is not matched by the availability of parking lots, especially cars. Like in public places, namely, offices, shops, and other public places. However, in Indonesia the use of parking lots is still less organized, such as too close the position of one car to another, the position of the vehicle that is not in line with the slot, this can cause inconvenience in the use of parking lots or both parties. Supervision carried out by the manager of the parking lot is still lacking because it can be caused by the vast parking area and the number of supervised vehicles, so that a parking control system is needed that can help overcome this problem. The control system to be designed uses a proximity sensor to detect the proximity of the vehicle to one another, where the position of the vehicle has been determined, not only to detect proximity, but the number of vehicles that have entered the parking area, so parking users know whether the slot provided is still available or not. To detect distance, fuzzy logic method is applied. Fuzzy methods are applied to read the conditions received by the proximity sensor, and calculate the number of vehicles using infra red and photodiode sensors. If information from the proximity sensor that is processed in the microcontroller by fuzzy logic is detected, the output is in the form of an LED indicator and alarm warning.
Design of Water Level Detection Using Ultrasonic Sensor Based On Fuzzy Logic Azmi, Fadhillah; Fawwaz, Insidini; Muhathir, Muhathir; Dharshinni, N P
JITE (JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING) Vol 3, No 1 (2019): EDISI JULI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (621.541 KB) | DOI: 10.31289/jite.v3i1.2668

Abstract

Water is one of the natural resources that are needed by creatures on earth. And the need for clean water is increasing, so the price of water, both bottled water and the price of water from the PDAM. Therefore, it is necessary to have a design that can control water needs, such as the water level for filling the required containers, controlling the water level in the reservoir, etc. according to human needs so that no waste of water occurs. This research was conducted to design water level detection by combining hardware and software, namely ultrasonic sensors as detection, Arduino Uno microcontroller as a process, and fuzzy logic as an analysis of data delivered by ultrasonic sensors. So, this design can be utilized in various fields both industrial and home. This water level detection is designed using ultrasonic sensors as distance monitoring, servo motor, LED warning, and buzzer. Fuzzy logic is applied to the ability of a tool designed by determining the desired set point of water. Test results that have been carried out with Fuzzy Logic with 5 levels, are level 1 (0 ? 6 cm), level 2 (6.1 ? 12 cm), level 3 (12.1 cm ? 18 cm), level 4 (18.1 cm ? 24 cm), and level 5 (24.1 ? 30 cm).
Design of Water Level Detection Using Ultrasonic Sensor Based On Fuzzy Logic Fadhillah Azmi; Insidini Fawwaz; Muhathir Muhathir; N P Dharshinni
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 3, No 1 (2019): EDISI JULI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v3i1.2668

Abstract

Water is one of the natural resources that are needed by creatures on earth. And the need for clean water is increasing, so the price of water, both bottled water and the price of water from the PDAM. Therefore, it is necessary to have a design that can control water needs, such as the water level for filling the required containers, controlling the water level in the reservoir, etc. according to human needs so that no waste of water occurs. This research was conducted to design water level detection by combining hardware and software, namely ultrasonic sensors as detection, Arduino Uno microcontroller as a process, and fuzzy logic as an analysis of data delivered by ultrasonic sensors. So, this design can be utilized in various fields both industrial and home. This water level detection is designed using ultrasonic sensors as distance monitoring, servo motor, LED warning, and buzzer. Fuzzy logic is applied to the ability of a tool designed by determining the desired set point of water. Test results that have been carried out with Fuzzy Logic with 5 levels, are level 1 (0 – 6 cm), level 2 (6.1 – 12 cm), level 3 (12.1 cm – 18 cm), level 4 (18.1 cm – 24 cm), and level 5 (24.1 – 30 cm).
Analisis Fast Fourier Tansform untuk Pengenalan Voice Register Wanita dalam Teknik Bernyanyi Muhathir Muhathir; Susilawati Susilawati; Rizki Muliono
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 2, No 2 (2019): EDISI JANUARI
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v2i2.2166

Abstract

Automatic speech recognition merupakan kemampuan untuk menerima dan mengidentifikasi kata-kata yang diucapkan dengan mengubah sinyal analog ke digital, dan mengekstraksi karakteristik vokal unik seperti pitch, frekuensi, nada dan irama untuk membentuk model speaker atau sampel suara. Sampel suara yang digunakan yaitu voice register, voice register adalah pembagian wilayah suara manusia berdasarkan sumber suara, sensasi ruang resonansi, bentuk, warna, timbre suara, dan tinggi rendahnya nada yang dihasilkan. Fast Fourier Transform digunakan sebagai transformasi untuk mengolah sample suara yang akan diklasifikasi. FFT dalam mentransormasikan sinyal voice register hanya mampu mengklasifikasikan dengan rata-rata true positive rate 65.4%. 
Shafiyyatul Amaliyyah School Student Face Absence Using Principal Component Analysis and K – Nearest Neighbor Aripin Rambe; Juliansyah Putra Tanjung; Muhathir Muhathir
JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING Vol 5, No 2 (2022): Issues January 2022
Publisher : Universitas Medan Area

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31289/jite.v5i2.6214

Abstract

Pattern recognition is one of the sciences used to classify things based on quantitative measurements of the main features or properties of an object. Pattern recognition has been widely used in various fields of research. One of the pattern recognition that is often discussed is facial recognition. The face is one of the human biometrics that is often used as the main information of a person. Face recognition is a field of research with many applications in applications such as attendance, population data collection, security systems, and others. The research utilizes feature extraction of PCA (Principal Component Analysis), and K-NN (K – Nearest Neighbor) with variations of the distance formula by applying facial recognition attendance at the Safiatul Amaliyah School. This research is expected to get accurate results in detecting, recognizing, and comparing a person's face with a small error rate. The distance formula with accuracy level is presented with the equation Cityblock < Euclidian < Minkowski < Chebychev. The effect of applying the variation of the distance formula on the performance of the facial attendance recognition model is not too big, but it is better.