Dr. Tri Arief Sardjono ST.,MT.

Profil Dosen

NIP   197002121995121001
Nama   Dr. Tri Arief Sardjono ST.,MT.
Email   sardjono[at]bme.its.ac.id
Pendidikan   S1: ITS, Teknik Elektro (1996-1999)
S2: ITB, Teknik Informatika (1996-1999)
S3: University of Groningen, Teknik Biomedika (Biomedical Engineering) (2003-2007 )

Penelitian dan Publikasi

Research


2009, Analisis Spektrum Frekwensi Suara untuk menentukan frekwensi dasar pasien tuna laring, DIPA ITS

2010, Analisis spektrum sinyal EMG (electromyogram) pada otot leher untuk klasifikasi suara pasien tuna laring, DIPA ITS

2009, Electronic Voice Producing Element (EVPE) berbasis ANFIS (Artificial Neuro Fuzzy Inference System) bagi penderita tuna laring, DP2M – Dikti

 

 

Journal Articles

2016

[1] Dikairono, Rudy; Sardjono, Tri Arief; Yulianto, Lucas;, "SISTEM NAVIGASI DAN PENGHINDAR RINTANGAN PADA MOBILE ROBOT MENGGUNAKAN GPS DAN PENGUKUR JARAK ULTRASONIK", JAVA Journal of Electrical and Electronics Engineering, Vol. 11, No. 1, 2016

Seiring perkembangan teknologi, teknologi robot juga ikut berkembang. Salah satu perkembangan dalam teknologi robot adalah navigasi mobile robot. Sistem navigasi mobile robot ini memanfaatkan GPS dan kompas pada android sebagai penentu posisi dan arah, serta ultrasonik sebagai sensor pendeteksi rintangan. Android dihubungkan dengan mikrokontroler sebagai penghasil sinyal kontrol pada mobile robot menggunakan sistem komunikasi Bluetooth . Data dikirimkan melalui Bluetooth untuk dikonversi menjadi suatu sinyal kontrol kemudi pada motor. Implementasi dari sistem yang dibuat menghasilkan mobile robot yang dapat bergerak secara otomatis menuju titik yang telah ditentukan oleh user. Data kontrol kemudi yang diberikan adalah belok kanan, belok kiri dan maju lurus dengan dua level kecepatan yakni lambat dan cepat. Namun, ketika ultrasonik mendeteksi rintangan, maka perintah dari android akan diabaikan sementara dan laju mobile robot mengikuti perintah kemudi dari hasil pembacaan ultrasonik. Hasil dari 10 kali pengujian tanpa rintangan menunjukkan proses navigasi mobile robot mencapai tingkat keberhasilan 60% untuk radius target 5 meter, dan 70% untuk radius target 8 meter. Sedangkan pada pengujian navigasi dengan rintangan mencapai tingkat keberhasilan 50% untuk panjang rintangan 100 cm dengan radius target 5 meter dan 60% untuk panjang rintangan 50cm dengan radius target 8 meter

[2] Subur, Joko; Sardjono, Tri Arief; Mardiyanto, Ronny;, "Braille Character Recognition Using Artificial Neural Network", IPTEK Journal of Proceedings Series, Vol. 2, No. 1, 2016

Braille letter is characters designed for the blind, consist of six embossed points, arranged in a standard braille character. Braille letters is touched and read using fingers, therefore the sensitivity of the fingers is important. Those characters need to be memorized, so it is very difficult to be learned. The aim of this research is to create a braille characters recognition system and translate it to alpha-numeric text. Webcam camera is used to capture braille image from braille characters on the paper sheet. Cropping, grayscale, thresholding, erotion, and dilation techniques are used for image preprocessing. Then, artificial neural network method are used to recognize the braille characters. The system can recognize braille characters with 99% accuracy even when the braille image is tilted up to 1 degrees.

2013

[1] Kurniaji, Paskalis; Kurniaji, Paskalis; Pirngadi, Harris; Sardjono, Tri Arief;, "Perancangan dan Simulasi Ultrasonik Doppler Gelombang Kontinyu 4MHz Berbasis Mikrokontroler ATmega16", Jurnal Teknik ITS, Vol. 2, No. 1, pp. A42-A45, 2013

Dalam penelitian ini telah dirancang sebuah sistem ultrasonik yang akan digunakan untuk mengukur kecepatan aliran darah. Sistem yang dirancang ini menggunakan prinsip ultrasonik doppler gelombang kontinyu dengan frekuensi 4MHz. Prinsip kerja dari sistem ini adalah dengan memancarkan gelombang sinus yang memiliki frekuensi 4 MHz  ke bagian pembuluh darah oleh tranduser pemancar, dan gelombang pantul yang dihasilkan dari reflektor sel darah merah akan diterima kembali oleh tranduser penerima. Gelombang pantul yang diterima oleh tranduser penerima ini akan memiliki frekuensi yang berbeda dari gelombang yang dipancarkan. Untuk mendapatkan perbedaan frekuensi ini, maka digunakan dua buah sumber generator gelombang sebagai bagian dari simulasi sistem. Rentang frekuensi yang digunakan untuk proses simulasi sistem adalah 4MHz – 4.007 MHz. Dari hasil pengujian dan simulasi, telah diperoleh nilai kecepatan aliran pada sudut <30° sebesar 50.74 cm/s dan nilai kecepatan aliran minimum pada sudut >80° memiliki kecepatan sebesar 1.3 cm/s dengan estimasi cepat rambat gelombang di dalam medium darah sebesar 1500m/s. Hasil pengujian dan simulasi untuk sudut doppler yang sesuai adalah untuk pengujian  kecepatan aliran pada sudut  <60°.
link: ejurnal.its.ac.id

[2] Sardjono, Tri Arief; Wilkinson, Michael H. F.; Veldhuizen, Albert G.; van Ooijen, Peter M. A.; Purnama, Ketut E.; Verkerke, Gijsbertus J.;, "Automatic Cobb angle determination from radiographic images.", Spine, Vol. 38, No. 20, pp. E1256-62, LWW, 2013

STUDY DESIGN: Automatic measurement of Cobb angle in patients with scoliosis.\n\nOBJECTIVE: To test the accuracy of an automatic Cobb angle determination method from frontal radiographical images.\n\nSUMMARY OF BACKGROUND DATA: Thirty-six frontal radiographical images of patients with scoliosis.\n\nMETHODS: A modified charged particle model is used to determine the curvature on radiographical spinal images. Three curve fitting methods, piece-wise linear, splines, and polynomials, each with 3 variants were used and evaluated for the best fit. The Cobb angle was calculated out of these curve fit lines and compared with a manually determined Cobb angle. The best-automated method is determined on the basis of the lowest mean absolute error and standard deviation, and the highest R2.\n\nRESULTS: The error of the manual Cobb angle determination among the 3 observers, determined as the mean of the standard deviations of all sets of measurements, was 3.37°. For the automatic method, the best piece-wise linear method is the 3-segments method. The best spline method is the 10-steps method. The best polynomial method is poly 6. Overall, the best automatic methods are the piece-wise linear method using 3 segments and the polynomial method using poly 6, with a mean absolute error of 4,26° and 3,91° a standard deviation of 3,44° and 3,60°, and a R2 of 0.9124 and 0.9175. The standard measurement error is significantly lower than the upper bound found in the literature (11.8°).\n\nCONCLUSION: The automatic Cobb angle method seemed to be better than the manual methods described in the literature. The piece-wise linear method using 3 segments and the polynomial method using poly 6 yield the 2 best results because the mean absolute error, standard deviation, and R2 are the best of all methods.\n\nLEVEL OF EVIDENCE: 3.

2012

[1] Herjuno, Dimas; Rivai, Muhammad; Sardjono, Tri Arief; Herjuno, Dimas; Rivai, Muhammad;, "Teledekteksi Gas pada Mobile Robot yang dikendalikan Gelombang Radio", Jurnal Teknik ITS, Vol. 1, No. 1, pp. A160--A163, 2012

Beberapa tahun terakhir terjadi peristiwa hilangnya nyawa manusia karena keracunan gas alam diarea pertambangan. Ada pula terjadi peristiwa dicurigainya bungkusan atau kemasan yang diduga adalah barang yang membahayakan jiwa. Karena banyaknya peristiwa yang meresahkan dan membahayakan masyarakat, maka dibutuhkan suatu alat yang dapat melakukan pengecekan pada suatu area atau benda dimana manusia tidak terlibat secara langsung atau melakukan kontak secara langsung yang dapat membahayakan manusia. Pada penlitian ini telah dibuat robot yang dilengkapi dengan sensor gas, sistem mikrokontroler serta beberapa perangkat jaringan seperti router, kamera ip yang digunakan untuk mensupport kelengkapan sistem. Dibutuhkan juga sebuah server komputer yang dapat memberikan perintah maupun memantau dari jarak jauh. Berdasarkan hasil pengukuran, resistansi sensor pada saat tidak terdeteksi gas bernilai paling tinggi 30KΩ dan resistansi sensor saat terdeteksi gas bernilai paling rendah sebesar 3KΩ. Dalam pengujian keseluruhan alat , robot ini berhasil bergerak sesuai perintah yang diberikan melalui gelombang radio dan mendeteksi gas dengan keberhasilan sebanyak 10 kali dari 10 kali percobaan dengan kecepatan rata-rata 0,12 m/s
link: www.ejurnal.its.ac.id

[2] Tompunu, Alan Novi; Kusumanto, RD D; Sardjono, Tri Arief;, "IMPLEMENTASI ALGORITMA LEAST MEAN SQUARE UNTUK PENINGKATAN KUALITAS SUARA PENDERITA TUNA LARING BERBASIS PROCESSOR TMS320C6713", Semantik, Vol. 2, No. 1, 2012

Seseorang yang telah mengalami laryngectomy biasa disebut dengan tuna laring. Laryngectomy adalah penghapusan laringdan pemisahan jalan napas dari hidung, mulut, dan kerongkongan. Laryngectomee bernafas melalui sebuah lubang di leher,yaitu stoma. Ada tiga usaha yang telah dilakukan untuk rehabilitasi suara tersebut yaitu dengan esophageal speech,tracheoesophageal dan eletrolarynx. Pembangkitan suara dengan eletrolarynx paling sering diadopsi untuk phonation.Kejelasan wicara electrolarynx dipengaruhi oleh noise yang dihasilkan oleh perangkat tersebut maupun noise yang timbul darilingkungan sekitarnya. Tujuan dari penelitian ini adalah untuk memberikan salah satu alternatif penyelesaian masalah bagipenderita tuna laring agar memiliki kejelasan dalam berbicara menggunakan perangkat electrolarynx neck-type, Servox SI –SERVOXD, dengan cara menggunakan adaptive filter berdasarkan algoritma least mean square. Dua microphone digunakansecara simultan, untuk memperoleh rekaman sinyal wicara dan noise melalui Starter-Kit DSP TMS320C6713. Microphonepertama digunakan untuk merekam wicara dan noise. Microphone kedua digunakan untuk merekam background noise.Pengukuran signal to noise ratio (SNR) telah dilakukan untuk mengetahui perbandingan antara sinyal ucapan dengan sinyalnoise. Dari hasil eksperimen, diperoleh bahwa nilai SNR sebelum pemfilteran sebesar 10.817 ± 2.5 dB dan setelah pemfilteransebesar 28,312 ± 9,7 dB dan terjadi peningkatan kualitas wicara electrolarynx sebesar 17,4948 ± 11.2 dB dengan bantuan Starter-Kit DSP TMS320C6713. Kata kunci : penderita tuna laring, electrolarynx, least mean square, DSP TMS 320C6713.

2011

[1] Dikairono, Rudy; Sardjono, Tri Arief; Purwanto, Djoko;, "Pengembangan Perencanaan Gerak Robot Kartesian Berbasis PLC", JAVA Journal of Electrical and Electronics Engineering, Vol. 9, No. 1, pp. 23-28, 2011

[2] Sardjono, Tri Arief; Purwanto, Djoko; Ibadillah, Achmad Fiqhi;, "Sistem Penjejakan Obyek Dengan Stereo Vision", JAVA Journal of Electrical and Electronics Engineering, Vol. 9, No. 1, 2011

2010

[1] Arifin, Fatchul; Sardjono, Tri Arief; Purnomo, Mauridhy Hery;, "Electrolarynx Voice Recognition Utilizing Pulse Coupled Neural Network", IPTEK The Journal for Technology and Science, Vol. 21, No. 3, 2010

The laryngectomies patient has no ability to speak normally because their vocal chords have been removed. The easiest option for the patient to speak again is by using electrolarynx speech. This tool is placed on the lower chin. Vibration of the neck while speaking is used to produce sound. Meanwhile, the technology of "voice recognition" has been growing very rapidly. It is expected that the technology of "voice recognition" can also be used by laryngectomies patients who use electrolarynx.This paper describes a system for electrolarynx speech recognition. Two main parts of the system are feature extraction and pattern recognition. The Pulse Coupled Neural Network – PCNN is used to extract the feature and characteristic of electrolarynx speech. Varying of β (one of PCNN parameter) also was conducted. Multi layer perceptron is used to recognize the sound patterns. There are two kinds of recognition conducted in this paper: speech recognition and speaker recognition. The speech recognition recognizes specific speech from every people. Meanwhile, speaker recognition recognizes specific speech from specific person. The system ran well. The "electrolarynx speech recognition" has been tested by recognizing of “A” and "not A" voice. The results showed that the system had 94.4% validation. Meanwhile, the electrolarynx speaker recognition has been tested by recognizing of “saya” voice from some different speakers. The results showed that the system had 92.2% validation. Meanwhile, the best β parameter of PCNN for electrolarynx recognition is 3.
link: iptek.its.ac.id

[2] Purnama, Ketut E.; Wilkinson, Michael. H. F.; Veldhuizen, Albert G.; Van Ooijen, Peter. M. A.; Lubbers, Jaap; Burgerhof, Johannes G.M. M; Sardjono, Tri A.; Verkerke, Gijbertus J.;, "A framework for human spine imaging using a freehand 3D ultrasound system", Technology and Health Care, Vol. 18, No. 1, pp. 1-17, IOS Press, 2010

The use of 3D ultrasound imaging to follow the progression of scoliosis, i.e., a 3D deformation of the spine, is described. Unlike other current examination modalities, in particular based on X-ray, its non-detrimental effect enables it to be used frequently to follow the progression of scoliosis which sometimes may develop rapidly. Furthermore, 3D ultrasound imaging provides information in 3D directly in contrast to projection methods. This paper describes a feasibility study of an ultrasound system to provide a 3D image of the human spine, and presents a framework of procedures to perform this task. The framework consist of an ultrasound image acquisition procedure to image a large part of the human spine by means of a freehand 3D ultrasound system and a volume reconstruction procedure which was performed in four stages: bin-filling, hole-filling, volume segment alignment, and volume segment compounding. The overall results of the procedures in this framework show that imaging of the human spine using ultrasound is feasible. Vertebral parts such as the transverse processes, laminae, superior articular processes, and spinous process of the vertebrae appear as clouds of voxels having intensities higher than the surrounding voxels. In sagittal slices, a string of transverse processes appears representing the curvature of the spine. In the bin-filling stage the estimated mean absolute noise level of a single measurement of a single voxel was determined. Our comparative study for the hole-filling methods based on rank sum statistics proved that the pixel nearest neighbour (PNN) method with variable radius and with the proposed olympic operation is the best method. Its mean absolute grey value error was less in magnitude than the noise level of a single measurement.

2007

[1] Purnama, Ketut E; Wilkinson, Michael H F; Veldhuizen, Albert G; van Ooijen, Peter; Lubbers, Jaap; Sardjono, Tri A; Verkerke, Gijbertus J;, "Ultrasound imaging for human spine: imaging and analysis", International Journal of Computer Assisted Radiology and Surgery, Vol. 2, pp. S114--S116, SPRINGER HEIDELBERG TIERGARTENSTRASSE 17, D-69121 HEIDELBERG, GERMANY, 2007

The results of ultrasound imaging of the human spine of a volunteer and the derivation of vertebral axial rotation (AR) and vertebral tilt (VT) are presented. The ARs and VTs were derived semi-automatically. In an ultrasound volume, the vertebral parts were enhanced using a length attribute filter, and localized using Robust Automatic Threshold Selection (RATS). Afterwards, a pair of two prominent regions of each vertebra was selected by ultrasound landmark points. Then, the centers of mass of these regions were used to calculate the ARs and VTs. The ARs and VTs were also determined manually based on the set of landmark points. The difference between the two methods determined the accuracy of the semi-automatic method. The overall results can be categorized into a confident, moderate, and less confident region, respectively, T3-T9, L3-L4, and other vertebrae. For the manual landmark determination, the confident region gave an error range of the ARs determination of 0 degrees-2.1 degrees/0.4 degrees-1.2 degrees (intraobserver/interobserver), and in the VTs determination it had the range of 0.3 degrees-3.2 degrees/0.2 degrees-1.9 degrees (intraobserver/interobserver). The difference between the results of semi-automatic method and the manual results was in the range -1.6 degrees to 1.3 degrees. The results confirm that ultrasound imaging is feasible to scan the human spine, and a semi-automatic method to derive ARs and VTs is also feasible.

Conference Proceedings

2016

[1] Hikmah, Nada Fitrieyatul; Arifin, Achmad; Sardjono, Tri Arief; Suprayitno, Eko Agus;, "A sequential hypothesis testing of multimodal cardiac analysis", Asea Uninet Scientific and Plenary Meeting 2016, pp. 63-77, 2016

Focus of our research group is development of integrated cardiac analysis system. A measurement and analysis system of cardiovascular system can be realized in an integrated system that includes all cardiac vital signs [1]. We have tested a signal processing framework of multimodal cardiac signals, electrocardiogram, carotid pulse, and phonocardiogram of normal subjects [2]. This paper describes a follow up effort in analysis and classification of heart conditions. Multimodal cardiac signals were recorded from 20 normal and 3 abnormal subjects. The measurements were performed after obtaining the consent of subjects. The data were recorded using a special instrument designed by our group, and digitized with 1 kHz sampling frequency. The recordings were performed in 10 trials, with 5 second for each trial. Parameters of the cardiac signals were extracted. Sequential hypothesis testing [3] was used in classification stage to produce a diagnosis of normal and abnormal heart based on the extracted parameters. The overlapping problem was solved by selecting two thresholds, upper and lower, resulted in no decision taken while the value of data tested was in the overlapping zone. The results of normal subjects showed that 90% of the data were identified in the 3rd test and 100% of the data could be identified after the 4th test, while the abnormal subjects showed that 80% of data were identified in the 3rd test and 100% of the data could be identified after the 4th test. The classification result recommended the proposed method should be realized in clinical use.

2015

[1] Al Kindhi, Berlian; Sardjono, Tri Arief;, "Pattern Matching Performance Comparison as Big Data Analysis Recomendations for Hepatitis C Virus (HCV) Sequence DNA", 2015 Third International Conference on Artificial Intelligence, Modelling and Simulation Pattern, pp. 99-104, 2015

A data bank can provide very useful information while mined properly.[27] In order to be optimally extracted, data mining can be done by observing capacity and characteristics of the data; so it can generates Knowledge Discovery in Databases as expected. For instance in Gene Bank, every single record of DNA, there are at least ten thousand sequences recorded. If the data is more than a hundred records, it will be a big sequence of data to be processed. Hepatitis C Virus (HCV) is a liver disease which can infect humans through blood. HCV infection can be asymptomatic, or it can be hepatitis acute, chronic, furthermore cirrhosis. Hepatitis C is generally does not show symptoms in the early stages. About 75 percent people with hepatitis C did not realize that they had infected until liver damage years later. Therefore needed a sequences DNA Mining is needed to analyse the DNA history whether it is infected by HCV or not. This study compares several methods of string matching to discover which methods have the best performance in processing DNA mining. In addition, this study also analyzed DNA HCV genetic mutations trend as a Knowledege Discovery in Database in DNA mining. Keywords

[2] Bangsawan, Hadid Tunas; Mardiyanto, Ronny; Sardjono, Tri Arief;, "Six key points lip's feature extraction using adaptive threshold segmentation", 2015 International Seminar on Intelligent Technology and Its Applications (ISITIA), pp. 261-266, IEEE, 2015

Key points of lip give important cues of lip shape. The application of lip's shape tracking could be used for speech recognition, lip reading and many multimedia applications. In this paper, a novel adaptive threshold segmentation for six key points lip's feature extraction algorithm is proposed. First, Viola Jones method is used to detects face in an image frame, after that the ROI of mouth is set. Color transformation in RGB space and adaptive threshold are used for lip segmentation. Further step, contour of the segmented lip is defined and filled in with certain color. Finally, the six key points, which are left and right corners, lower point, and three points of the Cupidon's bow of lip are scanned. The performance of the proposed method is satisfactory and compared with existing methods it brings a significant improvement in accuracy.
link: ieeexplore.ieee.org

[3] Hikmah, Nada Fitrieyatul; Arifin, Achmad; Sardjono, Tri Arief; Suprayitno, Eko Agus;, "A signal processing framework for multimodal cardiac analysis", 2015 International Seminar on Intelligent Technology and Its Applications, ISITIA 2015 - Proceeding, pp. 125-130, IEEE, 2015

The heart is a complex organ in the cardiovascular system which its measurement and analysis system in clinical level should be realized in an integrated system including all cardiac vital signs. A previous study combined ECG and PCG analysis could detect murmur symptom. However, the heart mechanical activity could not be described. This study developed a multimodal analysis of cardiac signals consisting of ECG signals, carotid pulse, and PCG. The purpose of this study was to develop and test an appropriate signal processing framework to facilitate parameter extraction and to enhance understanding of underlying mechanisms in the cardiac physiology. Frequency and time-frequency domain analysis of cardiac signals were performed to design sophisticated digital filters. Recursive digital filters were chosen in realizing segmentation methods and the advanced signal processing techniques were performed in parameter extraction. Results show the proposed method was able to detect QRS complex, P and T waves in ECG signal with 88% sensitivity and also percussion wave with 85.62% sensitivity. Sistolic (S1) and diastolic (S2) heart sound also could be separated. Classification of normal and the disease type of heart based on the cardiac parameters resulted by the presented signal processing framework would be next research topic.
link: ieeexplore.ieee.org

[4] Subur, Joko; Sardjono, Tri Arief; Mardiyanto, Ronny;, "Braille Character Recognition Using Find Contour Method", Electrical Engineering and Informatics (ICEEI), 2015 International Conference on, pp. 699-703, IEEE, 2015

Braille letters is characters designed for the blind, composed of six embossed points, arranged in a standard braille character. Braille letters is touched and read using fingers, therefore the sensitivity of the fingers is important. Those characters need to be memorized, so it is very difficult to be learned. The aim of this research is to create a braille characters recognition system and translate it to alpha-numeric text. Webcam camera is used to capture braille image from braille characters on the paper sheet. Cropping, grayscale, thresholding, erotion, and dilation techniques are used for image preprocessing. Then, find contour method and image recognition lookup table method are used to recognize the braille characters. The system can recognize braille characters with 100% accuracy even when the braille image is tilted up to 0.5 degrees
link: ieeexplore.ieee.org

[5] Wibowo, Madha Christian; Sardjono, Tri Arief;, "Spinal Curvature Determination from X-Ray Image using GVF Snake", Information & Communication Technology and Systems (ICTS), 2015 International Conference on, pp. 35-40, IEEE, 2015

Scoliosis is where the spine is curved, forming a "C" or "S" shape. The treatments are differs depending on the severity of Cobb Angle. But Cobb Angle measurement has a very low accuracy because of the unclear feature of spine in x-ray image. This paper discuss about spinal curvature determination using GVF Snake as the segmentation method and modified top-hat filter as pre-processing method. GVF Snake could fit the "S" shape best with parameters alpha=0.9, beta=0.5, and gamma=0.3. 10 frontal spinal x-ray images of scoliosis patients were used as segmentation samples. The modified top-hat filter is used for pre-processing the image with combination of disk sizes and attenuation factors of 1, 3, 5, 7, and 9. The average error of the qualified contour results is 6569 pixels. The best result gave an error of 3118 which is still couldn't fit the desired contour well.
link: ieeexplore.ieee.org

2014

[1] Arifin, Fatchul; Sardjono, Tri Arief; Purnomo, Mauridhi Hery;, "The Relationship Between Electromyography Signal of Neck Muscle and Human Voice Signal for Controlling Loudness of Electrolarynx", Biomedical Engineering: Applications, Basis and Communications, Vol. 26, No. 5, pp. 1450054, National Taiwan University, 2014

Human voice intonation is affected by pitch and loudness. Pitch is related to the frequency of human voice, while loudness is related to the magnitude of human voice. Someone who does not have vocal cords, has no ability to produce voice. This problem is suffered by laryngectomy patients. Over half of all laryngectomy patients worldwide use electrolarynx for the rehabilitation of their speech ability. Unfortunately, the electrolarynx voice produces monotonic and flat intonation. Small changes in pitch and loudness of electrolarynx will give a better expression in laryngectomy patients. However, previous researches have focused on utilization of electromyography (EMG) signal of neck muscle for only pitch control. In this research, the relationship between human voice intonation (i.e. frequency and magnitude) and EMG signals of neck muscles was studied by looking for their correlation and their mutual information. Human voice signal and EMG signal of neck muscle were recorded simultaneously while subjects w...
link: www.worldscientific.com

2013

[1] Madona, Putri; Arifin, Achmad; Sardjono, Tri Arief; Hendradi, Rimuljo;, "Segmentasi Suara Jantung S1 dan S2 Menggunakan Kurva Amplop", The 13th Seminar on Intelligent Technology and Its Applications, pp. 109-114, 2013

Proses segmentasi suara jantung adalah tahapan yang penting dalam analisa suara jantung. Mengetahui lokasi dan interval dari suara jantung S1 dan S2 serta komponen-komponennya yang didapatkan melalui proses segmentasi dapat menjadi informasi tentang kondisi kerja jantung. Salah satu metode segmentasi yang bisa digunakan adalah wavelet transform dan kurva amplop. Dalam penelitian ini digunakan Discrete Wavelet Transform (DWT), serta 2 algoritma kurva amplop yaitu Moving Average Filter dan Normalized Average Shannon Energy untuk segmentasi 28 data suara jantung yang terdiri dari normal dan 3 murmur. Perhitungan pada kedua algoritma kurva amplop tersebut menghasilkan kurva amplop yang bergeser dari sinyal aslinya. Semakin lebar window yang digunakan semakin besar pergeseran yang terjadi. Dari hasil segmentasi menunjukkan bahwa periode sistolik mempunyi durasi yang lebih pendek dan lebih konstan dibandingkan periode diastolik. Dan interval suara jantung S1 murmur sistolik lebih panjang dibandingkan suara jantung normal sementara interval suara jantung S2 murmur diastolik lebih panjang dibandingkan suara jantung normal. Algoritma segmentasi yang digunakan telah menunjukkan kemampuan dalam segmentasi suara jantung S1, S2 dan komponen-komponennya dengan tingkat keberhasilan 71.43%. Sebagai langkah selanjutnya perlu dilakukan ekstraksi ciri pada suara jantung S1 dan S2 hasil segmentasi untuk mengetahui kandungan frekuensi dari masing-masing suara jantung tersebut. Kata

[2] Nasuha, Aris; Sardjono, Tri Arief; Purnomo, Mauridhi Hery;, "Lip segmentation and tracking based on Chan-Vese model", 2013 International Conference on Information Technology and Electrical Engineering (ICITEE), pp. 155-158, 2013

Lip reading has wide spread application, e.g. audio-visual Automatic Speech Recognition (AV-ASR), silent speech interface and person identification. Lip segmentation is one of important step in lip reading, because it provides basic information to be processed in subsequent steps. Lip tracking is a process of locating lip to associate lip in consecutive video frames. Chan-Vese model is a region-based segmentation algorithm, which also can be used as tracking method. This algorithm can detect boundary of object which not defined by gradient, while classical active contour can't be applied. This method also can detect object by any initial curve in the image, not necessarily surround the object. This paper investigates about lip segmentation and tracking based on Chan-Vese model, preceded by the color segmentation. © 2013 IEEE.
link: www.scopus.com

2012

[1] Hakim, Luqman; Arifin, Achmad; Sardjono, Tri Arief;, "Identifikasi Suara Serak Berbasis Transformasi Wavelet Dan Algoritma Jaringan Syaraf Tiruan", The 13th Seminar on Intelligent Technology and Its Applications, pp. 119-124, 2012

Paper ini membahas identifikasi suara serak berbasis transformasi wavelet dan algoritma jaringan syaraf tiruan (JST). Serak merupakan indikator gangguan pada pita suara, sehingga identifikasi jenis suara normal dan serak yang sistematis dapat membantu diagnosa gangguan pita suara. Continous Wavelet Transform (CWT) dengan fungsi morlet digunakan untuk mengeksplorasi karakter sinyal suara dalam domain waktu dan frekuensi secara simultan Data objek penelitian berupa suara vokal “A”, “E”, “I”, “O”,”U” normal dan serak karena radang tenggorokan.Topologi JST terdiri 900 neuron pada layer input, 40 neuron pada hidden layer 1 dan 2, dan 10 neuron layer output. Hasil CWT menunjukan perbedaan karakter waktu-frekuensi antara sinyal suara normal dan serak. Pengujian menggunakan yang sudah dilatih (50 data, terdiri atas 5 sampel dari setiap vokal normal dan serak) 100% teridentifikasi dengan tepat. Kemampuan JST mengenali data baru diuji secara online dengan suara normal dan suara serak secara random. Didapatkan nilai sensitifitas 84%, spesifisitas 86%, dan efisiensi rata–rata 85% untuk kelima jenis suara vokal. Dengan hasil tersebut dapat diketahui bahwa CWT dan JST dapat digunakan untuk mengidentifikasi jenis suara normal dan serak. Hasil penelitian ini diharapkan dapat dikembangkan hingga terealisasi sisitem identifikasi jenis penyakit daerah pita suara berdasarkan analisa suara pasien.

[2] Madona, Putri; Arifin, Achmad; Tri, Arief; Hendradi, Rimuljo;, "Analisa Suara Jantung Berbasis Complex Continuous Wavelet Transform", Conference Paper, 2012

Penyakit jantung merupakan salah satu penyakit berbahaya yang masih menjadi penyebab utama kematian di seluruh dunia. Penyakit jantung valvular merupakan salah satu jenis penyakit jantung yang disebabkan ketidaknormalan fungsi katup-katup jantung. Teknik auskultasi tradisional yang masih umum dijalankan hingga saat ini mengandung kelemahan yang utama, yaitu faktor variabilitas intra- subjek dan inter-subjek, sehingga dapat mengakibatkan perbedaan hasil diagnosa. Dalam rangka mengembangkan sistem auskultasi modern diperlukan suatu metode yang mampu menganalisa suara jantung dengan baik. Oleh karena itu diusulkan sebuah metode analisis data suara jantung menggunakan Complex Continuous Wavelet Transform. Data yang digunakan adalah 28 data suara jantung yang dikumpulkan dari database publik serta 16 data dari pengambilan sampel suara jantung normal dari subjek normal menggunakan stetoskop digital. Prosedur pemrosesan sinyal untukmengekstrak fenomena fisik tersembuyi dari sinyal suara jantung terdiri dari 3 tahap. Pertama, Discrete Wavelet Transform, digunakan untuk mengurangi background noise pada sinyal asli. Kedua, sinyal disegmentasi menggunakan Normalized Average Shannon Energy. Ketiga, karakteristik dari sinyal akan diekstrak menggunakan Complex Continuous Wavelet Transform (CWT). Metode CWT yang telah diusulkan ini, menunjukkan kemampuan dalam mengekstrak dan mengidentifikasi suara jantung pertama S1, suara jantung kedua S2 dan komponen- komponennya. Hasil kontur time-frekuensi yang merefleksikan aktifitas mekanik dari katup maupun otot jantung diharapkan dapat digunakan dalam mendiagnosa kelainan jantung manusia.

[3] Subiyanto, Lilik; Sardjono, Tri Arief;, "Deteksi Cacat pada Material Baja Menggunakan Ultrasonik Non-Destructive Testing dengan Metode Continuous Transform", Seminar Nasional Teknologi Informasi & Komunikasi Terapan (Semantik), Vol. 2012, No. Semantik, pp. 466-472, 2012

Ultrasonik Non-Destructive Testing (NDT) adalah salah satu teknik pengujian material tanpa merusak benda uji melalui pantulan gelombang ultrasonik. Pengujian ini dilakukan untuk mendeteksi adanya cacat (flaw) atau retak (crack) padamaterial secara dini, dan menghindari kegagalan saat digunakan. Propagasi gelombang ultrasonik didalam struktur baja mengalami pemantulan atau pembelokan pada saat mengenai medium dengan indek yang berbeda. Propagasi gelombang ultrasonik tersebut kemudian diekstrak menggunakan metode Continuous Wavelet Transform (CWT) untuk merepresentasikan permukaan material yang didasarkan pada frekuensi dan waktu pantul/belok sebagai dasar jarak keberadaan rongga (cacat). CWT mempunyai keunggulan pada proses analisis sinyal yang lebih cepat dibandingkandengan metode lain seperti transformasi fourier dan mempunyai kemampuan untuk mentransformasikan sinyal nonstasioner dalam domain waktu-frekuensi. Material uji yang digunakan pada penelitian ini adalah baja rendah karbon (steel 1020) , sedangkan peralatan penunjang utama yang digunakan adalah probe ultrasonik tipe pulse-echo singleprobe 4MHz. Software utama yang digunakan untuk pengolahan sinyal pada penelitian ini adalah DELPHI. Dari hasilanalisis sinyal diketahui bahwa NDT dengan metode CWT mampu merekonstruksi cacat material dengan baik. Kata kunci : Ultrasonik NDT, Flaw, Crack, Pulse-echo, Continuous Wavelet Transform.

[4] Yatmono, Sigit; Arifin, Fatchul; Sardjono, Tri Arief; Purnomo, Mauridhy Hery;, "Pengenalan Suara Vocal Berbasis Microcamera", Prosiding Seminar Nasional Aplikasi Sains & Teknologi (SNAST) Periode III, No. November, pp. 146-152, 2012

Suara merupakan salah satu alat komunikasi manusia yang utama. Tanpa suara, manusia tidak akan dapat lagi berkomunikasi, menyampaikan kemauannya kepada orang lain secara bebas. Berbagai usaha agar para penderita tuna laring (laringnya diambil, karena menderita kanker stadium tinggi) dapat kembali berbicara telah banyak dilakukan. Diantaranya melalui suara perut esophagus dan menggunakan alat electrolarynx. Berbicara dengan suara perut bukanlah hal yang mudah. Untuk dapat melakukanya para pasien harus belajar ekstra keras. Sedangkan berbicara menggunakan alat elektrolarynx, disamping harga alatnya yang sangat maha,l suara yang dihasilkannya pun sangat datar, tidak ada intonasi sama sekali. Suara yang dihasilkan nya “mirip robot”. Oleh karena itu perlu ada inovasi lain bagaimana mendesain alat bantú wicara bagi pasien tunalaring.Dalam paper ini akan disajikan bagaimana dapat mengenali suara vocal berbasis microcamera. Microcamera digunakan untuk merekam bentuk mulut ketika mengucapkan vocal tertentu. Selanjutnya citra hasil perekaman diolah untuk dikenali. Pengenalan dilakukan dengan menggunakan algoritma Jaringan syaraf tiruan. Hasil pengujian menunjukkan sistem yang dibangun mempunyai validitas 78,3 %. Hasil yang disajikan dalam paper ini diharapkan akan dapat menjadi dasar pengembangan alat bantú wicara bagi pasien tunalaring

2010

[1] Arifin, Fatchul; Sardjono, Tri Arief; Purnomo, Mauridhy Hery;, "Esophageal speech Recognition Utilizing Pulse Coupled Neural Network.", The 6th International Converence on Boiomedical Engineering., pp. 1-4, 2010

The laryngectomies patient has no ability to speak normally because their vocal chords have been removed. The simplest option for the patient to speech again is esophageal speech. Meanwhile, the voice recognition technology has been increased rapidly. In order the voice recognition technology also can be used by esophageal speech correctly, the esophageal speech recognition technology must be developed. This paper describes a system for esophageal speech identification. Two main parts of the system, feature extraction and pattern recognition were used in this system. The Pulse Coupled Neural Network – PCNN is used to extract the feature and characteristic of esophageal speech. The pattern recognition, multi layer perceptron, will recognize the sound patterns. From the experiments and results It can be concluded that the system can recognize esophageal speech very well up to 95,8 %. It is also can be known that PCNN can be utilized as feature extractor very well. Keywords:

2009

[1] Purnama, I. K. E.; Wilkinson, M. H. F.; Veldhuizen, A. G.; van Ooijen, P. M. A.; Sardjono, T. A.; Lubbers, J.; Verkerke, G. J.;, "Following scoliosis progression in the spine using ultrasound imaging", World Congress on Medical Physics and Biomedical Engineering, IFMBE Proceedings, Vol. 25, No. 2, pp. 600-602, Springer Berlin Heidelberg, 2009

Scoliosis is a three-dimensional deformation of the spine which is characterized by a lateral deviation of the spine and axial rotation of the vertebrae. It must be monitored frequently to be in time to start the treatment in case of progression. Nowadays, X-ray is used, but has a detrimental effect and provide only 2D data. Ultrasound would allow a frequent and 3D view on the spine and thus is ideal to follow scoliosis progression. A feasibility study on ultrasound is presented. A freehand 3D ultrasound system was used to scan the back of a volunteer. In the resulting ultrasound volume, the vertebral features such as transverse processes, laminae, and superior articular processes appear prominently along with the non-vertebral features like muscles, head of the ribs and parts of the pleura. The 3D orientation of the vertebrae, determined by the axial rotation and vertebral tilt was determined semiautomatically. The axial rotation and vertebral tilt measurements in the region of the thoracic vertebrae T4 - T9 delivered good accuracy, in other regions the accuracy was acceptable. In conclusion, imaging the human spine using ultrasound is feasible. The result provides a basis towards the aim to follow scoliosis progression using ultrasound.
link: link.springer.com

[2] Sardjono, T. A.; Hidayati, R; Purnami, N; Noortjahja, A; Verkerke, G. J.; Purnomo, M. H.;, "A preliminary result of voice spectrum analysis from laryngectomised patients with and without electro larynx: A case study in Indonesian laryngectomised patients", Instrumentation, Communications, Information Technology, and Biomedical Engineering (ICICI-BME), 2009 International Conference on, pp. 1-5, IEEE, 2009

Laryngectomy is the treatment to totally remove the larynx in order to clear out laryngeal cancer. The trachea is led outside to the neck and thus is separated from the esophagus. The patient no longer breathes through its mouth but through a hole in his neck. This drastic change in the human body causes a loss of the ability of speech for the patient. Patient will learn to speech using esophageal speech or using an electro-larynx. This paper describes the preliminary speech spectrum analysis resulted from the normal voice and Indonesian laryngectomised patient with and without electro larynx. The voice will be recorded and analyzed using a spectrum analysis application to know the fundamental frequency. The result shows that the fundamental frequency of `a' and `b' sound from laryngectomised patient without electrolarynx are 363 Hz and 727 Hz, respectively. By using an electrolarynx those frequency are 888 Hz and 1000 Hz, respectively. It is hope that these result can be used to develop a new electronic voice producing element with an appropriate voice based on each human voice characteristics.
link: ieeexplore.ieee.org

2007

[1] Pumama, K.E.; Wilkinson, M.H.F.; Veidhuizen, A.G.; Van Ooijen, P.M.A.; Lubbers, J.; Sardjono, T.A.; Verkerke, G.J.;, "Branches filtering approach for max-tree", VISAPP 2007 - 2nd International Conference on Computer Vision Theory and Applications, Proceedings, Vol. IFP, pp. 328-332, 2007

A new filtering approach called branches filtering is presented. The filtering approach is applied to the Max-Tree representation of an image. Instead of applying filtering criteria to all nodes of the tree, this approach only evaluate the leaf nodes. The expected objects can be found by collecting a number of parent nodes of the selected leaf nodes. The more parent nodes involve the wider the area of the expected objects. The maximum value of the number of parents (PLmax) can be determined by inspecting the output image before having unexpected image. Different images have found have different PLmax values. The branches filtering approach is suitable to extract objects in a noisy image as long as these objects can be recognised from its prominent information such as intensity, shape, or other scalar or vector values. Furthermore, the optimum result can be achieved if the areas which have the prominent information are present in the leaf nodes. The experiments to extract bacteria from noisy image, localizing bony parts in a speckled ultrasound image, and acquiring certain features from a natural image appeared to be feasible give the expected results. The application of the branches filtering approach to a 3D MRA image of human brain to extract the blood vessels gave also the expected image. The results show that the branches filtering can be used as an alternative filtering approach to the original filtering approach of Max-Tree.

[2] Sardjono, T. A.; Wilkinson, M. H. F.; van Ooijen, P. M. A.; Veldhuizen, A. G.; Purnama, K. E.; Verkerke, G. J.; Ooijen, P M A Van; Veldhuizen, A. G.;, "Spinal Curvature Determination from an X-Ray Image Using a Deformable Model", 3rd Kuala Lumpur International Conference on Biomedical Engineering 2006, Vol. 15, pp. 291-295, Springer Berlin Heidelberg, 2007

This paper presents a spinal curvature determination from frontal X-ray images of scoliotic patients. A new deformable model, Modified CPM (Charged Particles Model), has been developed and used to determine the spinal curvature. The Modified CPM is a new approach of a deformable model based on CPM, which was introduced in 2004. The X-ray image is charged negatively according to the edge-map or gradient-magnitude image. The particles are attracted towards the contour of the object of interest, because this contour is very dark, thus charged very negatively. We modified the CPM by putting springs between the particles to prevent the particles from moving away and keep the movement of the particles in the appropriate distance without reducing the flexibility to follow the curvature. The results of the implementation show the effectiveness of the modified charged-particle model for spinal curvature determination on X-ray images.
link: link.springer.com

Books/Thesis

2007

[1] Sardjono, Tri Arief;, "Spinal X-ray image analysis in scoliosis", 2007

In this thesis new image analysis methods are discussed to determine the curvature of scoliotic patients characterised by the Cobb angle and to enhance the vertebral parts based on features from a frontal X-ray image. Chapter 1 provides some background information on scoliosis, how to diagnose it, the treatment options and the problems related to spinal X-ray images. Then, a problem definition is formulated and a general block diagram of a proposed solution is explained briefly, followed by a detailed explanation of each part. The knowledge of the vertebral geometry helps us to have a better understanding about the relevant features of a vertebra so that we can develop an image analysis system that can detect those features