No abstract

Aplikasi Decision Support Systems  (DSS) atau Sistem Penunjang Keputusan (SPK) penentuan Uang Kuliah Tunggal  (UKT)  Mahasiswa  Politeknik  Negeri  Malang  adalah  aplikasi  yang  digunakan  untuk  menentukan kelompok biaya  kuliah tunggal  yang ditanggung oleh masing  mahasiswa Politeknik Negeri Malang aplikasi ini dikembangkan  menggunakan  bahasa  pemrograman  PHP,  database  Mysql  dan  mengimplementasikan  Metode Multi Objective Optimization on the Basis of Ratio Analysis  (MOORA)  dengan menggunakan metode tersebut dapat  memberikan  alternatif  terbaik  dalam  penentuan  uang  kuliah  tunggal  berdasarkan  kemampuan  ekonomi mahasiswa.

Human face recognition is one of the most challenging topics in the areas of image processing, computer vision, and pattern recognition. Before recognizing the human face, it is necessary to detect a face then extract the face features. Many methods have been created and developed in order to perform face detection and two of the most popular methods are Viola-Jones Haar Cascade Classifier (V-J) and Histogram of Oriented Gradients (HOG). This paper proposed a comparison between VJ and HOG for detecting the face. V-J method calculate Integral Image through Haar-like feature with AdaBoost process to make a robust cascade classifier, HOG compute the classifier for each image in and scale of the image, applied the sliding windows, extracted HOG descriptor at each window and applied the classifier, if the classifier detected an object with enough probability that resembles a face, the classifier recording the bounding box of the window and applied non-maximum suppression to make the accuracy increased. The experimental results show that the system successfully detected face based on the determined algorithm. That is mean the application using computer vision can detect face and compare the results.

Abstract-Feature extraction for gait recognition has been created widely. The ancestor for this task is divided into two parts, model based and free-model based. Model-based approaches obtain a set of static or dynamic skeleton parameters via modeling or tracking body components such as limbs, legs, arms and thighs. Model-free approaches focus on shapes of silhouettes or the entire movement of physical bodies. Model-free approaches are insensitive to the quality of silhouettes. Its advantage is a low computational costs comparing to modelbased approaches. However, they are usually not robust to viewpoints and scale. Imaging technology also developed quickly this decades. Motion capture (mocap) device integrated with motion sensor has an expensive price and can only be owned by big animation studio. Fortunately now already existed Kinect camera equipped with depth sensor image in the market with very low price compare to any mocap device. Of course the accuracy not as good as the expensive one, but using some preprocessing method we can remove the jittery and noisy in the 3D skeleton points.Our proposed method is to analyze the effectiveness of 3D skeleton feature extraction using 3D Discrete Wavelet Transforms (3D DWT). We use Kinect Camera to get the depth data. We use Ipisoft mocap software to extract 3d skeleton model from Kinect video. From the experimental results shows 83.75% correctly classified instances using SVM.

Lahar flow is recognized as among the worst secondary hazards from volcanic disaster. Intense rainfall with long duration is frequently associated with lahar flow. In this study, estimation of a rainfall threshold likely to trigger lahar flow is presented in the first part. The second part discusses its implementation by assessing the growth of observed and predicted rainfall, including the uncertainties. The study area is Merapi Volcano, one of the most active volcanoes in Indonesia, including rivers on the flank of Mount Merapi that are vulnerable to debris flow. The rainfall indices needed to describe the conditions that generate lahars or not were determined empirically by evaluating the hourly and working rainfall using X-band multiparameter (X-MP) weather radar. Using past records of lahar flow, the threshold lines separating rainfall that triggers lahars or not were analyzed for the Putih, Gendol, Pabelan, and Krasak Rivers. The performance of several critical lines was evaluated using Bayesian probability based on skill rates from a contingency matrix. The study shows that the line intercept of the critical lines after a significant eruption in 2010 was higher than those lines developed before 2010, indicating that the rivers are currently at lesser risk. Good representation was shown by the thresholds verified with actual rainfall progression and lahar event information on February 17, 2016, at the Gendol and Pabelan Rivers. These rainfall critical lines were the basis for judging the debris flow occurrence by analyzing the track record of predicted rainfall progression. The uncertainty of rainfall short-term prediction from the extrapolation model was evaluated by perturbing the advection vector of rain echo motion. This ensemble forecast product could provide a plausible range of prediction possibility as assistance in gaining the confidence with which a lahar could be predicted. The scheme presented herein could serve as a useful tool for a lahar early warning system in the area of the Merapi Volcano.

Abstract-Feature extraction for gait recognition has been created widely. The ancestor for this task is divided into two parts, model based and free-model based. Model-based approaches obtain a set of static or dynamic skeleton parameters via modeling or tracking body components such as limbs, legs, arms and thighs. Model-free approaches focus on shapes of silhouettes or the entire movement of physical bodies. Model-free approaches are insensitive to the quality of silhouettes. Its advantage is a low computational costs comparing to modelbased approaches. However, they are usually not robust to viewpoints and scale. Imaging technology also developed quickly this decades. Motion capture (mocap) device integrated with motion sensor has an expensive price and can only be owned by big animation studio. Fortunately now already existed Kinect camera equipped with depth sensor image in the market with very low price compare to any mocap device. Of course the accuracy not as good as the expensive one, but using some preprocessing we can remove the jittery and noisy in the 3D skeleton points. Our proposed method is part of model based feature extraction and we call it 3D Skeleton model. 3D skeleton model for extracting gait itself is a new model style considering all the previous model is using 2D skeleton model. The advantages itself is getting accurate coordinate of 3D point for each skeleton model rather than only 2D point. We use Kinect to get the depth data. We use Ipisoft mocap software to extract 3d skeleton model from Kinect video. From the experimental results shows 86.36% correctly classified instances using SVM.

<p><strong>Abstrak</strong><em><br /></em></p><p><em>Internet of Things</em> merupakan perkembangan teknologi berbasis internet masa kini yang memiliki konsep untuk memperluas manfaat yang benda yang tersambung dengan koneksi internet secara terus menerus. Sebagai contoh benda elektronik, salah satunya adalah Raspberry Pi. Teknologi ini memiliki kemampuan memberikan informasi secara otomatis dan <em>real time</em>. Salah satu pemanfaatan perkembangan teknologi ini di bidang perikanan adalah sistem pemantauan air kolam. Pada prakteknya, para pembudidaya ikan lele masih melakukan pemantauan tersebut secara konvensional yaitu dengan cara mendatangi kolam ikan. Hal ini berpengaruh terhadap efisiensi waktu dan keefektifan kerja pembudidayaan ikan.<strong></strong></p><p>Pada penelitian ini dikembangkan alat yang berfungsi untuk membantu memantau dan mengontrol kualitas air kolam ikan lele berbasis <em>Internet of Things</em>. Piranti yang diperlukan adalah sensor keasaman (pH), sensor suhu dan sebuah relay untuk mengatur aerator oksigen air. Data dari sensor-sensor tersebut direkam oleh Raspberry Pi untuk kemudian diolah menjadi informasi sesuai kebutuhan pengguna melalui perantara internet secara otomatis. Selanjutnya data-data tersebut dapat ditampilkan dengan berbagai macam platform, salah satunya dengan model <em>mobile web</em>.  <strong></strong></p><p>Hasil uji menunjukan bahwa pengembangan teknologi <em>Internet of Things</em>  pada sistem ini dapat membantu pembudidaya untuk melakukan pemantauan terhadap kualitas air secara otomatis. Sistem otomasi yang dikembangkan menjanjikan peningkatan keberhasilan dalam pembudidayaan ikan lele.</p><p> </p><p><em><strong>Abstract</strong></em></p><p><em>For recent years, the Internet of Things becomes the topic interest of improvement based on technologies that have the concept of extending the benefits of an object that is connected to an internet constantly. This technology has the ability to provide information automatically and real time. One of expansion in the field of fishery is the water ponds monitoring system. In the fact, the catfish farmers are still doing conventional monitoring by coming to the fish pond. This could affects the efficiency of time and effectiveness of fish cultivation work.</em></p><p><em>In this research, the systems that can monitor and control the quality of catfish water ponds based on the Internet of Things is proposed. The necessary tools are acidity sensor (pH), temperature sensor and a relay to adjust water oxygen aerator. The data sensors have been recorded by Raspberry Pi that processed into information according to user needs through internet automatically. Furthermore, these data have been displayed with a variety of platforms, one with a mobile web model.</em></p><p><em>The results shows that the system based on Internet of Things technology can monitor the water quality automatically. The automation system promises the productivity of catfish farming.</em></p>

Proses pemilihan produk hasil pertanian dan perkebunan umumnya sangat bergantung pada presepsi manusia terhadap komposisi warna yang dimiliki citra yaitu buah­buahan. Cara manual dilakukan berdasarkan pengamatan visual secara langsung pada buah yang akan diklasifikasi. Identifikasi dengan cara ini memiliki beberapa kelemahan diantaranya adalah waktu yang dibutuhkan relatif lama serta menghasilkan produk yang beragam karena adanya keterbatasan visual manusia, tingkat kelelahan dan perbedaan persepsi tentang mutu buah. Perkembangan ilmu pengetahuan dan teknologi pengolahan citra digital memungkinkan untuk memilah produk pertanian dan perkebunan tersebut secara otomatis dengan bantuan aplikasi pengolahan citra. Identifikasi kematangan buah tomat ini menerapkan metode pembelajaran Perceptron.  Pendukung identifikasi menggunakan bantuan  media  webcam  sebagai  pengambilan  gambar  tomat  yang  dibuat  histogram  warnanya  kemudian diidentifikasi menggunakan jaringan syaraf tiruan agar komputer dapat memperoleh informasi citra dan dapat mengetahui jenis kematangan buah tersebut. Tingkat keberhasilan identifikasi kematangan buah tomat yang didapatkan menggunakan  metode pembelajaran perceptron dengan  tingkat  keberhasilan 43,33%. Dari hasil identifikasi yang diperoleh menghasilkan 3 output yaitu Mentah 10%, Setengah Matang  6,66%, dan Matang 26,66%.