EMITTER International Journal of Engineering Technology
Not a member yet
160 research outputs found
Sort by
Enhancing the Productivity of Wire Electrical Discharge Machining Toward Sustainable Production by using Artificial Neural Network Modelling
No full textSustainability plays an important role in manufacturing industries through economically-sound processes that able to minimize negative environmental impacts while having the social benefits. In this present study, the modeling of wire electrical discharge machining (WEDM) cutting process using an artificial neural network (ANN) for prediction has been carried out with a focus on sustainable production. The objective was to develop an ANN model for prediction of two sustainable measures which were material removal rate (as an economic aspect) and surface roughness (as a social aspect) of titanium alloy with ten input parameters. By concerning environmental pollution due to its intrinsic characteristics such as liquid wastes, the water-based dielectric fluid has been used in this study which represents an environmental aspect in sustainability. For this purpose, a feed-forward backpropagation ANN was developed and trained using the minimal experimental data. The other empirical modelling techniques (statistics based) are less in flexibility and prediction accuracy. The minimal, vague data and nonlinear complex input-output relationship make this ANN model simple and perfects method in the manufacturing environment as well as in this study. The results showed good agreement with the experimental data confirming the effectiveness of the ANN approach in the modeling of material removal rate and surface roughness of this cutting process
AI-Josyu: Thinking Support System in Class by Real-time Speech Recognition and Keyword Extraction
No full textIn this paper, we present a thinking support system, AI-Josyu. This system also operates as a class support system which helps to teachers for lightening their work. AI-Josyu is implemented based on media-driven real-time content management framework. The system links real world media and legacy media contents together. In resent years, it is easier to collect a large amount of various kinds of data which are created with sensors in the real world. The system realizes interconnection and utilization of legacy media contents. The legacy media contents are generated and scattered on the Internet. The framework has four modules, which are called “acquisition,†“extraction,†“selection,†and “retrieval.†The real world media and the legacy media contents are interconnected by these modules. This interconnection includes semantic components. This system records teacher's voice of its lecture in real time and presents retrieved legacy media contents corresponding to subject of the lecture. By this presentation, preparing of the legacy contents is not required. This system automatically retrieves and shows the legacy media contents. This system helps students to understand contents of the lecture. In addition, the system attends to expansion of ideas. We constructed the system and conducted the demonstration in class. It shows that the system is helpful to teacher and students for expansion of thinking
Spatio-Temporal Associative Mining for Earthquake Data Distribution in Indonesia
No full textIndonesia is a country that has the highest seismically activity in the world. This country has really high earthquake frequency because of it traversed by three plate meeting plate and located in Ring of Fire area. The shaking events from an earthquake are very strong and propagate in all directions, capable of destroying even the strongest civilian buildings, so there is no doubt that there are many victims of human lives. The other facts, earthquake in Indonesia have seismic relation between the provinces. In this paper, we present a new earthquake Spatio-temporal mapping system based on the association confidence value from the result of associative mining process on earthquake data distribution in Indonesia. The system proposed three main functions which are (1) Data Acquisition which taken from four data provider, then preprocess and combine it become one, (2) Associative Mining process to get the rule of association earthquake between provinces in Indonesia, and (3) Earthquake Association Spatio-Temporal Model from the highest confidence value and Visualization. We use data from several earthquake data providers from 1900 until 2018. To perform our proposed Spatio-temporal earthquake association mapping system, we divided the data to become a 5-year discrete partition. After that, we mining the rule and get the highest confidence value from each period. This confidence value is used for modeling and visualization of our Spatio-temporal mapping system. As a result of this study, we manage to generate earthquake association risk mapping from 13 provinces that had earthquake connectivity between each other. The provinces are Aceh, Sumatera Utara, Bengkulu, East Java, Bali, NTB, NTT, Maluku, North Maluku, Gorontalo, North Sulawesi, Papua dan West Papua
Nuclei Detection and Classification System Based On Speeded Up Robust Feature (SURF)
No full textTumors contain a high degree of cellular heterogeneity. Various type of cells infiltrate the organs rapidly due to uncontrollable cell division and the evolution of those cells. The heterogeneous cell type and its quantity in infiltrated organs determine the level maglinancy of the tumor. Therefore, the analysis of those cells through their nuclei is needed for better understanding of tumor and also specify its proper treatment. In this paper, Speeded Up Robust Feature (SURF) is implemented to build a system that can detect the centroid position of nuclei on histopathology image of colon cancer. Feature extraction of each nuclei is also generated by system to classify the nuclei into two types, inflammatory nuclei and non-inflammatory nuclei. There are three classifiers that are used to classify the nuclei as performance comparison, those are k-Nearest Neighbor (k-NN), Random Forest (RF), and State Vector Machine (SVM). Based on the experimental result, the highest F1 score for nuclei detection is 0.722 with Determinant of Hessian (DoH) thresholding = 50 as parameter. For classification of nuclei, Random Forest classifier produces F1 score of 0.527, it is the highest score as compared to the other classifier
Observation of Fish Dissemination Pattern on Madura Coastal Using Segmentation of Satellite Images
No full textAlmost traditional fishermen still use manual methods to catch fish that rely on experience in fishing and information among fellow fishermen. This method is not effective for maximizing fish production. A good pattern or strategy is needed to increase fish production. In determining dissemination pattern of fish, it can be predicted from physical parameters such as temperature, salinity, chlorophyll, turbidity, total suspended solids, and colored dissolved organic matter using the Landsat 8 images. Â This research area is on the Island of Madura Coast. The pattern is determined by using Lagrange Interpolation and clustering using K-Means. The results of the study of the pattern of fish dissemination were then validated with data from the Dinas Kelautan dan Perikanan Jawa Timur. The results between fish patterns and validation data in 2015 showed similarities in January, February, March, May, June, July, August, September. In 2016, results between fish patterns and validation data showed that similarities in July, August, September, and December. In 2017, results between fish patterns and validation data showed similarities in November. 2015 has the most similarities between the patterns and validation data and the least similarity are 2017
The Multipath Influence in Real-Time Kinematic of GNSS Observations at Different Antenna Heights
No full textMultipath is a dominant error source in Real-Time Kinematic (RTK) applications that reduces the position, time and velocity accuracy. Mitigation of such errors can be achieved by better signal processing and antenna design. This paper attempts to examine the different height of RTK system antenna with regards to the multipath error. The results obtained in this work show height significantly change of multipath in pseudo range (MP1) and multipath in the carrier phase (MP2). Different antenna height does not give the same multipath error result in the tests that we have conducted in this work. The optimal height of the antenna was achieved as two meters in order to obtain a minimum multipath error for MP1 and MP2. At the end of this work, we experimentally proved that there is an inverse relationship between the height of the antenna and multipath with RTK algorithm
Medical Image Encryption Using Modified Identity Based Encryption
No full textThe development of technology and communication also affects the level of security needed for digital image transmission. It is known that digital images now have important meanings in both communication and video conference. In this paper, we propose a security method for medical encryption in the form of images. The proposed method is implemented in the modified Identity-Based Encryption scheme. The encryption algorithm used is Elliptic Curve Cryptography (ECC) to generate key pairs and the Advanced Encryption Standard (AES) to generate symmetric keys and encrypt process. This method has been tested based on computation time, histogram analysis and statistical analysis. The results of the test were obtained that the proposed method was resistant to multiple attacks despite having slower computing time. The proposed compute time error percentage is 1.69% for key generator stages and 0.07% for total compute time at the encrypt-decrypt stage
Implementation Fuzzy C-Means on Decision Support System BPNT (Bantuan Pangan Non-Tunai) Ministry of Social Affairs Indonesia
No full textDecision Support System can be an alternative solution to determine the candidate's decision. Bantuan Pangan Non-Tunai (BPNT) are selected based on criteria determined by the Ministry of Social Affairs of the Republic of Indonesia. BPNT recipients are conducted by the government to help someone who is less able to meet their daily needs. The occurrence of errors in determining the eligibility of prospective beneficiaries is a major problem, based on these problems there needs to be an information system that can provide a valid BPNT recommendation and one of which uses a grouping method with the Fuzzy C-Means (FCM) algorithm. System development using the waterfall method. The results of system implementation and testing showed that 90% of the system was following what was expected according to the results of the test with the system being built
Focused Time Delay Neural Network For Tuning Automatic Voltage Regulator
No full textThis paper proposes a novel controller for automatic voltage regulator (AVR) system. The controller is used Focused Time Delay Neural Network (FTDNN). It does not require dynamic backpropagation to compute the network gradient. FTDNN AVR can train network faster than other dynamic networks. Simulation was performed to compare load angle (load angle) and Speed. The performance of the system with FTDNN-AVR has compared with a Conventional AVR (C-AVR) and RNN AVR. Simulations in Matlab/Simulink show the effectiveness of FTDNN-AVR design, and superior robust performance with different cases
Multi-Distance Veins Projection Based on Single Axis Camera and Projector System
No full textEvery person has different location of veins, some veins are easily detected because it is visible due to thin tissue, and the other are invisible. This different location of veins causes intravenous access procedures and the procreas of intravenous therapy become longer. Multi-distance vein projections aim to simplify the measurement process where the device and object do not have to be at a certain distance. Some research that has been done especially for real-time vein projection does not conduct how the characteristics of projection at different distances. In this paper, we propose a method for performing multi-distance real-time back-projection by using the intersection between camera and projector. This method equiped with an ultrasonic distance sensor to identify the projection characteristic in any distance. In its implementation, this method is able to project at a distance of 20-40 cm with a maximum projection error of 0.6 mm. The measurement angle tolerance between the object and the device is ±5 degrees with a maximum error of 0.7 mm