Hasil Pencarian  ::  Simpan CSV :: Kembali

"Komputasi intelejensia yang digunakan dalam masalah klasifikasi pola dapat digolongkan menjadi dua bagian, yaitu yang berbasis pada Neural Network dan yang berbasis pada Pembelajaran Statistika (Statistical Learning). Pembelajaran yang berbasis statistika, pertama kali ditemukan oleh Vapnik pada dekade tujuh-puluhan. Untuk masalah klasifikasi pola Vapnik mengembangkan metode hyperplane optimal separation, atau dikenal juga dengan nama metode Support Vector Machines (SVM). Pada awalnya SVM dirancang hanya untuk menyelesaikan masalah klasifikasi biner, yaitu dari data-data yang ada, diklasifikasikan menjadi dua kelas. Untuk mengklasifikasikan data yang terdiri dari lebih dari dua kelas, metode SVM tidak dapat langsung digunakan. Ada beberapa metode yang dapat digunakan untuk menyelesaikan masalah klasifikasi multikelas SVM yaitu: metode One-vs-One dan metode One-vs-Rest. Kedua metode ini merupakan perluasan dari klasifikasi biner SVM. Kedua metode tersebut akan dibahas di artikel ini dan akan dilihat kinerjanya dalam mengklasifikasikan aroma. Data aroma yang digunakan dalam percobaaan ini terdiri dari 3 jenis aroma, masing-masing aroma terdiri atas 6 kelas. Pembagian kelas ini berdasarkan pada konsentrasi alkohol yang dicampurkan pada masing-masing aroma. Misalkan untuk aroma A, terdapat 6 jenis aroma A dengan kandungan alkohol : 0%, 15%, 25%, 30%, 45% dan 75%. Kinerja dari kedua metode diukur berdasarkan kemampuan untuk mengenal dan mengklasifikasikan aroma, dengan tepat dan sesuai dengan jenis atau kelas, dari data yang diberikan.

---

Aroma classification using one-vs-one and one-vs-rest methods. Computational Intelligence used in pattern classification problem can be divided into two different parts, one based on Neural Network and the other based on Statistical Learning. The Statistical Learning discovered by Vapnik on 70-est decade. For the pattern classification, Vapnik developed hyperplane optimal separation, which is known as Support Vector Machines Method (SVM). In the beginning, SVM was designed only to solve binary classification problem, where data existing are classified into two classes. To classify data whose consist of more than two classes, the SVM method can not directly be used. There are several methods can be used to solve SVM multiclasses classification problem, they are One-vs-One Method and One-vs-Rest Method. Both of this methods are the extension of SVM binary classification, they will be discussed in this article so that we can see their performance in aroma classification process. Data of aroma used in this experiment is consisted of three classes of aroma, each of them has six classes. The division of this class is based on alcohol concentration mixed into each of those aromas. For example, for aroma A, there are six kinds of aroma A with different alcohol concentration: 0%, 15%, 25%, 30%, 45% and 75%. The performance of these methods is measured based on their ability to recognize and classify aroma, precisely and match with the right class or variety of data existed."

"Upaya pengembangan sistem deteksi kebocoran gas telah menjadi penelitian serius bagi banyak ahli di bidang komputasi, informatika dan fisika. Sistem deteksi gas menjadi kebutuhan mendesak saat ini mengingat banyaknya ancaman yang muncul dalam kehidupan masyarakat, seperti ancaman bom, kebocoran pipa gas, kebakaran hutan, dan lain sebagainya. Particle Swram Optimization (PSO) adalah salah satu algoritma yang handal untuk pencarian sumber gas. Penelitian ini akan menganalisa simulator 3D robot pencari sumber gas yang dibuat dengan menggunakan Open Dynamics Engine. Simulator ini merupakan pengembangan beberapa orang secara bertahap di mana terdapat beberapa variasi dalam implementasi algoritmanya. Penulis akan mencoba menganalisa kinerja setiap simulator ini. Riset robot pendeteksi gas ini dimulai oleh Wisnu Jatmiko yang berhasil mengembangkan sistem deteksi gas melalui modifikasi PSO dengan memanfaatkan mekanisme Detect and Response, penggunaan Charge Robot, dan pemanfaatan prinsip Wind Utilities. Pada penelitian selanjutnya, algoritma ini dikembangkan menjadi empat metode, yaitu metode penutupan sumber gas, metode peningkatan mekanisme DR-PSO dengan penambahan fase spread, metode pemanfaatan paralelisasi niche, dan metode penggunaan range global best.Penulis akan menganalisa performa robot dalam menutup semua kebocoran gas berdasarkan metode-metode tersebut. Analisa pertama dilakukan pada kasus dimana robot menggunakan metode penutupan sumber gas dan metode penigkatan mekanisme DR-PSO dengan penambahan fase spread namun belum mengenal paralel niche. Analisa kedua dilakukan pada kasus dimana robot menggunakan metode seperti pada analisa pertama namun dengan paralel niche. Analisa ketiga dilakukan pada kasus di mana robot menggunakan metode seperti pada analisa kedua namun dengan adanya tambahan sebuah robot yang menjadi pemimpin setiap niche.

---

Developing a gas leakage detection system has become a serious research for many experts in the field of computing, informatics and physics. Gas detection system is an urgent need especially nowadays considering the threats that appear in people's lives, such as bomb threats,gas leaks, forest fires, and so forth. Particle Swarm Optimization (PSO) algorithm is one of the algorithm to search the source of the gas leak. This research will analyze the performance of 3D robot simulators that search source of gas leak. This simulator is built using the Open Dynamics Engine. This simulator is developed by some people which are differs in the implementation of algorithm. The author tries to analyze the performance of each simulator. Research on robotic that serve as gas detection started by Wisnu Jatmiko when he successfully developed gas detection systems through PSO using the Detect and Response mechanisms, the use of Charge Robot, and the principles of Wind Utilities. On further research, algorithms were developed into four methods, namely methods of closing the gas source, methods of increasing DR-PSO mechanism with the addition of phase spread, the utilization of parallelization niche methods, and methods using of global best range. The author will analyze the performance of all robots in the gas leak detection based on these methods. The first analysis is done on cases where the robot using the method of closing the gas method and the improving of DR-PSO mechanism with the addition of spread phase but have not implemented parallel niche. On second analysis, conducted on cases where robots use the method which is similar to first analysis but with a parallel niche implemented. On third analysis, conducted on cases where robot uses methods such as on the second analysis but with the addition of a robot or more which is being the leader of each niche."

"ABSTRAKDalam makalah ini, penelitian difokuskan kepada medan makna kata bau di dalam bahasa Indonesia. Metode yang digunakan dalam penelitian ini adalah kualitatif. Data di dalam penelitian ini adalah kata-kata yang memiliki hubungan makna dengan kata bau di dalam Kamus Besar Bahasa Indonesia. Teori yang digunakan di dalam penelitian ini adalah teori analisis komponen makna Nida 1975 . Hasil penelitian ini menunjukkan bahwa kata bau memiliki dua kategori, yaitu bau sedap dan bau tidak sedap.Kata kunci: bau, medan makna, komponen makna.

---

ABSTRACTIn this paper, the research focused on the field of the meaning of the word odor in Indonesian. The method used in this study is qualitative. The data in this study are words that have a meaning relationship with the word odor in the Kamus Besar Bahasa Indonesia. The theory used in this study is the component analysis of meaning Nida 1975 . The results of this study indicate that the word odor has two categories, namely pleasant odor and unpleasant odor.Keyword: odor, semantic field, component of meaning."

"Summary:A book on biotechnological processes for odor and air pollution control, the nuisance and hazard side effects of industries. It describes various biotechnological methods ranging from laboratory, to pilot evaluation and to full-scale process implementation"

"Makalah ini membahas pengembangan Sistem Penciuman Elektronik menggunakan 16 buah sensor kuarsa terlapis membran sensitif. Penulis telah mengembangkan Sistem Penciuman Elektronik dengan jumlah sensor sebanyak 4 buah, akan tetapi sistem ini hanya mampu membuat klasifikasi aroma campuran dengan tingkat pengenalan dibawah 40%. Pengembangan sistem dilakukan dengan meningkatkan jumlah sensor untuk memperbesar dimensi ruang pengamatan dan peningkatan frekuensi dasar sensor untuk mendapatkan akurasi yang lebih tinggi.Hasil penelitian menunjukkan bahwa sistem 16 sensor mempunyai kapabilitas yang tinggi untuk klasifikasi aroma campuran. Tingkat pengenalan sistem dengan 16 sensor untuk aroma campuran dengan 6 tingkat konsentrasi alkohol berkisar 89.9%, bila diproses secara terpisah, sedangkan apabila dilaksanakan secara ?batch? akan menghasilkan tingkat pengenalan sekitar 82.4%.

---

An artificial odor recognition system is developed for discriminating odors. This artificial system consisted of 16 quartz resonator crystals as the sensor array, a frequency modulator and a frequency counter for each sensor that are connected directly to a microcomputer. We have already shown that the artificial odor recognition system with 4 sensors is high enough to discriminate simple odor correctly, however, when it was used to discriminate compound odors, the recognition capability of this system is dropped significantly to be about 40%.Results of experiments show that the developed artificial system with 16 sensors could discriminate compound aroma based on 6 gradient of alcohol concentrations with high recognition rate of 89.9% for non batch processing system, and 82.4% for batch processing of the classes of odors."

"Air Traffic Control (ATC) tasks require a high mental workload with complex cognitive activities. Since the tasks are likely to be fatigue-inducing and may cause aircraft accidents, ergonomics interventions are needed. This study investigated the effectiveness of peppermint odor on improved performance and fatigue while conducting simulated ATC tasks. A total of 16 participants performed ATC tasks using SkyHigh simulation software for two hours in two conditions (with and without peppermint odor). While the simulator was able to record participants’ performance during ATC tasks, participants’ fatigue development was monitored using an electroencephalograph (EEG), a heart rate monitor (HRM), and psychomotor vigilance task (PVT) apparatus. The results of this study show that the use of peppermint odor significantly (p < 0.05) improved simulation performance, based on all simulation indicators. The peppermint odor also significantly (p < 0.05) inhibited fatigue development, based on an EEG measure (decline in parietal ?), two HRM measures (decline in low frequency power (LF) and increase in high frequency power (HF)), and a PVT measure (10% of the longest time reaction)."

"To improve the recognition accuracy of a developed artificial odor discrimination system for three mixture fragrance recognition, Fuzzy similarity based Self-Organized Network inspired by Immune Algorithm (F-SONIA) is proposed.Minimum, average, and maximum values of fragrance data acquisition are used to form triangular fuzzy numbers. THen, the fuzzy similarity measure is used to define the relationship between fragrance inputs and connection strengths of hidden units. The fuzzy similarity is defined as the maximum value of the intersection region between triangular fuzzy set of hidden units. In experiments, performances of the proposed method is compared with the conventional self-organized Network inspired by Immune Algorithm (SONIA) and the Fuzzy Learning Vector Quantization (FLVQ). Experiments show that F-SONIA improves recognition accuracy of SONIA by 3-9%. Comparing to the previously developed artificial odor discrimination system that used FLVQ as pattern classifier, the recognition accuracy is increased by 14-15%."

"Air sungai di wilayah DKI Jakarta memiliki kandungan pencemar organik dan anorganik yang tinggi. Berdasarkan pemantauan yang dilakukan DLH DKI Jakarta pada tahun 2018- 2022, parameter pencemar utama yang mencemari sungai adalah fecal coliform, total coliform, klorin bebas, BOD, hidrogen sulfida, COD, dan amonia. Hidrogen sulfida dan amonia merupakan pencemar yang dapat menimbulkan bau di air sungai, sehingga dapat mengganggu kenyamanan di ruang terbuka. Melalui penelitian ini, persepsi pengunjung taman terhadap timbulan bau dan kualitas air di saluran air Tebet Eco Park dapat diketahui. Persepsi pengunjung didapatkan melalui kuesioner, pengujian timbulan bau di saluran air dilakukan dengan menggunakan SNI 06-6860-2002, dan pengujian pH, suhu, TDS, COD, amonia, total coliform dilakukan berdasarkan SNI Kualitas Air dan Air Limbah. Hasil kuesioner persepsi pengunjung menunjukkan bahwa 43% pengunjung tidak mencium bau, sedangkan 57% pengunjung yang lain mencium bau dalam intensitas yang berbeda. Dari hasil pengujian kualitas air menunjukkan bahwa parameter COD, amonia, dan total coliform tidak memenuhi standar baku mutu kelas 4 dari Peraturan Pemerintah Republik Indonesia Nomor 22 Tahun 2021 dan standar WHO dengan masing- masing parameter memiliki konsentrasi tertinggi sebesar 98 mg/L, 13 mg/L, dan 9.200.000 MPN/100 mL. Rekomendasi untuk meningkatkan kualitas air diberikan melalui perancangan sistem pengolahan air yang terdiri dari Bioretention Basin, Cascade Aerator, dan Constructed Wetland yang mampu menyisihkan konsentrasi COD, amonia, dan total coliform masing-masing sebesar 96,72%, 99,25%, dan 99,58%.

---

The river water in Jakarta has high levels of organic and inorganic pollutants. Based on monitoring conducted by DLH DKI Jakarta from 2018-2022, the main pollutant contaminating the rivers are fecal coliform, total coliform, free chlorine, BOD, hydrogen sulfide, COD, and ammonia. Hydrogen sulfide and ammonia are pollutants that can cause odor in the river water and might affecting comfort in open spaces. Through this study, the perception of park visitors regarding odor and the water quality in the Tebet Eco Park waterways can be understood. Visitor perceptions were obtained through questionnaires, while odor tests in the waterways were conducted using SNI 06-6860-2002, and tests for pH, temperature, TDS, COD, ammonia, and total coliform were conducted based on SNI Water and Wastewater Quality Standards. The results of the visitor perception questionnaires showed that 43% of visitors did not detect any odor, while 57% of visitors detected odors of varying intensity. The results of the water quality tests showed that COD, ammonia, and total coliform did not meet the class 4 quality standards of Peraturan Pemerintah Republik Indonesia Nomor 22 Tahun 2021 and WHO Standards, with the highest concentrations for each parameter being 98 mg/L, 13 mg/L, and 9.200.000 MPN/100 mL, respectively. Recommendations for improving water quality were provided through the design of a water treatment system consisting of a Bioretention Basin, Cascade Aerator, and Constructed Wetland, which are capable of reducing COD, ammonia, and total coliform concentrations by 96.72%, 99.25%, and 99.58%, respectively."