Hasil Pencarian  ::  Simpan CSV :: Kembali

"Search and classification using multiple autonomous vehicles provides a comprehensive study of decision-making strategies for domain search and object classification using multiple autonomous vehicles (MAV) under both deterministic and probabilistic frameworks. It serves as a first discussion of the problem of effective resource allocation using MAV with sensing limitations, i.e., for search and classification missions over large-scale domains, or when there are far more objects to be found and classified than there are autonomous vehicles available. Under such scenarios, search and classification compete for limited sensing resources. This is because search requires vehicle mobility while classification restricts the vehicles to the vicinity of any objects found. The authors develop decision-making strategies to choose between these competing tasks and vehicle-motion-control laws to achieve the proposed management scheme. Deterministic Lyapunov-based, probabilistic Bayesian-based, and risk-based decision-making strategies and sensor-management schemes are created in sequence. Modeling and analysis include rigorous mathematical proofs of the proposed theorems and the practical consideration of limited sensing resources and observation costs. A survey of the well-developed coverage control problem is also provided as a foundation of search algorithms within the overall decision-making strategies. Applications in both underwater sampling and space-situational awareness are investigated in detail. The control strategies proposed in each chapter are followed by illustrative simulation results and analysis. "

"This is the first book dedicated to this topic, in the areas of constraint programming, machine learning, evolutionary computing, and feedback control theory. After the editors' introduction to autonomous search, the chapters are focused on tuning algorithm parameters, autonomous complete (tree-based) constraint solvers, autonomous control in metaheuristics and heuristics, and future autonomous solving paradigms."

"Classification analysis is considered one of the most important areas of pattern recognition and data mining . It has been used in many industries to istablish a structure or model based on raw data...."

"Salah satu isu yang sangat penting dalam dunia internet saat ini adalah serangan-serangan dalam dunia maya dengan motivasi keuangan dan perangkat lunak berbahaya yang memiliki kemampuan untuk melakukan serangan secara otomatis. Honeypot dan IDS bekerja sama untuk memberikan solusi keamanan jaringan yaitu sebagai intrusion detection yang dapat mengumpulkan data serangan. Pada penelitian ini, akan dibangun sistem keamanan jaringan menggunakan Honeynet multiple sensor yang berbasis open-source. Integrasi beberapa sensor Honeypot dan IDS dalam satu sistem disebut Honeynet. Honeypot dan IDS diimplementasikan pada suatu Host komputer dengan menggunakan MHN server sebagai web server, yang didalamnya dibangun sensor-sensor seperti Dionaea, Glastopf, Wortpot, p0f, Snort, dan Suricata. Berdasarkan pengujian yang telah dilakukan diperoleh total keseluruhan alert yang berhasil direkam oleh sistem yaitu skenario 1: 5453 alert, skenario 2: 3021 alert, dan skenario 3:7035 alert dengan total keseluruhan serangan yaitu 15509 alert. Dari total keseluruhan serangan dideteksi 35% serangan berasal dari IP 192.168.1.103, 20% serangan berasal dari IP 192.168.1.104 , dan 45% serangan berasal dari IP 192.168.1.105. Hasil pengujian ini menunjukkan bahwa sistem telah berhasil menjebak, memonitoring, dan mendeteteksi serangan. Pengimplementasian sistem Honeynet ini bertujuan agar kekurangan dari suatu sensor seperti halnya hanya dapat mendeteksi serangan terhadap port dan protocol tertentu dapat diatasi oleh sensor yang lain. Sehingga apapun bentuk serangan yang ada dapat dideteksi. Penggunaan Honeynet multiple sensor berbasis open-source dapat menjadi langkah awal yang baik untuk mitigasi resiko dan sebagai peringatan awal adanya serangan cyber.

---

Recently, some of the important issues in the internet things are the attacks in a network with profit motivation and malicious software which has the ability to do the attack automatically. Honeypot and IDS are working together to give the solution for network security and act as the instrusion detection which has the ability to collect the attack's log.

This research will build network security system using multiple sensor Honeynet based on open-source. The integration of Honeypot's sensors and IDS in one system is called Honeynet. Honeypot and IDS are implemented in a computer host using MHN server as the web server, that contains various of sensors such as Dionaea, Glastopf, Wortpot, p0f, Snort, and Suricata.

Based on the research that has been done, it showed total of alerts that is successfully recorded by system are for the first scenario, there are 5453 alerts, second scenario is 3021 alerts, and the third scenario is 7035 alerts with total of alerts are 15509. From the total attacks, it is detected that 35% of the attacks are from IP address 192.168.1.103, 20% are from IP 192.168.1.104, and the 45% are from IP 192.168.1.105.

This testing result showed that the system successfully monitores and detected the attacks. The purpose of this implementation of Honeynet system is that one sensor can be able to handle another sensor's lack of ability, such as that can only detect the attack to the particular port and protocol. So, it can detect all various of attack. The application of Honeypot multiple sensors based on open-source could be the first step for the risk mitigation and acts as the first alert for the possibility of attack."

"Pengukuran kadar gula darah merupakan salah satu kebutuhan utama dalam penanganan diabetes. Namun, moda pengukuran kadar gula darah yang umum saat ini, dilakukan secara invasive atau perlu melukai bagian tubuh manusia untuk mendapat nilai kadar gula darahnya. Terdapat metode pengukuran non invasive tanpa melukai manusia, namun metode ini masih belum dapat diandalkan karena banyaknya factor yang mempengaruhi glukosa tersebut. Penelitian ini mencoba untuk menganalisis akurasi dan performa dari pengukuran gula darah secara non invasive menggunakan sensor infrared pada panjang gelombang 940 nm dengan dibantu oleh Artificial Neural Network dan juga untuk mengevaluasi hubungan komponen dasar dari sinyal analog dari sensor yang bersangkutan terhadap kadar gula darah menggunakan Multiple Regression. Akurasi prediksi gula darah dievaluasi menggunakan Clark Grid Error analysis Dalam analisis ini, 81% dari 97 sampel data berada pada zona yang dapat diterima secara klinis, sedangkan sisanya berada pada zona yang tidak. Hal ini belum mencukupi kebutuhan akurasi 95% yang dapat diterima berdasarkan dari standar ISO 15197, maka hasil daripada penelitian ini masih belum memberikan hasil yang baik. Evaluasi menggunakan multiple regression sendiri menghasilkan hubungan yang tidak signifikan antara komponen dari sinyal analog dengan kadar gula darah dengan nilai R-squared sebesar 0.0174, RMSE 66.9, dan P-value keseluruhan sebesar 0.801.

---

Measuring blood sugar levels is one of the main needs in managing diabetes. However, the current common method of measuring blood sugar levels is carried out invasively or requires injuring parts of the human body to obtain blood sugar levels. There are non-invasive measurement methods without injuring humans, but this method is still not reliable because of the many factors that influence glucose. This research attempts to analyze the accuracy and performance of non-invasive blood sugar measurements using an infrared sensor at a wavelength of 940 nm assisted by an Artificial Neural Network and also to evaluate the relationship of the basic components of the analog signal from the sensor in question to blood sugar levels using Multiple Regression. The accuracy of blood sugar predictions was evaluated using Clark Grid Error analysis. In this analysis, 81% of the 97 data samples were in the clinically acceptable zone, while the rest were in the zone that was not. This does not meet the acceptable 95% accuracy requirement based on the ISO 15197 standard, thus the results of this research still do not provide relatively good results. Evaluation using multiple regression itself produced an insignificant relationship between the components of the analog signal and blood sugar levels with an R-squared value of 0.0174, RMSE 66.9, and an overall P-value of 0.801."

"Cloud computing has revolutionized the IT industry by offering huge storage for data outsourcing and also for computation. Various security issues concerned with security and privacy of data arise in the context of data outsourcing. The framework enables clients to outsource encrypted data to the cloud, enables users to retrieve preferred documents using multiple keywords and allows the user to verify the response from the server. The strength of the proposed model relies on the discrete logarithmic problem of Hyper Elliptic Curve Cryptography (HECC) and the security of Merkle trees. The paper proposes a user verifiable multi-keyword search scheme, which focuses on: (i) construction of inverted index for the documents with keywords; (ii) index and document encryption by HECC; (iii) index and document authentication by the Merkle tree; and (iv) verification of the accuracy of response from server by top hash or root hash value of the Merkle tree. Security analysis and results demonstrate the correctness of proposed multiple keyword search (MKS) scheme. The search algorithm combined with the hash value verification process by the Merkle tree is strong enough to provide data security, privacy, and integrity. The proposed model reduces the storage overhead on both the client’s and user’s side. As the number of documents increases, the retrieval time is less, which reduces the storage overhead on both sides."

"This book provides cutting-edge insights into autonomous vehicles and road terrain classification, and introduces a more rational and practical method for identifying road terrain. It presents the MRF algorithm, which combines the various sensors classification results to improve the forward LRF for predicting upcoming road terrain types. The comparison between the predicting LRF and its corresponding MRF show that the MRF multiple-sensor fusion method is extremely robust and effective in terms of classifying road terrain. The book also demonstrates numerous applications of road terrain classification for various environments and types of autonomous vehicle, and includes abundant illustrations and models to make the comparison tables and figures more accessible. "

"Kota Depok mengalami pertumbuhan yang pesat dalam hal penduduk dan ekonomi yang menyebabkan tingginya permintaan transportasi. Hal ini mengakibatkan permasalahan transportasi yang memerlukan perencanaan transportasi. Penelitian ini bertujuan untuk menghitung besaran trip rate untuk setiap kategori dari karakteristik rumah tangga yang berpengaruh pada bangkitan perjalanan pada tahun dasar. Penelitian ini dilakukan dengan metode klasifikasi berganda yang berbasis rumah tangga. Uji statistik yang digunakan untuk mendapatkan variabel bebas adalah uji korelasi pearson dan ANOVA.Dari hasil analisis, didapat variabel bebas yang digunakan adalah Kategori Rumah Tangga, Kepemilikan Kendaraan, dan Tingkat Pengeluaran Transportasi. Sedangkan variabel terikatnya adalah perjalanan bekerja, perjalanan sekolah, perjalanan lain-lain, dan total perjalanan. Hasil trip rate yang didapat untuk tiap maksud perjalanan adalah perjalanan bekerja = 2.69 perjalanan/ rumah tangga, perjalanan sekolah = 2.06 perjalanan/ rumah tangga, perjalanan lain-lain = 0.63 perjalanan/ rumah tangga, dan total perjalanan = 5.4 perjalanan/ rumah tangga.

---

Depok city has rapid growth in terms of population and economy leading to high transport demand. This growth makes transportation problems that need transportation management. This study aimed to calculate the trip rate for each category of household characteristics affecting trip generation in the base year. Trip rate model is developed by apply multiple classification method based on household. The statistical test used to obtain independent variable are the Pearson correlation test and ANOVA test.

The analysis show that the independent variables are Household Category, Vehicles Ownership, and Transportation Expenditure Levels, while the dependent variable are work trips, school trips, other trips, and total trips. Trip rate values obtained for each purpose of the trip are a work trip 2.69 trips household, school trips 2.06 trips household, other trip 0.63 trips household, and total trips 5.4 trips household."

"Bencana alam merupakan salah satu ancaman paling serius di Indonesia. Keberadaan dua lempeng gunung aktif membuat ancaman bencana mengintai di Indonesia setiap tahun kedua. Penanggulangan bencana saat ini masih menggunakan cara tradisional yaitu turun ke lapangan dan melihat langsung titik-titik yang terkena bencana alam. Namun, situasi ini sebenarnya cukup berisiko mengingat kondisi lingkungan yang masih belum stabil sehingga cukup berbahaya bagi tim yang sedang mengamati daerah yang terkena bencana alam. Kendaraan udara tak berawak juga bisa disebut drone adalah perangkat yang beroperasi dengan cara diterbangkan secara vertikal. Alat ini sangat mumpuni untuk melewati berbagai rintangan sehingga sangat cocok digunakan sebagai pengamatan daerah yang terkena bencana. Namun, saat ini drone perlu ditingkatkan kemampuannya untuk dapat terbang secara otomatis dan mendekati objek sasaran. SURF sebagai ekstraksi ciri merupakan metode pendeteksian yang cukup ringan. Namun, kondisi bencana yang cukup kompleks memerlukan cara penyederhanaan citra agar mudah dideteksi. Di sini fitur canny edge berfungsi untuk menyederhanakan gambar dan menghasilkan deteksi yang lebih baik dan dapat diimplementasikan secara real time.

---

Natural disasters are one of the most serious threats in Indonesia. Existence two active mountain plates make a threat of disaster lurking in Indonesia every year the second. Disaster management is currently still using traditional methods to go to the field and see firsthand the points affected by natural disasters. However, this situation is actually quite risky considering the environmental conditions that are still not yet stable so it is quite dangerous for the team that is observing the area affected by natural disasters. Unmanned aerial vehicles can also be called drones is a device that operates by being flown vertically. This tool very qualified to pass through various obstacles so it is suitable for use as an observation of disaster-affected areas. However, currently drones need to be upgraded the ability to be able to fly automatically and approach the target object. SURF as feature extraction is a fairly light detection method. However, disaster conditions that are quite complex require a way to simplify images for easy detection. Here the canny edge feature acts for can simplify images and produce better detection and can implemented in real time.

"