The Experts below are selected from a list of 3054 Experts worldwide ranked by ideXlab platform
Pengcheng Li - One of the best experts on this subject based on the ideXlab platform.
-
Probabilistic Event Discrimination Algorithm for Fiber Optic Perimeter Security Systems
Journal of Lightwave Technology, 2018Co-Authors: Junfeng Jiang, Zhichen Li, Pengcheng LiAbstract:This paper proposes an event discrimination algorithm with probabilistic output for fiber optic perimeter security systems. Multiscale permutation entropy and the Zero-Crossing Rate are employed to increase the efficiency of the algorithm and extract intrusion features. A probabilistic support vector machine is used to calculate multiple event probabilities by solving a convex quadratic programming problem. The experimental results demonstRate that the proposed algorithm can distinguish six intrusion events at an average recognition Rate of 92.68% and in a processing time of 0.32 s. Compared with traditional discrimination methods, the proposed algorithm obtains more detailed information (probabilities) of intrusion events. The recognition results are obtained after analyzing the probabilities, which not only reduces the decision-making costs but also reduces the losses from erroneous decisions. Therefore, the proposed high-efficiency feature extraction method and reliable discrimination algorithm can be used to improve the monitoring efficiency of fiber optic perimeter security systems.
Junfeng Jiang - One of the best experts on this subject based on the ideXlab platform.
-
a multiple events recognition scheme based on improved feature vectors for fiber optic perimeter security system
2019 International Conference on Optical Instruments and Technology: Optical Sensors and Applications, 2020Co-Authors: Junfeng JiangAbstract:In this paper, we propose an improved feature extraction based multiple events recognition scheme for fiber optic perimeter security system. In the scheme, four common types of security sensing events, namely, background noises, waggling the fence, cutting the fence and climbing the fence are collected based on a dual Mach-Zehnder interferometry vibration sensor. Variational mode decomposition in frequency domain, sample entropy in irregularity and Zero Crossing Rate in time domain are considered as the feature description of the given security sensing events. A series of experiments have been implemented by a radial basis foundation neural network, which shows that the proposed recognition scheme can accuRately discriminate the three kinds of man-made intrusions from the background noises. The average identification Rates of 98.42% and 100% are achieved for the three types of intrusions and background noises, respectively, which can fully satisfy the field application requirements, the recognition response time is also good of real time performance, which can be controlled less than 1.6 s. Therefore, the proposed events recognition scheme can provide a quite promising field application prospect in the fiber optic perimeter security system.
-
Probabilistic Event Discrimination Algorithm for Fiber Optic Perimeter Security Systems
Journal of Lightwave Technology, 2018Co-Authors: Junfeng Jiang, Zhichen Li, Pengcheng LiAbstract:This paper proposes an event discrimination algorithm with probabilistic output for fiber optic perimeter security systems. Multiscale permutation entropy and the Zero-Crossing Rate are employed to increase the efficiency of the algorithm and extract intrusion features. A probabilistic support vector machine is used to calculate multiple event probabilities by solving a convex quadratic programming problem. The experimental results demonstRate that the proposed algorithm can distinguish six intrusion events at an average recognition Rate of 92.68% and in a processing time of 0.32 s. Compared with traditional discrimination methods, the proposed algorithm obtains more detailed information (probabilities) of intrusion events. The recognition results are obtained after analyzing the probabilities, which not only reduces the decision-making costs but also reduces the losses from erroneous decisions. Therefore, the proposed high-efficiency feature extraction method and reliable discrimination algorithm can be used to improve the monitoring efficiency of fiber optic perimeter security systems.
Zhichen Li - One of the best experts on this subject based on the ideXlab platform.
-
Probabilistic Event Discrimination Algorithm for Fiber Optic Perimeter Security Systems
Journal of Lightwave Technology, 2018Co-Authors: Junfeng Jiang, Zhichen Li, Pengcheng LiAbstract:This paper proposes an event discrimination algorithm with probabilistic output for fiber optic perimeter security systems. Multiscale permutation entropy and the Zero-Crossing Rate are employed to increase the efficiency of the algorithm and extract intrusion features. A probabilistic support vector machine is used to calculate multiple event probabilities by solving a convex quadratic programming problem. The experimental results demonstRate that the proposed algorithm can distinguish six intrusion events at an average recognition Rate of 92.68% and in a processing time of 0.32 s. Compared with traditional discrimination methods, the proposed algorithm obtains more detailed information (probabilities) of intrusion events. The recognition results are obtained after analyzing the probabilities, which not only reduces the decision-making costs but also reduces the losses from erroneous decisions. Therefore, the proposed high-efficiency feature extraction method and reliable discrimination algorithm can be used to improve the monitoring efficiency of fiber optic perimeter security systems.
Yuedong Wang - One of the best experts on this subject based on the ideXlab platform.
-
Hybrid Feature Extraction-Based Intrusion Discrimination in Optical Fiber Perimeter Security System
IEEE Photonics Journal, 2017Co-Authors: Xiangdong Huang, Haojie Zhang, Yuedong WangAbstract:This paper proposes a hybrid feature extraction-based intrusion discrimination scheme for an optical fiber perimeter security system, which concurrently possesses high classification Rate and high efficiency. The high classification Rate lies in two aspects: On one hand, plentiful contents (including bandwidth segmentation in frequency domain, kurtosis in statistics, and the Zero-Crossing Rate in time domain) are incorpoRated into the proposed hybrid feature vector; on the other hand, a configurable filter bank is adopted to reduce the intercoupling between features in the hybrid vector. The high efficiency also arises for two reasons: For one thing, the configurable filter bank works in a pipeline stream; for another, an efficient support vector machine is employed to classify hybrid vectors. Experiments demonstRated that the proposed scheme can accuRately identify four common intrusions (fence climbing, knocking the cable, waggling, and fence cutting) with an average recognition Rate higher than 94%. Moreover, the recognition efficiency is also high.
Lutfi Ahmad - One of the best experts on this subject based on the ideXlab platform.
-
deteksi pulpitis reversibel melalui sinyal wicara dengan metoda Zero Crossing Rate dan average energy serta klasifikasi learning vector quantization
eProceedings of Engineering, 2019Co-Authors: Lutfi Ahmad, Bambang Hidayat, Aptanti AptantiAbstract:Abstrak Suara merupakan salah satu sarana manusia untuk berkomunikasi. Suara juga salah satu pembeda antar individu yang satu dengan yang lainnya. Hal ini dapat dijadikan suatu sarana untuk mendeteksi penyakit lewat suara maanusia. Untuk mendeteksi suatu penyakit melalui suara manusia diperlukan bantuan proses pengambilan informasi yang diinginkan melalui rekaman sinyal suara yang disebut speech processing. Ada beberapa faktor yang dapat mempengaruhi suara manusia yaitu dari proses pembentukan suara yang terjadi pada individu itu sendiri dan juga dari struktur giginya. Tugas akhir ini membuat sebuah aplikasi yang dapat mendeteksi penyakit pulpitis reversibel dengan menggunakan beberapa parameter akustik suara yaitu frekuensi dasar (F0), durasi, amplitudo, gelombang spektrum suara, dan kualitas vokal. Dari parameter akustik suara akan dihitung nilai sample Rate sebagai inputan awal untuk mendaapatkan ciri dan juga klasifikasi yang ditargetkan. Proses pengambilan ciri ini menggunakan metode Zero Crossing Rate (ZCR) dan Average Energy (AE) yang merupakan metode analisis pengambilan ciri atau fitur berdasarkan panjang frame dari rekaman sinyal suara. Proses klasfikasi dilakukan dengan menggunakan metode Learning Vector Quantization (LVQ). Klasifikasi bertujuan untuk mengklasifikasikan audio ke dalam dua kondisi yaitu sehat dan pulpitis reversibel. Dari penelitian ini diperoleh hasil dengan tingkat akurasi tertinggi yaitu 72.5% dengan parameter pre-processing yang digunakan yaitu non-ccenter clipping dan non-overlapping. Parameter statistik yang digunakan variance serta parameter LVQ yaitu epoch = 750 dan hidden layer = 40. Kata kunci : Suara, Barodontalgia, Pulpitis Reversibel, Zero Crossing Rate Quantiztion Average Energy, Learning Vector Quantization Abstract Sound is one of the human means to communicate. Sound is also one differentiator between individuals with each other. This can be used as a means to detect disease through the voice of humans. To detect a disease through human voice is needed the help of the desired information retrieval process through recording voice signals called speech processing. There are several factors that can affect human voice, namely from the sound formation process that occurs in the individual itself and also from the structure of the teeth. This final project creates an application that can detect reversible pulpitis by using several sound acoustic parameters, namely the basic frequency (F0), duration, amplitude, sound spectrum waves, and vocal quality. From the sound acoustic parameters, the value of the sample Rate will be calculated as the initial input to get the targeted characteristics and classification. The process of taking this feature uses the Zero Crossing Rate (ZCR) and Average Energy (AE) method, which is a method of analyzing characteristics or features based on the length of the sound signal recording. The classification process is done using the Learning Vector Quantization (LVQ) method. Classification aims to classify audio into two conditions namely healthy and reversible pulpitis. From this study the results obtained with the highest accuracy were 72.5% with the preprocessing parameters used namely non-ccenter clipping and non-overlapping. The statistical parameters used are variance and LVQ parameters, namely epoch = 750 and hidden layer = 40. Keywords: Sound, Barodontalgia, Pulpitis Reversibel, Zero Crossing Rate Quantiztion and Average Energy, Learning Vector Quantization
-
DETEKSI PULPITIS REVERSIBEL MELALUI SINYAL WICARA DENGAN METODA Zero Crossing Rate DAN AVERAGE ENERGY SERTA KLASIFIKASI LEARNING VECTOR QUANTIZATION
Universitas Telkom Fakultas Teknik Elektro, 2019Co-Authors: Lutfi AhmadAbstract:Suara merupakan salah satu sarana manusia untuk berkomunikasi. Suara juga salah satu pembeda antar individu yang satu dengan yang lainnya. Hal ini dapat dijadikan suatu sarana untuk mendeteksi penyakit lewat suara maanusia. Untuk mendeteksi suatu penyakit melalui suara manusia diperlukan bantuan proses pengambilan informasi yang diinginkan melalui rekaman sinyal suara yang disebut speech processing. Ada beberapa faktor yang dapat mempengaruhi suara manusia yaitu dari proses pembentukan suara yang terjadi pada individu itu sendiri dan juga dari struktur giginya. Tugas akhir ini membuat sebuah aplikasi yang dapat mendeteksi penyakit pulpitis reversibel dengan menggunakan beberapa parameter akustik suara yaitu frekuensi dasar (F0), durasi, amplitudo, gelombang spektrum suara, dan kualitas vokal. Dari parameter akustik suara akan dihitung nilai sample Rate sebagai inputan awal untuk mendaapatkan ciri dan juga klasifikasi yang ditargetkan. Proses pengambilan ciri ini menggunakan metode Zero Crossing Rate (ZCR) dan Average Energy (AE) yang merupakan metode analisis pengambilan ciri atau fitur berdasarkan panjang frame dari rekaman sinyal suara. Proses klasfikasi dilakukan dengan menggunakan metode Learning Vector Quantization (LVQ). Klasifikasi bertujuan untuk mengklasifikasikan audio ke dalam dua kondisi yaitu sehat dan pulpitis reversibel. Dari penelitian ini diperoleh hasil dengan tingkat akurasi tertinggi yaitu 72.5% dengan parameter pre-processing yang digunakan yaitu non-ccenter clipping dan non-overlapping. Parameter statistik yang digunakan variance serta parameter LVQ yaitu epoch = 750 dan hidden layer = 40. Kata Kunci : Suara, Pulpitis Reversibel, Zero Crossing Rate Quantiztion Average Energy, Learning Vector Quantizatio