Research on a New Convolutional Neural Network Model Combined With Random Edges Adding

It is always a hot and difficult point to improve the accuracy of the convolutional neural network model and speed up its convergence. Based on the idea of the small world network, a random edge adding algorithm is proposed to improve the performance of the convolutional neural network model. This algorithm takes the convolutional neural network model as a benchmark and randomizes backwards and cross layer connections with probability p to form a new convolutional neural network model. The proposed idea can optimize the cross-layer connectivity by changing the topological structure of the convolutional neural network and provide a new idea for the improvement of the model. The simulation results based on Fashion-MINST and cifar10 data set show that the model recognition accuracy and training convergence speed are greatly improved by random edge adding reconstructed models with a probability of p = 0.1.

Download Full-text

Phát hiện mã độc IoT botnet dựa trên đồ thị PSI với mô hình Skip-gram

Journal of Science and Technology on Information security ◽

10.54654/isj.v7i1.53 ◽

2020 ◽

Vol 7 (1) ◽

pp. 29-36

Author(s):

Ngô Quốc Dũng ◽

Lê Văn Hoàng ◽

Nguyễn Huy Trung

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Model ◽

Neural Network Model ◽

Experimental Results ◽

Data Set ◽

Iot Devices

Tóm tắt— Trong bài báo này, nhóm tác giả đề xuất một phương pháp phát hiện mã độc IoT botnet dựa trên đồ thị PSI (Printable String Information) sử dụng mạng nơ-ron tích chập (Convolutional Neural Network - CNN). Thông qua việc phân tích đặc tính của Botnet trên các thiết bị IoT, phương pháp đề xuất xây dựng đồ thị để thể hiện các mối liên kết giữa các PSI, làm đầu vào cho mô hình mạng nơ-ron CNN phân lớp. Kết quả thực nghiệm trên bộ dữ liệu 10033 tập tin ELF gồm 4002 mẫu mã độc IoT botnet và 6031 tập tin lành tính cho thấy phương pháp đề xuất đạt độ chính xác (accuracy) và độ đo F1 lên tới 98,1%. Abstract— In this paper, the authors propose a method for detecting IoT botnet malware based on PSI graphs using Convolutional Neural Network (CNN). Through analyzing the characteristics of Botnet on IoT devices, the proposed method construct the graph to show the relations between PSIs, as input for the CNN neural network model. Experimental results on the 10033 data set of ELF files including 4002 IoT botnet malware samples and 6031 benign files show Accuracy and F1-score up to 98.1%.

Download Full-text

Effect of frost on plants, leaves, and forecast of frost events using convolutional neural networks

International Journal of Distributed Sensor Networks ◽

10.1177/15501477211053777 ◽

2021 ◽

Vol 17 (10) ◽

pp. 155014772110537

Author(s):

Sobia Wassan ◽

Chen Xi ◽

NZ Jhanjhi ◽

Laiqa Binte-Imran

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Model ◽

Neural Network Model ◽

The United States ◽

Plant Structure ◽

Weather Extremes ◽

Model Framework ◽

Data Set ◽

Frost Event

Climate change brings many changes in a physical environment like plants and leaves. The flowers and plants get affected by natural climate and local weather extremes. However, the projected increase in the frost event causes sensitivity in plant reproduction and plant structure vegetation. The timing of growing and reproduction might be an essential tactic by which plant life can avoid frost. Flowers are more sensitive to hoarfrost than leaves but more sensitive to frost in most cases. In most cases, frost affects the size of the plant, its growth, and the production of seeds. In this article, we examined that how frost affects plants and flowers? How it affects the roots and prevents the growth of plants, vegetables, and fruits? Furthermore, we predicted how the frost will grow and how we should take early precautions to protect our crops? We presented the convolutional neural network model framework and used the conv1d algorithm to evaluate one-dimensional data for frost event prediction. Then, as part of our model contribution, we preprocessed the data set. The results were comparable to four weather stations in the United States. The results showed that our convolutional neural network model configuration is reliable.

Download Full-text

Research and implementation of NN based on TensorFlow

Connectivity ◽

10.31673/2412-9070.2020.062025 ◽

2020 ◽

Vol 148 (6) ◽

Author(s):

B. V. Shefkin ◽

◽

I. V. Krasyuk ◽

V. O. Khomenchuk ◽

K. P. Storchak ◽

...

Keyword(s):

Neural Network ◽

Feature Extraction ◽

Deep Learning ◽

Convolutional Neural Network ◽

Network Model ◽

Neural Network Model ◽

Classical Model ◽

Test Accuracy ◽

Data Set ◽

The Neural Network

TensorFlow is Google’s open-source machine learning and deep learning framework, which is convenient and flexible to build the current mainstream deep learning model. Convolutional neural network is a classical model of deep learning, the advantage lies in its powerful feature extraction capabilities of convolutional blocks. A neural network in the simplest case is a mathematical model consisting of several layers of elements that perform parallel calculations. Initially, such an architecture was created by analogy with the small computing elements of the human brain — neurons. The minimal computing elements of an artificial neural network are also called neurons. Neural networks typically consist of three or more layers: an input layer, a hidden layer (or layers), and an output layer. An important feature of the neural network is its ability to learn by example, this is called learning with a teacher. The neural network is trained on a large number of examples consisting of input-output pairs (corresponding to each other input and output). In object recognition problems, such a pair will be the input image and the corresponding label — the name of the object. Neural network learning is an iterative process that reduces the deviation of the network output from a given «teacher response» — a label that corresponds to a given image. This process consists of steps called epochs of learning (they are usually calculated in thousands), each of which is the adjustment of the «weights» of the neural network — the parameters of the hidden layers of the network. Upon completion of the learning process, the quality of the neural network is usually good enough to perform the task for which it was trained, although the optimal set of parameters that perfectly recognizes all the images, it is often impossible to choose. Based on the TensorFlow platform, a convolutional neural network model with two-convolution-layers was built. The model was trained and tested with the MNIST data set. The test accuracy rate could reach 99,15%, and compared with the rate of 98,69% with only one-convolution-layer model, which shows that the two-convolution-layers convolutional neural network model has a better ability of feature extraction and classification decision-making.

Download Full-text

KLASIFIKASI CITRA GENUS PANTHERA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN)

Jurnal Ilmiah Informatika Komputer ◽

10.35760/ik.2019.v24i3.2364 ◽

2019 ◽

Vol 24 (3) ◽

pp. 220-228

Author(s):

Gusti Alfahmi Anwar ◽

Desti Riminarsih

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Network Model ◽

Neural Network Model ◽

Input Layer ◽

Fully Connected

Panthera merupakan genus dari keluarga kucing yang memiliki empat spesies popular yaitu, harimau, jaguar, macan tutul, singa. Singa memiliki warna keemasan dan tidak memilki motif, harimau memiliki motif loreng dengan garis-garis panjang, jaguar memiliki tubuh yang lebih besar dari pada macan tutul serta memiliki motif tutul yang lebih lebar, sedangkan macan tutul memiliki tubuh yang sedikit lebih ramping dari pada jaguar dan memiliki tutul yang tidak terlalu lebar. Pada penelitian ini dilakukan klasifikasi genus panther yaitu harimau, jaguar, macan tutul, dan singa menggunakan metode Convolutional Neural Network. Model Convolutional Neural Network yang digunakan memiliki 1 input layer, 5 convolution layer, dan 2 fully connected layer. Dataset yang digunakan berupa citra harimau, jaguar, macan tutul, dan singa. Data training terdiri dari 3840 citra, data validasi sebanyak 960 citra, dan data testing sebanyak 800 citra. Hasil akurasi dari pelatihan model untuk training yaitu 92,31% dan validasi yaitu 81,88%, pengujian model menggunakan dataset testing mendapatan hasil 68%. Hasil akurasi prediksi didapatkan dari nilai F1-Score pada pengujian didapatkan sebesar 78% untuk harimau, 70% untuk jaguar, 37% untuk macan tutul, 74% untuk singa. Macan tutul mendapatkan akurasi terendah dibandingkan 3 hewan lainnya tetapi lebih baik dibandingkan hasil penelitian sebelumnya.

Download Full-text