Classification Model
Recently Published Documents





Julián D. Miranda ◽  
Diego J. Parada

AbstractEmbedding graphic content in multimedia through steganography is a useful and fast practice to hide information. However, detecting the use of this technique is complex and sometimes unsuccessful because variations are not visually perceptible. This article proposes the use of a binary classification model based on artificial neural networks to detect the presence of LSB steganography on monochromatic still images of 256x256 and 8 bits, based on the Standford Genome Project. The steganograms were generated by varying the payload from 0.1 to 0.5 to obtain image pairs of carriers and steganograms. For each steganogram, the following features were extracted from image histograms: kurtosis, skewness, standard deviation, range, median, harmonic mean, Hjorth mobility, and complexity. The results show that the classifier reaches a 91.45% accuracy in detecting LSB steganography when learning from all payloads, as well as a 96.78% individual classification accuracy in the best case with a payload of 0.5.

2021 ◽  
Bangaru Kamatchi S ◽  
R. Parvathi

Abstract The agriculture yield mostly depends on climate factors. Any information associated with climatic factors will help farmers in foreordained farming. Choosing a right crop at right time is most important to get proper yield. To help the farmers in decision making process a classification model is built by considering the agro climatic parameters of a crop like temperature, relative humidity, type of soil, soil pH and crop duration and a recommendation system is built based on three factors namely crop, type of crop and the districts. Predicting the districts is the novel approach in which crop pattern of 33 districts of Tamilnadu is marked and based on that classification model is built. Thorough analysis of machine learning algorithms incorporating pre-processing, data augmentation and comparison of optimizers and activation function of ANN. Log loss metric is used to validate the models. The results shows that artificial neural network is the best predictive model for classification of crops crop type and district based on agrometeorological climatic condition. The accuracy of artificial neural network model is compared with five different machine learning algorithms to analyse the performance.

2021 ◽  
Vol 7 ◽  
pp. e671
Shilpi Bose ◽  
Chandra Das ◽  
Abhik Banerjee ◽  
Kuntal Ghosh ◽  
Matangini Chattopadhyay ◽  

Background Machine learning is one kind of machine intelligence technique that learns from data and detects inherent patterns from large, complex datasets. Due to this capability, machine learning techniques are widely used in medical applications, especially where large-scale genomic and proteomic data are used. Cancer classification based on bio-molecular profiling data is a very important topic for medical applications since it improves the diagnostic accuracy of cancer and enables a successful culmination of cancer treatments. Hence, machine learning techniques are widely used in cancer detection and prognosis. Methods In this article, a new ensemble machine learning classification model named Multiple Filtering and Supervised Attribute Clustering algorithm based Ensemble Classification model (MFSAC-EC) is proposed which can handle class imbalance problem and high dimensionality of microarray datasets. This model first generates a number of bootstrapped datasets from the original training data where the oversampling procedure is applied to handle the class imbalance problem. The proposed MFSAC method is then applied to each of these bootstrapped datasets to generate sub-datasets, each of which contains a subset of the most relevant/informative attributes of the original dataset. The MFSAC method is a feature selection technique combining multiple filters with a new supervised attribute clustering algorithm. Then for every sub-dataset, a base classifier is constructed separately, and finally, the predictive accuracy of these base classifiers is combined using the majority voting technique forming the MFSAC-based ensemble classifier. Also, a number of most informative attributes are selected as important features based on their frequency of occurrence in these sub-datasets. Results To assess the performance of the proposed MFSAC-EC model, it is applied on different high-dimensional microarray gene expression datasets for cancer sample classification. The proposed model is compared with well-known existing models to establish its effectiveness with respect to other models. From the experimental results, it has been found that the generalization performance/testing accuracy of the proposed classifier is significantly better compared to other well-known existing models. Apart from that, it has been also found that the proposed model can identify many important attributes/biomarker genes.

2021 ◽  
Vol 11 (18) ◽  
pp. 8621
Chang-Min Kim ◽  
Ellen J. Hong ◽  
Kyungyong Chung ◽  
Roy C. Park

Although mammography is an effective screening method for early detection of breast cancer, it is also difficult for experts to use since it requires a high level of sensitivity and expertise. A computer-aided detection system was introduced to improve the detection accuracy of breast cancer in mammography, which is difficult to read. In addition, research to find lesions in mammography images using artificial intelligence has been actively conducted in recent days. However, the images generally used for breast cancer diagnosis are high-resolution and thus require high-spec equipment and a significant amount of time and money to learn and recognize the images and process calculations. This can lower the accuracy of the diagnosis since it depends on the performance of the equipment. To solve this problem, this paper will propose a health risk detection and classification model using multi-model-based image channel expansion and visual pattern shaping. The proposed method expands the channels of breast ultrasound images and detects tumors quickly and accurately through the YOLO model. In order to reduce the amount of computation to enable rapid diagnosis of the detected tumors, the model reduces the dimensions of the data by normalizing the visual information and use them as an input for the RNN model to diagnose breast cancer. When the channels were expanded through the proposed brightness smoothing and visual pattern shaping, the accuracy was the highest at 94.9%. Based on the images generated, the study evaluated the breast cancer diagnosis performance. The results showed that the accuracy of the proposed model was 97.3%, CRNN 95.2%, VGG 93.6%, AlexNet 62.9%, and GoogleNet 75.3%, confirming that the proposed model had the best performance.

2021 ◽  
Vol 11 (18) ◽  
pp. 8613
Qinglong Li ◽  
Xinzhe Li ◽  
Byunghyun Lee ◽  
Jaekyeong Kim

As the e-commerce market grows worldwide, personalized recommendation services have become essential to users’ personalized items or services. They can decrease the cost of user information exploration and have a positive impact on corporate sales growth. Recently, many studies have been actively conducted using reviews written by users to address traditional recommender system research problems. However, reviews can include content that is not conducive to purchasing decisions, such as advertising, false reviews, or fake reviews. Using such reviews to provide recommendation services can lower the recommendation performance as well as a trust in the company. This study proposes a novel review of the helpfulness-based recommendation methodology (RHRM) framework to support users’ purchasing decisions in personalized recommendation services. The core of our framework is a review semantics extractor and a user/item recommendation generator. The review semantics extractor learns reviews representations in a convolutional neural network and bidirectional long short-term memory hybrid neural network for review helpfulness classification. The user/item recommendation generator models the user’s preference on items based on their past interactions. Here, past interactions indicate only records in which the user-written reviews of items are helpful. Since many reviews do not have helpfulness scores, we first propose a helpfulness classification model to reflect the review helpfulness that significantly impacts users’ purchasing decisions in personalized recommendation services. The helpfulness classification model is trained about limited reviews utilizing helpfulness scores. Several experiments with the Amazon dataset show that if review helpfulness information is used in the recommender system, performance such as the accuracy of personalized recommendation service can be further improved, thereby enhancing user satisfaction and further increasing trust in the company.

2021 ◽  
Mohamed Masoud ◽  
W. Scott Meddaugh ◽  
Masoud Eljaroshi ◽  
Khaled Elghanduri

Abstract The Harash Formation was previously known as the Ruaga A and is considered to be one of the most productive reservoirs in the Zelten field in terms of reservoir quality, areal extent, and hydrocarbon quantity. To date, nearly 70 wells were drilled targeting the Harash reservoir. A few wells initially naturally produced but most had to be stimulated which reflected the field drilling and development plan. The Harash reservoir rock typing identification was essential in understanding the reservoir geology implementation of reservoir development drilling program, the construction of representative reservoir models, hydrocarbons volumetric calculations, and historical pressure-production matching in the flow modelling processes. The objectives of this study are to predict the permeability at un-cored wells and unsampled locations, to classify the reservoir rocks into main rock typing, and to build robust reservoir properties models in which static petrophysical properties and fluid properties are assigned for identified rock type and assessed the existed vertical and lateral heterogeneity within the Palaeocene Harash carbonate reservoir. Initially, an objective-based workflow was developed by generating a training dataset from open hole logs and core samples which were conventionally and specially analyzed of six wells. The developed dataset was used to predict permeability at cored wells through a K-mod model that applies Neural Network Analysis (NNA) and Declustring (DC) algorithms to generate representative permeability and electro-facies. Equal statistical weights were given to log responses without analytical supervision taking into account the significant log response variations. The core data was grouped on petrophysical basis to compute pore throat size aiming at deriving and enlarging the interpretation process from the core to log domain using Indexation and Probabilities of Self-Organized Maps (IPSOM) classification model to develop a reliable representation of rock type classification at the well scale. Permeability and rock typing derived from the open-hole logs and core samples analysis are the main K-mod and IPSOM classification model outputs. The results were propagated to more than 70 un-cored wells. Rock typing techniques were also conducted to classify the Harash reservoir rocks in a consistent manner. Depositional rock typing using a stratigraphic modified Lorenz plot and electro-facies suggest three different rock types that are probably linked to three flow zones. The defined rock types are dominated by specifc reservoir parameters. Electro-facies enables subdivision of the formation into petrophysical groups in which properties were assigned to and were characterized by dynamic behavior and the rock-fluid interaction. Capillary pressure and relative permeability data proved the complexity in rock capillarity. Subsequently, Swc is really rock typing dependent. The use of a consistent representative petrophysical rock type classification led to a significant improvement of geological and flow models.

2021 ◽  
Vol 11 (1) ◽  
Leonardo Fiusa de Morais ◽  
Ana Clara Rodrigues Cavalcante ◽  
Deodato do Nascimento Aquino ◽  
Felipe Hermínio Meireles Nogueira ◽  
Magno José Duarte Cândido

AbstractThis study aimed to analyze fragments of rangelands through spectral responses and land cover change by livestock in regions of the Caatinga biome through remote sensing. For spectral behavior, the surface reflectance bidirectional (SRB) and spectral indexes of vegetation were used to verify the ragelands seasonality. Land cover change detection of Ouricuri and Tauá through Landsat-8 images with a 16-day revisit interval, were processed in the Google Earth Engine platform (GEE) and software Quantum GIS version 2.18 (QGIS). In the GEE platform, annual mosaics and stacking of the spectral bands were generated for the classification of images, and in sequence the production of thematic maps in QGIS. The analysis of land cover change considered the classes: thinned Caatinga, conserved Caatinga, herbaceous vegetation, bare soil, water and others. The analysis of the spectral responses showed that the vegetation monitored in Ouricuri presented higher SRB in the infrared band and lower SRB in the red and blue bands, and that caused the pasture to produce higher vegetation indexes than the other locations. Through validation, it was observed that in Tauá, there was an overall accuracy of 91% and Kappa index of 89%, and in Ouricuri there was an overall accuracy of 90% and Kappa index of 86%, indicating excellent correctness of the classification model. The classification model proved to be effective in verifying the temporal and spatial land cover change, making it possible to identify places with the vegetation that was most affected and susceptible to degradation and generation of political support to minimize damage to the Caatinga Biome.

2021 ◽  
Vol 13 (18) ◽  
pp. 10279
Dejan Križaj ◽  
Miha Bratec ◽  
Peter Kopić ◽  
Tadej Rogelja

Similar to the concept of “Smart Cities”, “Smart Tourism” has undoubtedly become a promising field of research, and “the” buzzword in the last five years. But how much of this is “smart washing”, and how much progress has really been made? We focus on the adoption and implementation of technological innovations to analyze the publicly available descriptions of Smart Tourism projects implemented in Europe according to the stringent technological criteria of contemporary Smart Tourism definitions. The results show that the vast majority of projects branded as “smart” predominantly pursue environmental sustainability goals, but do not feature advanced technology that meets the Smart Actionable attribute criteria, and do not address social sustainability issues to the same extent as the environmental ones.

Sign in / Sign up

Export Citation Format

Share Document