scholarly journals Invoices Classification Using Deep Features Based on SME Perspectives

2021 ◽  
Author(s):  
Nurul Akmar Azman ◽  
Azlinah Mohamed ◽  
Amsyar Mohmad Jamil
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Learning Model ◽  
Discussion Section ◽  
Validation Data ◽  
Record Keeping ◽  
Small And Medium Enterprise ◽  
Lower Productivity ◽  
Medium Enterprise ◽  
Deep Learning Model

Abstract Automation is seen as a potential alternative in improving productivity in the twenty-first century. Invoicing is the essential foundation of accounting record keeping and serves as a critical foundation for law enforcement inspections by auditing agencies and tax authorities. With the rise of artificial intelligence, automated record keeping systems are becoming more widespread in major organizations, allowing them to do tasks in real time and with no effort as well as a decision-making tool. Despite the system's benefits, many small and medium-sized businesses, particularly in Malaysia, are hesitant to implement it. Invoices are mostly processed manually that prone to human errors and lower productivity of the company. Artificial intelligence will further improve automated invoice handling making it simpler and efficient for all levels of businesses especially the small and medium enterprise This study presents a deep learning approach on record keeping focusing on invoices recognition by detecting invoice image classification. The deep learning model used in this research including the classic architecture of Convolutional Neural Network and its other variation such as VGG-16, VGG-19 and ResNet-50. Besides that, the constrains and expectation of the system to be implemented in small and medium enterprise in Malaysia are also presented in the interview scores. The research highlighted a comparison result between deep learning model and the perspective of SME presented in the discussion section. ResNet-50 shows a significant value in both training and validation accuracy compared to the other models with 95.90% accuracy in training and 74.24% accuracy for validation data. Future work will look at the suggested other deep learning method and intelligence features to be implemented for a more efficient invoices recognition and for small and medium enterprise.

scholarly journals Advanced Deep Learning Model

2021 ◽  
Author(s):  
Yew Kee Wong
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Decision Making ◽  
Deep Learning ◽  
Learning Algorithms ◽  
Learning Model ◽  
Intelligence Analysis ◽  
Basic Parameters ◽  
Deep Learning Model ◽  
Learning Sets

Deep learning is a type of machine learning that trains a computer to perform human-like tasks, such as recognizing speech, identifying images or making predictions. Instead of organizing data to run through predefined equations, deep learning sets up basic parameters about the data and trains the computer to learn on its own by recognizing patterns using many layers of processing. This paper aims to illustrate some of the different deep learning algorithms and methods which can be applied to artificial intelligence analysis, as well as the opportunities provided by the application in various decision making domains.

Supporting risk management in the Caribbean by application of Deep Learning for object classification of aerial imagery with MATLAB

2020 ◽  
Author(s):  
Sebastian Bomberg ◽  
Neha Goel
Keyword(s):  
Risk Management ◽  
Deep Learning ◽  
Gpu Computing ◽  
Learning Model ◽  
Aerial Imagery ◽  
Validation Data ◽  
Data Set ◽  
Roof Material ◽  
Caribbean Islands ◽  
Deep Learning Model

<p>The presented work focuses on disaster risk management of cities which are prone to natural hazards. Based on aerial imagery captured by drones of regions in Caribbean islands, we show how to process and automatically identify roof material of individual structures using a deep learning model. Deep learning refers to a machine learning technique using deep artificial neural networks. Unlike other techniques, deep learning does not necessarily require feature engineering but may process raw data directly. The outcome of this assessment can be used for steering risk mitigations measures, creating risk hazard maps or advising municipal bodies or help organizations on investing their resources in rebuilding reinforcements. Data at hand consists of images in BigTIFF format and GeoJSON files including the building footprint, unique building ID and roof material labels. We demonstrate how to use MATLAB and its toolboxes for processing large image files that do not fit in computer memory. Based on this, we perform the training of a deep learning model to classify roof material present in the images. We achieve this by subjecting a pretrained ResNet-18 neural network to transfer learning. Training is further accelerated by means of GPU computing. The accuracy computed from a validation data set achieved by this baseline model is 74%. Further tuning of hyperparameters is expected to improve accuracy significantly.</p>

scholarly journals Artificial Intelligence in Automated Bookkeeping: A Value-added Function for Small and Medium Enterprises

2021 ◽  
Vol 5 (3) ◽  
pp. 224
Author(s):  
Nurul Akmar Azman ◽  
Azlinah Mohamed ◽  
Amsyar Mohmad Jamil
Keyword(s):  
Artificial Intelligence ◽  
Optical Character Recognition ◽  
Small And Medium Enterprises ◽  
Value Added ◽  
Accounting System ◽  
Document Recognition ◽  
Record Keeping ◽  
Small And Medium Enterprise ◽  
Medium Enterprise ◽  
Medium Enterprises

Bookkeeping plays a vital role in dealing with records of day-to-day financial transactions from invoices until payment. It is also a method of documenting all company transactions in order to create a collection of accounting documents. Studies show that an evolution of bookkeeping management from manual record keeping to electronic record keeping had simplified most burden of bookkeepers as well as more reliable and accurate. Bookkeeping includes, in particular, classifying items correctly and entering financial details into an accounting system. However, with the rise of artificial intelligence, automated bookkeeping system is common to large businesses tasks at real time with hassle free. The system will function more than just journal management but also a decision-making tool to any businesses. Despite the benefits of the system, many small and medium enterprises especially in Malaysia still hesitate to implement the system. Artificial intelligence will further improve automated bookkeeping making it simpler and efficient for all levels of businesses. This paper presents an Artificial Intelligence perspective and methods used in automated bookkeeping focuses on invoices processes such as Optical Character Recognition (OCR), for document recognition, machine learning and auto journal record entries. Besides that, its challenges to be implemented in small and medium enterprise. The result of these studies highlighted benefits in the automated bookkeeping process to suit Malaysian small and medium enterprises. Future work will look at the suggested intelligence features to be implemented for a more efficient automated bookkeeping for small and medium enterprise.

scholarly journals Voice Recognition and Inverse Kinematics Control for a Redundant Manipulator Based on a Multilayer Artificial Intelligence Network

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Mai Ngoc Anh ◽  
Duong Xuan Bien
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Inverse Kinematics ◽  
Degrees Of Freedom ◽  
Voice Recognition ◽  
Learning Model ◽  
Redundant Manipulator ◽  
Efficient Operation ◽  
Inverse Kinematics Problem ◽  
Deep Learning Model

This study presents the construction of a Vietnamese voice recognition module and inverse kinematics control of a redundant manipulator by using artificial intelligence algorithms. The first deep learning model is built to recognize and convert voice information into input signals of the inverse kinematics problem of a 6-degrees-of-freedom robotic manipulator. The inverse kinematics problem is solved based on the construction and training. The second deep learning model is built using the data determined from the mathematical model of the system’s geometrical structure, the limits of joint variables, and the workspace. The deep learning models are built in the PYTHON language. The efficient operation of the built deep learning networks demonstrates the reliability of the artificial intelligence algorithms and the applicability of the Vietnamese voice recognition module for various tasks.

Deep Learning Model for Spatial Interpolation of Real-Time Seismic Intensity

2020 ◽  
Vol 91 (6) ◽  
pp. 3433-3443
Author(s):  
Ryota Otake ◽  
Jun Kurima ◽  
Hiroyuki Goto ◽  
Sumio Sawada
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Weighted Average ◽  
Learning Model ◽  
Seismic Intensity ◽  
Validation Data ◽  
Seismic Stations ◽  
Geological Information ◽  
Deep Learning Model ◽  
Better Than

Abstract Spatial distribution of seismic intensity plays an important role in emergency response during and immediately after an earthquake. In this study, we propose a deep learning model to predict the seismic intensity based on only the observation records at the seismic stations in a surrounding area. The deep learning model is trained using the observation records at both the input and target stations, and no geological information is used. Once the model is developed, for example, using the data from a temporal seismic array, the model can spatially interpolate the seismic intensity from the sparse layout of the seismic stations. The model consists of long short-term memory cells, which are well-established neural network components for time series analysis. We used observed seismograms in 1996 through 2019 at the Kyoshin Network (K-NET) and Kiban–Kyoshin Network (KiK-net) stations located in the northeastern part of Japan. In our deep learning model, approximately 85% of validation data is successfully classified into seismic intensity scales, which is better than adopting either the maximum or weighted average of the input data. We also apply the deep learning model to earthquake early warning (EEW). The model can predict the seismic intensity accurately and provides a long warning time. We concluded that our approach is a possible future solution for increasing the accuracy of EEW.

scholarly journals Patent Analysis Using Vector Space Model and Deep Learning Model : A Case of Artificial Intelligence Industry Technology

2021 ◽  
Author(s):  
Yongmin Yoo ◽  
Dongjin Lim ◽  
Kyungsun Kim
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Vector Space ◽  
Rapid Development ◽  
Vector Space Model ◽  
Learning Model ◽  
Patent Data ◽  
Space Model ◽  
Artificial Intelligence Technology ◽  
Deep Learning Model

Thanks to rapid development of artificial intelligence technology in recent years, the current artificial intelligence technology is contributing to many part of society. Education, environment, medical care, military, tourism, economy, politics, etc. are having a very large impact on society as a whole. For example, in the field of education, there is an artificial intelligence tutoring system that automatically assigns tutors based on student's level. In the field of economics, there are quantitative investment methods that automatically analyze large amounts of data to find investment laws to create investment models or predict changes in financial markets. As such, artificial intelligence technology is being used in various fields. So, it is very important to know exactly what factors have an important influence on each field of artificial intelligence technology and how the relationship between each field is connected. Therefore, it is necessary to analyze artificial intelligence technology in each field. In this paper, we analyze patent documents related to artificial intelligence technology. We propose a method for keyword analysis within factors using artificial intelligence patent data sets for artificial intelligence technology analysis. This is a model that relies on feature engineering based on deep learning model named KeyBERT, and using vector space model. A case study of collecting and analyzing artificial intelligence patent data was conducted to show how the proposed model can be applied to real-world problems.

scholarly journals To perform road signs recognition for autonomous vehicles using cascaded deep learning pipeline

2019 ◽  
Vol 1 (1) ◽  
Author(s):  
Riadh Ayachi ◽  
Yahia ElFahem Said ◽  
Mohamed Atri
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Autonomous Vehicles ◽  
High Performance ◽  
Autonomous Vehicle ◽  
Sensory Information ◽  
Learning Model ◽  
The Road ◽  
Road Signs ◽  
Deep Learning Model

Autonomous vehicle is a vehicle that can guide itself without human conduction. It is capable of sensing its environment and moving with little or no human input. This kind of vehicle has become a concrete reality and may pave the way for future systems where computers take over the art of driving. Advanced artificial intelligence control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant road signs. In this paper, we introduce an intelligent road signs classifier to help autonomous vehicles to recognize and understand road signs. The road signs classifier will be based on an artificial intelligence technique. In particular, a deep learning model is used, Convolutional Neural Networks (CNN). CNN is a widely used Deep Learning model to solve pattern recognition problems like image classification and object detection. CNN has been successfully used to solve computer vision problems because of its methodology in processing images which is similar to the human brain decision making. The evaluation of the proposed pipeline is proved using two different datasets. The proposed CNNs achieved high performance in road sign classification with a validation accuracy of 99.8% and a testing accuracy of 99.6%. The proposed method can be easily implemented for real-time application.

scholarly journals MolAICal: a soft tool for 3D drug design of protein targets by artificial intelligence and classical algorithm

2020 ◽  
Author(s):  
Qifeng Bai ◽  
Shuoyan Tan ◽  
Tingyang Xu ◽  
Huanxiang Liu ◽  
Junzhou Huang ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Drug Design ◽  
Membrane Protein ◽  
Learning Model ◽  
Glucagon Receptor ◽  
Protein Targets ◽  
Lipinski’S Rule ◽  
Classical Algorithm ◽  
Deep Learning Model

Abstract Deep learning is an important branch of artificial intelligence that has been successfully applied into medicine and two-dimensional ligand design. The three-dimensional (3D) ligand generation in the 3D pocket of protein target is an interesting and challenging issue for drug design by deep learning. Here, the MolAICal software is introduced to supply a way for generating 3D drugs in the 3D pocket of protein targets by combining with merits of deep learning model and classical algorithm. The MolAICal software mainly contains two modules for 3D drug design. In the first module of MolAICal, it employs the genetic algorithm, deep learning model trained by FDA-approved drug fragments and Vinardo score fitting on the basis of PDBbind database for drug design. In the second module, it uses deep learning generative model trained by drug-like molecules of ZINC database and molecular docking invoked by Autodock Vina automatically. Besides, the Lipinski’s rule of five, Pan-assay interference compounds (PAINS), synthetic accessibility (SA) and other user-defined rules are introduced for filtering out unwanted ligands in MolAICal. To show the drug design modules of MolAICal, the membrane protein glucagon receptor and non-membrane protein SARS-CoV-2 main protease are chosen as the investigative drug targets. The results show MolAICal can generate the various and novel ligands with good binding scores and appropriate XLOGP values. We believe that MolAICal can use the advantages of deep learning model and classical programming for designing 3D drugs in protein pocket. MolAICal is freely for any nonprofit purpose and accessible at https://molaical.github.io.

scholarly journals Research on Model Compression for Embedded Platform through Quantization and Pruning

2021 ◽  
Vol 2078 (1) ◽  
pp. 012047
Author(s):  
Xiao Hu ◽  
Hao Wen
Keyword(s):  
Artificial Intelligence ◽  
Deep Learning ◽  
Learning Model ◽  
Model Simplification ◽  
Accuracy Rate ◽  
Embedded Platform ◽  
Remarkable Improvement ◽  
Model Compression ◽  
Artificial Intelligence Technology ◽  
Deep Learning Model

Abstract So far, artificial intelligence has gone through decades of development. Although artificial intelligence technology is not yet mature, it has already been applied in many walks of life. With the explosion of IoT technology in 2019, artificial intelligence has ushered in a new climax. It can be said that the development of IoT technology has led to the development of artificial intelligence once again. But the traditional deep learning model is very complex and redundant. The hardware environment of IoT can not afford the time and resources cost by the model which runs on the GPU originally, so model compression without decreasing accuracy rate so much is applicable in this situation. In this paper, we experimented with using two tricks for model compression: Pruning and Quantization. By utilizing these methods, we got a remarkable improvement in model simplification while retaining a relatively close accuracy.

Sign in / Sign up

Export Citation Format

Share Document