Search

We develop and commercialize autonomous machines, such as logistic robots and self-driving cars, around the globe. A critical challenge to our—and any—autonomous machine is accurate and efficient localization under resource constraints, which has fueled specialized localization accelerators recently. Prior acceleration efforts are point solutions in that they each specialize for a specific localization algorithm. In real-world commercial deployments, however, autonomous machines routinely operate under different environments and no single localization algorithm fits all the environments. Simply stacking together point solutions not only leads to cost and power budget overrun, but also results in an overly complicated software stack.This paper demonstrates our new software-hardware co-designed framework for autonomous machine localization, which adapts to different operating scenarios by fusing fundamental algorithmic primitives. Through characterizing the software framework, we identify ideal acceleration candidates that contribute significantly to the end-to-end latency and/or latency variation. We show how to co-design a hardware accelerator to systematically exploit the parallelisms, locality, and common building blocks inherent in the localization framework. We build, deploy, and evaluate an FPGA prototype on our next-generation self-driving cars. To demonstrate the flexibility of our framework, we also instantiate another FPGA prototype targeting drones, which represent mobile autonomous machines. We achieve about $2 \times$ speedup and $4 \times$ energy reduction compared to widely-deployed, optimized implementations on general-purpose platforms.

Now a days due to the development in color printing technology the rate of counterfeit notes production and distribution is increasing. This is a massive problem, faced by almost all the countries. It affects the economy, sine it compromises the security of the real economy. Such counterfeit currencies are used to fuel nefarious motives, usually involving terrorist activities. According to the research, developing countries like India have been impacted by this very negatively. Even after the steps taken in 2016 to remove the counterfeits, by executing the demonetization of 500 and 1000 rupees bank notes in India the counterfeits of the new notes have begun circulating. This is due to the highly advanced technology adopted by the counterfeiters which makes the tracking of these counterfeit notes hard. This has become a very critical issue and the negative impact due to the counterfeit currency keeps rising. The only one solution for this problem for a common man is to detect the fake currency, by using the fake currency detector machine. These machines are used in banks and large scale business, but for a small business or for a common man these machines are not affordable. This paper gives the complete methodology of fake note detector machine, which is affordable even for a common man. By implementing the applications of image processing techniques we can find out whether the currency notes are fake or not. Image processing technique consists of a number of operations that can be performed on an image, some of which include image segmentation, edge detection, gray scale conversion etc. The proposed system will have advantages like simplicity, reliability and costs less.

Nowadays, there is a rapidly increasing number of conferences and journals in computer science that make a lot of challenges for researchers to find an appropriate venue to submit their scientific work. There is a need for a recommendation system that can support researchers for a better process of paper submission. In this paper, we present an efficient approach for building such a recommendation model by using embedding methods, Global Vector (GloVe) 1 created by Pennington et al. [1] and FastText 2 proposed by Facebook [2], Convolutional Neural Network (CNN) [3], and LSTM. The experimental results show that the combination of CNNs and FastText, CNN + FastText, can achieve the best performance in terms of the Top 1 Accuracy compared with other techniques, including the S2RSCS model, as presented in [4]. Moreover, the performance by using GloVe or FastText is much better, faster, and more stable than S2RSCS in most cases.

Which are the segmentation algorithms proposed during 2018-2019 in CVPR that have CNN architecture?’ Answering this question involves identifying and analyzing the deep learning architecture diagrams from several research papers. Retrieving such information poses significant challenge as most of the existing academic search engines are primarily based on only the text content. In this paper, we introduce Diag2Graph, an end-to-end framework for parsing deep learning diagram-figures, that enables powerful search and retrieval of architectural details in research papers. Our proposed approach automatically localizes figures from research papers, classifies them, and analyses the content of the diagram-figures. The key steps in analyzing the Figure content is the extraction of the different components data and finding their structural relation. Finally, the extracted components and their relations are represented in the form of a deep knowledge graph. A thorough evaluation on a real-word annotated dataset has been done to demonstrate the efficacy of our approach.

The increasing number of research papers from Indonesia and the higher the need to manage large amounts of documents, including memory capacity and the availability of time to manage research documents, keyphrase can provide a picture representing a text document. Thus, the management of documents in large quantities will become easier to prepare and find a collection of documents. For this reason, proper and correct keyphrase extraction can assist in managing paper documents. This study tried to compare three extraction methods using unsupervised graph-based techniques, including TextRank, TopicRank, and PositionRank. We compare the extraction results with the keyphrase made by the authors of the paper to see the three method’s performance. From the results of our research, we found that the method TextRank Providing the highest performance compared to other methods using the ROUGE test with average Recall, Precision, and F1-Score are 0.558, 0.71, and 0.225. However, the extracted phrases are longer compared to others. The performance of TopicRank, although it does not provide higher results with TextRank, the extracted keyphrase is more compact than TextRank and PositionRank methods.

In this paper, machine learning approaches have been used to predict whether a scientific paper will be accepted in a top-tier AI conferences or not. This shall help authors identify the likelihood of their paper getting accepted in a top-tier AI conference. We have used the PeerRead dataset containing papers collected from major AI conferences that are publicly available. We have achieved an accuracy of 81% using Random Forest classifier. The novelty of the paper lies in accurately predicting whether a scientific paper will be accepted in the top AI conference.

In recent years, with the increasing investment in scientific research, the number of papers has proliferated, and the development of scientific research has also received widespread attention from scholars. Paper citations as an indicator to measure academic influence have essential reference value for future research directions. Aiming at the future paper citation number prediction problem, we propose a citation number prediction model based on the recurrent neural network method with gated recurrent unit(GRU-CPM). In this paper, we first extract features from real data sets that are useful for predicting the number of citations in papers, and then the features were input into GRU-CPM for prediction. Finally, the prediction results are compared with other regression models. Experimental results demonstrate that the GRU-CPM has higher prediction accuracy and faster convergence speed. The time series prediction of citation count is better than existing methods.

This project represents the design of a safety system for conveying and storing valuable documents while restricting unauthorized access. The system consists of a couple of security lair to prevent any leakage from important documents such as question paper, banknotes, and statements, etc. from collection to distribution. The system has been made with a Memory module, Ultrasonic sensor, Fingerprint security, RFID module, GPS and GSM module, etc. This proposed security system has been featured in such a way that the navigation box where we will put our question paper can be opened only by an authorized person in specific places and in a specific time. Education is the most important aspect of our life and through the exams, we can judge people's outlook on their respective fields of study. But question paper leak is a major problem in several countries and this project is here to end it.

In worldwide, security plays a significant role in preventing different assets and crimes. Education has become an essential right of human life as it has been transferred from one era to next. The examination is a significant part of the coaching structure. The key objective of the examination would be to select the suitable applicants for different positions. Every year the updates that exams have been postponed or canceled due to inquiry paper leakage are occurring. So, an innovative system is implemented to prevent this spillage of examination papers. This system is designed on the embedded system. The main types of equipment of this advanced system are Arduino Mega, solar panel, fingerprint scanner, GSM module, and GPS module.

Electronic examinations provide numerous advantages over traditional examination carried out on paper, such as more streamlined logistic and savings of cost, manpower and time. However, when solving examination problems in the field of engineering, the use of pencil and paper is frequently preferred to using the most common computer input devices, the mouse and the keyboard. The traditional paper approach offers the students flexibility in expressing their thoughts in a free form, experimenting and visualizing their approaches while working out their solutions. The focus of this work, which is in progress, is to modify and adapt certain aspects of traditional engineering exam problems to make them more suitable for electronic examinations. This allows the students to continue use the traditional tools of pencil and paper, but the electronic exam will extract the information needed for automatic grading, combining the best of both methods.

In many fields, a mass of algorithms with completely different hyperparameters have been developed to address the same type of problems. Choosing the algorithm and hyperparameter setting correctly can promote the overall performance greatly, but users often fail to do so due to the absence of knowledge. How to help users to effectively and quickly select the suitable algorithm and hyperparameter settings for the given task instance is an important research topic nowadays, which is known as the CASH problem. In this paper, we design the Auto-Model approach, which makes full use of known information in the related research paper and introduces hyperparameter optimization techniques, to solve the CASH problem effectively. Auto-Model tremendously reduces the cost of algorithm implementations and hyperparameter configuration space, and thus capable of dealing with the CASH problem efficiently and easily. To demonstrate the benefit of Auto-Model, we compare it with classical Auto-Weka approach. The experimental results show that our proposed approach can provide superior results and achieves better performance in a short time., 12 pages, 3 figures

Mobile augmented reality (AR) has been attracting considerable attention from industry and academia due to its potential to provide vibrant immersive experiences that seamlessly blend physical and virtual worlds. In this paper we focus on creating contextual and personalized AR experiences via edge-based on-demand provisioning of holographic content most appropriate for the conditions and/or most matching user interests. We present edge-based hologram provisioning and pre-provisioning frameworks we developed for Google ARCore and Magic Leap One AR experiences, and describe open challenges and research directions associated with this approach to holographic content storage and transfer. The code we have developed for this paper is available online.

In the contemporary world, security plays the major role to prevent various assets and thefts. Education is the integral part of every human life as it delivers from one age then onto the next. Examination is the heart of the training structure. The main aim of the examination is to pick the qualified applicants for various positions. We hear the news of postponed or cancellation of exams each year due to question paper spillage. So, to stop this leakage of question papers a smart system is proposed. This system is designed on the embedded system. The key components of the device are NodeMcu, Biometric Sensor and GPS Module.

On average, 2.5 quintillion bytes of data are generated on the internet every day. So, the demand for data storage is growing exponentially, but the capacity of existing storage media is not keeping up. A revolution in the field of data storage is the need of an hour. This paper surveys a very unique technique of storing digital data in DNA sequences. The idea is to replicate nature’s way of storing information. It has been around with us for ages. This paper elaborates on the procedure, applications, and challenges that are associated with this fictitious idea of data storage. Using DNA to archive data is an attractive possibility because it is extremely dense, with a raw limit of 1 Exabyte/mm3 (109 GB/mm3), and long-lasting, with an observed half-life of over 500 years.

Sentiment Analysis is done by gathering the data, analyzing the text and aggregating the words in the text. The main focus of this survey is on the evaluation methods used and their respective core solutions. In this paper we are going to study the aspect based sentiment classification, which is classified into three. Those are Implicit, Explicit and Coreferential aspect based sentiment classification. In this paper we are also going to elaborate the polarity of the reviews into positive and negative sentiments. Aspect Based Classification not only promises to suppress the noisy data but also provides high efficiency in identifying the aspects with an addition of performing classification task with higher accuracy. This accuracy can be achieved by using Neural Network algorithms.

In the present work, the 48 input-output data points of the paper mill process have been considered with the desired machine speed as the input and required total head as the output. The data has been taken from the literature. Two clustering techniques are applied on this data using MATLAB. One is the FCM (fuzzy C-means clustering), another is the subtractive clustering. In present work, initial FIS (fuzzy inference system) developed by subtractive clustering is further optimized to improve its performance, and finally their responses are compared.

Facing the difficulty and inefficiency of creating and maintaining High-Definition (HD) maps in our commercial deployments, we have developed an edge-based crowdsourcing task distribution framework for HD Map in autonomous driving. Our key observation is that: HD map data crowdsourcing exhibits the diminishing marginal utility thus there exists an inflection point for maximum utility, meanwhile its premature convergence of utility will leave some map updates not notified in time. Based on this observation, we develop a periodic crowdsourcing task distribution framework. It discretizes the demands for collecting source data into different periods and uses an optimal stopping rule to terminate the data collection for the maximum crowdsourcing utility. The experimental results verify that our crowdsourcing framework can achieve high time coverage and high efficiency with lower cost.

In autonomous driving, 3D object detection is es-sential as it provides basic knowledge about the environment. However, as deep learning based 3D detection methods are usually computation intensive, it is challenging to support realtime 3D object detection on edge-computing devices in selfdriving cars with limited computation and memory resources. To facilitate this, we propose a compiler-aware pruning search framework, to achieve real-time inference of 3D object detection on the resource-limited mobile devices. Specifically, a generator is applied to sample better pruning proposals in the search space based on current proposals with their performance, and an evaluator is adopted to evaluate the sampled pruning proposal performance. To accelerate the search, the evaluator employs Bayesian optimization with an ensemble of neural predictors. We demonstrate in experiments that for the first time, the pruning search framework can achieve real-time 3D object detection on mobile (Samsung Galaxy S20 phone) with state-of-the-art detection performance.

Graph neural networks (GNN) have achieved state-of-the-art performance on various industrial tasks. However, the poor efficiency of GNN inference and frequent Out-of-Memory (OOM) problem limit the successful application of GNN on edge computing platforms. To tackle these problems, a feature decomposition approach is proposed for memory efficiency optimization of GNN inference. The proposed approach could achieve outstanding optimization on various GNN models, covering a wide range of datasets, which speeds up the inference by up to 3×. Furthermore, the proposed feature decomposition could significantly reduce the peak memory usage (up to 5× in memory efficiency improvement) and mitigate OOM problems during GNN inference.

As a fundamental component in the autonomous driving technology stack, High Definition Maps (HD map) provide high-precision descriptions of the environment. It enables extremely accurate perception and localization while improving the efficiency of path planning. However, the HD map’s extremely large data volume poses great challenges for the real-time and safety requirements of autonomous driving. Based on our real-world deployment experiences, we first demonstrate how the existing data transmission mechanism is weak in supporting HD map services. To address this problem, we propose an HD map data service mechanism on top of Vehicle-to-Infrastructure (V2I) data transmission under a tight time and energy budget. By this mechanism, the selected road side unit (RSU) nodes cooperate on map provisioning tasks and transmit HD map data proportionately. Furthermore, we model the real-time map data service into a partial knapsack problem and develop a greedy data transmission algorithm. Experimental results confirm that the proposed mechanism can ensure the real-time HD map data service meanwhile meeting the energy limits.

As a tool for human technological advancement, the peer-review system acts as a gateway for ensuring academic paper qualities. However, the system has proven to be slow and expensive. Also, biasedness remains an unsolved problem. Such issues could become a major bottleneck, which can adversely impact research progress and dissemination of knowledge. This paper aims to propose a double-blind paper review system to preserve the authors and reviewers anonymity. This system also addresses issues concerning the reviewers payment, inconsistent review metrics, and biased reviews. The proposed solution utilizes the Hyperledger Fabric blockchain with the InterPlanetary File System (IPFS). The blockchain smart contracts provide a base for financial transactions between paper publishers and the reviewers. Hence, we introduce AcadCoin, a novel cryptocurrency used for supporting said financial transactions. Also, the Hyperledger blockchain provides user access control to achieve double-blindness in reviews. Along with the Hyperledger blockchain, the IPFS is used to store the paper documents, review documents and open metrics documents to reduce the storage requirement of the blockchain. A broad system architecture is constructed to combine the blockchain and the file storage system. This system architecture distributes nodes of the system to related parties. Finally, the blockchain network is implemented and tested using the Hyperledger Composer Playground environment.

With the great technological advances in colour printing, duplicating and scanning, counterfeit notes haves posed an increasing threat to currency markets all over the world. Over the past few years, the Yemeni currency market has suffered extensively from this problem. Although the Yemeni Paper Counterfeit- Currency Detection System (YPCDS) has made steps to counter this problem, it is limited to the 1000 denomination, leaving a considerable chance for counterfeiting other dominations. This paper offers a technical remedial solution to this problem for all denominations using image processing and machine learning techniques. The main aim of this system is to create an automatic system robot to recognize and detect Yemeni paper currency genuine or counterfeit. The system framework consists of five phases: acquisition of the currency image, preprocessing, feature extraction, classification, and verification. MATLAB is the main program for creating this system. The efficacy of the system was tested experimentally using four Yemeni currency categories and the system was found to be able to detect whether currency is genuine or counterfeit with high accuracy and fast processing time.

BBoxDB is a distributed key-bounding-box-value store which is capable of handling large scale $n-$dimensional data. Unlike existing key-value stores, each value is stored together with a bounding box which describes the location of the value in an $n-$dimensional space. BBoxDB splits large datasets automatically and spreads them across a cluster of nodes. The software works primarily on the bounding boxes of the stored data; operations like range queries or joins take only the bounding boxes of the data into consideration. In version 0.9.1, we implemented support for user defined filters (UDF) in BBoxDB; UDFs operate on the real values of the data. In this paper, we describe this novel feature for the first time. As an example, a UDF is developed in this paper which is capable of handling GeoJSON encoded data. The UDF consists only of a few lines of code and turns the generic distributed datastore BBoxDB into a specialized system that is capable of processing large scale GeoJSON encoded datasets. Operations like spatial joins or range queries on the real geometries of the data become possible. During our demonstration, we show the implementation of the UDF and perform range queries and spatial joins. The used dataset contains spatial data of the whole world and is obtained from the Open Street Map project. For visualization, the GUI of BBoxDB was extended in a way that spatial queries can easily be executed. Using the GUI, query results can be interactively explored; they are shown as an overlay on a map dynamically fetched from the Open Street Map project.

The study aimed to realize the automatic production scheduling of waste paper in paper mills. Based on the quantities of the field data (mixing ratios of waste paper and pulp properties) stored in a paper mill, the methods of back propagation neural networks (BP-NN) and support vector machine (SVM), the all data set and the average data set, were firstly applied to develop the prediction models of the pulp properties; and then the genetic algorithm was used to search for the suitable scheduling solutions. The simulation results revealed that: demonstrating its acceptable prediction accuracy and fast training time, the prediction model with SVM method and the average data set was good enough to be used in the genetic algorithm to search for the optimal scheduling ratios of waste paper, the obtained optimal scheduling solution not only had the lowest purchase cost of waste paper, but also met the requirements of the mill: specified types of waste paper, specified ratio of some kind of waste paper and the required pulp brightness.

U.S. Department of Defense regulations intended to improve cybersecurity within the Defense Industrial Base may cause degradation of critical defense infrastructure. Four impediments to 'clean' compliance, environmental and internal, are detailed. Inability to functionally comply, or to correctly insure, will impact the DIB's cybersecurity decision-making at the enterprise level. Economic impact to the DIB may drive withdrawal and attrition from the sector, or aversion to R&D, which negatively affects mission resilience with concomitant capability loss to the DoD.

Currently, anomaly detection is receiving a great deal of attention due to its importance in many real-world applications especially in data analytics. Anomaly detection has two important purposes in data pre-processing stages: one is to detect and attempts to eliminate them if and only if it is really outlier, while the other requires attention be paid to valid outlier (extreme value) because extreme value themselves carry the significant and critical information, such as extreme weather events. It will lead to significant harm if not detected and treated properly. This paper begins with the summary of anomaly detection, challenges, type of anomalies, extreme value followed by machine learning algorithms approach that deal with anomaly detection. Finally, we provide a conclusion that discusses about the important of detecting clearly between outlier or extreme value in data pre-processing stage, so that an effective and efficient prediction can be achieved later in modelling stage.

This Embedded Graphics libraries have evolved from OpenGL to next gen Vulkan libraries. OpenCL and CUDA have been used for many years for GPU compute on a range of SoC devices with powerful embedded GPU chipsets. OpenCL and CUDA were never able to be certified, due to the contributions from many developers. Next generation autonomous vehicles, unmanned aircraft, transportation and even military vehicles will require both graphics, as well as GPU compute to implement DSP or FPGA logic is software, as well as Deep Machine Learning. Vulkan libraries are available now and are defined by the Kronos Group, as well as this, a next generation of Vulkan safety critical library for safe Shader and GPU Compute is now available. This white paper will look at Vulkan architectures, embedded system use and the implications for using GPU Compute, where certification may be a critical requirement for ISO 26262, EN50182, IEC 61508, DO178C certifiable embedded systems.

Academic advising of the postgraduate students is considered as a fundamental rule and one of the significant positive services and responsibilities for the academic staff follow up in most of the e-leading educations. The expert system is considered as one of most achievement areas in artificial intelligence and highly appreciated for application with e-learning and teaching methods. The aim of this paper, is to survey the most expert systems used in advisory model and replaced with the manual registration and advising system of face to face communication and discussion in Instructor office. The method used of determined the key factors related to student advising and expert system models though open access databases. The finding of this section reviews out nine selected expert systems in order to explore the strengths, and limitations of existing expert system approaches to advising undergraduate students.

Security is becoming an important issue everywhere nowadays. Every person wants his house, factory, bank etc. to be secured. House security is becoming necessary as the possibilities of intrusion are increasing day by day. Here in this paper, we are trying to present research made on various door locking systems that have been used at homes, offices, shops, industries, etc. The research will also put some light on the pros and cons of the various door lock systems and the technology used in the respective systems. The research will include traditional door lock system, RFID based system, gesture-based systems, Bluetooth and GSM technology- based and various other technologies used in the door lock security systems. The advance in technology in each passing day can help us come across various technologies that can be used in the door lock security system. Since security is the major concern of the majority of the people at present, we feel research made on the various system relevant to the topic can help people to choose the best technology for their upcoming projects or make changes in the past projects and use effective door lock systems for their needs.

Technology grows at a rapid rate and trust has involved in a risk judgment between different parties. Authentication and Authorization generally determines the trust while dealing with transactions of data over different channels. Blockchain has become a digital backbone due to its security, time-management, and transparency on data decentralization ledger. This survey paper studies the existing blockchain structure, analyses the research gaps and proposes a new theoretical approach based on neighbor monitoring and updating model. This model may help the patients to decentralize real data and results in the blockchain network. This work discusses in detail about the various security challenges in block chain against 51% attack and double-spend attack by proposing a theoretical framework for the problem.

This paper introduces the time stamped bijective MAC algorithm (bMAC), which aims at proving firmware integrity in embedded systems. bMAC computes a MAC over a set of memories, in a pseudo random way relying on a permutation. It is based on exponential permutations that induce computing time distributions. Because bMAC performs calculations on SRAM content, it can be bound to physical chips, by means Physical Unclonable Functions (PUF), extracted from SRAM.

Cloud computing is the emerging way of computing that is being used by wide range of users. At present 80 % of workload is on cloud. There are many safety risks in cloud computing, “Cloud Security Alliance” (CSA) listed top 7 security threats as Maltreat and Obnoxious utilization of cloud, Uncertain API, Vicious Infiltrators, Distributed mechanism challenges, Information drop, Unidentified Risk Report and Account, Service and Traffic Hijacking. An IT company spends 42 percent of its funds for the security of cloud and 80 percent of the funds will be bounded to attain the solution to security issues. Researchers have proposed no. of solutions to cloud security. Proposed solutions fall under three primary categories, Cryptographic, data storage and data semantics. In this paper we have reviewed the concerns in cloud computing with some of the subsequent proposed models to tackle the security issues in cloud computing.

During the past decade or so, knowledge graphs have stealthily made way into our daily lives, whether through voice assistants (the likes of Alexa, Google Assistant or Siri), spontaneous search results or customized personal shopping experiences through online stores recommenders. Today, we are surrounded and constantly interacting with knowledge graphs on a regular basis. The scope and impact of knowledge graphs and underlying graph databases are still a mystery to people. Considering its smooth entry into our lives, most of us are unaware of how dependent we actually are on the technology. In this paper, we have shown the working of the Google knowledge graph and how the knowledge graph works as the most effective recommendation system. We have discussed how it finds its way through daily life in various fields like Banking, Social media (Facebook, LinkedIn, Netflix), Food application (Uber Eats) and the Healthcare sector.

Prior work on texture analysis of historic, photographic papers has focused primarily on measures of texture similarity. However, automated grouping or clustering of photographic paper textures in a way that is meaningful to art conservators remains an open problem. In this work a deep learning approach to automated classification is presented, for clusters derived from a human sorting experiment conducted by 19 art conservators and paper experts and subsequently extended through crowd-sourcing. The proposed approach uses a deep convolutional neural network, and results are presented on the performance in automatically classifying images when compared to human experts.

European Rail Traffic Management System(ERTMS) efficiently manages and schedules the trainsguaranteeing passengers safety and service constraints andmaximizing railways capacity. The management system isresponsible of the elaboration needed to control the trainscirculation and to derive the necessary commands for trainsand trackside actuators such as railroad switches. Theseoperations need heavy computational resources and require anexchange of information between trains, trackside equipmentsand elaboration components. Currently the managementsystem is hosted in the Central Control Rooms that centrallymanage and supervise trains traffic of different geographicalareas. This paper proposes a new paradigm about the executionof the ERTMS management activities taking advantage fromcloud networks. It suggests to distribute among cloud resourcesthe computational load due to the elaboration of the collecteddata and the derivation of required commands for trains andactuators. This can make possible a proactive approach tothe trains management, suitable not only to consider the datasent by the trackside equipments, but also the informationdirectly collected onboard of the train. Despite trackside dataare considered by the management system, actually they arenot integrated with onboard real-time data that are sent tothe ground system for diagnosis purposes. These two sourcesof information can be jointly used to simulate in advance thetrain transit, deduce possible delays and anomalies and moreefficiently manage the trains circulation.

With the proliferation of threats of leakage of sensitive information such as military classified documents, information guards have recently gained increased interest. An information guard is merely a filter than controls the content of the exchanged information between two domains where one of them has a higher confidentiality level than the other one. The main role of an information guard is to block leakage of the sensitive information from the higher confidentiality domain to the lower confidentiality domain. An example of a higher confidentiality domain is a military network while a subcontractor network is an example of a lower confidentiality domain. The common practice is to use an automatic information guard based on predefined list of words that is called "dirty word list" in order to decide the security level of a document and consequently release it to the lower confidentially domain or block it. Traditional information guards are configured manually based on the notion of "Dirty Lists". The classification logic of traditional information guards uses the occurrence of words from the "Dirty Lists". In this paper, we advocate the use of machine learning as a corner stone for building advanced information guards. Machine learning can also be used as a supplement to the decision obtained based on "Dirty Lists" classification. Machine learning has hardly been analysed for this problem, and the analysis on topical classification presented here provides new knowledge and a basis for further work within this area. Ten different machine learning algorithms were applied on real life data from a military context. Presented results are promising and demonstrates that machine learning can become a useful tool to assist humans in determining the appropriate security label of an information object.

In this work, different Machine Learning (ML) techniques are used and evaluated based on their performance of classifying peer reviewed published content. The ultimate objective is to extract meaningful information from published abstracts. In pursuing this objective, the ML techniques are utilized to classify different publications into three fields: Science, Business, and Social Science. The ML techniques applied in this work are Support Vector Machines, Naive Bayes, K-Nearest Neighbor, and Decision Tree. In addition to the description of the utilized ML algorithms, the methodology and algorithms for text recognition using the aforementioned ML techniques are provided. The comparative study based on four different performance measures suggests that – with the exception of Decision Tree algorithm – the proposed ML techniques with the detailed pre-processing algorithms work well for classifying publications into categories based on the text provided in the abstract.

Adversarial Machine Learning has been gaining attention from the NLP community due to low interpretability and low robustness of the current state-of-the-art systems. In this work, we study the effect of various adversarial attacks for detection of suicidal intent in social media setting. Suicide Ideation is a sensitive issue and is a leading cause of death. We show how various models are rendered useless after attacks and perform adversarial training using the most ideal attacks to improve their robustness. We also conduct several experiments with the attacks to study their effect and propose an approach for adversarial training using Generative Adversarial Networks.

Latent Semantic Analysis uses Singular Value Decomposition (SVD) to effectively retrieve relevant information from the information corpus. However, LSA has a high computational cost. In order to address this aspect, it is proposed to filter only those words carrying high semantic importance. The aim is to improve the execution time of semantic space construction and dimensionality reduction. We present how the use of data filter can effectively meet the proposed goals in comparison to baseline method of performing recommendations. The proposed system was assessed over a dataset of 80 articles (Titles and Abstracts). The results of the experiments show that the proposed system performed better in terms of elapsed time with an average precision of 85.54% (78.64% for baseline method) and an average recall of 92.96% (89.70% for baseline method).

E-hailing industry is a new concept in the taxi services whereby private cars can register with online transport. Despite the rapid popularity of e-hailing services, there are major public concerns pertaining to cyber security behavior issues both to the passengers and the drivers such as hit and run accident, robbery, rape, sexual harassment, murder, rude drivers and grab driver scams. Hence, this study intends to investigate the predictors of cyber security behaviors of e-hailing services in Malaysia. The prevailing factors to be examined are perceived threats, perceived privacy, fraud victimization, response efficacy, perceived vulnerability, security self-efficacy, perceived benefit and government policy. The research methods to be used are quantitative and qualitative research design. The sampling technique is to collect data passengers and drivers of e-hailing services operating in Malaysia. The measurement of the twelve main variables consists of 90 items. The data will be collected using self-administered survey and analyzed using SMART PLS 3.0. The expected finding is a new cyber security behavior model for Malaysia, provide new inputs for e-hailing regulation and policy improvement in line with Industrial Revolution 4, new suggestions for e-hailing market segmentation according gender and generation gaps, enhancement of the existing applications according to research findings, set new guidelines on the development of similar application in line with industrial Revolution 4 and the installation of panic button in e-hailing automobile. From the pilot study results, all scales were found to be consistent and reliable with Cronbach's alpha readings above 0.70.

Showing animations on electronic papers for highlighting some important items is always desirable, but none of mature driving methods have been developed. In this paper, a new driving method aiming at reducing ghost images as well as improving the panel reliability is presented. The method has been integrated with the hardware system we developed, and thereby a promising displayed quality on the electronic paper can be achieved.

Gamification is one of the trends in education that is best suited to the current learning environment. Putra BINGO is a transformative assessment tool that uses gamification techniques. This research starts by elaborating the concept of Putra BINGO and its implementation using traditional method with pen and paper. The feedbacks gathered from the implementation are analyzed and applied to develop a multiplayer educational online game using Unity Game Engine. This paper describes details of the development for its two components; the database and the digital online game. Putra Bingo is available on PC and Android devices. It required additional plugins such as Photon Networking to handle game communication between multiple players. This is crucial to accommodate its test case application as an alternative assessment for teamwork skills using Rubrics and questionnaires. Further research will be conducted to enhance its functionality and user experience after the initial development of the digital online version is completed.

First launched nearly three decades ago, PDF, which stands for Portable Document Format, has become one of the most common formats for text documents. Nowadays, PDF is widely used by individuals, companies, and organizations. At most notable academic conferences, including IEEEs, papers are required to be submitted in PDF format. Along with its increasing popularity in recent times, PDF has been a target for many attacks, some of which are called content-masking attacks. Content-masking attacks are based on the idea of causing underlying text, which is extracted by text-mining softwares and read by machines, to be displayed differently to humans. Inspired by the same idea but is designed and implemented differently, our proposed attack is against the paper submission process at large academic conferences, which consists of two subprocesses: plagiarism detection and automatic assignment of reviewers to papers. Our attack overcomes many weaknesses of previous attacks. In addition, we introduce a method to avoid content masking attacks against the automatic reviewers' assignment process by preventing attackers from getting true topic information from PDF documents.

Paper illustrates the process of topic modeling and text classification. Specifically, the dataset used is a corpus consisting of scientific publications published by Neural Information Systems Processing Conference. Topic modeling itself is performed using Latent Dirichlet Allocation model. It is followed by optimization of a number of topics on the basis of topic coherence, a quality measure of human interpretability. Results of topic modeling are used for labeling data prior to text classification. Labels are determined based on the distribution of assigned papers' topics over time. Specifically, peak changes used for differentiating between time periods dominated by specific topics are calculated as a Kullback-Leibler divergence. Finally, transforming data into the feature vectors, several different text classification approaches are evaluated. As observed, the greatest accuracy score is recorded for the use of extreme gradient boosting classifier being 77.1%.

Privacy can be revealed from many sources, since data is available in papers and digital forms. Many techniques available to infer some private data based on these available sources, for example, data mining techniques. In this paper, it is investigated whether it is possible to derive some private information from shopping receipts, which are paper traces of people activities. Since people do not think that shopping receipts may harm them, usually they do not keep these shopping receipts safely. The techniques used in this research are data mining techniques; classification and clustering algorithm. In this first stage of research, the aim of this research is to determine whether it is possible to classify shopping data to correct shopper profiles, and to separate a set of shopping data into two meaningful groups, according to the shopping profiles. From the results, it can be concluded that it is possible to predict to which profile the data belongs to, with the percentage of data correctly classified higher than 97%. It also can be concluded that it is possible to separate the shopping receipts data into two groups, where each group represents each profile.

In this survey paper, we point out a comparative study on different types of plant leaf diseases and all the techniques of machine learning which had been used to detect plant leaf disease. This was accomplished for two principle reasons: to restrain the length of the paper and in light of the fact that techniques managing roots, seeds and natural products have a few idiosyncrasies that would warrant a particular study. The chose proposition are isolated into three classes as indicated by their goal: recognition, seriousness measurement, and characterization. Every one of those classes, thus, are subdivided by the primary specialized arrangement utilized in the calculation. This paper is required to be helpful to specialists working both on vegetable pathology and example acknowledgment, giving a thorough and open outline of this significant field of research.

In an ongoing discussion comparing the security properties of electronic and paper voting, decreased privacy is often presented as an argument against remote Internet voting. We contribute to this discussion by presenting a side-channel attack against the physical environment of traditional paper-based elections. More precisely, we build a device based on an Arduino development board and cheap electret microphones, capable of triangulating the locations of marks made on wooden tables with high precision. In the best configuration, we are able to determine the correct cell having dimensions 4×5 cm with more than 90% accuracy. This will allow breaching privacy of ballot sheet designs that rely on the voter marking her choice(s) between a potentially high number of candidates printed on one large sheet. We complement our attack with a study on various aspects of deployment of facial recognition. This gives rise to the setup where the attacker installs cameras in the polling stations, aiming at automated detection of people leaving the voting booths. Combining the two approaches, we will have a completely automated (and hence relatively well scalable) attack against the privacy of paper-based voting.

Association Rule Hiding is the Data Mining method which is used for extracting hidden information from huge dataset. In our paper, Two approaches are introduced. In first approach FP Growth Algorithm is being presented that generate association rules efficiently and it reduces time of forming frequent item sets every time. In second approach we have tried to hide sensitive association rules by Genetic Algorithm. Generally from large databases frequent items are extracted by applying different algorithms. In this paper, we compare all the algorithms for extracting frequent items which are Association Rule Mining, Apriori Algorithm and FP growth Algorithm. We also compare Fuzzy Logic Algorithms and Genetic Algorithm for hiding sensitive association rules.

At the present time evaluating an exam papers and declaring end result in a restricted period of time is a difficult task for educational schools, colleges, institutions, departments and Universities. Thus manual exam paper correction becomes more difficult and many fraudulent activities are happened today. To make it easier and more accurate the proposed aim is to develop a software for automatic exam paper evaluation and grading system, the system works by scanning the handwritten written exam papers then the scanned image be improved into an editable text using OCR tool and the evaluation will perform by matching the key terms which is maintained in the template. It is entirely integrated approach upon dissimilar level of knowledge by the method of examination, evaluation, result and formulation of subject papers. In a field of education though teaching, evaluation and the performance method many organizations initiated with the use of advanced technologies. The approach of evaluating the examination papers is evolved although use of computer wherever the utilization of computer is obligatory in every varied techniques for analysis. This paper structured in different patterns such as offline, online and the manual exam paper evaluation with different analysis and techniques.