Search results for: hard classifiers

Authors: Annapureddy Srikant Reddy, Atthanti Mahendra, Samala Chinni Krishna, N. Neelima

Abstract:

In our present world, we are generating a lot of data and we, need a specific device to store all these data. Generally, we store data in pen drives, hard drives, etc. Sometimes we may loss the data due to the corruption of devices. To overcome all these issues, we implemented a cloud space for storing the data, and it provides more security to the data. We can access the data with just using the internet from anywhere in the world. We implemented all these with the java using Net beans IDE. Once user uploads the data, he does not have any rights to change the data. Users uploaded files are stored in the cloud with the file name as system time and the directory will be created with some random words. Cloud accepts the data only if the size of the file is less than 2MB.

Keywords: cloud space, AES, FTP, NetBeans IDE

Procedia PDF Downloads 177

Authors: Bandar Alahmadi, Lethia Jackson

Abstract:

Machine Learning model is used today in many real-life applications. The safety and security of such model is important, so the results of the model are as accurate as possible. One challenge of machine learning model security is the adversarial examples attack. Adversarial examples are designed by the attacker to cause the machine learning model to misclassify the input. We propose a method to generate adversarial examples to attack image classifiers. We are modifying the successfully classified images, so a classifier misclassifies them after the modification. In our method, we do not update the whole image, but instead we detect the important region, modify it, place it back to the original image, and then run it through a classifier. The algorithm modifies the detected region using two methods. First, it will add abstract image matrix on back of the detected image matrix. Then, it will perform a rotation attack to rotate the detected region around its axes, and embed the trace of image in image background. Finally, the attacked region is placed in its original position, from where it was removed, and a smoothing filter is applied to smooth the background with foreground. We test our method in cascade classifier, and the algorithm is efficient, the classifier confident has dropped to almost zero. We also try it in CNN (Convolutional neural network) with higher setting and the algorithm was successfully worked.

Keywords: adversarial examples, attack, computer vision, image processing

Procedia PDF Downloads 312

Authors: Elad Harison

Abstract:

The paper identifies the complex links between post-COVID-19 inflationary pressures and global supply chains. Throughout the COVID-19 lockdowns and long periods after the termination of social distancing policies, consumers, notably in the U.S., have confronted and still face disruptions in the supply of goods. The study analyzes the monetary policy in the U.S. that led to the significant shift in consumer demand during a limited supply period, hence resulting in shortages and emphasizing inflationary dynamics. We argue that the monetary guidelines applied by the U.S. government further elevated the scope of supply chain disruptions.

Keywords: consumer demand, COVID-19, inflation, monetary policy, supply chain

Procedia PDF Downloads 71

Authors: R. Joseph Raviselvan, K. Ramanathan, P. Perumal, M. R. Thansekhar

Abstract:

Hard coatings are widely used in cutting and forming tool industries. Titanium Nitride (TiN) possesses good hardness, strength and corrosion resistant. The coating properties are influenced by many process parameters. The coatings were deposited on steel substrate by changing the process parameters such as substrate temperature, nitrogen flow rate and target power in a D.C planer magnetron sputtering. The structure of coatings were analysed using XRD. The hardness of coatings was found using Micro hardness tester. From the experimental data, a regression model was developed and the optimum response was determined using Response Surface Methodology (RSM).

Keywords: hardness, RSM, sputtering, TiN XRD

Procedia PDF Downloads 292

Authors: Seyedeza Baharisaravi

Abstract:

As we know, we are living in the hyper competitive environment and all of companies strive hard to engross more and more customers. Thus, in this milieu, we should produce and deliver diverse commodities, regarding with the consumers' interests. So, all companies elicit that they should pay attention on the external resources besides the internal ones. Hence, the meaning of supply chain management has been introduced as a fundamental issue for global e-business, e-commerce and e-government. The present paper explains prominences, challenges, keys, various descriptions, advantages and disadvantages, globalization and the future of one of the vital issues in the business realm which is supply chain management (SCM). This issue is one of the newest concepts of business science that has transformed the essence of every business and attitude of marketers.

Keywords: SCM concepts, supply chain management, the importance of SCM, SCM in organization

Procedia PDF Downloads 278

Authors: Yang Cao

Abstract:

Analyzing the oral production of Chinese-speaking learners of English as a second language (L2), we can find a large variety of verb inflections – Why does it seem so hard for them to use consistent correct past morphologies in obligatory past contexts? Failed Functional Features Hypothesis (FFFH) attributes the rather non-target-like performance to the absence of [±past] feature in their L1 Chinese, arguing that for post puberty learners, new features in L2 are no more accessible. By contrast, Missing Surface Inflection Hypothesis (MSIH) tends to believe that all features are actually acquirable for late L2 learners, while due to the mapping difficulties from features to forms, it is hard for them to realize the consistent past morphologies on the surface. However, most of the studies are limited to the verb morphologies in finite clauses and few studies have ever attempted to figure out these learners’ performance in non-finite clauses. Additionally, it has been discussed that Chinese learners may be able to tell the finite/infinite distinction (i.e. the [±finite] feature might be selected in Chinese, even though the existence of [±past] is denied). Therefore, adopting a self-paced reading task (SPR), the current study aims to analyze the processing patterns of Chinese-speaking learners of L2 Russian, in order to find out if they are sensitive to misuse of tense morphologies in both finite and non-finite clauses and whether they are sensitive to the finite/infinite distinction presented in Russian. The study targets L2 Russian due to its systematic morphologies in both present and past tenses. A native Russian group, as well as a group of English-speaking learners of Russian, whose L1 has definitely selected both [±finite] and [±past] features, will also be involved. By comparing and contrasting performance of the three language groups, the study is going to further examine and discuss the two theories, FFFH and MSIH. Preliminary hypotheses are: a) Russian native speakers are expected to spend longer time reading the verb forms which violate the grammar; b) it is expected that Chinese participants are, at least, sensitive to the misuse of inflected verbs in non-finite clauses, although no sensitivity to the misuse of infinitives in finite clauses might be found. Therefore, an interaction of finite and grammaticality is expected to be found, which indicate that these learners are able to tell the finite/infinite distinction; and c) having selected [±finite] and [±past], English-speaking learners of Russian are expected to behave target-likely, supporting L1 transfer.

Keywords: features, finite clauses, morphosyntax, non-finite clauses, past morphologies, present morphologies, Second Language Acquisition, self-paced reading task, verb inflections

Procedia PDF Downloads 81

Authors: Shah S. M. A., Aftab U.

Abstract:

It is imperative in today’s world to get a real time information about different emergency situation occurred in the environment. Helicopters are mostly used to access places which are hard to access in emergencies like earthquake, floods, bridge failure or in any other disasters conditions. Use of helicopters are considered more costly to properly collect the data. Therefore a new technique has been introduced in this research to promptly collect data using drones. The drone designed in this research is based on trial and error experimental work with objective to construct an economical drone. Locally available material have been used for this purpose. And a mobile camera were also attached to prepare video during the flight. It was found that within very limited resources the result were quite successful.

Keywords: UAV, real time, camera, disasters

Procedia PDF Downloads 207

Authors: Khalida Douibi, Rodrigo Balp, Solène Le Bars

Abstract:

In the medical field, applications related to human experiments are frequently linked to reduced samples size, which makes the training of machine learning models quite sensitive and therefore not very robust nor generalizable. This is notably the case in Brain-Computer Interface (BCI) studies, where the sample size rarely exceeds 20 subjects or a few number of trials. To address this problem, several resampling approaches are often used during the data preparation phase, which is an overly critical step in a data science analysis process. One of the naive approaches that is usually applied by data scientists consists in the transformation of the entire database before the resampling phase. However, this can cause model’ s performance to be incorrectly estimated when making predictions on unseen data. In this paper, we explored the effect of data leakage observed during our BCI experiments for device control through the real-time classification of SSVEPs (Steady State Visually Evoked Potentials). We also studied potential ways to ensure optimal validation of the classifiers during the calibration phase to avoid overfitting. The results show that the scaling step is crucial for some algorithms, and it should be applied after the resampling phase to avoid data leackage and improve results.

Keywords: data leackage, data science, machine learning, SSVEP, BCI, overfitting

Procedia PDF Downloads 124

Authors: Mohinder Kumar

Abstract:

Sports are considered as the very prominent social institution in almost every society because it reflects the mores, values, and general culture of a society. Sports activity tend to pave the foundation for learning acceptable values and beliefs and for acquiring desirable character traits such as self-discipline, sportsmanship, and an appreciation for hard work, fairness, self-respect, leadership, followership, justice, perseverance, competition, and goal attainment. The present study focuses on ideal ways of socializing youngsters into sports. Influences of some socializing agents (e.g. family, school, community) are reviewed and suggestions made as to how these socializing agents can be oriented and made effective in carrying out functional processes toward target ends.

Keywords: sports, socializing, family, community, society

Procedia PDF Downloads 435

Authors: Htay Htay Yi, Zin May Aye

Abstract:

Network security is role of the ICT environment because malicious users are continually growing that realm of education, business, and then related with ICT. The network security contravention is typically described and examined centrally based on a security event management system. The firewalls, Intrusion Detection System (IDS), and Intrusion Prevention System are becoming essential to monitor or prevent of potential violations, incidents attack, and imminent threats. In this system, the firewall rules are set only for where the system policies are needed. Dataset deployed in this system are derived from the testbed environment. The traffic as in DoS and PortScan traffics are applied in the testbed with firewall and IDS implementation. The network traffics are classified as normal or attacks in the existing testbed environment based on six machine learning classification methods applied in the system. It is required to be tested to get datasets and applied for DoS and PortScan. The dataset is based on CICIDS2017 and some features have been added. This system tested 26 features from the applied dataset. The system is to reduce false positive rates and to improve accuracy in the implemented testbed design. The system also proves good performance by selecting important features and comparing existing a dataset by machine learning classifiers.

Keywords: false negative rate, intrusion detection system, machine learning methods, performance

Procedia PDF Downloads 98

Authors: Ahmad Saleem

Abstract:

Ethereum is the second largest crypto currency in blockchain ecosystem. Along with standard transactions, it supports smart contracts and NFT’s. Current research trends are focused on analyzing the overall structure of the network its growth and behavior. Ethereum addresses are anonymous and can be created on fly. The nature of Ethereum network and addresses make it hard to predict their behavior. The activity period of an ethereum address is not much analyzed. Using machine learning we can make early prediction about the disposability of the address. In this paper we analyzed the lifetime of the addresses. We also identified and predicted the disposable addresses using machine learning models and compared the results.

Keywords: blockchain, Ethereum, cryptocurrency, prediction

Procedia PDF Downloads 71

Authors: Sammani Danwawu Abdullahi

Abstract:

Vertex Enumeration Algorithms explore the methods and procedures of generating the vertices of general polyhedra formed by system of equations or inequalities. These problems of enumerating the extreme points (vertices) of general polyhedra are shown to be NP-Hard. This lead to exploring how to count the vertices of general polyhedra without listing them. This is also shown to be #P-Complete. Some fully polynomial randomized approximation schemes (fpras) of counting the vertices of some special classes of polyhedra associated with Down-Sets, Independent Sets, 2-Knapsack problems and 2 x n transportation problems are presented together with some discovered open problems.

Keywords: counting with uncertainties, mathematical programming, optimization, vertex enumeration

Procedia PDF Downloads 325

Authors: Steffy Maria Joseph, Abdu Rahiman V, Abdul Hameed K. M.

Abstract:

Online handwritten character recognition is a challenging field in Artificial Intelligence. The classification success rate of current techniques decreases when the dataset involves similarity and complexity in stroke styles, number of strokes and stroke characteristics variations. Malayalam is a complex south indian language spoken by about 35 million people especially in Kerala and Lakshadweep islands. In this paper, we consider the significant feature extraction for the similar stroke styles of Malayalam. This extracted feature set are suitable for the recognition of other handwritten south indian languages like Tamil, Telugu and Kannada. A classification scheme based on support vector machines (SVM) is proposed to improve the accuracy in classification and recognition of online malayalam handwritten characters. SVM Classifiers are the best for real world applications. The contribution of various features towards the accuracy in recognition is analysed. Performance for different kernels of SVM are also studied. A graphical user interface has developed for reading and displaying the character. Different writing styles are taken for each of the 44 alphabets. Various features are extracted and used for classification after the preprocessing of input data samples. Highest recognition accuracy of 97% is obtained experimentally at the best feature combination with polynomial kernel in SVM.

Keywords: SVM, matlab, malayalam, South Indian scripts, onlinehandwritten character recognition

Procedia PDF Downloads 549

Authors: Maryam Shayani Rad, Seyed Ahmad Mohajeri, Mohsen Mouhebati, Seyed Danial Mousavi

Abstract:

High blood pressure is one of the most important and serious health-threatening because of no symptoms in most people, which can lead to sudden heart attack, heart failure, and stroke. Nowadays, herbal medicine is one of the best and safest strategies for treatment that have no adverse effects. Apium graveolens (celery) can be used as an alternative treatment for many health conditions such as hypertension. Natural compounds reduce blood pressure via different mechanisms in which Apium graveolens extract provides potent calcium channel blocking properties. A randomized, double-blind, placebo-controlled, cross-over clinical trial was done to evaluate the efficacy of formulated Apium graveolens extract with a maximum yield of 3-n-butylphthalide to reduce systolic and diastolic blood pressure in patients with hypertension. 54 hypertensive patients in the range of 20-68 years old were randomly assigned to the treatment group (26 cases) and the placebo control group (26 cases) and were crossed over after washout duration. The treatment group received at least 2 grams of formulated powder in hard capsules orally, before each meal, 2 times daily. The control group received 2 grams of placebo in hard capsules orally, exactly as the same as shape, time, and doses of treatment group. Treatment was administrated in 12 weeks with 4 weeks washout period at the middle of the study, meaning 4 weeks drug consumption for the treatment group, 4 weeks washout and 4 weeks placebo consumption, and vice versa for the placebo control group. The clinical assessment was done 4 times, including at the beginning and ending of the drug and placebo consumption period by 24-hour ambulatory blood pressure monitoring (ABPM) holter, which measured blood pressure every 15 minutes continuously. There was a statistically significant decrease in both systolic blood pressure (SBP) and diastolic blood pressure (DBP) at the end of drug duration compared to baseline. The changes after 4 weeks on average was about 12.34 mm Hg for the SBP (P < 0.005) and 7.83 mm Hg for the DBP (P < 0.005). The results from this clinical trial study showed this Apium graveolens extract formulation in the mentioned dosage had a significant effect on blood pressure-lowering for hypertensive patients.

Keywords: Apium graveolens extract, clinical trial, cross-over, hypertension

Procedia PDF Downloads 183

Authors: M. Dasgupta, S. Banerjee

Abstract:

Content Based Image Retrieval (CBIR) coupled with Case Based Reasoning (CBR) is a paradigm that is becoming increasingly popular in the diagnosis and therapy planning of medical ailments utilizing the digital content of medical images. This paper presents a survey of some of the promising approaches used in the detection of abnormalities in retina images as well in mammographic screening and detection of regions of interest in MRI scans of the brain. We also describe our proposed algorithm to detect hard exudates in fundus images of the retina of Diabetic Retinopathy patients.

Keywords: case based reasoning, exudates, retina image, similarity based retrieval

Procedia PDF Downloads 323

Authors: Ersegün Ömer Erol

Abstract:

Since the first civilizations, armies have been the most significant part of the countries. As generally known, in today’s world, people are trying hard to find the best way to educate their armies so as to prepare them effectively for the war. Due to the fact that, as rarely known, collective punishment is in fact one of the methods used commonly in militaries in order to educate personnel and cadets. In this study, it is purposed to find out the constructive and unfavorable impacts of collective punishment on cadets’ psychology and by comparing these impacts to decide whether the collective punishment is functional or not. These impacts are obtained from the questionnaire applied on cadets and personnel. The main goal of the study is to provide new point of views and more scientific information about the discussed education way-the collective punishment.

Keywords: army, cadet, collective punishment, psychology

Procedia PDF Downloads 280

Authors: Bowen Ding, Yihao Kuang

Abstract:

In recent years, large-scale pre-trained language models have achieved state-of-the-art performance on a variety of natural language processing tasks. The word vectors produced by these language models can be viewed as dense encoded presentations of natural language that in text form. However, it is unknown how much linguistic information is encoded and how. In this paper, we construct several corresponding probing tasks for multiple linguistic information to clarify the encoding capabilities of different language models and performed a visual display. We firstly obtain word presentations in vector form from different language models, including BERT, ELMo, RoBERTa and GPT. Classifiers with a small scale of parameters and unsupervised tasks are then applied on these word vectors to discriminate their capability to encode corresponding linguistic information. The constructed probe tasks contain both semantic and syntactic aspects. The semantic aspect includes the ability of the model to understand semantic entities such as numbers, time, and characters, and the grammatical aspect includes the ability of the language model to understand grammatical structures such as dependency relationships and reference relationships. We also compare encoding capabilities of different layers in the same language model to infer how linguistic information is encoded in the model.

Keywords: language models, probing task, text presentation, linguistic information

Procedia PDF Downloads 75

Authors: Preston Nabors, Nasseh Tabrizi

Abstract:

Portable Document Format (PDF) files have gained significant popularity for sharing and distributing documents due to their universal compatibility. However, the widespread use of PDF files has made them attractive targets for cybercriminals, who exploit vulnerabilities to deliver malware and compromise the security of end-user systems. This paper reviews notable contributions in PDF malware detection, including static, dynamic, signature-based, and hybrid analysis. It presents a comprehensive examination of PDF malware detection techniques, focusing on the emerging threat of adversarial sampling and the need for robust defense mechanisms. The paper highlights the vulnerability of machine learning classifiers to evasion attacks. It explores adversarial sampling techniques in PDF malware detection to produce mimicry and reverse mimicry evasion attacks, which aim to bypass detection systems. Improvements for future research are identified, including accessible methods, applying adversarial sampling techniques to malicious payloads, evaluating other models, evaluating the importance of features to malware, implementing adversarial defense techniques, and conducting comprehensive examination across various scenarios. By addressing these opportunities, researchers can enhance PDF malware detection and develop more resilient defense mechanisms against adversarial attacks.

Keywords: adversarial attacks, adversarial defense, adversarial machine learning, intrusion detection, PDF malware, malware detection, malware detection evasion

Procedia PDF Downloads 14

Authors: Peter Nave Shirga

Abstract:

Obadia Kehemen Orkor’s songs that focus on the predicament of the Tiv man in Taraba in North Central Nigeria handle themes such as poverty, social inequality, discrimination and tyranny perpetrated by Jukun against the Tiv. The major thrust of his focus in the songs is the overriding longing for mutual understanding between the Jukun and Tiv that would usher in love, equality, peace and harmonious co-existence for the two antagonistic ethnic groups. This paper examines Obadia’s hard-hitting lyrics that reveal the anger, frustration and boiling emotionalism of Tiv people in Taraba state of Nigeria.

Keywords: poet, crisis, emotionalism, frustration

Procedia PDF Downloads 276

Authors: Ola A. Younis, Said Ghoul

Abstract:

Systems running these days are huge, complex and exist in many versions. Controlling these versions and tracking their changes became a very hard process as some versions are created using meaningless names or specifications. Many versions of a system are created with no clear difference between them. This leads to mismatching between a user’s request and the version he gets. In this paper, we present a system versions meta-modeling approach that produces versions based on system’s features. This model reduced the number of steps needed to configure a release and gave each version its unique specifications. This approach is applicable for systems that use features in its specification.

Keywords: features, meta-modeling, semantic modeling, SPL, VCS, versioning

Procedia PDF Downloads 416

Authors: Yongde Dai

Abstract:

The recent Chinese military action blockbusters, notably known as, Wolf Warrior/Zhan Lang (2015), Operation Mekong/Mei gong he xing dong (2016), Warrior 2/Zhan Lang 2 (2017) and Operation Red Sea/Hong hai xing dong (2018), have achieved phenomenal box-office successes and in particular, Wolf Warrior 2 became China’s highest-grossing film of all time. However, their yearly presence tends to show a paradigmic shift from China’s primacy of wen manliness (soft) to wu masculinity (hard). With the increasing cinematic exposure of a more muscular image manifesting in both the Chinese heroic soldiers and China itself as a rising global power, the backlash of the Chinese public against the proliferation of the feminized masculinity influenced by the ‘pretty-boy’ pop-culture and China’s harder approach to the current Sino-US tensions have correspondingly emerged and continued to brew. Chinese masculinity imagined in these films is one of the key factors that enable a gendered interpretation of the correlation between the Chinese on-screen fantasy and off-screen reality, that is, China’s public and official discourse about the hegemonic masculinity and non-hegemonic masculinity as well as China’s international profile on cinematic appearance and in today’s Sino-US relation. By reading closely at the four megahits as visual-audio texts with Chinese masculinity studies by Kam Louie and Geng Song, this paper attempts to examine the Chinese construction of manliness with historical accounts and argue why and how the recurrent emphasis of hard/military masculinity (wu) on screen are viewed as China’s contemporary rewriting of the ‘sick-man’ history in the film form. Through this investigation, the paper finds that the rewriting of the ‘sick-man’ history in the cinematic world through heroic brawny soldiers comes to resonate a collective anxiety of China in countering the real-life increasing feminized masculinity on the public appearance, particularly on the male celebrities. In addition, the superpower fantasy about China illuminates a hypermasculine imaginary of China as a global rising power and this coincidently echoes China’s current tougher diplomatic strategy tackling the Sino-US trade war, South China sea dispute and Huawei-US lawsuits.

Keywords: Chinese masculinity, Chinese military action film, feminized masculinity, manhood and nationhood, sick man of Asia

Procedia PDF Downloads 117

Authors: Y. de Smet, J. Hubinont

Abstract:

PROMETHEE and GAIA are well-known Multiple Criteria Decision Aid methods. Given an evaluation table and preference parameters they allow to rank the alternatives, to visualize the problem, to perform sensitivity and robustness analysis, etc. Unfortunately, it is often hard for the Decision Maker (DM) to estimate the precise values of these parameters. Therefore an alternative option is to give ranges of potential values in order to apply Stochastic Multicriteria Acceptability Analysis. This has been recently studied in the context of the SMAA-PROMETHEE method. The aim of this contribution is to propose an SMAA extension of GAIA. We show how this tool can be useful and provide complementary information to SMAA-PROMETHEE. This is illustrated on a pedagogical example.

Keywords: multiple criteria decision making, PROMETHEE, GAIA, SMAA

Procedia PDF Downloads 401

Authors: Emin Gundogar, Burak Erkayman, Nusret Sazak

Abstract:

Providing effective management performance through the whole supply chain is critical issue and hard to applicate. The proper evaluation of integrated data may conclude with accurate information. Analysing the supply chain data through OLAP (On-Line Analytical Processing) technologies may provide multi-angle view of the work and consolidation. In this study, association rules and classification techniques are applied to measure the supply chain performance metrics of an automotive manufacturer in Turkey. Main criteria and important rules are determined. The comparison of the results of the algorithms is presented.

Keywords: supply chain performance, performance measurement, data mining, automotive

Procedia PDF Downloads 483

Authors: Parisa Khoshvaght, Mehdi Hosseinzadeh

Abstract:

During the past few years, the Residue Number System (RNS) has been receiving considerable interest due to its parallel and fault-tolerant properties. This system is a useful tool for Digital Signal Processing (DSP) since it can support parallel, carry-free, high-speed and low power arithmetic. One of the drawbacks of Residue Number System is the fractional numbers, that is, the corresponding circuit is very hard to realize in conventional CMOS technology. In this paper, we propose a method in which the numbers of transistors are significantly reduced. The related delay is extremely diminished, in the first glance we use this method to solve concerning problem of one decimal functional number some how this proposition can be extended to generalize the idea. Another advantage of this method is the independency on the kind of moduli.

Keywords: computer arithmetic, residue number system, number system, one-Hot, VLSI

Procedia PDF Downloads 472

Authors: S. Sharan Sundar, Nithish B. Moudhgalya, Nidhi Bhandari, Vineeth Vijayaraghavan

Abstract:

Automatic Short Answer Grading is one of the prime applications of artificial intelligence in education. Several approaches involving the utilization of selective handcrafted features, graphical matching techniques, concept identification and mapping, complex deep frameworks, sentence embeddings, etc. have been explored over the years. However, keeping in mind the real-world application of the task, these solutions present a slight overhead in terms of computations and resources in achieving high performances. In this work, a simple and effective solution making use of elemental features based on statistical, linguistic properties, and word-based similarity measures in conjunction with tree-based classifiers and regressors is proposed. The results for classification tasks show improvements ranging from 1%-30%, while the regression task shows a stark improvement of 35%. The authors attribute these improvements to the addition of multiple similarity scores to provide ensemble of scoring criteria to the models. The authors also believe the work could reinstate that classical natural language processing techniques and simple machine learning models can be used to achieve high results for short answer grading.

Keywords: artificial intelligence, intelligent systems, natural language processing, text mining

Procedia PDF Downloads 114

Authors: Osayande Pascal Omondiagbe, Sherlock a Licorish

Abstract:

Stack Overflow is a popular community question and answer portal which is used by practitioners to solve technology-related challenges during software development. Previous studies have shown that this forum is becoming a substitute for official software programming languages documentation. While tools have looked to aid developers by presenting interfaces to explore Stack Overflow, developers often face challenges searching through many possible answers to their questions, and this extends the development time. To this end, researchers have provided ways of predicting acceptable Stack Overflow answers by using various modeling techniques. However, less interest is dedicated to examining the performance and quality of typically used modeling methods, and especially in relation to models’ and features’ complexity. Such insights could be of practical significance to the many practitioners that use Stack Overflow. This study examines the performance and quality of various modeling methods that are used for predicting acceptable answers on Stack Overflow, drawn from 2014, 2015 and 2016. Our findings reveal significant differences in models’ performance and quality given the type of features and complexity of models used. Researchers examining classifiers’ performance and quality and features’ complexity may leverage these findings in selecting suitable techniques when developing prediction models.

Keywords: feature selection, modeling and prediction, neural network, random forest, stack overflow

Procedia PDF Downloads 112

Authors: Dipo Dunsin, Mohamed C. Ghanem, Karim Ouazzane

Abstract:

Digital investigators often have a hard time spotting evidence in digital information. It has become hard to determine which source of proof relates to a specific investigation. A growing concern is that the various processes, technology, and specific procedures used in the digital investigation are not keeping up with criminal developments. Therefore, criminals are taking advantage of these weaknesses to commit further crimes. In digital forensics investigations, artificial intelligence is invaluable in identifying crime. It has been observed that an algorithm based on artificial intelligence (AI) is highly effective in detecting risks, preventing criminal activity, and forecasting illegal activity. Providing objective data and conducting an assessment is the goal of digital forensics and digital investigation, which will assist in developing a plausible theory that can be presented as evidence in court. Researchers and other authorities have used the available data as evidence in court to convict a person. This research paper aims at developing a multiagent framework for digital investigations using specific intelligent software agents (ISA). The agents communicate to address particular tasks jointly and keep the same objectives in mind during each task. The rules and knowledge contained within each agent are dependent on the investigation type. A criminal investigation is classified quickly and efficiently using the case-based reasoning (CBR) technique. The MADIK is implemented using the Java Agent Development Framework and implemented using Eclipse, Postgres repository, and a rule engine for agent reasoning. The proposed framework was tested using the Lone Wolf image files and datasets. Experiments were conducted using various sets of ISA and VMs. There was a significant reduction in the time taken for the Hash Set Agent to execute. As a result of loading the agents, 5 percent of the time was lost, as the File Path Agent prescribed deleting 1,510, while the Timeline Agent found multiple executable files. In comparison, the integrity check carried out on the Lone Wolf image file using a digital forensic tool kit took approximately 48 minutes (2,880 ms), whereas the MADIK framework accomplished this in 16 minutes (960 ms). The framework is integrated with Python, allowing for further integration of other digital forensic tools, such as AccessData Forensic Toolkit (FTK), Wireshark, Volatility, and Scapy.

Keywords: artificial intelligence, computer science, criminal investigation, digital forensics

Procedia PDF Downloads 183

Authors: Xin-Yan Ji, Jing Wang, Chang Liu, Yan-Qiang Bi, Zhong-Xu Xu, Xi-Yuan Li

Abstract:

Thermal tests of electronic units are critically important for the reliability validation and performance demonstration of the spacecraft hard-wares. The tailoring equation in MIL-STD-1540 is based on fatigue of solder date. In the present paper, a new test condition tailoring expression is proposed to fit different thermo-mechanical fatigue and different subsystems, by introducing an integrated evaluating method for the fatigue acceleration exponent. The validate test has been accomplished and the data has been analyzed and compared with that from the MIL-STD-1540 tailoring equations. The results are encouraging and reasonable.

Keywords: thermal cycling test, thermal fatigue, tailoring equation, test condition planning

Procedia PDF Downloads 422

Authors: Ganesh B. Shinde, Vijaya B. Musande

Abstract:

Cotton crop identification based on the timely information has significant advantage to the different implications of food, economic and environment. Due to the significant advantages, the accurate detection of cotton crop regions using supervised learning procedure is challenging problem in remote sensing. Here, classifiers on the direct image are played a major role but the results are not much satisfactorily. In order to further improve the effectiveness, variety of vegetation indices are proposed in the literature. But, recently, the major challenge is to find the better vegetation indices for the cotton crop identification through the proposed methodology. Accordingly, fuzzy c-means clustering is combined with neural network algorithm, trained by Levenberg-Marquardt for cotton crop classification. To experiment the proposed method, five LISS-III satellite images was taken and the experimentation was done with six vegetation indices such as Simple Ratio, Normalized Difference Vegetation Index, Enhanced Vegetation Index, Green Atmospherically Resistant Vegetation Index, Wide-Dynamic Range Vegetation Index, Green Chlorophyll Index. Along with these indices, Green Leaf Area Index is also considered for investigation. From the research outcome, Green Atmospherically Resistant Vegetation Index outperformed with all other indices by reaching the average accuracy value of 95.21%.

Keywords: Fuzzy C-Means clustering (FCM), neural network, Levenberg-Marquardt (LM) algorithm, vegetation indices

Procedia PDF Downloads 288

Authors: Huda Al Shuaily, Karen Renaud

Abstract:

Databases comprise the foundation of most software systems. System developers inevitably write code to query these databases. The de facto language for querying is SQL and this, consequently, is the default language taught by higher education institutions. There is evidence that learners find it hard to master SQL, harder than mastering other programming languages such as Java. Educators do not agree about explanations for this seeming anomaly. Further investigation may well reveal the reasons. In this paper, we report on our investigations into how novices learn SQL, the actual problems they experience when writing SQL, as well as the differences between expert and novice SQL query writers. We conclude by presenting a model of SQL learning that should inform the instructional material design process better to support the SQL learning process.

Keywords: pattern, SQL, learning, model

Procedia PDF Downloads 238