DALLAS (Oct. 14, 2013) – Imagine having the ability to teach your computer to instantly know when an intruder is calling. It is called machine learning, and protects individual computers over and above current virus protection, which itself is often compromised. These latest security techniques will be thoroughly explored when the highly respected IEEE homeland security conference opens in Boston November 12 -14.
“To solve the problems that are currently out there in the security space we have to start looking at things in a different way,” says William Huba, founder of Hiveary, a firm that uses machine learning to automate server monitoring and alerting, one of the authorities on the subject who will be presenting at the conference. Huba says when tracking methods are looked at in the aggregate “you get something new and unique that can drastically change the security world.”
Another tool being presented at the conference is made by BCL Technologies. “This tool can identify whether this is an original, genuine person writing (you) or this is written by a fraud,” says Aman Kumar, senior computational linguist at BCL. The tool is also strong in spam detection, “Emails coming in phishing, for example asking to send money to your brother who is stuck in London or Syria. So those kind of messages you will be able to identify if fraud or not,” Kumar said.
Both Kumar and Huba spoke by phone from separate offices in California on the ScienceNews Radio Network program, the Promise of Tomorrow with Colonel Mason
. Kumar was joined on the program by Hassan Alam, the firm’s CEO. The broadcast originates in Dallas, Texas, and can now be heard Webcast and archived for its world audience.
The IEEE International Conference on Homeland Security (HST’13) will be held at the Westin hotel in Waltham, Massachusetts , November 12 - 14. Early registration discount deadline extended to November 1, 2013. Information and registration can also be found at http://www.ieee-hst.org/
. The conference each year brings together global science and technology thought leaders in homeland security technology innovation, and showcases peer-reviewed technical papers highlighting emerging technologies in:
* Cyber Security
* Attack & Disaster Preparation, Recovery & Response
* Land & Maritime Border Security
* Biometrics & Forensics
HST ‘13 is produced by IEEE with technical support from Department of Homeland Security Science & Technology, IEEE Biometrics Council, IEEE Engineering in Medicine and Biology Society and IEEE-USA. MIT Lincoln Laboratory, Raytheon and MITRE are providing organizational support.
) is the world’s largest professional association dedicated to advancing technological innovation and excellence for the benefit of humanity. IEEE-USA (www.ieeeusa.org
) advances the public good and promotes the careers and public policy interests of more than 206,000 engineers, scientists and allied professionals who are U.S. members of IEEE.
BCL Technologies won the National Science Foundation (NSF) SBIR Phase I award. In its Phase I NSF research BCL Technologies will develop a financial data extraction system that uses machine learning and Natural Language Processing methods.
The National Science Foundation (NSF) is a United States government agency that supports fundamental research and education in all the non-medical fields of science and engineering.
NSF SBIR/STTR programs incentivize and enable startups and small business to undertake R&D with high technical risk and high commercial reward.
BCL Technologies is going to present its
latest research project, "Automated Financial Data Extraction - An AI
Approach," at the 2013 International Conference on Artificial Intelligence
(ICAI). The conference will be held on July 22-25, 2013 in Las Vegas, USA.
BCL Technologies has been a leader in
performing research that combines the fields of Natural Language Processing
(NLP) and Document Analysis and Recognition (DAR). Our widely published
research on document layout analysis has been incorporated in our award winning
document conversion products.
BCL Technologies has also developed a simplified
and automated way to create an SEC-compliant XBRL document. The primary goals are to:
- Identify and extract DEI (Document Entity
- Locate, extract, and modify the four financial
tables (Income statement, cash flow, balance sheet, and stockholders’ equity)
- Extract and present parenthetical information
from the four financials in a tabular format
- Extract financial notes
- Detail tag
ICAI is an international conference that
serves researchers, scholars, professionals, students, and academicians who are
looking to both foster working relationships and gain access to the latest
research results. It is being held jointly (same location and dates) with a
number of other research conferences; namely, The 2013 World Congress in
Computer Science, Computer Engineering, and Applied Computing (WORLDCOMP). The
Congress is the largest annual gathering of researchers in computer science,
computer engineering and applied computing.
For more information about ICAI 2013,
For more information about BCL
Technologies' current and past research projects and commercial products,
November 5, 2012. BCL Technologies' XBRL tool, SmartXBRL, was awarded Best XBRL Tool at 25th XBRL International Conference in Yokohama, organized by XBRL Japan Educational Working Group, XBRL Japan. The competition celebrates the invaluable contribution of researchers, students, software developers, and anyone who is interested in XBRL development, by providing implementations of software tools for XBRL documents, definitions of taxonomies, and other useful and effective applications of XBRL.
Friday, May 8, 2009. BCL Technologies successfully completed AFRL Phase II deliverables toward title - Linguist Ambiguity, Training, and Rehearsal System.
In its Phase II SBIR efforts BCL Technologies developed a Linguist Ambiguity Training and Rehearsal System (LATARS) for Arabic, Korean, and Urdu to help train linguists to become experts in understanding the right meaning of an ambiguous word or phrase. The LATARS disambiguates polysemous text in these three languages and recommends correct meaning of an ambiguous word or phrase based on the context in which the word or phrase is used. The Arabic LATARS records an accuracy of 80% while the Korean and the Urdu LATARS record accuracies of 76% and 56% respectively.
Wednesday, July 18, 2007 BCL Technologies is selected as the winner or Session's Best Paper Award at the 5th International Conference on Computing, Communication and Control Technologies.
Title: Spoken Language Understanding Software for Language Learning
Hassan Alam, Aman Kumar, Fuad Rahman, Yuliya Tarnikova, Rachmat Hartono
In this study we have developed a proof-of-concept, work-in-progress Spoken Language Understanding Software (SLUS) with tailored feedback options, which uses interactive spoken language interface to teach foreign language (Arabic) and culture. The SLUS analyzes input speech by the second language learner and grades not only for correct pronunciation, vocabulary, and grammar, but also for prosody and intonation. Arabic language itself has many features that cause difficulties for strategies developed for processing Romance and Germanic languages, as reported in Kirchhoff (2002) and in Chiang et al. (2005). Due to the nature of the challenges posed by less-studied languages such as Arabic, the sophistication of computer-based models of Arabic speech, and especially of dialectical speech, has lagged behind that of the European languages. In order to build such a system we developed a comprehensive model of Iraqi Arabic against which the student’s performance is measured. This model includes many aspects: (1) an acoustic model; (2) an articulation model; (2) a dictionary or vocabulary model; (3) a grammar model; and (4) a model of common errors or “disfluencies”. In traditional (not computer-assisted) instructions, these models take the form of written descriptions and examples of sounds, vocabulary lists, and grammatical rules; and the student’s performance in the language is graded by human instructors. For computer-based language instruction, all of these must be cast as explicit databases and mathematical models, so that they can be used to automatically grade student performance, to identify errors, and to evoke appropriate and believable responses from simulated tutors.
In order to test new methodologies for creating Language Models we created a corpus by transcribing and recording the scenarios in both Modern Standard Arabic and in the Iraqi dialect that is most prevalent in central and southern Iraq. Using the test sentences from the corpus and an acoustic analysis software, preliminary prosodic and intonational models were developed for the target language to create training data with acoustic features. We use COTS SRI speech recognition engine (DynaSpeak) for speech-to-text processing. We prototyped and performed (1) evaluation of stress and pitch contours of the input speech, (2) addition of phonetic information to SRI's DynaSpeak, and (3) re-ranking of the ASR output using a Support Vector Machine (SVM). In addition, the SLUS figured out rudimentary segmental errors (corresponds to missing consonant or vowel). We evaluated this software on training data with the help of two native speakers, and found that the software recorded an accuracy of around 70% in law and order domain.
See our research (Chapter 6) in:
Document Analysis: Challenges and Opportunities.
Editors: Apostolos Antonacopoulos
and Jianying Hu.
Hardcover - 344 pages 1 edition (February
World Scientific Publishing ISBN: 9812385827