Goto

Collaborating Authors

Investigative Data Mining for Security and Criminal Detection: Jesus Mena: 9780750676137: Amazon.com: Books

#artificialintelligence

"It shows how myriad distributed data streams can be harnessed to fight crime. Through easy-to-read prose, the reader learns how to use both public and private databases and networks to find threats and minimize risks. Besides explaining how data mining is done, the book introduces the reader to such techniques as intelligent agents (software that performs user-delegated tasks autonomously), link analysis (a process involving the mapping of the associations between suspects and locations), and text mining (a process used to identify a document's content based on linguistic analysis) and how they can aid law enforcement. For example, law enforcement in the United Kingdom use text mining to "institutionalize the knowledge of criminal perpetrators and organized gangs and groups," author Jesús Mena writes. Case studies buttress these points.


Mena

AAAI Conferences

Probabilistic Classifiers Chains (PCC) offers interesting properties to solve multi-label classification tasks due to its ability to estimate the joint probability of the labels. However, PCC presents the major drawback of having a high computational cost in the inference process required to predict new samples. Lately, several approaches have been proposed to overcome this issue, including beam search and an epsilon-Approximate algorithm based on uniform-cost search. Surprisingly, the obvious possibility of using heuristic search has not been considered yet. This paper studies this alternative and proposes an admisible heuristic that, applied in combination with A* algorithm, guarantees, not only optimal predictions in terms of subset 0/1 loss, but also that it always explores less nodes than epsilon-Approximate algorithm. In the experiments reported, the number of nodes explored by our method is less than two times the number of labels for all datasets analyzed. But, the difference in explored nodes must be large enough to compensate the overhead of the heuristic in order to improve prediction time. Thus, our proposal may be a good choice for complex multi-label problems.


Lenovo offers surveillance security solutions at Intersec 2020

#artificialintelligence

Video surveillance systems are evolving and are using artificial intelligence (AI) to inspect and analyse video footage, interpret patterns and flag unusual activity. Lenovo DCG and Pivot3 provide a state-of-the-art upgraded infrastructure solutions that aim to enhance current technology required to support these systems rather than entrusting the preservation of crucial data to outdated NVR technology. Commenting on the partnership, Dr. Chris Cooper, General Manager for Lenovo DCG, Middle East, Turkey and Africa, said, "We are delighted to showcase our partnership with Pivot3 at one the world's leading technology trade shows. The Middle East is exhibiting tremendous growth in terms of adopting smart solutions. The UAE in particular is investing heavily in implementing the latest innovations in their technological infrastructure; therefore, we see great potential from our partnership with Pivot3 as we work together to supply the appetite for next generation computing products and services."


Controlling Deliberation with the Success Probability in a Dynamic Environment

AAAI Conferences

Seiji Yamada Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology 4259 Nagatsuda, Midori-ku, Yokohama, Kanagawa 226, JAPAN Email: yamada ai.sanken.osaka-u.ac.j p Abstract This paper describes a novel method to interleave planning with execution in a dynamic environment. Though, in such planning, it is very important to control deliberation: to determine the timing for interleaving them, few research has been done. To cope with this problem, we propose a method to determine the interleave timing with the success probability, SP, that a plan will be successfully executed in an environment. We also developed a method to compute it efficiently with Bayesian networks and implemented SZ system. The system stops planning when the locally optimal plan's SP falls below an execution threshold, and executes the plan. Since SP depends on dynamics of an environment, a system does reactive behavior in a very dynamic environment, and becomes deliberative in a static one. We made experiments in Tileworld by changing dynamics and observation costs. As a result, we found the optimal threshold between reactivity and deliberation in some problem classes. Furthermore we found out the optimal threshold is robust against the change of dynamics and observation cost, and one of the classes in which S2"P works well is that the dynamics itself changes.


Thuraya & eSAT successfully complete tests of satellite IoT tech

#artificialintelligence

Thuraya, the mobile satellite services subsidiary of the Al Yah Satellite Communications Company (Yahsat), the leading UAE-based global satellite operator, and eSAT Global, a pioneer in low cost Satellite IoT connectivity, announced the completion of successful tests validating eSAT's revolutionary Global LPWAN (Low Power Wide Area Network) communications technology over Thuraya's satellite system. As a leading provider of mobile satellite services (MSS) over its geostationary (GEO) satellites, Thuraya offers an expanding range of compelling voice, broadband data, and M2M/IoT capabilities for land, maritime and aeronautical applications. These include cost-effective solutions, catering to a wide range of technical and commercial market requirements. To date, only modest consideration has been given to the use of direct links to GEO MSS satellites for LPWAN connectivity for Internet of Things (IoT) applications.