It is a matter of pleasure for us to put forth the special issue on “Machine Learning (ML) and Knowledge Mining (KM)” in
Recent Patents on Engineering, Bentham Science. The special issue on Machine Learning (ML) and Knowledge Mining (KM)
invited researchers /Academia to submit the original work in the area of Machine learning and Knowledge Mining. Machine
learning and Knowledge Mining represents the development in the field of Computer Science, Artificial Intelligence, Robotics
& Business Intelligence and played a vital role in information technology and sciences. Basically, Machine learning is the technology
of implementing a system which can act without being explicitly programmed. ML & KM has the ability to adapt to
new circumstances and to detect and extrapolate patterns. One key goal of ML and KM was to be able to generalize a limited
set of data. Machine learning has been used to develop self-driving cars, practical speech recognition system, effective web
search engines, and a greatly improved understanding of the human genome. In general, Machine learning deals with designing
and developing algorithms to evolve behaviors based on empirical data. Machine learning and Knowledge Mining applications
include algorithms to identify spam or to stop credit card fraud, systems that analyze past sales data to predict customer behavior,
extract knowledge from bioinformatics data, images and video, optimize robot behavior so that a task can be completed
using minimum resources, identify listening failures not limited to them but a long list of interesting and extremely useful applications.
Machine learning and Knowledge Mining are so persistent today that we probably use them dozens of times a day
without knowing it.
The main scope of this special issue is to bring together applications of machine learning in the area given below in order to
provide a wide range of techniques that can be effectively applied and also to show how such techniques should be adapted to
each particular domain. This issue presents a compilation of six papers that span a broad variety of research topics in various
emerging areas of Information Technology and Computer Science. Finalizing the constitution of the panel of referees, for
double-blind peer review(s) of the considered manuscripts, was a painstaking process, but it helped us to ensure that the best of
the considered manuscripts are showcased and that too after undergoing multiple cycles of review, as required. The six papers,
that were finally published, were chosen out of twenty-five papers that we received from all over the world for this issue. We
understand that the confirmation of the final acceptance, to the authors / contributors, sometimes is delayed, but we also hope
that you concur with us in the fact that quality review is a time taking process which is further delayed if the reviewers are
senior researchers in their respective fields and hence, are hard pressed for time.
The first paper is “Security of NoSQL Database Against Intruders”. The goal of this paper is to discuss NoSQL features
over traditional databases such as high scalability, distributed computing, lower cost, schema flexibility, semi or un-semi structural
data and no complex relationship. In this paper, authors described the security of NoSQL database against intruders which
is growing rapidly. Conclusion: This paper also defines probably the most prominent NoSQL databases and describes their security
aspects and problems [1].
The second paper is “Energy Efficient Techniques in Wireless Sensor Networks”. The aim is to enhance energy efficiency
that leads to a prolonged lifetime of networks. In this paper, authors have emphasized on energy efficient clustering technique
along with feature wise summary of existing clustering protocols [2].
The third paper is “A Review on Sentiment Classification: Natural Language Understanding”. The goal is to understand the
basic steps involved in analyzing the text data which can be helpful in determining sentiments behind them. This review provides
a detailed description of steps involved in sentiment analysis with the recent research done. Patents related to sentiment
analysis and classifications have been reviewed to throw some light on the work done related to the field. Results: Sentiment
analysis determines the polarity behind the text data/review. This analysis helps in increasing the business revenue, e-health, or
determining the behavior of a person. In this paper, authors concluded that this study helps in understanding the basic steps involved
in natural language understanding. At each step, there are multiple techniques that can be applied to data. Different classifiers
provide variable accuracy depending on the data set and classification technique used [3].
The fourth paper is “QoS Enabled Improved Location Aided Routing (QEILA)”, the objective of this work is to harness the
location aided routing and build a protocol which provides Quality of Service in terms of required battery life and available
bandwidth. Method: In this work, various patented and non-patented location-based routing and Quality of Service methods for
a wireless network have been reviewed. The improved location aided routing protocol has been utilized and equipped with
Quality of Service to check while selecting the next forwarding node for path construction. In this paper, the proposed system
can be utilized for transmitting heavy data traffic in Mobile Ad-hoc net-work with Quality of Service in real time situation [4].
The fifth paper of this issue is “A Hybrid Filtering Approach for an Improved Context-aware Recommender System”. The
goal of this work is to identify and propose a new hybrid approach which can include contextual information to improve the
current movie recommender systems. Method: Post evaluation of various patents related to recommender systems, the proposed
approach modifies the post filter approach to rectify its shortcomings and combines it with the pre-filter approach based on the
importance of contextual attribute provided by the user. Results: The performance of the proposed system is measured in terms
of the precision of the system and ranking of the recommended movies to the user. In this paper, authors concluded with the
help of this hybrid approach, the proposed system eliminates the problem of sparsity which is present in the pre-filter algorithm, and has performance improvement over the traditional post-filter approach. The proposed system will be vital for movie ticketing
brands for promotional purposes and various online content providers to recommend accurate movies to their users [5].
The sixth paper is “Model for Gestational Diabetes on web-based parameters”; the goal of this paper is to depict a
differential equation-based model for gestational diabetes i.e. glucose concentration, insulin concentration, placental volume,
beta-cell mass and haemoglobin alc. Further in this work, the stability of the model is discussed by routh-hurwitz stability criterion.
In this paper, authors have taken different parameters associated with diabetes mellitus into consideration for the mathematical
model which shows the effects on glucose level and thus helpful in under-standing the role of these parameters in
diabetes. In future, by understanding the role of these parameters, a necessary action can be taken as precautions to avoid/treat
gestational diabetes mellitus [6].
We give sincere thanks to Dr, Togay Ozbakkaloglu, Editor-in-Chief, Recent Patents on Engineering for giving us an
opportunity to convene the special issue in his esteemed publishing Journal and Mr. M. Shahid Nisar, Assistant Manager
Publication, Bentham Science for his kind cooperation in completion of this issue. We thank our esteemed authors for having
shown confidence in the special issue and considering Recent Patents on Engineering as a platform to showcase and share their
original research work. We would also wish to thank the authors whose papers were not published in this issue of the Journal,
probably because of the minor shortcomings.