Studying the Invasion of Drones in Indigenous Areas Using Machine Learning Techniques

Full text

Date available online: 18-03-2024
Vol. 1, Issue 2 (July-December 2023)
This is an open-access article.
17 VOLUME 01, Issue 2, 2023
Studying the Invasion of Drones in
Indigenous Areas Using Machine Learning
Techniques
Samra Nawazish1, Amin Ullah2, Jawad Hassan3, Saddam Hussain Khan4, Abdul Aziz5 , Riaz Ud Din6,
Muhammad Adeel7
1Software Engineering Department, University of Engineering and Technology, Taxila, Pakistan. (samra5677@gmail.com)
2Postdoc Research Associate, School of Computer Science & Engineering, Southeast University, Nanjing, Jiangsu China. (aminullah@seu.edu.cn)
3Deparmtment of Computer Science and Information Technology, University of Lahore, Punjab, Pakistan. (jdravian@gmail.com)
4Department of Computer Systems Engineering, University of Engineering and Applied Science, Swat Pakistan (saddamhkhan@ueas.edu.pk)
5Phd Scholar, School of Computer Science and Engineering, Southeast University, Nanjing, China. (aziz@seu.edu.cn)
6Department of Computer Systems Engineering, University of Engineering and Applied Science, Swat, Pakistan. (riaz.uddin@ueas.edu.pk)
7Department of Computer Science, National Textile University, Faisalabad Pakistan (adeel@ntu.edu.pk)
Corresponding author: Samra Nawazish (e-mail: samra5677@gmail.com).
ABSTRACT The prevalence of drones in contemporary times has become widespread, representing a pivotal
technological advancement in aviation—characterized by its autonomous, pilot-less nature. However, its predominant
application for surveillance and targeted operations, particularly by the United States of America (USA), has sparked
vehement criticism due to perceived violations of human rights on a global scale. Especially, Pakistan-like countries
have borne the brunt of drone strikes, with the Federally Administered Tribal Areas being the primary target,
accounting for over 90% of these attacks. This research delves into the profound impact of drone strikes, focusing on
the often-overlooked innocent victims, including women and children, as well as the consequential damage to the
affected regions. In this paper, we posit that a classification-based approach offers a more comprehensive and
statistically informative means of elucidating patterns inherent in the data. By doing so, we aim to shed light on the
effectiveness of targeted killings in the context of counter-terrorism. The proposed approach includes machine
learning algorithms, such as ZeroR, J48, Naive Bayes, and OneR that have been employed to meticulously analyze
the dataset and unveil hidden patterns. In particular, the J48 algorithm demonstrated exceptional performance,
accurately discerning casualties within the standard Kaggle noisy dataset. The Weka tool, known for its advanced
capabilities, played a pivotal role in this analysis, handling crucial tasks such as initial pre-processing, numeric to
nominal conversion, and replacing missing values. This integrated approach ensures a robust exploration of the dataset,
leveraging the strengths of diverse algorithms and sophisticated tools for comprehensive insights. This departure from
traditional legal analyses broadens the discourse surrounding drone warfare, emphasizing the importance of data-
driven insights in understanding the broader implications of these operations.
INDEX TERMS: Drone attack, civilian, Data Mining, Pattern Analysis
I.
INTRODUCTION
Unmanned Aerial Vehicles (UAVs), commonly
referred to as drones, have become synonymous with
modern aviation [1]. The initiation of drone attacks
traces back to June 2004 under the administration of
George Bush in Pakistan. However, it was during the
tenure of Barrack Obama that these strikes witnessed
a substantial surge. Pakistan, in particular, emerged as
the primary theater for such operations, overshadowing
the prevalence of drone activities in other nations. The
Federal Administered Tribal Areas of Pakistan,
including
North & South Waziristan, Bajawer Agency, Kuram
Agency, Bannu, and Hangu, have predominantly been
the focal points of these targeted missions.
The Federally Administered Tribal Areas (FATA) [2],
situated at the border with Afghanistan, have emerged
as the epicenter of joint operations conducted by the
USA and Pakistan against terrorist activities. This
shared border has rendered the FATA regions highly
susceptible to the impact of these collaborative efforts.
Following the USA's intervention in Afghanistan, a
substantial influx of Taliban members sought refuge in
these Tribal areas, with local communities generously
providing shelter to the influx of refugees. Within these
territories, the Taliban found fertile ground for
sustenance, and the USA contends that the FATA areas
have inadvertently become breeding grounds for Jihadist
Organizations. Moreover, assertions have been made
regarding the existence of training centers where the
Taliban undergo systematic training.
Following the 9/11 event [3] [5], the FATA regions
swiftly transformed into a focal point of substantial
unrest. The insurgent ratio experienced a notable
surge, prompting the Pakistani Government to grapple
with the formidable
challenge at hand. Recognizing the
gravity of the situation, the
USA advocated for proactive
measures, urging the Pakistani Government to
implement control mechanisms in these Tribal Areas.
Subsequently, in 2004, the USA intensified its
commitment to counter-terrorism efforts, initiating the
use of UAVs for targeted strikes against prominent
figures such as Al-Qaeda and Taliban leaders. This
marked a pivotal shift in the tactics employed in the
region.

18 VOLUME 01, Issue 2, 2023
The anti-terrorism policy, instead of yielding
positive outcomes, has become a source of numerous
challenges. The repercussions have been particularly
severe for the lives of innocent civilians [4]. The toll is
staggering, with thousands of individuals, including
women and children, bearing the brunt of these
consequences. Many have been left disabled, some
succumbing to injuries in hospitals. The widespread
impact has prompted hundreds of families to abandon
their homes, seeking refuge in other regions. Drone
strikes, beyond their immediate physical
consequences, cast profound and lasting effects on
the social, economic, and psychological facets of
individuals' lives.
A distinct and pervasive fear has permeated the
lives of residents due to drone strikes. Compounding
this, a significant issue arises from the plight of innocent
individuals who, without any discernible cause, find
themselves bereft of homes and families. For many
among them, this grievous loss transforms into a
vehement opposition to their government and military.
This opposition evolved into a perilous form with the rise
of suicide bombing attacks. Having lost
everything dear
to them, the affected individuals perceive their
lives as less
valuable, fueling a desperate turn toward suicidal acts
against the government and public sectors. The
perplexing question of why their Muslim government
seemingly endorses the killing of its citizens festers in
their minds. Moreover, a stark reality emerges that a
mere 10% of the casualties resulting from drone strikes
are genuine terrorists. In this grim scenario, the
sacrifices made by local people stand as poignant
testaments to the far-reaching consequences of such
actions.
The United States maintains a veil of secrecy over
the precise details of damages and casualties resulting
from drone strikes, refraining from divulging accurate
data. Nonetheless, select media channels have
undertaken the task of collating information and
presenting it to the public, albeit with certain
assumptions. Numerous research endeavors have
been undertaken to aggregate data from diverse
sources, resulting in the publication of various papers.
Each of these papers approaches the subject of drone
attacks in Pakistan from distinct perspectives, adding
layers of nuance to the discourse. In this context, our
paper endeavors to contribute to this body of knowledge
by meticulously analyzing the dataset provided by
Pakistan Body Count—a recognized authority for
accuracy in Pakistan's information landscape.
Numerous analyses have been conducted on the
identical dataset, exploring diverse dimensions such as
attacks by time, attacks by day, attacks by month, and
attacks by year. Consequently, a comprehensive
picture emerges, delineating the total number of
casualties and injuries, albeit with slight variations. Our
primary focus lies in discerning the ramifications of
drone strikes on innocent victims, delving into the
multifaceted repercussions in terms of social,
economic, and psychological aspects. By honing in on
these specific dimensions, we aim to illuminate the
nuanced impact that extends beyond mere numerical
statistics.
II.
LITERATURE REVIEW
In the scrutiny of drone attacks, Mahmood [6] has
astutely probed their legal standing within both
international law and the domestic legal framework of
the United States. While these strikes are ostensibly
targeted at terrorists, Mahmood notes a considerable
number of civilians falling victim, prompting significant
criticism from the Pakistani populace. The observation
contends that drone attacks lack legality under both
international and U.S. domestic law, raising questions
about their justification within the legal frameworks.
Furthermore, it underscores a glaring lack of
transparency on the part of the United States in the
execution of these operations.
Alcides Eduardo [7] delves into the legal constraints
surrounding the use of UAVs. The study highlights a
disconcerting reality—despite the presumed precision
and visual acuity of UAVs, over a quarter of those killed
in a decade were civilians. Strikingly, the percentage of
high-priority targeted terrorists stood at a mere 2%. The
process of identifying adversaries relies on patterns
such as area height
and details about an individual's
social life. However, a critical
flaw surfaces: when the
enemy is identified using these patterns, individuals
related to them inadvertently fall within the target
domain. This practice of identifying enemies while
inadvertently causing harm to innocent individuals is
both critical and, according to Eduardo, woefully
insufficient.
Sarah E Kreps [8] underscores the pivotal role of
public opinion and support in shaping enduring and
legitimate government policies. From the
governmental perspective,
drone attacks are deemed
effective in both disrupting terrorists
and aligning with
international law. However, a contrasting narrative
emerges from international organizations (IO) and non-
governmental organizations (NGO), contending that
these strikes not only violate international law but also
contribute to an escalation of terrorism rather than
curbing it. Through experimental surveys, Kreps
concludes that the criticisms from IOs and NGOs wield
significant influence over public attitudes, even in the
realm of crucial national security issues like drone
strikes. This insight accentuates the nuanced interplay
between public perception, government policies, and
the assessments of international entities.
Kathrin Maurer [9] contributes a unique perspective
by arguing that while there has been significant
attention on the political, ethical, and legal dimensions
of drone strikes, the visual framing aspects often
remain unexplored. With the specific aim of elucidating
the visual landscape of military drones, Maurer
conducts a detailed analysis of their visual
configuration. The article delves into the intricate
process of how individuals are targeted by drone
operators, creating a framework of visual recognition
that delineates whom to include or exclude from the
scope of pursuit. The conclusion drawn is nuanced —
while drone warfare holds the potential to save lives, its
efficacy hinges on a carefully calibrated grammar of

19 VOLUME 01, Issue 2, 2023
visual exclusion and bi-political power that must be
meticulously accurate.
Maurer's exploration underscores the significance of
understanding the visual dynamics inherent in drone
operations for a comprehensive evaluation of their
impact.
In Jonathan Kennedy's examination [10], the focus
shifts to the polio vaccination mission viewed through
the lens of drone strikes. Notably, the areas targeted
align significantly with regions where polio vaccination
groups were actively engaged between 2004 and
2012. Kennedy brought attention to the claims made
by militants, asserting that polio vaccination campaigns
TABLE 1.
References of recent related published articles are shown below
No.
Author
Year
Problem Statement
Solution
1.
Amna
Mahmood
&Sadaf Farooq
2015
To focus on the justification and legal
position of Drone attacks within the
boundaries of a sovereign state
Drone attacks are not supported by
international law
2.
Alcides
Eduard
o dos Reis Peron
2014
From the accuracy and visual capacity of
The UAVs, information on the deaths of
civilians, and legal limitations in
International Humanitarian Law.
Would help establish the legitimacy of
such targeted killings b/w civilians or
Taliban
3.
Sarah E Kreps
2016
How criticisms impact public support for
drone strikes
Criticisms focusing on the effectiveness
of strikes have little impact on the
public.
4.
Kathrin Maurer
2016
Research often focuses on the political,
legal, and ethical aspects of this drone
strike violence;
It is shown how the scope regime of
military drones executes violence as a
form of man-hunting.
5.
Jonathan
Kennedy
2017
Drone strikes in FATA have disrupted
efforts to eradicate polio. Drone strikes and
polio have not yet been systematically
investigated.
It is recognized that vaccination
programs were a Cover for espionage.
6.
Katharine
Hall
Kindervater
2016
ISR capabilities are directly linked to
targeted killing, effectively merging
mechanisms of surveillance and
knowledge production with decisions on
life and death.
Lethal surveillance and the drone strike
reflect a tendency. This not only allows
us to connect the drone to other
practices of war and security but as a
practice that falls squarely within the
history and development of Western
warfare and violence.
7.
Milena Sterio
2012
battlefield and the applicability of the law of
armed conflict; the identity of targetable
individuals and their status as combatants
or civilians under international law;
If the USA truly engaged with the
Taliban, it can be argued that drone
attacks are not so illegal. Issues that
remain unanswered are those
regarding the nature of the conflict that
the United States has been engaged in
since 9/11,
8
Dennis G. Barten
, Derrick Tin,
Harald De
Cauwer, Robert
G. Ciottone,
Gregory
R. Ciottone
2022
focuses on assessing the medical
challenges and responses associated with
drone attacks in counter-terrorism
scenarios, with a specific emphasis on
understanding the injuries and medical
requirements resulting from such incidents.
They discuss strategies for enhancing
medical response and preparedness in
the face of drone attacks, aiming to
develop effective measures to address
injuries and casualties resulting from
such incidents in counter-terrorism
operations
9
Zhambyl
Shaikhanov,
Sherif Badran,
Josep M. Jornet,
Daniel M.
Mittleman,
Edward W.
Knightly
2023
concerns the development and potential
risks associated with deploying
metasurface-equipped drones for remote
attacks, requiring examination of security
and technological challenges in mobile
computing systems and applications.
The article may propose methods to
detect and defend against drone
attacks using metasurfaces,
addressing the emerging security
concerns posed by remotely positioned
drones equipped with advanced
technology in mobile computing
systems and applications.

20 VOLUME 01, Issue 2, 2023
served as a front for gathering covert information
intended for the Central Intelligence Agency (CIA) to
identify specific targeted individuals. The
repercussions were stark—militants successfully
disrupted immunization campaigns. Intriguingly, from
2013 onward, as drone attacks diminished, there was a
dramatic surge in polio cases. Kennedy posits that this
shift marked an attempt by the
CIA to exploit fake
immunization campaigns in a bid to obtain
Osama bin
Laden's DNA, thereby revealing that these seemingly
innocuous vaccination programs were, in fact, a
strategic cover for espionage.
Katharine Hall Kindervater [11] explores and
scrutinizes the revolution brought about by drone
technology, delving into its historical evolution in
surveillance and targeting and elucidating how it has
fundamentally shaped contemporary drone warfare.
Her observation unfolds to reveal two pivotal trends
within Western warfare—a burgeoning demand for
intelligence, surveillance, and reconnaissance (ISR),
and the concurrent development of dynamic targeting,
both becoming ever more intricately interwoven. The
convergence of these trends manifests in the
contemporary landscape as a form of lethal
surveillance, wherein ISR capabilities are seamlessly
tethered to targeted killing. Kindervater's analysis
provides valuable insights into the evolving dynamics of
warfare, shedding light on the symbiotic relationship
between intelligence gathering and precision targeting in
TABLE 2.
Comparison of recent published articles' results based on attribute
No.
Paper author
Legality by
international
law
Follow the
principles
of Just
War/Jus in
Bello
civilian
casualties
Priority
Target
Effective at
killing
terrorists
Public Attitude
1.
Mahmood, A.,
S. Farooq, and
A. Karim,
Illegal
No
>50%
No
2.
Dos Reis Peron,
A.E
Illegal
No
22%
<2%
No
3.
Kreps, S.E.
and G.P.
Illegal
No
2%
No
International
legal principles
significantly
altered
4.
Maurer, K.
Illegal
>50%
No, Visual
field model
5.
Kennedy, J.
Illegal
>50%
Boycotted the
vaccination
programs in
2012
6.
Kindervater, K.H.
Illegal
No
7.
Sterio, M.
Illegal
No
No
8
Dennis G. Barten
, Derrick Tin,
Harald De
Cauwer, Robert
G. Ciottone,
Gregory R.
Ciottone
Illegal
No
2%
No
9
Zhambyl
Shaikhanov,
Sherif Badran,
Josep M. Jornet,
Daniel M.
Mittleman,
Edward W.
Knightly
Illegal
No
>50%

21 VOLUME 01, Issue 2, 2023
the context of drone warfare.
Milena Sterio [12] delves into the intricate debate
surrounding the compliance of drone attacks with the
principles of jus in Bello. The United States has faced
widespread criticism from numerous international
communities regarding the geographic application of
drones against Al-Qaida forces. However, it's
noteworthy that six officials within the Bush
Administration staunchly defended the drone program,
asserting its consistency and alignment with
international law. Stereo prompts a critical inquiry into
the legality of drone strikes under the jus in Bello law.
The fundamental question emerges: is there a
legitimate framework for the legal use of drones? Stereo
posits that if a military commander were to opt for a
drone attack against a well-known military target, and
such an attack could substantially advance military
objectives without causing disproportionate harm to
civilians or unnecessary suffering, then such a drone
strike could indeed align with the principles of jus in
Bello. This nuanced exploration underscores the
complexity and nuanced considerations inherent in
evaluating the legal parameters of drone warfare.
Barten et al. [13] appear to delve into the
multifaceted realm of medical implications and
responses associated with drone attacks in the context
of counter-terrorism endeavors. While the specific
details of the article are currently inaccessible to me,
the framing suggests a comprehensive exploration of
the injuries and medical challenges arising from drone
strikes in conflict zones. The focus extends to
strategizing effective medical assistance in these
challenging situations. This study holds the promise of
offering valuable insights into the intricate intersection of
medicine and counter-terrorism efforts. By shedding
light on the medical dimensions of drone warfare, it
could potentially inform strategies for
mitigating the
health-related consequences of such operations.
Zhambyl Shaikhanov et al. [14] appear to concentrate
their focus on the innovative concept of incorporating
metasurfaces
in drone attacks conducted remotely. The
anticipation is that their work explores the technological
intricacies and potential implications of employing
metasurfaces in the realm of drone attacks, particularly
in the context of mobile computing systems and
applications. This suggests an investigation into the
intersection of advanced technology, such as
metasurfaces, with the evolving landscape of drone-
based operations. By contemplating the potential
utilization of
metasurfaces, the study may provide
insights into the evolving
dynamics of drone technology
and its applications in remote and mobile computing
scenarios.
III.
METHODOLOGY
The methodology has been adopted to address a
critical gap in existing research, which often
emphasizes the legality of drone strikes under
international and domestic law, neglecting the
substantial impact on individuals and communities. Our
proposed approach revolves around employing
classification algorithms to uncover hidden patterns
within the dataset through the application of data mining
techniques. We leverage the sophisticated capabilities of
the widely recognized tool, "Weka [15]," designed for
advanced data mining tasks. It is an advanced-level tool
for data mining tasks. The proposed flow model is
presented in the below figure.
Initially, the dataset, sourced from Kaggle, was
characterized by its noisy and incomplete nature. To
enhance its suitability for analysis, we initiated a pre-
processing phase within Weka. This involved crucial
steps such as converting numeric values to nominal
ones and employing a filter to replace missing values.
These measures were pivotal in preparing the dataset
for in-depth analysis.
The core of our methodology lies in the selection of
a classification algorithm. This algorithm was applied to
scrutinize the data, bringing forth discernible patterns.
The successful execution of this process led to the
discovery of valuable insights based on the identified
patterns, thereby contributing to a deeper
understanding of the nuanced implications of drone
strikes beyond the legal realm. A classification
algorithm is selected to perform the analysis of data,
which present patterns, and after that, we succeeded in
knowledge discovery on those patterns base.
a.
Results and Discussion
We have focused on diverse algorithms accessible
within Weka [16]. Specifically, we chose to employ
classification-based algorithms, namely ZeroR, J48
[17], Naive Bayes [18], and OneR. The ensuing table
elucidates the accuracy results of these selected
algorithms across various attributes. The evaluation
aimed to discern the performance of various
algorithms
across key attributes. Notably, time-based analyses
revealed consistent patterns among all algorithms.
Further exploration into location-based analyses
showed subtle differences, especially between ZeroR
and J48, indicating nuanced distinctions in their
predictive capabilities.
Significant disparities emerged in analyses related
to the number of injuries, civilian deaths, and total
casualties. J48 consistently outperformed other
algorithms in these critical categories, suggesting its
potential superiority in accurately identifying and
predicting the impact of drone strikes on individuals,
emphasizing its efficacy in gauging the human cost of
operations. An intriguing finding from time-based
analyses unveiled a concentration of attacks at 10 am,
shared across all algorithms. This temporal pattern
prompts further inquiry into reasons for this specific
timeframe, possibly revealing strategic considerations
or operational factors influencing the timing of drone
strikes. In essence, while consistencies were observed
in temporal and locational analyses across algorithms,
variations in predicting casualties highlight the nuanced
performance of each algorithm. These
outcomes
underscore the importance of thoughtful algorithm
selection based on specific attributes of interest in drone
strike analyses [Table 3].

22 VOLUME 01, Issue 2, 2023
b.
Time-based analyses
According to the proposed result findings, over 50%
of attacks were executed at 10 am, with ZeroR and J48
yielding identical results [figure 1].
Figure 1. Time-based accuracy in percentage by applying the algorithms
c.
Location-based analyses
All the listed algorithms present the highest
number of attacks performed in North Waziristan, the
results are the same between ZeroR and J48 3%
higher than NaiveBayes and 5% higher than OneR
[figure 2].
Figure 2. Location-based accuracy in percentage by applying the
algorithms
d.
Number of Injured People Analysis
The number 5of injured people is truly classified by
different algorithms as given in the graph [figure 3].
Figure 3. No. of injured people based on accuracy in percentage by applying the
algorithms
e.
Civilian Death Analysis
In this attribute analysis, the J48 outperformed,
evaluating that more than 50% were civilians [figure 4].
Figure 4. Civilian death-based accuracy in percentage by applying the
algorithms
f.
Total Death Analysis
In this attribute, all algorithms showed different
results where J48 is more accurate than all others
[figure 5].
Figure 5. Total death-based accuracy in percentage by applying the
algorithms
TABLE 3.
Accuracy results based on algorithms
Algorithm
Time
City
Injured
No of Strikes
Civilian Death
Total Died
ZeroR
58%
72%
39%
77.7%
24%
15%
J48
58%
72%
39%
77.7%
55%
57%
NaiveBayes
56.6%
69%
37%
76.8%
36%
37%
OneR
56%
63%
36%
77.2%
23%
8%

23 VOLUME 01, Issue 2, 2023
g.
Merged Results Chart
After evaluation, it is clear that all the listed
algorithms performed almost the same on the first three
attributes time, location, and no of strikes while the
results vary on the last [figure 6].
Figure 6. Merged all the above results
IV.
CONCLUSION
The analysis of drone strikes has consistently
captivated researchers, with a predominant focus on
the legality of such operations within national and
international legal frameworks. However, a critical gap
exists in understanding the profound impact of these
strikes on innocent lives. This study delves into the
dataset, exploring various attributes to
comprehensively examine the consequences of drone
strikes. The temporal analysis reveals a striking pattern,
with over 50% of attacks concentrated at 10 am. This
temporal specificity raises intriguing questions about
the strategic considerations or operational factors
influencing the chosen timeframe for drone strikes.
Furthermore, location-based analyses underscore
North Waziristan as the most targeted area, shedding
light on the geographical dynamics of drone operations.
One of the most significant outcomes is the revelation
of substantial civilian sacrifices compared to the
intended targets. The algorithms, particularly J48,
consistently outperformed others in accurately
identifying and predicting the human cost of drone
strikes. This finding emphasizes the urgent need for a
nuanced understanding of the impacts, especially on
civilians, when assessing the efficacy of drone
operations. Finally, the study provides valuable insights
into the multifaceted aspects of drone strikes,
transcending the discourse on legality. The nuanced
performance of algorithms and the observed patterns in
time and location analyses highlight the complexity of
this issue. It is imperative for future research and policy
considerations to account for the intricate dynamics and
human costs associated with drone strikes.
REFERENCES
[1] Egan, G., R. Cooper, and B. Taylor. Unmanned aerial
vehicle research at Monash University. in AIAC-11
Eleventh Australian International Aerospace
Congress. 2005.
[2] Shinwari, N.A., Understanding FATA. Community
Appraisal and Motivation Program, Peshawar, 2008.
[3] Kellner, D., From 9/11 to terror war: The dangers of
the Bush legacy2003: Rowman & Littlefield.
[4] Fang, M., Nearly 90 Percent Of People Killed In
Recent Drone Strikes Were Not The Target. The
Huffington Post, 2015. 15.
[5] Shaw, R., I. Graham, and M. Akhter, The unbearable
humanness of drone warfare in FATA, Pakistan.
Antipode, 2012. 44(4): p. 1490- 1509.
[6] Mahmood, A., S. Farooq, and A. Karim, " US Drone
Attacks in Pakistan: An International Law
Perspective.
[7] dos Reis Peron, A.E., The" Surgical" Legitimacy of
Drone Strikes? Issues of Sovereignty and Human
Rights in the Use of Unmanned Aerial Systems in
Pakistan. Journal of Strategic Security, 2014. 7(4): p.
81.
[8] Kreps, S.E. and G.P. Wallace, International law,
military effectiveness, and public support for drone
strikes. Journal of Peace Research, 2016. 53(6): p.
830-844.
[9] Maurer, K., Visual power: The scopic regime of
military drone operations. Media, War & Conflict,
2016: p. 1750635216636137.
[10] Kennedy, J., How drone strikes and a fake
vaccination program have inhibited polio eradication
in Pakistan: An analysis of national level data.
International Journal of Health Services, 2017. 47(4):
p. 807-825.
[11] Kindervater, K.H., The emergence of lethal
surveillance: Watching and killing in the history of
drone technology. Security Dialogue, 2016. 47(3): p.
223-238.
[12] Stereo, M., The United States' use of drones in the
War on Terror: the (il) legality of targeted killings
under international law. Case W. Res. J. Int'l L.,
2012. 45: p. 197.
[13] Barten, D. G., Tin, D., De Cauwer, H., Ciottone, R.
G., & Ciottone, G.R. (2022). A counter-terrorism
medicine analysis of drone attacks. Prehospital and
disaster medicine, 37(2), 192-196.
[14] Shaikhanov, Z., Badran, S., Jornet, J. M., Mittleman,
D. M., & Knightly, E. W. (2023, February). Remotely
positioned metasurface- drone attack. In
Proceedings of the 24th International Workshop on
Mobile Computing Systems and Applications (pp.
110-116).
[15] Hall, M., et al., The WEKA data mining software: an
update. ACM SIGKDD explorations newsletter,
2009. 11(1): p. 10-18.
[16] Tiwari, M., M.B. Jha, and O. Yadav, Performance
analysis of Data Mining algorithms in Weka. IOSR
Journal of Computer Engineering, 2012. 6(3): p. 32-
41.
[17] Bhargava, N., et al., Decision tree analysis on j48
algorithm for data mining. Proceedings of
International Journal of Advanced Research in
Computer Science and Software Engineering, 2013.
3(6).
[18] Patil, T.R. and S. Sherekar, Performance analysis of
Naive Bayes and J48 classification algorithm for
data classification. International Journal of Computer
Science and Applications, 2013. 6(2): p. 256-261.