---

%PDF-1.4 %���� 1 0 obj << /S /GoTo /D (section.1) >> endobj 4 0 obj (Introduction) endobj 5 0 obj << /S /GoTo /D (subsection.1.1) >> endobj 8 0 obj (Real-World Examples) endobj 9 0 obj << /S /GoTo /D (subsection.1.2) >> endobj 12 0 obj (Proposed Procedure) endobj 13 0 obj << /S /GoTo /D (section.2) >> endobj 16 0 obj (Data Preprocessing) endobj 17 0 obj << /S /GoTo /D (subsection.2.1) >> endobj 20 0 obj (Categorical Feature) endobj 21 0 obj << /S /GoTo /D (subsection.2.2) >> endobj 24 0 obj (Scaling) endobj 25 0 obj << /S /GoTo /D (section.3) >> endobj 28 0 obj (Model Selection) endobj 29 0 obj << /S /GoTo /D (subsection.3.1) >> endobj 32 0 obj (RBF Kernel) endobj 33 0 obj << /S /GoTo /D (subsection.3.2) >> endobj 36 0 obj (Cross-validation and Grid-search) endobj 37 0 obj << /S /GoTo /D (section.4) >> endobj 40 0 obj (Discussion) endobj 41 0 obj << /S /GoTo /D (appendix.A) >> endobj 44 0 obj (Examples of the Proposed Procedure) endobj 45 0 obj << /S /GoTo /D (subsection.A.1) >> endobj 48 0 obj (Astroparticle Physics) endobj 49 0 obj << /S /GoTo /D (subsection.A.2) >> endobj 52 0 obj (Bioinformatics) endobj 53 0 obj << /S /GoTo /D (subsection.A.3) >> endobj 56 0 obj (Vehicle) endobj 57 0 obj << /S /GoTo /D (appendix.B) >> endobj 60 0 obj (Common Mistakes in Scaling Training and Testing Data) endobj 61 0 obj << /S /GoTo /D (appendix.C) >> endobj 64 0 obj (When to Use Linear but not RBF Kernel) endobj 65 0 obj << /S /GoTo /D (subsection.C.1) >> endobj 68 0 obj (Number of instances \040number of features) endobj 69 0 obj << /S /GoTo /D (subsection.C.2) >> endobj 72 0 obj (Both numbers of instances and features are large) endobj 73 0 obj << /S /GoTo /D (subsection.C.3) >> endobj 76 0 obj (Number of instances \040number of features) endobj 77 0 obj << /S /GoTo /D [78 0 R /Fit ] >> endobj 85 0 obj << /Length 2597 /Filter /FlateDecode >> stream xڝYK��6�ϯP�DU,$����M���ó٭�s�P 1E�|X�=�o�~���boN�F��\lr��F^�~}w��[�/T*�J����"�E��E��H2��[/~�^-WƦ��ڢ�}YTص������ ���=�TԴ=�����ȕ}�r��*�ο�*.��7��׻X%�$ѨB� k��J[!��U�����_$̃�4���gܢ������H+�M/����Ws�G?��LWO��r\H������E��`����tm�恿��n?�����һ�t(x
��@�77�E��m� ��n�������@M���?k����|�>"ӳ� ��0@�����|��ӊ�=����R� :�n�~������ ��;Q��p�A��e�PR�M�Q�$����� ����7�J�X����}�{?�#j��n��Ul�HKi�+e��~,�`��7�.z�|�����-�` -�DE���oM�P`�+�L�\X0ƛ��㐿�z�k�T�J�Vt�Ip�u���:� �'�Rػ���%�|��0�L�۟��b���[�'��UD��iE�ޱ�z�"�ap��R��6��I����8%Tб[�VF�n_����a�`#���1�nz�<;_y� }�e:�I�C�j�m\ϴ��@��@�<���\��uC���:�Q�1ͨ�o�#�v���]uEF�~�����j��H�ݾ�����l$n��ښ����o�����i >3~��.a�0�ZB���v���n�}膢����w[�@�=�3�]� KOp�ҹ�6
,� �V �J)��&
3{��로 �Y�J�����Q"�<A?�:���~:x�A�T�j�g���P��\0F�a��,-��3.�|�Ā��� ���f�lс�#�]��M݁[�ƾĨ��8��~A�@�"Vc�Z�/nZSl4��c%�qV���)A�G 2��Gs‰�@�r�`����2ah�"�P��h����:���;Gv:��y���hb��L\r�6����Q�!��s�v;ꔂ���Й5tς�ӠƀN����M���1[�����L�#<�I�x��w�hY�p)�<�n�0�i��h.\X�{���_U
mgt��}@k��������i���,!��GL)�`�r��A`�O.DNRS˰O ���?�@�߮���.�W�o�H{akL/;�O%��� ���v��6O��m�m@���/�K���q��
��N���t���O�ʱ�a�G��_cha���_�^fb���h�Ӂ��:"G��9���H�Ɔ#���> 5`J�S�}�12�@�H�����-�e�vy�C��W���

---